Real-time simulation of large-scale neural architectures for visual features computation based on GPU.

PubMed

Chessa, Manuela; Bianchi, Valentina; Zampetti, Massimo; Sabatini, Silvio P; Solari, Fabio

2012-01-01

The intrinsic parallelism of visual neural architectures based on distributed hierarchical layers is well suited to be implemented on the multi-core architectures of modern graphics cards. The design strategies that allow us to optimally take advantage of such parallelism, in order to efficiently map on GPU the hierarchy of layers and the canonical neural computations, are proposed. Specifically, the advantages of a cortical map-like representation of the data are exploited. Moreover, a GPU implementation of a novel neural architecture for the computation of binocular disparity from stereo image pairs, based on populations of binocular energy neurons, is presented. The implemented neural model achieves good performances in terms of reliability of the disparity estimates and a near real-time execution speed, thus demonstrating the effectiveness of the devised design strategies. The proposed approach is valid in general, since the neural building blocks we implemented are a common basis for the modeling of visual neural functionalities.

An Application Development Platform for Neuromorphic Computing

DOE Office of Scientific and Technical Information (OSTI.GOV)

Dean, Mark; Chan, Jason; Daffron, Christopher

2016-01-01

Dynamic Adaptive Neural Network Arrays (DANNAs) are neuromorphic computing systems developed as a hardware based approach to the implementation of neural networks. They feature highly adaptive and programmable structural elements, which model arti cial neural networks with spiking behavior. We design them to solve problems using evolutionary optimization. In this paper, we highlight the current hardware and software implementations of DANNA, including their features, functionalities and performance. We then describe the development of an Application Development Platform (ADP) to support efficient application implementation and testing of DANNA based solutions. We conclude with future directions.

Dendritic Properties Control Energy Efficiency of Action Potentials in Cortical Pyramidal Cells

PubMed Central

Yi, Guosheng; Wang, Jiang; Wei, Xile; Deng, Bin

2017-01-01

Neural computation is performed by transforming input signals into sequences of action potentials (APs), which is metabolically expensive and limited by the energy available to the brain. The metabolic efficiency of single AP has important consequences for the computational power of the cell, which is determined by its biophysical properties and morphologies. Here we adopt biophysically-based two-compartment models to investigate how dendrites affect energy efficiency of APs in cortical pyramidal neurons. We measure the Na+ entry during the spike and examine how it is efficiently used for generating AP depolarization. We show that increasing the proportion of dendritic area or coupling conductance between two chambers decreases Na+ entry efficiency of somatic AP. Activating inward Ca2+ current in dendrites results in dendritic spike, which increases AP efficiency. Activating Ca2+-activated outward K+ current in dendrites, however, decreases Na+ entry efficiency. We demonstrate that the active and passive dendrites take effects by altering the overlap between Na+ influx and internal current flowing from soma to dendrite. We explain a fundamental link between dendritic properties and AP efficiency, which is essential to interpret how neural computation consumes metabolic energy and how biophysics and morphologies contribute to such consumption. PMID:28919852

Dendritic Properties Control Energy Efficiency of Action Potentials in Cortical Pyramidal Cells.

PubMed

Yi, Guosheng; Wang, Jiang; Wei, Xile; Deng, Bin

2017-01-01

Neural computation is performed by transforming input signals into sequences of action potentials (APs), which is metabolically expensive and limited by the energy available to the brain. The metabolic efficiency of single AP has important consequences for the computational power of the cell, which is determined by its biophysical properties and morphologies. Here we adopt biophysically-based two-compartment models to investigate how dendrites affect energy efficiency of APs in cortical pyramidal neurons. We measure the Na + entry during the spike and examine how it is efficiently used for generating AP depolarization. We show that increasing the proportion of dendritic area or coupling conductance between two chambers decreases Na + entry efficiency of somatic AP. Activating inward Ca 2+ current in dendrites results in dendritic spike, which increases AP efficiency. Activating Ca 2+ -activated outward K + current in dendrites, however, decreases Na + entry efficiency. We demonstrate that the active and passive dendrites take effects by altering the overlap between Na + influx and internal current flowing from soma to dendrite. We explain a fundamental link between dendritic properties and AP efficiency, which is essential to interpret how neural computation consumes metabolic energy and how biophysics and morphologies contribute to such consumption.

A Case Study on Neural Inspired Dynamic Memory Management Strategies for High Performance Computing.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Vineyard, Craig Michael; Verzi, Stephen Joseph

As high performance computing architectures pursue more computational power there is a need for increased memory capacity and bandwidth as well. A multi-level memory (MLM) architecture addresses this need by combining multiple memory types with different characteristics as varying levels of the same architecture. How to efficiently utilize this memory infrastructure is an unknown challenge, and in this research we sought to investigate whether neural inspired approaches can meaningfully help with memory management. In particular we explored neurogenesis inspired re- source allocation, and were able to show a neural inspired mixed controller policy can beneficially impact how MLM architectures utilizemore » memory.« less

An efficient optical architecture for sparsely connected neural networks

NASA Technical Reports Server (NTRS)

Hine, Butler P., III; Downie, John D.; Reid, Max B.

1990-01-01

An architecture for general-purpose optical neural network processor is presented in which the interconnections and weights are formed by directing coherent beams holographically, thereby making use of the space-bandwidth products of the recording medium for sparsely interconnected networks more efficiently that the commonly used vector-matrix multiplier, since all of the hologram area is in use. An investigation is made of the use of computer-generated holograms recorded on such updatable media as thermoplastic materials, in order to define the interconnections and weights of a neural network processor; attention is given to limits on interconnection densities, diffraction efficiencies, and weighing accuracies possible with such an updatable thin film holographic device.

Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method.

PubMed

Xie, Xiurui; Qu, Hong; Yi, Zhang; Kurths, Jurgen

2017-06-01

The spiking neural network (SNN) is the third generation of neural networks and performs remarkably well in cognitive tasks, such as pattern recognition. The temporal neural encode mechanism found in biological hippocampus enables SNN to possess more powerful computation capability than networks with other encoding schemes. However, this temporal encoding approach requires neurons to process information serially on time, which reduces learning efficiency significantly. To keep the powerful computation capability of the temporal encoding mechanism and to overcome its low efficiency in the training of SNNs, a new training algorithm, the accurate synaptic-efficiency adjustment method is proposed in this paper. Inspired by the selective attention mechanism of the primate visual system, our algorithm selects only the target spike time as attention areas, and ignores voltage states of the untarget ones, resulting in a significant reduction of training time. Besides, our algorithm employs a cost function based on the voltage difference between the potential of the output neuron and the firing threshold of the SNN, instead of the traditional precise firing time distance. A normalized spike-timing-dependent-plasticity learning window is applied to assigning this error to different synapses for instructing their training. Comprehensive simulations are conducted to investigate the learning properties of our algorithm, with input neurons emitting both single spike and multiple spikes. Simulation results indicate that our algorithm possesses higher learning performance than the existing other methods and achieves the state-of-the-art efficiency in the training of SNN.

Computational neural learning formalisms for manipulator inverse kinematics

NASA Technical Reports Server (NTRS)

Gulati, Sandeep; Barhen, Jacob; Iyengar, S. Sitharama

1989-01-01

An efficient, adaptive neural learning paradigm for addressing the inverse kinematics of redundant manipulators is presented. The proposed methodology exploits the infinite local stability of terminal attractors - a new class of mathematical constructs which provide unique information processing capabilities to artificial neural systems. For robotic applications, synaptic elements of such networks can rapidly acquire the kinematic invariances embedded within the presented samples. Subsequently, joint-space configurations, required to follow arbitrary end-effector trajectories, can readily be computed. In a significant departure from prior neuromorphic learning algorithms, this methodology provides mechanisms for incorporating an in-training skew to handle kinematics and environmental constraints.

Characterizing Deep Brain Stimulation effects in computationally efficient neural network models.

PubMed

Latteri, Alberta; Arena, Paolo; Mazzone, Paolo

2011-04-15

Recent studies on the medical treatment of Parkinson's disease (PD) led to the introduction of the so called Deep Brain Stimulation (DBS) technique. This particular therapy allows to contrast actively the pathological activity of various Deep Brain structures, responsible for the well known PD symptoms. This technique, frequently joined to dopaminergic drugs administration, replaces the surgical interventions implemented to contrast the activity of specific brain nuclei, called Basal Ganglia (BG). This clinical protocol gave the possibility to analyse and inspect signals measured from the electrodes implanted into the deep brain regions. The analysis of these signals led to the possibility to study the PD as a specific case of dynamical synchronization in biological neural networks, with the advantage to apply the theoretical analysis developed in such scientific field to find efficient treatments to face with this important disease. Experimental results in fact show that the PD neurological diseases are characterized by a pathological signal synchronization in BG. Parkinsonian tremor, for example, is ascribed to be caused by neuron populations of the Thalamic and Striatal structures that undergo an abnormal synchronization. On the contrary, in normal conditions, the activity of the same neuron populations do not appear to be correlated and synchronized. To study in details the effect of the stimulation signal on a pathological neural medium, efficient models of these neural structures were built, which are able to show, without any external input, the intrinsic properties of a pathological neural tissue, mimicking the BG synchronized dynamics.We start considering a model already introduced in the literature to investigate the effects of electrical stimulation on pathologically synchronized clusters of neurons. This model used Morris Lecar type neurons. This neuron model, although having a high level of biological plausibility, requires a large computational effort to simulate large scale networks. For this reason we considered a reduced order model, the Izhikevich one, which is computationally much lighter. The comparison between neural lattices built using both neuron models provided comparable results, both without traditional stimulation and in presence of all the stimulation protocols. This was a first result toward the study and simulation of the large scale neural networks involved in pathological dynamics.Using the reduced order model an inspection on the activity of two neural lattices was also carried out at the aim to analyze how the stimulation in one area could affect the dynamics in another area, like the usual medical treatment protocols require.The study of population dynamics that was carried out allowed us to investigate, through simulations, the positive effects of the stimulation signals in terms of desynchronization of the neural dynamics. The results obtained constitute a significant added value to the analysis of synchronization and desynchronization effects due to neural stimulation. This work gives the opportunity to more efficiently study the effect of stimulation in large scale yet computationally efficient neural networks. Results were compared both with the other mathematical models, using Morris Lecar and Izhikevich neurons, and with simulated Local Field Potentials (LFP).

Low-cost autonomous perceptron neural network inspired by quantum computation

NASA Astrophysics Data System (ADS)

Zidan, Mohammed; Abdel-Aty, Abdel-Haleem; El-Sadek, Alaa; Zanaty, E. A.; Abdel-Aty, Mahmoud

2017-11-01

Achieving low cost learning with reliable accuracy is one of the important goals to achieve intelligent machines to save time, energy and perform learning process over limited computational resources machines. In this paper, we propose an efficient algorithm for a perceptron neural network inspired by quantum computing composite from a single neuron to classify inspirable linear applications after a single training iteration O(1). The algorithm is applied over a real world data set and the results are outer performs the other state-of-the art algorithms.

Emotional System for Military Target Identification

DTIC Science & Technology

2009-10-01

algorithm [23], and used it to solve a facial recognition problem. In other works [24,25], we explored the potential of using emotional neural...other application areas, such as security ( facial recognition ) and medical (blood cell identification), can be also efficiently used in military...Application of an emotional neural network to facial recognition . Neural Computing and Applications, 18(4), 309-320. [25] Khashman, A. (2009). Blood cell

A preferential design approach for energy-efficient and robust implantable neural signal processing hardware.

PubMed

Narasimhan, Seetharam; Chiel, Hillel J; Bhunia, Swarup

2009-01-01

For implantable neural interface applications, it is important to compress data and analyze spike patterns across multiple channels in real time. Such a computational task for online neural data processing requires an innovative circuit-architecture level design approach for low-power, robust and area-efficient hardware implementation. Conventional microprocessor or Digital Signal Processing (DSP) chips would dissipate too much power and are too large in size for an implantable system. In this paper, we propose a novel hardware design approach, referred to as "Preferential Design" that exploits the nature of the neural signal processing algorithm to achieve a low-voltage, robust and area-efficient implementation using nanoscale process technology. The basic idea is to isolate the critical components with respect to system performance and design them more conservatively compared to the noncritical ones. This allows aggressive voltage scaling for low power operation while ensuring robustness and area efficiency. We have applied the proposed approach to a neural signal processing algorithm using the Discrete Wavelet Transform (DWT) and observed significant improvement in power and robustness over conventional design.

Fitting neuron models to spike trains.

PubMed

Rossant, Cyrille; Goodman, Dan F M; Fontaine, Bertrand; Platkiewicz, Jonathan; Magnusson, Anna K; Brette, Romain

2011-01-01

Computational modeling is increasingly used to understand the function of neural circuits in systems neuroscience. These studies require models of individual neurons with realistic input-output properties. Recently, it was found that spiking models can accurately predict the precisely timed spike trains produced by cortical neurons in response to somatically injected currents, if properly fitted. This requires fitting techniques that are efficient and flexible enough to easily test different candidate models. We present a generic solution, based on the Brian simulator (a neural network simulator in Python), which allows the user to define and fit arbitrary neuron models to electrophysiological recordings. It relies on vectorization and parallel computing techniques to achieve efficiency. We demonstrate its use on neural recordings in the barrel cortex and in the auditory brainstem, and confirm that simple adaptive spiking models can accurately predict the response of cortical neurons. Finally, we show how a complex multicompartmental model can be reduced to a simple effective spiking model.

Fault Analysis of Space Station DC Power Systems-Using Neural Network Adaptive Wavelets to Detect Faults

NASA Technical Reports Server (NTRS)

Momoh, James A.; Wang, Yanchun; Dolce, James L.

1997-01-01

This paper describes the application of neural network adaptive wavelets for fault diagnosis of space station power system. The method combines wavelet transform with neural network by incorporating daughter wavelets into weights. Therefore, the wavelet transform and neural network training procedure become one stage, which avoids the complex computation of wavelet parameters and makes the procedure more straightforward. The simulation results show that the proposed method is very efficient for the identification of fault locations.

The Brain as an Efficient and Robust Adaptive Learner.

PubMed

Denève, Sophie; Alemi, Alireza; Bourdoukan, Ralph

2017-06-07

Understanding how the brain learns to compute functions reliably, efficiently, and robustly with noisy spiking activity is a fundamental challenge in neuroscience. Most sensory and motor tasks can be described as dynamical systems and could presumably be learned by adjusting connection weights in a recurrent biological neural network. However, this is greatly complicated by the credit assignment problem for learning in recurrent networks, e.g., the contribution of each connection to the global output error cannot be determined based only on locally accessible quantities to the synapse. Combining tools from adaptive control theory and efficient coding theories, we propose that neural circuits can indeed learn complex dynamic tasks with local synaptic plasticity rules as long as they associate two experimentally established neural mechanisms. First, they should receive top-down feedbacks driving both their activity and their synaptic plasticity. Second, inhibitory interneurons should maintain a tight balance between excitation and inhibition in the circuit. The resulting networks could learn arbitrary dynamical systems and produce irregular spike trains as variable as those observed experimentally. Yet, this variability in single neurons may hide an extremely efficient and robust computation at the population level. Copyright © 2017 Elsevier Inc. All rights reserved.

Prediction of Slot Shape and Slot Size for Improving the Performance of Microstrip Antennas Using Knowledge-Based Neural Networks.

PubMed

Khan, Taimoor; De, Asok

2014-01-01

In the last decade, artificial neural networks have become very popular techniques for computing different performance parameters of microstrip antennas. The proposed work illustrates a knowledge-based neural networks model for predicting the appropriate shape and accurate size of the slot introduced on the radiating patch for achieving desired level of resonance, gain, directivity, antenna efficiency, and radiation efficiency for dual-frequency operation. By incorporating prior knowledge in neural model, the number of required training patterns is drastically reduced. Further, the neural model incorporated with prior knowledge can be used for predicting response in extrapolation region beyond the training patterns region. For validation, a prototype is also fabricated and its performance parameters are measured. A very good agreement is attained between measured, simulated, and predicted results.

Prediction of Slot Shape and Slot Size for Improving the Performance of Microstrip Antennas Using Knowledge-Based Neural Networks

PubMed Central

De, Asok

2014-01-01

In the last decade, artificial neural networks have become very popular techniques for computing different performance parameters of microstrip antennas. The proposed work illustrates a knowledge-based neural networks model for predicting the appropriate shape and accurate size of the slot introduced on the radiating patch for achieving desired level of resonance, gain, directivity, antenna efficiency, and radiation efficiency for dual-frequency operation. By incorporating prior knowledge in neural model, the number of required training patterns is drastically reduced. Further, the neural model incorporated with prior knowledge can be used for predicting response in extrapolation region beyond the training patterns region. For validation, a prototype is also fabricated and its performance parameters are measured. A very good agreement is attained between measured, simulated, and predicted results. PMID:27382616

Livermore Big Artificial Neural Network Toolkit

DOE Office of Scientific and Technical Information (OSTI.GOV)

Essen, Brian Van; Jacobs, Sam; Kim, Hyojin

2016-07-01

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

Efficient shortest-path-tree computation in network routing based on pulse-coupled neural networks.

PubMed

Qu, Hong; Yi, Zhang; Yang, Simon X

2013-06-01

Shortest path tree (SPT) computation is a critical issue for routers using link-state routing protocols, such as the most commonly used open shortest path first and intermediate system to intermediate system. Each router needs to recompute a new SPT rooted from itself whenever a change happens in the link state. Most commercial routers do this computation by deleting the current SPT and building a new one using static algorithms such as the Dijkstra algorithm at the beginning. Such recomputation of an entire SPT is inefficient, which may consume a considerable amount of CPU time and result in a time delay in the network. Some dynamic updating methods using the information in the updated SPT have been proposed in recent years. However, there are still many limitations in those dynamic algorithms. In this paper, a new modified model of pulse-coupled neural networks (M-PCNNs) is proposed for the SPT computation. It is rigorously proved that the proposed model is capable of solving some optimization problems, such as the SPT. A static algorithm is proposed based on the M-PCNNs to compute the SPT efficiently for large-scale problems. In addition, a dynamic algorithm that makes use of the structure of the previously computed SPT is proposed, which significantly improves the efficiency of the algorithm. Simulation results demonstrate the effective and efficient performance of the proposed approach.

Nonvolatile Memory Materials for Neuromorphic Intelligent Machines.

PubMed

Jeong, Doo Seok; Hwang, Cheol Seong

2018-04-18

Recent progress in deep learning extends the capability of artificial intelligence to various practical tasks, making the deep neural network (DNN) an extremely versatile hypothesis. While such DNN is virtually built on contemporary data centers of the von Neumann architecture, physical (in part) DNN of non-von Neumann architecture, also known as neuromorphic computing, can remarkably improve learning and inference efficiency. Particularly, resistance-based nonvolatile random access memory (NVRAM) highlights its handy and efficient application to the multiply-accumulate (MAC) operation in an analog manner. Here, an overview is given of the available types of resistance-based NVRAMs and their technological maturity from the material- and device-points of view. Examples within the strategy are subsequently addressed in comparison with their benchmarks (virtual DNN in deep learning). A spiking neural network (SNN) is another type of neural network that is more biologically plausible than the DNN. The successful incorporation of resistance-based NVRAM in SNN-based neuromorphic computing offers an efficient solution to the MAC operation and spike timing-based learning in nature. This strategy is exemplified from a material perspective. Intelligent machines are categorized according to their architecture and learning type. Also, the functionality and usefulness of NVRAM-based neuromorphic computing are addressed. © 2018 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks

PubMed Central

Xie, Xiurui; Qu, Hong; Liu, Guisong; Zhang, Malu; Kurths, Jürgen

2016-01-01

The spiking neural networks (SNNs) are the third generation of neural networks and perform remarkably well in cognitive tasks such as pattern recognition. The spike emitting and information processing mechanisms found in biological cognitive systems motivate the application of the hierarchical structure and temporal encoding mechanism in spiking neural networks, which have exhibited strong computational capability. However, the hierarchical structure and temporal encoding approach require neurons to process information serially in space and time respectively, which reduce the training efficiency significantly. For training the hierarchical SNNs, most existing methods are based on the traditional back-propagation algorithm, inheriting its drawbacks of the gradient diffusion and the sensitivity on parameters. To keep the powerful computation capability of the hierarchical structure and temporal encoding mechanism, but to overcome the low efficiency of the existing algorithms, a new training algorithm, the Normalized Spiking Error Back Propagation (NSEBP) is proposed in this paper. In the feedforward calculation, the output spike times are calculated by solving the quadratic function in the spike response model instead of detecting postsynaptic voltage states at all time points in traditional algorithms. Besides, in the feedback weight modification, the computational error is propagated to previous layers by the presynaptic spike jitter instead of the gradient decent rule, which realizes the layer-wised training. Furthermore, our algorithm investigates the mathematical relation between the weight variation and voltage error change, which makes the normalization in the weight modification applicable. Adopting these strategies, our algorithm outperforms the traditional SNN multi-layer algorithms in terms of learning efficiency and parameter sensitivity, that are also demonstrated by the comprehensive experimental results in this paper. PMID:27044001

A hybrid architecture for the implementation of the Athena neural net model

NASA Technical Reports Server (NTRS)

Koutsougeras, C.; Papachristou, C.

1989-01-01

The implementation of an earlier introduced neural net model for pattern classification is considered. Data flow principles are employed in the development of a machine that efficiently implements the model and can be useful for real time classification tasks. Further enhancement with optical computing structures is also considered.

An Efficient Neural-Network-Based Microseismic Monitoring Platform for Hydraulic Fracture on an Edge Computing Architecture.

PubMed

Zhang, Xiaopu; Lin, Jun; Chen, Zubin; Sun, Feng; Zhu, Xi; Fang, Gengfa

2018-06-05

Microseismic monitoring is one of the most critical technologies for hydraulic fracturing in oil and gas production. To detect events in an accurate and efficient way, there are two major challenges. One challenge is how to achieve high accuracy due to a poor signal-to-noise ratio (SNR). The other one is concerned with real-time data transmission. Taking these challenges into consideration, an edge-computing-based platform, namely Edge-to-Center LearnReduce, is presented in this work. The platform consists of a data center with many edge components. At the data center, a neural network model combined with convolutional neural network (CNN) and long short-term memory (LSTM) is designed and this model is trained by using previously obtained data. Once the model is fully trained, it is sent to edge components for events detection and data reduction. At each edge component, a probabilistic inference is added to the neural network model to improve its accuracy. Finally, the reduced data is delivered to the data center. Based on experiment results, a high detection accuracy (over 96%) with less transmitted data (about 90%) was achieved by using the proposed approach on a microseismic monitoring system. These results show that the platform can simultaneously improve the accuracy and efficiency of microseismic monitoring.

A novel nonlinear adaptive filter using a pipelined second-order Volterra recurrent neural network.

PubMed

Zhao, Haiquan; Zhang, Jiashu

2009-12-01

To enhance the performance and overcome the heavy computational complexity of recurrent neural networks (RNN), a novel nonlinear adaptive filter based on a pipelined second-order Volterra recurrent neural network (PSOVRNN) is proposed in this paper. A modified real-time recurrent learning (RTRL) algorithm of the proposed filter is derived in much more detail. The PSOVRNN comprises of a number of simple small-scale second-order Volterra recurrent neural network (SOVRNN) modules. In contrast to the standard RNN, these modules of a PSOVRNN can be performed simultaneously in a pipelined parallelism fashion, which can lead to a significant improvement in its total computational efficiency. Moreover, since each module of the PSOVRNN is a SOVRNN in which nonlinearity is introduced by the recursive second-order Volterra (RSOV) expansion, its performance can be further improved. Computer simulations have demonstrated that the PSOVRNN performs better than the pipelined recurrent neural network (PRNN) and RNN for nonlinear colored signals prediction and nonlinear channel equalization. However, the superiority of the PSOVRNN over the PRNN is at the cost of increasing computational complexity due to the introduced nonlinear expansion of each module.

Machine learning action parameters in lattice quantum chromodynamics

NASA Astrophysics Data System (ADS)

Shanahan, Phiala E.; Trewartha, Daniel; Detmold, William

2018-05-01

Numerical lattice quantum chromodynamics studies of the strong interaction are important in many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. The high information content and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.

Energy-efficient neural information processing in individual neurons and neuronal networks.

PubMed

Yu, Lianchun; Yu, Yuguo

2017-11-01

Brains are composed of networks of an enormous number of neurons interconnected with synapses. Neural information is carried by the electrical signals within neurons and the chemical signals among neurons. Generating these electrical and chemical signals is metabolically expensive. The fundamental issue raised here is whether brains have evolved efficient ways of developing an energy-efficient neural code from the molecular level to the circuit level. Here, we summarize the factors and biophysical mechanisms that could contribute to the energy-efficient neural code for processing input signals. The factors range from ion channel kinetics, body temperature, axonal propagation of action potentials, low-probability release of synaptic neurotransmitters, optimal input and noise, the size of neurons and neuronal clusters, excitation/inhibition balance, coding strategy, cortical wiring, and the organization of functional connectivity. Both experimental and computational evidence suggests that neural systems may use these factors to maximize the efficiency of energy consumption in processing neural signals. Studies indicate that efficient energy utilization may be universal in neuronal systems as an evolutionary consequence of the pressure of limited energy. As a result, neuronal connections may be wired in a highly economical manner to lower energy costs and space. Individual neurons within a network may encode independent stimulus components to allow a minimal number of neurons to represent whole stimulus characteristics efficiently. This basic principle may fundamentally change our view of how billions of neurons organize themselves into complex circuits to operate and generate the most powerful intelligent cognition in nature. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

A neural net based architecture for the segmentation of mixed gray-level and binary pictures

NASA Technical Reports Server (NTRS)

Tabatabai, Ali; Troudet, Terry P.

1991-01-01

A neural-net-based architecture is proposed to perform segmentation in real time for mixed gray-level and binary pictures. In this approach, the composite picture is divided into 16 x 16 pixel blocks, which are identified as character blocks or image blocks on the basis of a dichotomy measure computed by an adaptive 16 x 16 neural net. For compression purposes, each image block is further divided into 4 x 4 subblocks; a one-bit nonparametric quantizer is used to encode 16 x 16 character and 4 x 4 image blocks; and the binary map and quantizer levels are obtained through a neural net segmentor over each block. The efficiency of the neural segmentation in terms of computational speed, data compression, and quality of the compressed picture is demonstrated. The effect of weight quantization is also discussed. VLSI implementations of such adaptive neural nets in CMOS technology are described and simulated in real time for a maximum block size of 256 pixels.

An efficient annealing in Boltzmann machine in Hopfield neural network

NASA Astrophysics Data System (ADS)

Kin, Teoh Yeong; Hasan, Suzanawati Abu; Bulot, Norhisam; Ismail, Mohammad Hafiz

2012-09-01

This paper proposes and implements Boltzmann machine in Hopfield neural network doing logic programming based on the energy minimization system. The temperature scheduling in Boltzmann machine enhancing the performance of doing logic programming in Hopfield neural network. The finest temperature is determined by observing the ratio of global solution and final hamming distance using computer simulations. The study shows that Boltzmann Machine model is more stable and competent in term of representing and solving difficult combinatory problems.

Large-Scale Simulations of Plastic Neural Networks on Neuromorphic Hardware

PubMed Central

Knight, James C.; Tully, Philip J.; Kaplan, Bernhard A.; Lansner, Anders; Furber, Steve B.

2016-01-01

SpiNNaker is a digital, neuromorphic architecture designed for simulating large-scale spiking neural networks at speeds close to biological real-time. Rather than using bespoke analog or digital hardware, the basic computational unit of a SpiNNaker system is a general-purpose ARM processor, allowing it to be programmed to simulate a wide variety of neuron and synapse models. This flexibility is particularly valuable in the study of biological plasticity phenomena. A recently proposed learning rule based on the Bayesian Confidence Propagation Neural Network (BCPNN) paradigm offers a generic framework for modeling the interaction of different plasticity mechanisms using spiking neurons. However, it can be computationally expensive to simulate large networks with BCPNN learning since it requires multiple state variables for each synapse, each of which needs to be updated every simulation time-step. We discuss the trade-offs in efficiency and accuracy involved in developing an event-based BCPNN implementation for SpiNNaker based on an analytical solution to the BCPNN equations, and detail the steps taken to fit this within the limited computational and memory resources of the SpiNNaker architecture. We demonstrate this learning rule by learning temporal sequences of neural activity within a recurrent attractor network which we simulate at scales of up to 2.0 × 104 neurons and 5.1 × 107 plastic synapses: the largest plastic neural network ever to be simulated on neuromorphic hardware. We also run a comparable simulation on a Cray XC-30 supercomputer system and find that, if it is to match the run-time of our SpiNNaker simulation, the super computer system uses approximately 45× more power. This suggests that cheaper, more power efficient neuromorphic systems are becoming useful discovery tools in the study of plasticity in large-scale brain models. PMID:27092061

Efficient Computations and Representations of Visible Surfaces.

DTIC Science & Technology

1979-12-01

position as stated. The smooth contour generator may lie along a sharp ridge, for instance. Richards & Stevens -28- 6m lace contout s ?S ,.......... ceoonec...From understanding computation to understanding neural circuitry. Neurosci. Res. Prog. Bull. 13. 470-488. Metelli, F. 1970 An algebraic development of

ANNarchy: a code generation approach to neural simulations on parallel hardware

PubMed Central

Vitay, Julien; Dinkelbach, Helge Ü.; Hamker, Fred H.

2015-01-01

Many modern neural simulators focus on the simulation of networks of spiking neurons on parallel hardware. Another important framework in computational neuroscience, rate-coded neural networks, is mostly difficult or impossible to implement using these simulators. We present here the ANNarchy (Artificial Neural Networks architect) neural simulator, which allows to easily define and simulate rate-coded and spiking networks, as well as combinations of both. The interface in Python has been designed to be close to the PyNN interface, while the definition of neuron and synapse models can be specified using an equation-oriented mathematical description similar to the Brian neural simulator. This information is used to generate C++ code that will efficiently perform the simulation on the chosen parallel hardware (multi-core system or graphical processing unit). Several numerical methods are available to transform ordinary differential equations into an efficient C++code. We compare the parallel performance of the simulator to existing solutions. PMID:26283957

Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback.

PubMed

Orhan, A Emin; Ma, Wei Ji

2017-07-26

Animals perform near-optimal probabilistic inference in a wide range of psychophysical tasks. Probabilistic inference requires trial-to-trial representation of the uncertainties associated with task variables and subsequent use of this representation. Previous work has implemented such computations using neural networks with hand-crafted and task-dependent operations. We show that generic neural networks trained with a simple error-based learning rule perform near-optimal probabilistic inference in nine common psychophysical tasks. In a probabilistic categorization task, error-based learning in a generic network simultaneously explains a monkey's learning curve and the evolution of qualitative aspects of its choice behavior. In all tasks, the number of neurons required for a given level of performance grows sublinearly with the input population size, a substantial improvement on previous implementations of probabilistic inference. The trained networks develop a novel sparsity-based probabilistic population code. Our results suggest that probabilistic inference emerges naturally in generic neural networks trained with error-based learning rules.Behavioural tasks often require probability distributions to be inferred about task specific variables. Here, the authors demonstrate that generic neural networks can be trained using a simple error-based learning rule to perform such probabilistic computations efficiently without any need for task specific operations.

Efficient Embedded Decoding of Neural Network Language Models in a Machine Translation System.

PubMed

Zamora-Martinez, Francisco; Castro-Bleda, Maria Jose

2018-02-22

Neural Network Language Models (NNLMs) are a successful approach to Natural Language Processing tasks, such as Machine Translation. We introduce in this work a Statistical Machine Translation (SMT) system which fully integrates NNLMs in the decoding stage, breaking the traditional approach based on [Formula: see text]-best list rescoring. The neural net models (both language models (LMs) and translation models) are fully coupled in the decoding stage, allowing to more strongly influence the translation quality. Computational issues were solved by using a novel idea based on memorization and smoothing of the softmax constants to avoid their computation, which introduces a trade-off between LM quality and computational cost. These ideas were studied in a machine translation task with different combinations of neural networks used both as translation models and as target LMs, comparing phrase-based and [Formula: see text]-gram-based systems, showing that the integrated approach seems more promising for [Formula: see text]-gram-based systems, even with nonfull-quality NNLMs.

Fitting Neuron Models to Spike Trains

PubMed Central

Rossant, Cyrille; Goodman, Dan F. M.; Fontaine, Bertrand; Platkiewicz, Jonathan; Magnusson, Anna K.; Brette, Romain

2011-01-01

Computational modeling is increasingly used to understand the function of neural circuits in systems neuroscience. These studies require models of individual neurons with realistic input–output properties. Recently, it was found that spiking models can accurately predict the precisely timed spike trains produced by cortical neurons in response to somatically injected currents, if properly fitted. This requires fitting techniques that are efficient and flexible enough to easily test different candidate models. We present a generic solution, based on the Brian simulator (a neural network simulator in Python), which allows the user to define and fit arbitrary neuron models to electrophysiological recordings. It relies on vectorization and parallel computing techniques to achieve efficiency. We demonstrate its use on neural recordings in the barrel cortex and in the auditory brainstem, and confirm that simple adaptive spiking models can accurately predict the response of cortical neurons. Finally, we show how a complex multicompartmental model can be reduced to a simple effective spiking model. PMID:21415925

Efficient Simulation of Wing Modal Response: Application of 2nd Order Shape Sensitivities and Neural Networks

NASA Technical Reports Server (NTRS)

Kapania, Rakesh K.; Liu, Youhua

2000-01-01

At the preliminary design stage of a wing structure, an efficient simulation, one needing little computation but yielding adequately accurate results for various response quantities, is essential in the search of optimal design in a vast design space. In the present paper, methods of using sensitivities up to 2nd order, and direct application of neural networks are explored. The example problem is how to decide the natural frequencies of a wing given the shape variables of the structure. It is shown that when sensitivities cannot be obtained analytically, the finite difference approach is usually more reliable than a semi-analytical approach provided an appropriate step size is used. The use of second order sensitivities is proved of being able to yield much better results than the case where only the first order sensitivities are used. When neural networks are trained to relate the wing natural frequencies to the shape variables, a negligible computation effort is needed to accurately determine the natural frequencies of a new design.

Encoding neural and synaptic functionalities in electron spin: A pathway to efficient neuromorphic computing

NASA Astrophysics Data System (ADS)

Sengupta, Abhronil; Roy, Kaushik

2017-12-01

Present day computers expend orders of magnitude more computational resources to perform various cognitive and perception related tasks that humans routinely perform every day. This has recently resulted in a seismic shift in the field of computation where research efforts are being directed to develop a neurocomputer that attempts to mimic the human brain by nanoelectronic components and thereby harness its efficiency in recognition problems. Bridging the gap between neuroscience and nanoelectronics, this paper attempts to provide a review of the recent developments in the field of spintronic device based neuromorphic computing. Description of various spin-transfer torque mechanisms that can be potentially utilized for realizing device structures mimicking neural and synaptic functionalities is provided. A cross-layer perspective extending from the device to the circuit and system level is presented to envision the design of an All-Spin neuromorphic processor enabled with on-chip learning functionalities. Device-circuit-algorithm co-simulation framework calibrated to experimental results suggest that such All-Spin neuromorphic systems can potentially achieve almost two orders of magnitude energy improvement in comparison to state-of-the-art CMOS implementations.

Distributed collaborative probabilistic design of multi-failure structure with fluid-structure interaction using fuzzy neural network of regression

NASA Astrophysics Data System (ADS)

Song, Lu-Kai; Wen, Jie; Fei, Cheng-Wei; Bai, Guang-Chen

2018-05-01

To improve the computing efficiency and precision of probabilistic design for multi-failure structure, a distributed collaborative probabilistic design method-based fuzzy neural network of regression (FR) (called as DCFRM) is proposed with the integration of distributed collaborative response surface method and fuzzy neural network regression model. The mathematical model of DCFRM is established and the probabilistic design idea with DCFRM is introduced. The probabilistic analysis of turbine blisk involving multi-failure modes (deformation failure, stress failure and strain failure) was investigated by considering fluid-structure interaction with the proposed method. The distribution characteristics, reliability degree, and sensitivity degree of each failure mode and overall failure mode on turbine blisk are obtained, which provides a useful reference for improving the performance and reliability of aeroengine. Through the comparison of methods shows that the DCFRM reshapes the probability of probabilistic analysis for multi-failure structure and improves the computing efficiency while keeping acceptable computational precision. Moreover, the proposed method offers a useful insight for reliability-based design optimization of multi-failure structure and thereby also enriches the theory and method of mechanical reliability design.

Machine learning action parameters in lattice quantum chromodynamics

DOE Office of Scientific and Technical Information (OSTI.GOV)

Shanahan, Phiala; Trewartha, Daneil; Detmold, William

Numerical lattice quantum chromodynamics studies of the strong interaction underpin theoretical understanding of many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. Finally, the high information contentmore » and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.« less

Machine learning action parameters in lattice quantum chromodynamics

DOE PAGES

Shanahan, Phiala; Trewartha, Daneil; Detmold, William

2018-05-16

Numerical lattice quantum chromodynamics studies of the strong interaction underpin theoretical understanding of many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. Finally, the high information contentmore » and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.« less

Silicon synaptic transistor for hardware-based spiking neural network and neuromorphic system

NASA Astrophysics Data System (ADS)

Kim, Hyungjin; Hwang, Sungmin; Park, Jungjin; Park, Byung-Gook

2017-10-01

Brain-inspired neuromorphic systems have attracted much attention as new computing paradigms for power-efficient computation. Here, we report a silicon synaptic transistor with two electrically independent gates to realize a hardware-based neural network system without any switching components. The spike-timing dependent plasticity characteristics of the synaptic devices are measured and analyzed. With the help of the device model based on the measured data, the pattern recognition capability of the hardware-based spiking neural network systems is demonstrated using the modified national institute of standards and technology handwritten dataset. By comparing systems with and without inhibitory synapse part, it is confirmed that the inhibitory synapse part is an essential element in obtaining effective and high pattern classification capability.

Silicon synaptic transistor for hardware-based spiking neural network and neuromorphic system.

PubMed

Kim, Hyungjin; Hwang, Sungmin; Park, Jungjin; Park, Byung-Gook

2017-10-06

Brain-inspired neuromorphic systems have attracted much attention as new computing paradigms for power-efficient computation. Here, we report a silicon synaptic transistor with two electrically independent gates to realize a hardware-based neural network system without any switching components. The spike-timing dependent plasticity characteristics of the synaptic devices are measured and analyzed. With the help of the device model based on the measured data, the pattern recognition capability of the hardware-based spiking neural network systems is demonstrated using the modified national institute of standards and technology handwritten dataset. By comparing systems with and without inhibitory synapse part, it is confirmed that the inhibitory synapse part is an essential element in obtaining effective and high pattern classification capability.

Differential theory of learning for efficient neural network pattern recognition

NASA Astrophysics Data System (ADS)

Hampshire, John B., II; Vijaya Kumar, Bhagavatula

1993-09-01

We describe a new theory of differential learning by which a broad family of pattern classifiers (including many well-known neural network paradigms) can learn stochastic concepts efficiently. We describe the relationship between a classifier's ability to generate well to unseen test examples and the efficiency of the strategy by which it learns. We list a series of proofs that differential learning is efficient in its information and computational resource requirements, whereas traditional probabilistic learning strategies are not. The proofs are illustrated by a simple example that lends itself to closed-form analysis. We conclude with an optical character recognition task for which three different types of differentially generated classifiers generalize significantly better than their probabilistically generated counterparts.

Differential theory of learning for efficient neural network pattern recognition

NASA Astrophysics Data System (ADS)

Hampshire, John B., II; Vijaya Kumar, Bhagavatula

1993-08-01

We describe a new theory of differential learning by which a broad family of pattern classifiers (including many well-known neural network paradigms) can learn stochastic concepts efficiently. We describe the relationship between a classifier's ability to generalize well to unseen test examples and the efficiency of the strategy by which it learns. We list a series of proofs that differential learning is efficient in its information and computational resource requirements, whereas traditional probabilistic learning strategies are not. The proofs are illustrated by a simple example that lends itself to closed-form analysis. We conclude with an optical character recognition task for which three different types of differentially generated classifiers generalize significantly better than their probabilistically generated counterparts.

A subthreshold aVLSI implementation of the Izhikevich simple neuron model.

PubMed

Rangan, Venkat; Ghosh, Abhishek; Aparin, Vladimir; Cauwenberghs, Gert

2010-01-01

We present a circuit architecture for compact analog VLSI implementation of the Izhikevich neuron model, which efficiently describes a wide variety of neuron spiking and bursting dynamics using two state variables and four adjustable parameters. Log-domain circuit design utilizing MOS transistors in subthreshold results in high energy efficiency, with less than 1pJ of energy consumed per spike. We also discuss the effects of parameter variations on the dynamics of the equations, and present simulation results that replicate several types of neural dynamics. The low power operation and compact analog VLSI realization make the architecture suitable for human-machine interface applications in neural prostheses and implantable bioelectronics, as well as large-scale neural emulation tools for computational neuroscience.

Enabling large-scale viscoelastic calculations via neural network acceleration

NASA Astrophysics Data System (ADS)

Robinson DeVries, P.; Thompson, T. B.; Meade, B. J.

2017-12-01

One of the most significant challenges involved in efforts to understand the effects of repeated earthquake cycle activity are the computational costs of large-scale viscoelastic earthquake cycle models. Deep artificial neural networks (ANNs) can be used to discover new, compact, and accurate computational representations of viscoelastic physics. Once found, these efficient ANN representations may replace computationally intensive viscoelastic codes and accelerate large-scale viscoelastic calculations by more than 50,000%. This magnitude of acceleration enables the modeling of geometrically complex faults over thousands of earthquake cycles across wider ranges of model parameters and at larger spatial and temporal scales than have been previously possible. Perhaps most interestingly from a scientific perspective, ANN representations of viscoelastic physics may lead to basic advances in the understanding of the underlying model phenomenology. We demonstrate the potential of artificial neural networks to illuminate fundamental physical insights with specific examples.

A novel neural network for the synthesis of antennas and microwave devices.

PubMed

Delgado, Heriberto Jose; Thursby, Michael H; Ham, Fredric M

2005-11-01

A novel artificial neural network (SYNTHESIS-ANN) is presented, which has been designed for computationally intensive problems and applied to the optimization of antennas and microwave devices. The antenna example presented is optimized with respect to voltage standing-wave ratio, bandwidth, and frequency of operation. A simple microstrip transmission line problem is used to further describe the ANN effectiveness, in which microstrip line width is optimized with respect to line impedance. The ANNs exploit a unique number representation of input and output data in conjunction with a more standard neural network architecture. An ANN consisting of a heteroassociative memory provided a very efficient method of computing necessary geometrical values for the antenna when used in conjunction with a new randomization process. The number representation used provides significant insight into this new method of fault-tolerant computing. Further work is needed to evaluate the potential of this new paradigm.

Thermodynamic efficiency of learning a rule in neural networks

NASA Astrophysics Data System (ADS)

Goldt, Sebastian; Seifert, Udo

2017-11-01

Biological systems have to build models from their sensory input data that allow them to efficiently process previously unseen inputs. Here, we study a neural network learning a binary classification rule for these inputs from examples provided by a teacher. We analyse the ability of the network to apply the rule to new inputs, that is to generalise from past experience. Using stochastic thermodynamics, we show that the thermodynamic costs of the learning process provide an upper bound on the amount of information that the network is able to learn from its teacher for both batch and online learning. This allows us to introduce a thermodynamic efficiency of learning. We analytically compute the dynamics and the efficiency of a noisy neural network performing online learning in the thermodynamic limit. In particular, we analyse three popular learning algorithms, namely Hebbian, Perceptron and AdaTron learning. Our work extends the methods of stochastic thermodynamics to a new type of learning problem and might form a suitable basis for investigating the thermodynamics of decision-making.

Large Deviations for Nonlocal Stochastic Neural Fields

PubMed Central

2014-01-01

We study the effect of additive noise on integro-differential neural field equations. In particular, we analyze an Amari-type model driven by a Q-Wiener process, and focus on noise-induced transitions and escape. We argue that proving a sharp Kramers’ law for neural fields poses substantial difficulties, but that one may transfer techniques from stochastic partial differential equations to establish a large deviation principle (LDP). Then we demonstrate that an efficient finite-dimensional approximation of the stochastic neural field equation can be achieved using a Galerkin method and that the resulting finite-dimensional rate function for the LDP can have a multiscale structure in certain cases. These results form the starting point for an efficient practical computation of the LDP. Our approach also provides the technical basis for further rigorous study of noise-induced transitions in neural fields based on Galerkin approximations. Mathematics Subject Classification (2000): 60F10, 60H15, 65M60, 92C20. PMID:24742297

Use of neural image analysis methods in the process to determine the dry matter content in the compost

NASA Astrophysics Data System (ADS)

Wojcieszak, D.; Przybył, J.; Lewicki, A.; Ludwiczak, A.; Przybylak, A.; Boniecki, P.; Koszela, K.; Zaborowicz, M.; Przybył, K.; Witaszek, K.

2015-07-01

The aim of this research was investigate the possibility of using methods of computer image analysis and artificial neural networks for to assess the amount of dry matter in the tested compost samples. The research lead to the conclusion that the neural image analysis may be a useful tool in determining the quantity of dry matter in the compost. Generated neural model may be the beginning of research into the use of neural image analysis assess the content of dry matter and other constituents of compost. The presented model RBF 19:19-2-1:1 characterized by test error 0.092189 may be more efficient.

A sub-1-volt analog metal oxide memristive-based synaptic device with large conductance change for energy-efficient spike-based computing systems

NASA Astrophysics Data System (ADS)

Hsieh, Cheng-Chih; Roy, Anupam; Chang, Yao-Feng; Shahrjerdi, Davood; Banerjee, Sanjay K.

2016-11-01

Nanoscale metal oxide memristors have potential in the development of brain-inspired computing systems that are scalable and efficient. In such systems, memristors represent the native electronic analogues of the biological synapses. In this work, we show cerium oxide based bilayer memristors that are forming-free, low-voltage (˜|0.8 V|), energy-efficient (full on/off switching at ˜8 pJ with 20 ns pulses, intermediate states switching at ˜fJ), and reliable. Furthermore, pulse measurements reveal the analog nature of the memristive device; that is, it can directly be programmed to intermediate resistance states. Leveraging this finding, we demonstrate spike-timing-dependent plasticity, a spike-based Hebbian learning rule. In those experiments, the memristor exhibits a marked change in the normalized synaptic strength (>30 times), when the pre- and post-synaptic neural spikes overlap. This demonstration is an important step towards the physical construction of high density and high connectivity neural networks.

Combining neural networks and signed particles to simulate quantum systems more efficiently

NASA Astrophysics Data System (ADS)

Sellier, Jean Michel

2018-04-01

Recently a new formulation of quantum mechanics has been suggested which describes systems by means of ensembles of classical particles provided with a sign. This novel approach mainly consists of two steps: the computation of the Wigner kernel, a multi-dimensional function describing the effects of the potential over the system, and the field-less evolution of the particles which eventually create new signed particles in the process. Although this method has proved to be extremely advantageous in terms of computational resources - as a matter of fact it is able to simulate in a time-dependent fashion many-body systems on relatively small machines - the Wigner kernel can represent the bottleneck of simulations of certain systems. Moreover, storing the kernel can be another issue as the amount of memory needed is cursed by the dimensionality of the system. In this work, we introduce a new technique which drastically reduces the computation time and memory requirement to simulate time-dependent quantum systems which is based on the use of an appropriately tailored neural network combined with the signed particle formalism. In particular, the suggested neural network is able to compute efficiently and reliably the Wigner kernel without any training as its entire set of weights and biases is specified by analytical formulas. As a consequence, the amount of memory for quantum simulations radically drops since the kernel does not need to be stored anymore as it is now computed by the neural network itself, only on the cells of the (discretized) phase-space which are occupied by particles. As its is clearly shown in the final part of this paper, not only this novel approach drastically reduces the computational time, it also remains accurate. The author believes this work opens the way towards effective design of quantum devices, with incredible practical implications.

Reinforced dynamics for enhanced sampling in large atomic and molecular systems

NASA Astrophysics Data System (ADS)

Zhang, Linfeng; Wang, Han; E, Weinan

2018-03-01

A new approach for efficiently exploring the configuration space and computing the free energy of large atomic and molecular systems is proposed, motivated by an analogy with reinforcement learning. There are two major components in this new approach. Like metadynamics, it allows for an efficient exploration of the configuration space by adding an adaptively computed biasing potential to the original dynamics. Like deep reinforcement learning, this biasing potential is trained on the fly using deep neural networks, with data collected judiciously from the exploration and an uncertainty indicator from the neural network model playing the role of the reward function. Parameterization using neural networks makes it feasible to handle cases with a large set of collective variables. This has the potential advantage that selecting precisely the right set of collective variables has now become less critical for capturing the structural transformations of the system. The method is illustrated by studying the full-atom explicit solvent models of alanine dipeptide and tripeptide, as well as the system of a polyalanine-10 molecule with 20 collective variables.

Spiking Neurons for Analysis of Patterns

NASA Technical Reports Server (NTRS)

Huntsberger, Terrance

2008-01-01

Artificial neural networks comprising spiking neurons of a novel type have been conceived as improved pattern-analysis and pattern-recognition computational systems. These neurons are represented by a mathematical model denoted the state-variable model (SVM), which among other things, exploits a computational parallelism inherent in spiking-neuron geometry. Networks of SVM neurons offer advantages of speed and computational efficiency, relative to traditional artificial neural networks. The SVM also overcomes some of the limitations of prior spiking-neuron models. There are numerous potential pattern-recognition, tracking, and data-reduction (data preprocessing) applications for these SVM neural networks on Earth and in exploration of remote planets. Spiking neurons imitate biological neurons more closely than do the neurons of traditional artificial neural networks. A spiking neuron includes a central cell body (soma) surrounded by a tree-like interconnection network (dendrites). Spiking neurons are so named because they generate trains of output pulses (spikes) in response to inputs received from sensors or from other neurons. They gain their speed advantage over traditional neural networks by using the timing of individual spikes for computation, whereas traditional artificial neurons use averages of activity levels over time. Moreover, spiking neurons use the delays inherent in dendritic processing in order to efficiently encode the information content of incoming signals. Because traditional artificial neurons fail to capture this encoding, they have less processing capability, and so it is necessary to use more gates when implementing traditional artificial neurons in electronic circuitry. Such higher-order functions as dynamic tasking are effected by use of pools (collections) of spiking neurons interconnected by spike-transmitting fibers. The SVM includes adaptive thresholds and submodels of transport of ions (in imitation of such transport in biological neurons). These features enable the neurons to adapt their responses to high-rate inputs from sensors, and to adapt their firing thresholds to mitigate noise or effects of potential sensor failure. The mathematical derivation of the SVM starts from a prior model, known in the art as the point soma model, which captures all of the salient properties of neuronal response while keeping the computational cost low. The point-soma latency time is modified to be an exponentially decaying function of the strength of the applied potential. Choosing computational efficiency over biological fidelity, the dendrites surrounding a neuron are represented by simplified compartmental submodels and there are no dendritic spines. Updates to the dendritic potential, calcium-ion concentrations and conductances, and potassium-ion conductances are done by use of equations similar to those of the point soma. Diffusion processes in dendrites are modeled by averaging among nearest-neighbor compartments. Inputs to each of the dendritic compartments come from sensors. Alternatively or in addition, when an affected neuron is part of a pool, inputs can come from other spiking neurons. At present, SVM neural networks are implemented by computational simulation, using algorithms that encode the SVM and its submodels. However, it should be possible to implement these neural networks in hardware: The differential equations for the dendritic and cellular processes in the SVM model of spiking neurons map to equivalent circuits that can be implemented directly in analog very-large-scale integrated (VLSI) circuits.

Neural network fusion capabilities for efficient implementation of tracking algorithms

NASA Astrophysics Data System (ADS)

Sundareshan, Malur K.; Amoozegar, Farid

1997-03-01

The ability to efficiently fuse information of different forms to facilitate intelligent decision making is one of the major capabilities of trained multilayer neural networks that is now being recognized. While development of innovative adaptive control algorithms for nonlinear dynamical plants that attempt to exploit these capabilities seems to be more popular, a corresponding development of nonlinear estimation algorithms using these approaches, particularly for application in target surveillance and guidance operations, has not received similar attention. We describe the capabilities and functionality of neural network algorithms for data fusion and implementation of tracking filters. To discuss details and to serve as a vehicle for quantitative performance evaluations, the illustrative case of estimating the position and velocity of surveillance targets is considered. Efficient target- tracking algorithms that can utilize data from a host of sensing modalities and are capable of reliably tracking even uncooperative targets executing fast and complex maneuvers are of interest in a number of applications. The primary motivation for employing neural networks in these applications comes from the efficiency with which more features extracted from different sensor measurements can be utilized as inputs for estimating target maneuvers. A system architecture that efficiently integrates the fusion capabilities of a trained multilayer neural net with the tracking performance of a Kalman filter is described. The innovation lies in the way the fusion of multisensor data is accomplished to facilitate improved estimation without increasing the computational complexity of the dynamical state estimator itself.

Multiscale Quantum Mechanics/Molecular Mechanics Simulations with Neural Networks.

PubMed

Shen, Lin; Wu, Jingheng; Yang, Weitao

2016-10-11

Molecular dynamics simulation with multiscale quantum mechanics/molecular mechanics (QM/MM) methods is a very powerful tool for understanding the mechanism of chemical and biological processes in solution or enzymes. However, its computational cost can be too high for many biochemical systems because of the large number of ab initio QM calculations. Semiempirical QM/MM simulations have much higher efficiency. Its accuracy can be improved with a correction to reach the ab initio QM/MM level. The computational cost on the ab initio calculation for the correction determines the efficiency. In this paper we developed a neural network method for QM/MM calculation as an extension of the neural-network representation reported by Behler and Parrinello. With this approach, the potential energy of any configuration along the reaction path for a given QM/MM system can be predicted at the ab initio QM/MM level based on the semiempirical QM/MM simulations. We further applied this method to three reactions in water to calculate the free energy changes. The free-energy profile obtained from the semiempirical QM/MM simulation is corrected to the ab initio QM/MM level with the potential energies predicted with the constructed neural network. The results are in excellent accordance with the reference data that are obtained from the ab initio QM/MM molecular dynamics simulation or corrected with direct ab initio QM/MM potential energies. Compared with the correction using direct ab initio QM/MM potential energies, our method shows a speed-up of 1 or 2 orders of magnitude. It demonstrates that the neural network method combined with the semiempirical QM/MM calculation can be an efficient and reliable strategy for chemical reaction simulations.

ELIPS: Toward a Sensor Fusion Processor on a Chip

NASA Technical Reports Server (NTRS)

Daud, Taher; Stoica, Adrian; Tyson, Thomas; Li, Wei-te; Fabunmi, James

1998-01-01

The paper presents the concept and initial tests from the hardware implementation of a low-power, high-speed reconfigurable sensor fusion processor. The Extended Logic Intelligent Processing System (ELIPS) processor is developed to seamlessly combine rule-based systems, fuzzy logic, and neural networks to achieve parallel fusion of sensor in compact low power VLSI. The first demonstration of the ELIPS concept targets interceptor functionality; other applications, mainly in robotics and autonomous systems are considered for the future. The main assumption behind ELIPS is that fuzzy, rule-based and neural forms of computation can serve as the main primitives of an "intelligent" processor. Thus, in the same way classic processors are designed to optimize the hardware implementation of a set of fundamental operations, ELIPS is developed as an efficient implementation of computational intelligence primitives, and relies on a set of fuzzy set, fuzzy inference and neural modules, built in programmable analog hardware. The hardware programmability allows the processor to reconfigure into different machines, taking the most efficient hardware implementation during each phase of information processing. Following software demonstrations on several interceptor data, three important ELIPS building blocks (a fuzzy set preprocessor, a rule-based fuzzy system and a neural network) have been fabricated in analog VLSI hardware and demonstrated microsecond-processing times.

Potential implementation of reservoir computing models based on magnetic skyrmions

NASA Astrophysics Data System (ADS)

Bourianoff, George; Pinna, Daniele; Sitte, Matthias; Everschor-Sitte, Karin

2018-05-01

Reservoir Computing is a type of recursive neural network commonly used for recognizing and predicting spatio-temporal events relying on a complex hierarchy of nested feedback loops to generate a memory functionality. The Reservoir Computing paradigm does not require any knowledge of the reservoir topology or node weights for training purposes and can therefore utilize naturally existing networks formed by a wide variety of physical processes. Most efforts to implement reservoir computing prior to this have focused on utilizing memristor techniques to implement recursive neural networks. This paper examines the potential of magnetic skyrmion fabrics and the complex current patterns which form in them as an attractive physical instantiation for Reservoir Computing. We argue that their nonlinear dynamical interplay resulting from anisotropic magnetoresistance and spin-torque effects allows for an effective and energy efficient nonlinear processing of spatial temporal events with the aim of event recognition and prediction.

Neural dynamics in reconfigurable silicon.

PubMed

Basu, A; Ramakrishnan, S; Petre, C; Koziol, S; Brink, S; Hasler, P E

2010-10-01

A neuromorphic analog chip is presented that is capable of implementing massively parallel neural computations while retaining the programmability of digital systems. We show measurements from neurons with Hopf bifurcations and integrate and fire neurons, excitatory and inhibitory synapses, passive dendrite cables, coupled spiking neurons, and central pattern generators implemented on the chip. This chip provides a platform for not only simulating detailed neuron dynamics but also uses the same to interface with actual cells in applications such as a dynamic clamp. There are 28 computational analog blocks (CAB), each consisting of ion channels with tunable parameters, synapses, winner-take-all elements, current sources, transconductance amplifiers, and capacitors. There are four other CABs which have programmable bias generators. The programmability is achieved using floating gate transistors with on-chip programming control. The switch matrix for interconnecting the components in CABs also consists of floating-gate transistors. Emphasis is placed on replicating the detailed dynamics of computational neural models. Massive computational area efficiency is obtained by using the reconfigurable interconnect as synaptic weights, resulting in more than 50 000 possible 9-b accurate synapses in 9 mm(2).

An Information Theoretic Characterisation of Auditory Encoding

PubMed Central

Overath, Tobias; Cusack, Rhodri; Kumar, Sukhbinder; von Kriegstein, Katharina; Warren, Jason D; Grube, Manon; Carlyon, Robert P; Griffiths, Timothy D

2007-01-01

The entropy metric derived from information theory provides a means to quantify the amount of information transmitted in acoustic streams like speech or music. By systematically varying the entropy of pitch sequences, we sought brain areas where neural activity and energetic demands increase as a function of entropy. Such a relationship is predicted to occur in an efficient encoding mechanism that uses less computational resource when less information is present in the signal: we specifically tested the hypothesis that such a relationship is present in the planum temporale (PT). In two convergent functional MRI studies, we demonstrated this relationship in PT for encoding, while furthermore showing that a distributed fronto-parietal network for retrieval of acoustic information is independent of entropy. The results establish PT as an efficient neural engine that demands less computational resource to encode redundant signals than those with high information content. PMID:17958472

Human adenovirus serotypes 4p and 11p are efficiently expressed in cell lines of neural tumour origin.

PubMed

Skog, Johan; Mei, Ya-Fang; Wadell, Göran

2002-06-01

Most currently used adenovirus vectors are based upon adenovirus serotypes 2 and 5 (Ad2 and Ad5), which have limited efficiencies for gene transfer to human neural cells. Both serotypes bind to the known adenovirus receptor, CAR (coxsackievirus and adenovirus receptor), and have restricted cell tropism. The purpose of this study was to find vector candidates that are superior to Ad5 in infecting human neural tumours. Using flow cytometry, the vector candidates Ad4p, Ad11p and Ad17p were compared to the commonly used adenovirus vector Ad5v for their binding capacity to neural cell lines derived from glioblastoma, medulloblastoma and neuroblastoma cell lines. The production of viral structural proteins and the CAR-binding properties of the different serotypes were also assessed in these cells. Computer-based models of the fibre knobs of Ad4p and Ad17 were created based upon the crystallized fibre knob structure of adenoviruses and analysed for putative receptor-interacting regions that differed from the fibre knob of Ad5. The non CAR-binding vector candidate Ad11p showed clearly the best binding capacity to all of the neural cell lines, binding more than 90% of cells of all of the neural cell lines tested, in contrast to 20% or less for the commonly used vector Ad5v. Ad4p and Ad11p were also internalized and produced viral proteins more successfully than Ad5. Ad4p showed a low binding ability but a very efficient capacity for infection in cell culture. Ad17p virions neither bound or efficiently infected any of the neural cell lines studied.

Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network

PubMed Central

Marcek, Dusan; Durisova, Maria

2016-01-01

This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process. PMID:26977450

Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network.

PubMed

Falat, Lukas; Marcek, Dusan; Durisova, Maria

2016-01-01

This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.

Is "efficiency" a useful concept in cognitive neuroscience?

PubMed

Poldrack, Russell A

2015-02-01

It is common in the cognitive neuroscience literature to explain differences in activation in terms of differences in the "efficiency" of neural function. I argue here that this usage of the concept of efficiency is empty and simply redescribes activation differences rather than providing a useful explanation of them. I examine a number of possible explanations for differential activation in terms of task performance, neuronal computation, neuronal energetics, and network organization. While the concept of "efficiency" is vacuous as it is commonly employed in the neuroimaging literature, an examination of brain development in the context of neural coding, neuroenergetics, and network structure provides a roadmap for future investigation, which is fundamental to an improved understanding of developmental effects and group differences in neuroimaging signals. Copyright © 2014 The Author. Published by Elsevier Ltd.. All rights reserved.

Real-time object-to-features vectorisation via Siamese neural networks

NASA Astrophysics Data System (ADS)

Fedorenko, Fedor; Usilin, Sergey

2017-03-01

Object-to-features vectorisation is a hard problem to solve for objects that can be hard to distinguish. Siamese and Triplet neural networks are one of the more recent tools used for such task. However, most networks used are very deep networks that prove to be hard to compute in the Internet of Things setting. In this paper, a computationally efficient neural network is proposed for real-time object-to-features vectorisation into a Euclidean metric space. We use L2 distance to reflect feature vector similarity during both training and testing. In this way, feature vectors we develop can be easily classified using K-Nearest Neighbours classifier. Such approach can be used to train networks to vectorise such "problematic" objects like images of human faces, keypoint image patches, like keypoints on Arctic maps and surrounding marine areas.

Computational models of epileptiform activity.

PubMed

Wendling, Fabrice; Benquet, Pascal; Bartolomei, Fabrice; Jirsa, Viktor

2016-02-15

We reviewed computer models that have been developed to reproduce and explain epileptiform activity. Unlike other already-published reviews on computer models of epilepsy, the proposed overview starts from the various types of epileptiform activity encountered during both interictal and ictal periods. Computational models proposed so far in the context of partial and generalized epilepsies are classified according to the following taxonomy: neural mass, neural field, detailed network and formal mathematical models. Insights gained about interictal epileptic spikes and high-frequency oscillations, about fast oscillations at seizure onset, about seizure initiation and propagation, about spike-wave discharges and about status epilepticus are described. This review shows the richness and complementarity of the various modeling approaches as well as the fruitful contribution of the computational neuroscience community in the field of epilepsy research. It shows that models have progressively gained acceptance and are now considered as an efficient way of integrating structural, functional and pathophysiological data about neural systems into "coherent and interpretable views". The advantages, limitations and future of modeling approaches are discussed. Perspectives in epilepsy research and clinical epileptology indicate that very promising directions are foreseen, like model-guided experiments or model-guided therapeutic strategy, among others. Copyright © 2015 Elsevier B.V. All rights reserved.

Competition in high dimensional spaces using a sparse approximation of neural fields.

PubMed

Quinton, Jean-Charles; Girau, Bernard; Lefort, Mathieu

2011-01-01

The Continuum Neural Field Theory implements competition within topologically organized neural networks with lateral inhibitory connections. However, due to the polynomial complexity of matrix-based implementations, updating dense representations of the activity becomes computationally intractable when an adaptive resolution or an arbitrary number of input dimensions is required. This paper proposes an alternative to self-organizing maps with a sparse implementation based on Gaussian mixture models, promoting a trade-off in redundancy for higher computational efficiency and alleviating constraints on the underlying substrate.This version reproduces the emergent attentional properties of the original equations, by directly applying them within a continuous approximation of a high dimensional neural field. The model is compatible with preprocessed sensory flows but can also be interfaced with artificial systems. This is particularly important for sensorimotor systems, where decisions and motor actions must be taken and updated in real-time. Preliminary tests are performed on a reactive color tracking application, using spatially distributed color features.

Closed Loop Interactions between Spiking Neural Network and Robotic Simulators Based on MUSIC and ROS.

PubMed

Weidel, Philipp; Djurfeldt, Mikael; Duarte, Renato C; Morrison, Abigail

2016-01-01

In order to properly assess the function and computational properties of simulated neural systems, it is necessary to account for the nature of the stimuli that drive the system. However, providing stimuli that are rich and yet both reproducible and amenable to experimental manipulations is technically challenging, and even more so if a closed-loop scenario is required. In this work, we present a novel approach to solve this problem, connecting robotics and neural network simulators. We implement a middleware solution that bridges the Robotic Operating System (ROS) to the Multi-Simulator Coordinator (MUSIC). This enables any robotic and neural simulators that implement the corresponding interfaces to be efficiently coupled, allowing real-time performance for a wide range of configurations. This work extends the toolset available for researchers in both neurorobotics and computational neuroscience, and creates the opportunity to perform closed-loop experiments of arbitrary complexity to address questions in multiple areas, including embodiment, agency, and reinforcement learning.

Closed Loop Interactions between Spiking Neural Network and Robotic Simulators Based on MUSIC and ROS

PubMed Central

Weidel, Philipp; Djurfeldt, Mikael; Duarte, Renato C.; Morrison, Abigail

2016-01-01

In order to properly assess the function and computational properties of simulated neural systems, it is necessary to account for the nature of the stimuli that drive the system. However, providing stimuli that are rich and yet both reproducible and amenable to experimental manipulations is technically challenging, and even more so if a closed-loop scenario is required. In this work, we present a novel approach to solve this problem, connecting robotics and neural network simulators. We implement a middleware solution that bridges the Robotic Operating System (ROS) to the Multi-Simulator Coordinator (MUSIC). This enables any robotic and neural simulators that implement the corresponding interfaces to be efficiently coupled, allowing real-time performance for a wide range of configurations. This work extends the toolset available for researchers in both neurorobotics and computational neuroscience, and creates the opportunity to perform closed-loop experiments of arbitrary complexity to address questions in multiple areas, including embodiment, agency, and reinforcement learning. PMID:27536234

Adaptively combined FIR and functional link artificial neural network equalizer for nonlinear communication channel.

PubMed

Zhao, Haiquan; Zhang, Jiashu

2009-04-01

This paper proposes a novel computational efficient adaptive nonlinear equalizer based on combination of finite impulse response (FIR) filter and functional link artificial neural network (CFFLANN) to compensate linear and nonlinear distortions in nonlinear communication channel. This convex nonlinear combination results in improving the speed while retaining the lower steady-state error. In addition, since the CFFLANN needs not the hidden layers, which exist in conventional neural-network-based equalizers, it exhibits a simpler structure than the traditional neural networks (NNs) and can require less computational burden during the training mode. Moreover, appropriate adaptation algorithm for the proposed equalizer is derived by the modified least mean square (MLMS). Results obtained from the simulations clearly show that the proposed equalizer using the MLMS algorithm can availably eliminate various intensity linear and nonlinear distortions, and be provided with better anti-jamming performance. Furthermore, comparisons of the mean squared error (MSE), the bit error rate (BER), and the effect of eigenvalue ratio (EVR) of input correlation matrix are presented.

Stochastic Spiking Neural Networks Enabled by Magnetic Tunnel Junctions: From Nontelegraphic to Telegraphic Switching Regimes

NASA Astrophysics Data System (ADS)

Liyanagedera, Chamika M.; Sengupta, Abhronil; Jaiswal, Akhilesh; Roy, Kaushik

2017-12-01

Stochastic spiking neural networks based on nanoelectronic spin devices can be a possible pathway to achieving "brainlike" compact and energy-efficient cognitive intelligence. The computational model attempt to exploit the intrinsic device stochasticity of nanoelectronic synaptic or neural components to perform learning or inference. However, there has been limited analysis on the scaling effect of stochastic spin devices and its impact on the operation of such stochastic networks at the system level. This work attempts to explore the design space and analyze the performance of nanomagnet-based stochastic neuromorphic computing architectures for magnets with different barrier heights. We illustrate how the underlying network architecture must be modified to account for the random telegraphic switching behavior displayed by magnets with low barrier heights as they are scaled into the superparamagnetic regime. We perform a device-to-system-level analysis on a deep neural-network architecture for a digit-recognition problem on the MNIST data set.

Neural network fusion capabilities for efficient implementation of tracking algorithms

NASA Astrophysics Data System (ADS)

Sundareshan, Malur K.; Amoozegar, Farid

1996-05-01

The ability to efficiently fuse information of different forms for facilitating intelligent decision-making is one of the major capabilities of trained multilayer neural networks that is being recognized int eh recent times. While development of innovative adaptive control algorithms for nonlinear dynamical plants which attempt to exploit these capabilities seems to be more popular, a corresponding development of nonlinear estimation algorithms using these approaches, particularly for application in target surveillance and guidance operations, has not received similar attention. In this paper we describe the capabilities and functionality of neural network algorithms for data fusion and implementation of nonlinear tracking filters. For a discussion of details and for serving as a vehicle for quantitative performance evaluations, the illustrative case of estimating the position and velocity of surveillance targets is considered. Efficient target tracking algorithms that can utilize data from a host of sensing modalities and are capable of reliably tracking even uncooperative targets executing fast and complex maneuvers are of interest in a number of applications. The primary motivation for employing neural networks in these applications comes form the efficiency with which more features extracted from different sensor measurements can be utilized as inputs for estimating target maneuvers. Such an approach results in an overall nonlinear tracking filter which has several advantages over the popular efforts at designing nonlinear estimation algorithms for tracking applications, the principle one being the reduction of mathematical and computational complexities. A system architecture that efficiently integrates the processing capabilities of a trained multilayer neural net with the tracking performance of a Kalman filter is described in this paper.

A Stochastic Spiking Neural Network for Virtual Screening.

PubMed

Morro, A; Canals, V; Oliver, A; Alomar, M L; Galan-Prado, F; Ballester, P J; Rossello, J L

2018-04-01

Virtual screening (VS) has become a key computational tool in early drug design and screening performance is of high relevance due to the large volume of data that must be processed to identify molecules with the sought activity-related pattern. At the same time, the hardware implementations of spiking neural networks (SNNs) arise as an emerging computing technique that can be applied to parallelize processes that normally present a high cost in terms of computing time and power. Consequently, SNN represents an attractive alternative to perform time-consuming processing tasks, such as VS. In this brief, we present a smart stochastic spiking neural architecture that implements the ultrafast shape recognition (USR) algorithm achieving two order of magnitude of speed improvement with respect to USR software implementations. The neural system is implemented in hardware using field-programmable gate arrays allowing a highly parallelized USR implementation. The results show that, due to the high parallelization of the system, millions of compounds can be checked in reasonable times. From these results, we can state that the proposed architecture arises as a feasible methodology to efficiently enhance time-consuming data-mining processes such as 3-D molecular similarity search.

Algorithmic design of a noise-resistant and efficient closed-loop deep brain stimulation system: A computational approach.

PubMed

Karamintziou, Sofia D; Custódio, Ana Luísa; Piallat, Brigitte; Polosan, Mircea; Chabardès, Stéphan; Stathis, Pantelis G; Tagaris, George A; Sakas, Damianos E; Polychronaki, Georgia E; Tsirogiannis, George L; David, Olivier; Nikita, Konstantina S

2017-01-01

Advances in the field of closed-loop neuromodulation call for analysis and modeling approaches capable of confronting challenges related to the complex neuronal response to stimulation and the presence of strong internal and measurement noise in neural recordings. Here we elaborate on the algorithmic aspects of a noise-resistant closed-loop subthalamic nucleus deep brain stimulation system for advanced Parkinson's disease and treatment-refractory obsessive-compulsive disorder, ensuring remarkable performance in terms of both efficiency and selectivity of stimulation, as well as in terms of computational speed. First, we propose an efficient method drawn from dynamical systems theory, for the reliable assessment of significant nonlinear coupling between beta and high-frequency subthalamic neuronal activity, as a biomarker for feedback control. Further, we present a model-based strategy through which optimal parameters of stimulation for minimum energy desynchronizing control of neuronal activity are being identified. The strategy integrates stochastic modeling and derivative-free optimization of neural dynamics based on quadratic modeling. On the basis of numerical simulations, we demonstrate the potential of the presented modeling approach to identify, at a relatively low computational cost, stimulation settings potentially associated with a significantly higher degree of efficiency and selectivity compared with stimulation settings determined post-operatively. Our data reinforce the hypothesis that model-based control strategies are crucial for the design of novel stimulation protocols at the backstage of clinical applications.

Magnetic Tunnel Junction Based Long-Term Short-Term Stochastic Synapse for a Spiking Neural Network with On-Chip STDP Learning

NASA Astrophysics Data System (ADS)

Srinivasan, Gopalakrishnan; Sengupta, Abhronil; Roy, Kaushik

2016-07-01

Spiking Neural Networks (SNNs) have emerged as a powerful neuromorphic computing paradigm to carry out classification and recognition tasks. Nevertheless, the general purpose computing platforms and the custom hardware architectures implemented using standard CMOS technology, have been unable to rival the power efficiency of the human brain. Hence, there is a need for novel nanoelectronic devices that can efficiently model the neurons and synapses constituting an SNN. In this work, we propose a heterostructure composed of a Magnetic Tunnel Junction (MTJ) and a heavy metal as a stochastic binary synapse. Synaptic plasticity is achieved by the stochastic switching of the MTJ conductance states, based on the temporal correlation between the spiking activities of the interconnecting neurons. Additionally, we present a significance driven long-term short-term stochastic synapse comprising two unique binary synaptic elements, in order to improve the synaptic learning efficiency. We demonstrate the efficacy of the proposed synaptic configurations and the stochastic learning algorithm on an SNN trained to classify handwritten digits from the MNIST dataset, using a device to system-level simulation framework. The power efficiency of the proposed neuromorphic system stems from the ultra-low programming energy of the spintronic synapses.

Magnetic Tunnel Junction Based Long-Term Short-Term Stochastic Synapse for a Spiking Neural Network with On-Chip STDP Learning.

PubMed

Srinivasan, Gopalakrishnan; Sengupta, Abhronil; Roy, Kaushik

2016-07-13

Spiking Neural Networks (SNNs) have emerged as a powerful neuromorphic computing paradigm to carry out classification and recognition tasks. Nevertheless, the general purpose computing platforms and the custom hardware architectures implemented using standard CMOS technology, have been unable to rival the power efficiency of the human brain. Hence, there is a need for novel nanoelectronic devices that can efficiently model the neurons and synapses constituting an SNN. In this work, we propose a heterostructure composed of a Magnetic Tunnel Junction (MTJ) and a heavy metal as a stochastic binary synapse. Synaptic plasticity is achieved by the stochastic switching of the MTJ conductance states, based on the temporal correlation between the spiking activities of the interconnecting neurons. Additionally, we present a significance driven long-term short-term stochastic synapse comprising two unique binary synaptic elements, in order to improve the synaptic learning efficiency. We demonstrate the efficacy of the proposed synaptic configurations and the stochastic learning algorithm on an SNN trained to classify handwritten digits from the MNIST dataset, using a device to system-level simulation framework. The power efficiency of the proposed neuromorphic system stems from the ultra-low programming energy of the spintronic synapses.

Qualitatively similar processing for own- and other-race faces: Evidence from efficiency and equivalent input noise.

PubMed

Shafai, Fakhri; Oruc, Ipek

2018-02-01

The other-race effect is the finding of diminished performance in recognition of other-race faces compared to those of own-race. It has been suggested that the other-race effect stems from specialized expert processes being tuned exclusively to own-race faces. In the present study, we measured recognition contrast thresholds for own- and other-race faces as well as houses for Caucasian observers. We have factored face recognition performance into two invariant aspects of visual function: efficiency, which is related to neural computations and processing demanded by the task, and equivalent input noise, related to signal degradation within the visual system. We hypothesized that if expert processes are available only to own-race faces, this should translate into substantially greater recognition efficiencies for own-race compared to other-race faces. Instead, we found similar recognition efficiencies for both own- and other-race faces. The other-race effect manifested as increased equivalent input noise. These results argue against qualitatively distinct perceptual processes. Instead they suggest that for Caucasian observers, similar neural computations underlie recognition of own- and other-race faces. Copyright © 2018 Elsevier Ltd. All rights reserved.

Flexible Neural Electrode Array Based-on Porous Graphene for Cortical Microstimulation and Sensing

NASA Astrophysics Data System (ADS)

Lu, Yichen; Lyu, Hongming; Richardson, Andrew G.; Lucas, Timothy H.; Kuzum, Duygu

2016-09-01

Neural sensing and stimulation have been the backbone of neuroscience research, brain-machine interfaces and clinical neuromodulation therapies for decades. To-date, most of the neural stimulation systems have relied on sharp metal microelectrodes with poor electrochemical properties that induce extensive damage to the tissue and significantly degrade the long-term stability of implantable systems. Here, we demonstrate a flexible cortical microelectrode array based on porous graphene, which is capable of efficient electrophysiological sensing and stimulation from the brain surface, without penetrating into the tissue. Porous graphene electrodes show superior impedance and charge injection characteristics making them ideal for high efficiency cortical sensing and stimulation. They exhibit no physical delamination or degradation even after 1 million biphasic stimulation cycles, confirming high endurance. In in vivo experiments with rodents, same array is used to sense brain activity patterns with high spatio-temporal resolution and to control leg muscles with high-precision electrical stimulation from the cortical surface. Flexible porous graphene array offers a minimally invasive but high efficiency neuromodulation scheme with potential applications in cortical mapping, brain-computer interfaces, treatment of neurological disorders, where high resolution and simultaneous recording and stimulation of neural activity are crucial.

The Functional Neuroanatomy of Human Face Perception.

PubMed

Grill-Spector, Kalanit; Weiner, Kevin S; Kay, Kendrick; Gomez, Jesse

2017-09-15

Face perception is critical for normal social functioning and is mediated by a network of regions in the ventral visual stream. In this review, we describe recent neuroimaging findings regarding the macro- and microscopic anatomical features of the ventral face network, the characteristics of white matter connections, and basic computations performed by population receptive fields within face-selective regions composing this network. We emphasize the importance of the neural tissue properties and white matter connections of each region, as these anatomical properties may be tightly linked to the functional characteristics of the ventral face network. We end by considering how empirical investigations of the neural architecture of the face network may inform the development of computational models and shed light on how computations in the face network enable efficient face perception.

A Dynamic Bioinspired Neural Network Based Real-Time Path Planning Method for Autonomous Underwater Vehicles

PubMed Central

2017-01-01

Real-time path planning for autonomous underwater vehicle (AUV) is a very difficult and challenging task. Bioinspired neural network (BINN) has been used to deal with this problem for its many distinct advantages: that is, no learning process is needed and realization is also easy. However, there are some shortcomings when BINN is applied to AUV path planning in a three-dimensional (3D) unknown environment, including complex computing problem when the environment is very large and repeated path problem when the size of obstacles is bigger than the detection range of sensors. To deal with these problems, an improved dynamic BINN is proposed in this paper. In this proposed method, the AUV is regarded as the core of the BINN and the size of the BINN is based on the detection range of sensors. Then the BINN will move with the AUV and the computing could be reduced. A virtual target is proposed in the path planning method to ensure that the AUV can move to the real target effectively and avoid big-size obstacles automatically. Furthermore, a target attractor concept is introduced to improve the computing efficiency of neural activities. Finally, some experiments are conducted under various 3D underwater environments. The experimental results show that the proposed BINN based method can deal with the real-time path planning problem for AUV efficiently. PMID:28255297

A Dynamic Bioinspired Neural Network Based Real-Time Path Planning Method for Autonomous Underwater Vehicles.

PubMed

Ni, Jianjun; Wu, Liuying; Shi, Pengfei; Yang, Simon X

2017-01-01

Real-time path planning for autonomous underwater vehicle (AUV) is a very difficult and challenging task. Bioinspired neural network (BINN) has been used to deal with this problem for its many distinct advantages: that is, no learning process is needed and realization is also easy. However, there are some shortcomings when BINN is applied to AUV path planning in a three-dimensional (3D) unknown environment, including complex computing problem when the environment is very large and repeated path problem when the size of obstacles is bigger than the detection range of sensors. To deal with these problems, an improved dynamic BINN is proposed in this paper. In this proposed method, the AUV is regarded as the core of the BINN and the size of the BINN is based on the detection range of sensors. Then the BINN will move with the AUV and the computing could be reduced. A virtual target is proposed in the path planning method to ensure that the AUV can move to the real target effectively and avoid big-size obstacles automatically. Furthermore, a target attractor concept is introduced to improve the computing efficiency of neural activities. Finally, some experiments are conducted under various 3D underwater environments. The experimental results show that the proposed BINN based method can deal with the real-time path planning problem for AUV efficiently.

Computationally efficient modeling of proprioceptive signals in the upper limb for prostheses: a simulation study

PubMed Central

Williams, Ian; Constandinou, Timothy G.

2014-01-01

Accurate models of proprioceptive neural patterns could 1 day play an important role in the creation of an intuitive proprioceptive neural prosthesis for amputees. This paper looks at combining efficient implementations of biomechanical and proprioceptor models in order to generate signals that mimic human muscular proprioceptive patterns for future experimental work in prosthesis feedback. A neuro-musculoskeletal model of the upper limb with 7 degrees of freedom and 17 muscles is presented and generates real time estimates of muscle spindle and Golgi Tendon Organ neural firing patterns. Unlike previous neuro-musculoskeletal models, muscle activation and excitation levels are unknowns in this application and an inverse dynamics tool (static optimization) is integrated to estimate these variables. A proprioceptive prosthesis will need to be portable and this is incompatible with the computationally demanding nature of standard biomechanical and proprioceptor modeling. This paper uses and proposes a number of approximations and optimizations to make real time operation on portable hardware feasible. Finally technical obstacles to mimicking natural feedback for an intuitive proprioceptive prosthesis, as well as issues and limitations with existing models, are identified and discussed. PMID:25009463

Energy scaling advantages of resistive memory crossbar based computation and its application to sparse coding

DOE Office of Scientific and Technical Information (OSTI.GOV)

Agarwal, Sapan; Quach, Tu -Thach; Parekh, Ojas

In this study, the exponential increase in data over the last decade presents a significant challenge to analytics efforts that seek to process and interpret such data for various applications. Neural-inspired computing approaches are being developed in order to leverage the computational properties of the analog, low-power data processing observed in biological systems. Analog resistive memory crossbars can perform a parallel read or a vector-matrix multiplication as well as a parallel write or a rank-1 update with high computational efficiency. For an N × N crossbar, these two kernels can be O(N) more energy efficient than a conventional digital memory-basedmore » architecture. If the read operation is noise limited, the energy to read a column can be independent of the crossbar size (O(1)). These two kernels form the basis of many neuromorphic algorithms such as image, text, and speech recognition. For instance, these kernels can be applied to a neural sparse coding algorithm to give an O(N) reduction in energy for the entire algorithm when run with finite precision. Sparse coding is a rich problem with a host of applications including computer vision, object tracking, and more generally unsupervised learning.« less

Energy scaling advantages of resistive memory crossbar based computation and its application to sparse coding

DOE PAGES

Agarwal, Sapan; Quach, Tu -Thach; Parekh, Ojas; ...

2016-01-06

In this study, the exponential increase in data over the last decade presents a significant challenge to analytics efforts that seek to process and interpret such data for various applications. Neural-inspired computing approaches are being developed in order to leverage the computational properties of the analog, low-power data processing observed in biological systems. Analog resistive memory crossbars can perform a parallel read or a vector-matrix multiplication as well as a parallel write or a rank-1 update with high computational efficiency. For an N × N crossbar, these two kernels can be O(N) more energy efficient than a conventional digital memory-basedmore » architecture. If the read operation is noise limited, the energy to read a column can be independent of the crossbar size (O(1)). These two kernels form the basis of many neuromorphic algorithms such as image, text, and speech recognition. For instance, these kernels can be applied to a neural sparse coding algorithm to give an O(N) reduction in energy for the entire algorithm when run with finite precision. Sparse coding is a rich problem with a host of applications including computer vision, object tracking, and more generally unsupervised learning.« less

Neural Networks In Mining Sciences - General Overview And Some Representative Examples

NASA Astrophysics Data System (ADS)

Tadeusiewicz, Ryszard

2015-12-01

The many difficult problems that must now be addressed in mining sciences make us search for ever newer and more efficient computer tools that can be used to solve those problems. Among the numerous tools of this type, there are neural networks presented in this article - which, although not yet widely used in mining sciences, are certainly worth consideration. Neural networks are a technique which belongs to so called artificial intelligence, and originates from the attempts to model the structure and functioning of biological nervous systems. Initially constructed and tested exclusively out of scientific curiosity, as computer models of parts of the human brain, neural networks have become a surprisingly effective calculation tool in many areas: in technology, medicine, economics, and even social sciences. Unfortunately, they are relatively rarely used in mining sciences and mining technology. The article is intended to convince the readers that neural networks can be very useful also in mining sciences. It contains information how modern neural networks are built, how they operate and how one can use them. The preliminary discussion presented in this paper can help the reader gain an opinion whether this is a tool with handy properties, useful for him, and what it might come in useful for. Of course, the brief introduction to neural networks contained in this paper will not be enough for the readers who get convinced by the arguments contained here, and want to use neural networks. They will still need a considerable portion of detailed knowledge so that they can begin to independently create and build such networks, and use them in practice. However, an interested reader who decides to try out the capabilities of neural networks will also find here links to references that will allow him to start exploration of neural networks fast, and then work with this handy tool efficiently. This will be easy, because there are currently quite a few ready-made computer programs, easily available, which allow their user to quickly and effortlessly create artificial neural networks, run them, train and use in practice. The key issue is the question how to use these networks in mining sciences. The fact that this is possible and desirable is shown by convincing examples included in the second part of this study. From the very rich literature on the various applications of neural networks, we have selected several works that show how and what neural networks are used in the mining industry, and what has been achieved thanks to their use. The review of applications will continue in the next article, filed already for publication in the journal "Archives of Mining Sciences". Only studying these two articles will provide sufficient knowledge for initial guidance in the area of issues under consideration here.

Population coding and decoding in a neural field: a computational study.

PubMed

Wu, Si; Amari, Shun-Ichi; Nakahara, Hiroyuki

2002-05-01

This study uses a neural field model to investigate computational aspects of population coding and decoding when the stimulus is a single variable. A general prototype model for the encoding process is proposed, in which neural responses are correlated, with strength specified by a gaussian function of their difference in preferred stimuli. Based on the model, we study the effect of correlation on the Fisher information, compare the performances of three decoding methods that differ in the amount of encoding information being used, and investigate the implementation of the three methods by using a recurrent network. This study not only rediscovers main results in existing literatures in a unified way, but also reveals important new features, especially when the neural correlation is strong. As the neural correlation of firing becomes larger, the Fisher information decreases drastically. We confirm that as the width of correlation increases, the Fisher information saturates and no longer increases in proportion to the number of neurons. However, we prove that as the width increases further--wider than (sqrt)2 times the effective width of the turning function--the Fisher information increases again, and it increases without limit in proportion to the number of neurons. Furthermore, we clarify the asymptotic efficiency of the maximum likelihood inference (MLI) type of decoding methods for correlated neural signals. It shows that when the correlation covers a nonlocal range of population (excepting the uniform correlation and when the noise is extremely small), the MLI type of method, whose decoding error satisfies the Cauchy-type distribution, is not asymptotically efficient. This implies that the variance is no longer adequate to measure decoding accuracy.

Event-driven processing for hardware-efficient neural spike sorting

NASA Astrophysics Data System (ADS)

Liu, Yan; Pereira, João L.; Constandinou, Timothy G.

2018-02-01

Objective. The prospect of real-time and on-node spike sorting provides a genuine opportunity to push the envelope of large-scale integrated neural recording systems. In such systems the hardware resources, power requirements and data bandwidth increase linearly with channel count. Event-based (or data-driven) processing can provide here a new efficient means for hardware implementation that is completely activity dependant. In this work, we investigate using continuous-time level-crossing sampling for efficient data representation and subsequent spike processing. Approach. (1) We first compare signals (synthetic neural datasets) encoded with this technique against conventional sampling. (2) We then show how such a representation can be directly exploited by extracting simple time domain features from the bitstream to perform neural spike sorting. (3) The proposed method is implemented in a low power FPGA platform to demonstrate its hardware viability. Main results. It is observed that considerably lower data rates are achievable when using 7 bits or less to represent the signals, whilst maintaining the signal fidelity. Results obtained using both MATLAB and reconfigurable logic hardware (FPGA) indicate that feature extraction and spike sorting accuracies can be achieved with comparable or better accuracy than reference methods whilst also requiring relatively low hardware resources. Significance. By effectively exploiting continuous-time data representation, neural signal processing can be achieved in a completely event-driven manner, reducing both the required resources (memory, complexity) and computations (operations). This will see future large-scale neural systems integrating on-node processing in real-time hardware.

Recurrent neural network based virtual detection line

NASA Astrophysics Data System (ADS)

Kadikis, Roberts

2018-04-01

The paper proposes an efficient method for detection of moving objects in the video. The objects are detected when they cross a virtual detection line. Only the pixels of the detection line are processed, which makes the method computationally efficient. A Recurrent Neural Network processes these pixels. The machine learning approach allows one to train a model that works in different and changing outdoor conditions. Also, the same network can be trained for various detection tasks, which is demonstrated by the tests on vehicle and people counting. In addition, the paper proposes a method for semi-automatic acquisition of labeled training data. The labeling method is used to create training and testing datasets, which in turn are used to train and evaluate the accuracy and efficiency of the detection method. The method shows similar accuracy as the alternative efficient methods but provides greater adaptability and usability for different tasks.

Relabeling exchange method (REM) for learning in neural networks

NASA Astrophysics Data System (ADS)

Wu, Wen; Mammone, Richard J.

1994-02-01

The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.

Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data.

PubMed

Ching, Travers; Zhu, Xun; Garmire, Lana X

2018-04-01

Artificial neural networks (ANN) are computing architectures with many interconnections of simple neural-inspired computing elements, and have been applied to biomedical fields such as imaging analysis and diagnosis. We have developed a new ANN framework called Cox-nnet to predict patient prognosis from high throughput transcriptomics data. In 10 TCGA RNA-Seq data sets, Cox-nnet achieves the same or better predictive accuracy compared to other methods, including Cox-proportional hazards regression (with LASSO, ridge, and mimimax concave penalty), Random Forests Survival and CoxBoost. Cox-nnet also reveals richer biological information, at both the pathway and gene levels. The outputs from the hidden layer node provide an alternative approach for survival-sensitive dimension reduction. In summary, we have developed a new method for accurate and efficient prognosis prediction on high throughput data, with functional biological insights. The source code is freely available at https://github.com/lanagarmire/cox-nnet.

Hardware implementation of CMAC neural network with reduced storage requirement.

PubMed

Ker, J S; Kuo, Y H; Wen, R C; Liu, B D

1997-01-01

The cerebellar model articulation controller (CMAC) neural network has the advantages of fast convergence speed and low computation complexity. However, it suffers from a low storage space utilization rate on weight memory. In this paper, we propose a direct weight address mapping approach, which can reduce the required weight memory size with a utilization rate near 100%. Based on such an address mapping approach, we developed a pipeline architecture to efficiently perform the addressing operations. The proposed direct weight address mapping approach also speeds up the computation for the generation of weight addresses. Besides, a CMAC hardware prototype used for color calibration has been implemented to confirm the proposed approach and architecture.

A Spiking Neural Simulator Integrating Event-Driven and Time-Driven Computation Schemes Using Parallel CPU-GPU Co-Processing: A Case Study.

PubMed

Naveros, Francisco; Luque, Niceto R; Garrido, Jesús A; Carrillo, Richard R; Anguita, Mancia; Ros, Eduardo

2015-07-01

Time-driven simulation methods in traditional CPU architectures perform well and precisely when simulating small-scale spiking neural networks. Nevertheless, they still have drawbacks when simulating large-scale systems. Conversely, event-driven simulation methods in CPUs and time-driven simulation methods in graphic processing units (GPUs) can outperform CPU time-driven methods under certain conditions. With this performance improvement in mind, we have developed an event-and-time-driven spiking neural network simulator suitable for a hybrid CPU-GPU platform. Our neural simulator is able to efficiently simulate bio-inspired spiking neural networks consisting of different neural models, which can be distributed heterogeneously in both small layers and large layers or subsystems. For the sake of efficiency, the low-activity parts of the neural network can be simulated in CPU using event-driven methods while the high-activity subsystems can be simulated in either CPU (a few neurons) or GPU (thousands or millions of neurons) using time-driven methods. In this brief, we have undertaken a comparative study of these different simulation methods. For benchmarking the different simulation methods and platforms, we have used a cerebellar-inspired neural-network model consisting of a very dense granular layer and a Purkinje layer with a smaller number of cells (according to biological ratios). Thus, this cerebellar-like network includes a dense diverging neural layer (increasing the dimensionality of its internal representation and sparse coding) and a converging neural layer (integration) similar to many other biologically inspired and also artificial neural networks.

Binary Associative Memories as a Benchmark for Spiking Neuromorphic Hardware

PubMed Central

Stöckel, Andreas; Jenzen, Christoph; Thies, Michael; Rückert, Ulrich

2017-01-01

Large-scale neuromorphic hardware platforms, specialized computer systems for energy efficient simulation of spiking neural networks, are being developed around the world, for example as part of the European Human Brain Project (HBP). Due to conceptual differences, a universal performance analysis of these systems in terms of runtime, accuracy and energy efficiency is non-trivial, yet indispensable for further hard- and software development. In this paper we describe a scalable benchmark based on a spiking neural network implementation of the binary neural associative memory. We treat neuromorphic hardware and software simulators as black-boxes and execute exactly the same network description across all devices. Experiments on the HBP platforms under varying configurations of the associative memory show that the presented method allows to test the quality of the neuron model implementation, and to explain significant deviations from the expected reference output. PMID:28878642

Are artificial neural networks black boxes?

PubMed

Benitez, J M; Castro, J L; Requena, I

1997-01-01

Artificial neural networks are efficient computing models which have shown their strengths in solving hard problems in artificial intelligence. They have also been shown to be universal approximators. Notwithstanding, one of the major criticisms is their being black boxes, since no satisfactory explanation of their behavior has been offered. In this paper, we provide such an interpretation of neural networks so that they will no longer be seen as black boxes. This is stated after establishing the equality between a certain class of neural nets and fuzzy rule-based systems. This interpretation is built with fuzzy rules using a new fuzzy logic operator which is defined after introducing the concept of f-duality. In addition, this interpretation offers an automated knowledge acquisition procedure.

A quantum-implementable neural network model

NASA Astrophysics Data System (ADS)

Chen, Jialin; Wang, Lingli; Charbon, Edoardo

2017-10-01

A quantum-implementable neural network, namely quantum probability neural network (QPNN) model, is proposed in this paper. QPNN can use quantum parallelism to trace all possible network states to improve the result. Due to its unique quantum nature, this model is robust to several quantum noises under certain conditions, which can be efficiently implemented by the qubus quantum computer. Another advantage is that QPNN can be used as memory to retrieve the most relevant data and even to generate new data. The MATLAB experimental results of Iris data classification and MNIST handwriting recognition show that much less neuron resources are required in QPNN to obtain a good result than the classical feedforward neural network. The proposed QPNN model indicates that quantum effects are useful for real-life classification tasks.

Deep neural nets as a method for quantitative structure-activity relationships.

PubMed

Ma, Junshui; Sheridan, Robert P; Liaw, Andy; Dahl, George E; Svetnik, Vladimir

2015-02-23

Neural networks were widely used for quantitative structure-activity relationships (QSAR) in the 1990s. Because of various practical issues (e.g., slow on large problems, difficult to train, prone to overfitting, etc.), they were superseded by more robust methods like support vector machine (SVM) and random forest (RF), which arose in the early 2000s. The last 10 years has witnessed a revival of neural networks in the machine learning community thanks to new methods for preventing overfitting, more efficient training algorithms, and advancements in computer hardware. In particular, deep neural nets (DNNs), i.e. neural nets with more than one hidden layer, have found great successes in many applications, such as computer vision and natural language processing. Here we show that DNNs can routinely make better prospective predictions than RF on a set of large diverse QSAR data sets that are taken from Merck's drug discovery effort. The number of adjustable parameters needed for DNNs is fairly large, but our results show that it is not necessary to optimize them for individual data sets, and a single set of recommended parameters can achieve better performance than RF for most of the data sets we studied. The usefulness of the parameters is demonstrated on additional data sets not used in the calibration. Although training DNNs is still computationally intensive, using graphical processing units (GPUs) can make this issue manageable.

Efficiently passing messages in distributed spiking neural network simulation.

PubMed

Thibeault, Corey M; Minkovich, Kirill; O'Brien, Michael J; Harris, Frederick C; Srinivasa, Narayan

2013-01-01

Efficiently passing spiking messages in a neural model is an important aspect of high-performance simulation. As the scale of networks has increased so has the size of the computing systems required to simulate them. In addition, the information exchange of these resources has become more of an impediment to performance. In this paper we explore spike message passing using different mechanisms provided by the Message Passing Interface (MPI). A specific implementation, MVAPICH, designed for high-performance clusters with Infiniband hardware is employed. The focus is on providing information about these mechanisms for users of commodity high-performance spiking simulators. In addition, a novel hybrid method for spike exchange was implemented and benchmarked.

Biologically plausible learning in neural networks: a lesson from bacterial chemotaxis.

PubMed

Shimansky, Yury P

2009-12-01

Learning processes in the brain are usually associated with plastic changes made to optimize the strength of connections between neurons. Although many details related to biophysical mechanisms of synaptic plasticity have been discovered, it is unclear how the concurrent performance of adaptive modifications in a huge number of spatial locations is organized to minimize a given objective function. Since direct experimental observation of even a relatively small subset of such changes is not feasible, computational modeling is an indispensable investigation tool for solving this problem. However, the conventional method of error back-propagation (EBP) employed for optimizing synaptic weights in artificial neural networks is not biologically plausible. This study based on computational experiments demonstrated that such optimization can be performed rather efficiently using the same general method that bacteria employ for moving closer to an attractant or away from a repellent. With regard to neural network optimization, this method consists of regulating the probability of an abrupt change in the direction of synaptic weight modification according to the temporal gradient of the objective function. Neural networks utilizing this method (regulation of modification probability, RMP) can be viewed as analogous to swimming in the multidimensional space of their parameters in the flow of biochemical agents carrying information about the optimality criterion. The efficiency of RMP is comparable to that of EBP, while RMP has several important advantages. Since the biological plausibility of RMP is beyond a reasonable doubt, the RMP concept provides a constructive framework for the experimental analysis of learning in natural neural networks.

Efficient self-organizing multilayer neural network for nonlinear system modeling.

PubMed

Han, Hong-Gui; Wang, Li-Dan; Qiao, Jun-Fei

2013-07-01

It has been shown extensively that the dynamic behaviors of a neural system are strongly influenced by the network architecture and learning process. To establish an artificial neural network (ANN) with self-organizing architecture and suitable learning algorithm for nonlinear system modeling, an automatic axon-neural network (AANN) is investigated in the following respects. First, the network architecture is constructed automatically to change both the number of hidden neurons and topologies of the neural network during the training process. The approach introduced in adaptive connecting-and-pruning algorithm (ACP) is a type of mixed mode operation, which is equivalent to pruning or adding the connecting of the neurons, as well as inserting some required neurons directly. Secondly, the weights are adjusted, using a feedforward computation (FC) to obtain the information for the gradient during learning computation. Unlike most of the previous studies, AANN is able to self-organize the architecture and weights, and to improve the network performances. Also, the proposed AANN has been tested on a number of benchmark problems, ranging from nonlinear function approximating to nonlinear systems modeling. The experimental results show that AANN can have better performances than that of some existing neural networks. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.

Probabilistic Models and Generative Neural Networks: Towards an Unified Framework for Modeling Normal and Impaired Neurocognitive Functions

PubMed Central

Testolin, Alberto; Zorzi, Marco

2016-01-01

Connectionist models can be characterized within the more general framework of probabilistic graphical models, which allow to efficiently describe complex statistical distributions involving a large number of interacting variables. This integration allows building more realistic computational models of cognitive functions, which more faithfully reflect the underlying neural mechanisms at the same time providing a useful bridge to higher-level descriptions in terms of Bayesian computations. Here we discuss a powerful class of graphical models that can be implemented as stochastic, generative neural networks. These models overcome many limitations associated with classic connectionist models, for example by exploiting unsupervised learning in hierarchical architectures (deep networks) and by taking into account top-down, predictive processing supported by feedback loops. We review some recent cognitive models based on generative networks, and we point out promising research directions to investigate neuropsychological disorders within this approach. Though further efforts are required in order to fill the gap between structured Bayesian models and more realistic, biophysical models of neuronal dynamics, we argue that generative neural networks have the potential to bridge these levels of analysis, thereby improving our understanding of the neural bases of cognition and of pathologies caused by brain damage. PMID:27468262

Probabilistic Models and Generative Neural Networks: Towards an Unified Framework for Modeling Normal and Impaired Neurocognitive Functions.

PubMed

Testolin, Alberto; Zorzi, Marco

2016-01-01

Connectionist models can be characterized within the more general framework of probabilistic graphical models, which allow to efficiently describe complex statistical distributions involving a large number of interacting variables. This integration allows building more realistic computational models of cognitive functions, which more faithfully reflect the underlying neural mechanisms at the same time providing a useful bridge to higher-level descriptions in terms of Bayesian computations. Here we discuss a powerful class of graphical models that can be implemented as stochastic, generative neural networks. These models overcome many limitations associated with classic connectionist models, for example by exploiting unsupervised learning in hierarchical architectures (deep networks) and by taking into account top-down, predictive processing supported by feedback loops. We review some recent cognitive models based on generative networks, and we point out promising research directions to investigate neuropsychological disorders within this approach. Though further efforts are required in order to fill the gap between structured Bayesian models and more realistic, biophysical models of neuronal dynamics, we argue that generative neural networks have the potential to bridge these levels of analysis, thereby improving our understanding of the neural bases of cognition and of pathologies caused by brain damage.

Chaotic dynamics in nanoscale NbO2 Mott memristors for analogue computing

NASA Astrophysics Data System (ADS)

Kumar, Suhas; Strachan, John Paul; Williams, R. Stanley

2017-08-01

At present, machine learning systems use simplified neuron models that lack the rich nonlinear phenomena observed in biological systems, which display spatio-temporal cooperative dynamics. There is evidence that neurons operate in a regime called the edge of chaos that may be central to complexity, learning efficiency, adaptability and analogue (non-Boolean) computation in brains. Neural networks have exhibited enhanced computational complexity when operated at the edge of chaos, and networks of chaotic elements have been proposed for solving combinatorial or global optimization problems. Thus, a source of controllable chaotic behaviour that can be incorporated into a neural-inspired circuit may be an essential component of future computational systems. Such chaotic elements have been simulated using elaborate transistor circuits that simulate known equations of chaos, but an experimental realization of chaotic dynamics from a single scalable electronic device has been lacking. Here we describe niobium dioxide (NbO2) Mott memristors each less than 100 nanometres across that exhibit both a nonlinear-transport-driven current-controlled negative differential resistance and a Mott-transition-driven temperature-controlled negative differential resistance. Mott materials have a temperature-dependent metal-insulator transition that acts as an electronic switch, which introduces a history-dependent resistance into the device. We incorporate these memristors into a relaxation oscillator and observe a tunable range of periodic and chaotic self-oscillations. We show that the nonlinear current transport coupled with thermal fluctuations at the nanoscale generates chaotic oscillations. Such memristors could be useful in certain types of neural-inspired computation by introducing a pseudo-random signal that prevents global synchronization and could also assist in finding a global minimum during a constrained search. We specifically demonstrate that incorporating such memristors into the hardware of a Hopfield computing network can greatly improve the efficiency and accuracy of converging to a solution for computationally difficult problems.

Proposal for an All-Spin Artificial Neural Network: Emulating Neural and Synaptic Functionalities Through Domain Wall Motion in Ferromagnets.

PubMed

Sengupta, Abhronil; Shim, Yong; Roy, Kaushik

2016-12-01

Non-Boolean computing based on emerging post-CMOS technologies can potentially pave the way for low-power neural computing platforms. However, existing work on such emerging neuromorphic architectures have either focused on solely mimicking the neuron, or the synapse functionality. While memristive devices have been proposed to emulate biological synapses, spintronic devices have proved to be efficient at performing the thresholding operation of the neuron at ultra-low currents. In this work, we propose an All-Spin Artificial Neural Network where a single spintronic device acts as the basic building block of the system. The device offers a direct mapping to synapse and neuron functionalities in the brain while inter-layer network communication is accomplished via CMOS transistors. To the best of our knowledge, this is the first demonstration of a neural architecture where a single nanoelectronic device is able to mimic both neurons and synapses. The ultra-low voltage operation of low resistance magneto-metallic neurons enables the low-voltage operation of the array of spintronic synapses, thereby leading to ultra-low power neural architectures. Device-level simulations, calibrated to experimental results, was used to drive the circuit and system level simulations of the neural network for a standard pattern recognition problem. Simulation studies indicate energy savings by  ∼  100× in comparison to a corresponding digital/analog CMOS neuron implementation.

Beyond Scale-Free Small-World Networks: Cortical Columns for Quick Brains

NASA Astrophysics Data System (ADS)

Stoop, Ralph; Saase, Victor; Wagner, Clemens; Stoop, Britta; Stoop, Ruedi

2013-03-01

We study to what extent cortical columns with their particular wiring boost neural computation. Upon a vast survey of columnar networks performing various real-world cognitive tasks, we detect no signs of enhancement. It is on a mesoscopic—intercolumnar—scale that the existence of columns, largely irrespective of their inner organization, enhances the speed of information transfer and minimizes the total wiring length required to bind distributed columnar computations towards spatiotemporally coherent results. We suggest that brain efficiency may be related to a doubly fractal connectivity law, resulting in networks with efficiency properties beyond those by scale-free networks.

A new perspective on the perceptual selectivity of attention under load.

PubMed

Giesbrecht, Barry; Sy, Jocelyn; Bundesen, Claus; Kyllingsbaek, Søren

2014-05-01

The human attention system helps us cope with a complex environment by supporting the selective processing of information relevant to our current goals. Understanding the perceptual, cognitive, and neural mechanisms that mediate selective attention is a core issue in cognitive neuroscience. One prominent model of selective attention, known as load theory, offers an account of how task demands determine when information is selected and an account of the efficiency of the selection process. However, load theory has several critical weaknesses that suggest that it is time for a new perspective. Here we review the strengths and weaknesses of load theory and offer an alternative biologically plausible computational account that is based on the neural theory of visual attention. We argue that this new perspective provides a detailed computational account of how bottom-up and top-down information is integrated to provide efficient attentional selection and allocation of perceptual processing resources. © 2014 New York Academy of Sciences.

Algorithmic design of a noise-resistant and efficient closed-loop deep brain stimulation system: A computational approach

PubMed Central

Karamintziou, Sofia D.; Custódio, Ana Luísa; Piallat, Brigitte; Polosan, Mircea; Chabardès, Stéphan; Stathis, Pantelis G.; Tagaris, George A.; Sakas, Damianos E.; Polychronaki, Georgia E.; Tsirogiannis, George L.; David, Olivier; Nikita, Konstantina S.

2017-01-01

Advances in the field of closed-loop neuromodulation call for analysis and modeling approaches capable of confronting challenges related to the complex neuronal response to stimulation and the presence of strong internal and measurement noise in neural recordings. Here we elaborate on the algorithmic aspects of a noise-resistant closed-loop subthalamic nucleus deep brain stimulation system for advanced Parkinson’s disease and treatment-refractory obsessive-compulsive disorder, ensuring remarkable performance in terms of both efficiency and selectivity of stimulation, as well as in terms of computational speed. First, we propose an efficient method drawn from dynamical systems theory, for the reliable assessment of significant nonlinear coupling between beta and high-frequency subthalamic neuronal activity, as a biomarker for feedback control. Further, we present a model-based strategy through which optimal parameters of stimulation for minimum energy desynchronizing control of neuronal activity are being identified. The strategy integrates stochastic modeling and derivative-free optimization of neural dynamics based on quadratic modeling. On the basis of numerical simulations, we demonstrate the potential of the presented modeling approach to identify, at a relatively low computational cost, stimulation settings potentially associated with a significantly higher degree of efficiency and selectivity compared with stimulation settings determined post-operatively. Our data reinforce the hypothesis that model-based control strategies are crucial for the design of novel stimulation protocols at the backstage of clinical applications. PMID:28222198

SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method.

PubMed

Bernal, Javier; Torres-Jimenez, Jose

2015-01-01

SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller's scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller's algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller's algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller's algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data.

Inverse simulation system for manual-controlled rendezvous and docking based on artificial neural network

NASA Astrophysics Data System (ADS)

Zhou, Wanmeng; Wang, Hua; Tang, Guojin; Guo, Shuai

2016-09-01

The time-consuming experimental method for handling qualities assessment cannot meet the increasing fast design requirements for the manned space flight. As a tool for the aircraft handling qualities research, the model-predictive-control structured inverse simulation (MPC-IS) has potential applications in the aerospace field to guide the astronauts' operations and evaluate the handling qualities more effectively. Therefore, this paper establishes MPC-IS for the manual-controlled rendezvous and docking (RVD) and proposes a novel artificial neural network inverse simulation system (ANN-IS) to further decrease the computational cost. The novel system was obtained by replacing the inverse model of MPC-IS with the artificial neural network. The optimal neural network was trained by the genetic Levenberg-Marquardt algorithm, and finally determined by the Levenberg-Marquardt algorithm. In order to validate MPC-IS and ANN-IS, the manual-controlled RVD experiments on the simulator were carried out. The comparisons between simulation results and experimental data demonstrated the validity of two systems and the high computational efficiency of ANN-IS.

Equivalent Skin Analysis of Wing Structures Using Neural Networks

NASA Technical Reports Server (NTRS)

Liu, Youhua; Kapania, Rakesh K.

2000-01-01

An efficient method of modeling trapezoidal built-up wing structures is developed by coupling. in an indirect way, an Equivalent Plate Analysis (EPA) with Neural Networks (NN). Being assumed to behave like a Mindlin-plate, the wing is solved using the Ritz method with Legendre polynomials employed as the trial functions. This analysis method can be made more efficient by avoiding most of the computational effort spent on calculating contributions to the stiffness and mass matrices from each spar and rib. This is accomplished by replacing the wing inner-structure with an "equivalent" material that combines to the skin and whose properties are simulated by neural networks. The constitutive matrix, which relates the stress vector to the strain vector, and the density of the equivalent material are obtained by enforcing mass and stiffness matrix equities with rec,ard to the EPA in a least-square sense. Neural networks for the material properties are trained in terms of the design variables of the wing structure. Examples show that the present method, which can be called an Equivalent Skin Analysis (ESA) of the wing structure, is more efficient than the EPA and still fairly good results can be obtained. The present ESA is very promising to be used at the early stages of wing structure design.

Efficient digital implementation of a conductance-based globus pallidus neuron and the dynamics analysis

NASA Astrophysics Data System (ADS)

Yang, Shuangming; Wei, Xile; Deng, Bin; Liu, Chen; Li, Huiyan; Wang, Jiang

2018-03-01

Balance between biological plausibility of dynamical activities and computational efficiency is one of challenging problems in computational neuroscience and neural system engineering. This paper proposes a set of efficient methods for the hardware realization of the conductance-based neuron model with relevant dynamics, targeting reproducing the biological behaviors with low-cost implementation on digital programmable platform, which can be applied in wide range of conductance-based neuron models. Modified GP neuron models for efficient hardware implementation are presented to reproduce reliable pallidal dynamics, which decode the information of basal ganglia and regulate the movement disorder related voluntary activities. Implementation results on a field-programmable gate array (FPGA) demonstrate that the proposed techniques and models can reduce the resource cost significantly and reproduce the biological dynamics accurately. Besides, the biological behaviors with weak network coupling are explored on the proposed platform, and theoretical analysis is also made for the investigation of biological characteristics of the structured pallidal oscillator and network. The implementation techniques provide an essential step towards the large-scale neural network to explore the dynamical mechanisms in real time. Furthermore, the proposed methodology enables the FPGA-based system a powerful platform for the investigation on neurodegenerative diseases and real-time control of bio-inspired neuro-robotics.

Multivariate Cryptography Based on Clipped Hopfield Neural Network.

PubMed

Wang, Jia; Cheng, Lee-Ming; Su, Tong

2018-02-01

Designing secure and efficient multivariate public key cryptosystems [multivariate cryptography (MVC)] to strengthen the security of RSA and ECC in conventional and quantum computational environment continues to be a challenging research in recent years. In this paper, we will describe multivariate public key cryptosystems based on extended Clipped Hopfield Neural Network (CHNN) and implement it using the MVC (CHNN-MVC) framework operated in space. The Diffie-Hellman key exchange algorithm is extended into the matrix field, which illustrates the feasibility of its new applications in both classic and postquantum cryptography. The efficiency and security of our proposed new public key cryptosystem CHNN-MVC are simulated and found to be NP-hard. The proposed algorithm will strengthen multivariate public key cryptosystems and allows hardware realization practicality.

Multi-Stage System for Automatic Target Recognition

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Lu, Thomas T.; Ye, David; Edens, Weston; Johnson, Oliver

2010-01-01

A multi-stage automated target recognition (ATR) system has been designed to perform computer vision tasks with adequate proficiency in mimicking human vision. The system is able to detect, identify, and track targets of interest. Potential regions of interest (ROIs) are first identified by the detection stage using an Optimum Trade-off Maximum Average Correlation Height (OT-MACH) filter combined with a wavelet transform. False positives are then eliminated by the verification stage using feature extraction methods in conjunction with neural networks. Feature extraction transforms the ROIs using filtering and binning algorithms to create feature vectors. A feedforward back-propagation neural network (NN) is then trained to classify each feature vector and to remove false positives. The system parameter optimizations process has been developed to adapt to various targets and datasets. The objective was to design an efficient computer vision system that can learn to detect multiple targets in large images with unknown backgrounds. Because the target size is small relative to the image size in this problem, there are many regions of the image that could potentially contain the target. A cursory analysis of every region can be computationally efficient, but may yield too many false positives. On the other hand, a detailed analysis of every region can yield better results, but may be computationally inefficient. The multi-stage ATR system was designed to achieve an optimal balance between accuracy and computational efficiency by incorporating both models. The detection stage first identifies potential ROIs where the target may be present by performing a fast Fourier domain OT-MACH filter-based correlation. Because threshold for this stage is chosen with the goal of detecting all true positives, a number of false positives are also detected as ROIs. The verification stage then transforms the regions of interest into feature space, and eliminates false positives using an artificial neural network classifier. The multi-stage system allows tuning the detection sensitivity and the identification specificity individually in each stage. It is easier to achieve optimized ATR operation based on its specific goal. The test results show that the system was successful in substantially reducing the false positive rate when tested on a sonar and video image datasets.

Gradient-free MCMC methods for dynamic causal modelling

DOE PAGES

Sengupta, Biswa; Friston, Karl J.; Penny, Will D.

2015-03-14

Here, we compare the performance of four gradient-free MCMC samplers (random walk Metropolis sampling, slice-sampling, adaptive MCMC sampling and population-based MCMC sampling with tempering) in terms of the number of independent samples they can produce per unit computational time. For the Bayesian inversion of a single-node neural mass model, both adaptive and population-based samplers are more efficient compared with random walk Metropolis sampler or slice-sampling; yet adaptive MCMC sampling is more promising in terms of compute time. Slice-sampling yields the highest number of independent samples from the target density -- albeit at almost 1000% increase in computational time, in comparisonmore » to the most efficient algorithm (i.e., the adaptive MCMC sampler).« less

A hybrid fuzzy logic and extreme learning machine for improving efficiency of circulating water systems in power generation plant

NASA Astrophysics Data System (ADS)

Aziz, Nur Liyana Afiqah Abdul; Siah Yap, Keem; Afif Bunyamin, Muhammad

2013-06-01

This paper presents a new approach of the fault detection for improving efficiency of circulating water system (CWS) in a power generation plant using a hybrid Fuzzy Logic System (FLS) and Extreme Learning Machine (ELM) neural network. The FLS is a mathematical tool for calculating the uncertainties where precision and significance are applied in the real world. It is based on natural language which has the ability of "computing the word". The ELM is an extremely fast learning algorithm for neural network that can completed the training cycle in a very short time. By combining the FLS and ELM, new hybrid model, i.e., FLS-ELM is developed. The applicability of this proposed hybrid model is validated in fault detection in CWS which may help to improve overall efficiency of power generation plant, hence, consuming less natural recourses and producing less pollutions.

Neural Network Training by Integration of Adjoint Systems of Equations Forward in Time

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Barhen, Jacob (Inventor)

1999-01-01

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically. it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved. but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. Tbc trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

Neural network training by integration of adjoint systems of equations forward in time

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Barhen, Jacob (Inventor)

1992-01-01

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically, it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved, but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. The trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations.

PubMed

Xiao, Lin; Liao, Bolin; Li, Shuai; Chen, Ke

2018-02-01

In order to solve general time-varying linear matrix equations (LMEs) more efficiently, this paper proposes two nonlinear recurrent neural networks based on two nonlinear activation functions. According to Lyapunov theory, such two nonlinear recurrent neural networks are proved to be convergent within finite-time. Besides, by solving differential equation, the upper bounds of the finite convergence time are determined analytically. Compared with existing recurrent neural networks, the proposed two nonlinear recurrent neural networks have a better convergence property (i.e., the upper bound is lower), and thus the accurate solutions of general time-varying LMEs can be obtained with less time. At last, various different situations have been considered by setting different coefficient matrices of general time-varying LMEs and a great variety of computer simulations (including the application to robot manipulators) have been conducted to validate the better finite-time convergence of the proposed two nonlinear recurrent neural networks. Copyright © 2017 Elsevier Ltd. All rights reserved.

A neural-network-based model for the dynamic simulation of the tire/suspension system while traversing road irregularities.

PubMed

Guarneri, Paolo; Rocca, Gianpiero; Gobbi, Massimiliano

2008-09-01

This paper deals with the simulation of the tire/suspension dynamics by using recurrent neural networks (RNNs). RNNs are derived from the multilayer feedforward neural networks, by adding feedback connections between output and input layers. The optimal network architecture derives from a parametric analysis based on the optimal tradeoff between network accuracy and size. The neural network can be trained with experimental data obtained in the laboratory from simulated road profiles (cleats). The results obtained from the neural network demonstrate good agreement with the experimental results over a wide range of operation conditions. The NN model can be effectively applied as a part of vehicle system model to accurately predict elastic bushings and tire dynamics behavior. Although the neural network model, as a black-box model, does not provide a good insight of the physical behavior of the tire/suspension system, it is a useful tool for assessing vehicle ride and noise, vibration, harshness (NVH) performance due to its good computational efficiency and accuracy.

Spin-neurons: A possible path to energy-efficient neuromorphic computers

NASA Astrophysics Data System (ADS)

Sharad, Mrigank; Fan, Deliang; Roy, Kaushik

2013-12-01

Recent years have witnessed growing interest in the field of brain-inspired computing based on neural-network architectures. In order to translate the related algorithmic models into powerful, yet energy-efficient cognitive-computing hardware, computing-devices beyond CMOS may need to be explored. The suitability of such devices to this field of computing would strongly depend upon how closely their physical characteristics match with the essential computing primitives employed in such models. In this work, we discuss the rationale of applying emerging spin-torque devices for bio-inspired computing. Recent spin-torque experiments have shown the path to low-current, low-voltage, and high-speed magnetization switching in nano-scale magnetic devices. Such magneto-metallic, current-mode spin-torque switches can mimic the analog summing and "thresholding" operation of an artificial neuron with high energy-efficiency. Comparison with CMOS-based analog circuit-model of a neuron shows that "spin-neurons" (spin based circuit model of neurons) can achieve more than two orders of magnitude lower energy and beyond three orders of magnitude reduction in energy-delay product. The application of spin-neurons can therefore be an attractive option for neuromorphic computers of future.

Spin-neurons: A possible path to energy-efficient neuromorphic computers

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sharad, Mrigank; Fan, Deliang; Roy, Kaushik

Recent years have witnessed growing interest in the field of brain-inspired computing based on neural-network architectures. In order to translate the related algorithmic models into powerful, yet energy-efficient cognitive-computing hardware, computing-devices beyond CMOS may need to be explored. The suitability of such devices to this field of computing would strongly depend upon how closely their physical characteristics match with the essential computing primitives employed in such models. In this work, we discuss the rationale of applying emerging spin-torque devices for bio-inspired computing. Recent spin-torque experiments have shown the path to low-current, low-voltage, and high-speed magnetization switching in nano-scale magnetic devices.more » Such magneto-metallic, current-mode spin-torque switches can mimic the analog summing and “thresholding” operation of an artificial neuron with high energy-efficiency. Comparison with CMOS-based analog circuit-model of a neuron shows that “spin-neurons” (spin based circuit model of neurons) can achieve more than two orders of magnitude lower energy and beyond three orders of magnitude reduction in energy-delay product. The application of spin-neurons can therefore be an attractive option for neuromorphic computers of future.« less

USC orthogonal multiprocessor for image processing with neural networks

NASA Astrophysics Data System (ADS)

Hwang, Kai; Panda, Dhabaleswar K.; Haddadi, Navid

1990-07-01

This paper presents the architectural features and imaging applications of the Orthogonal MultiProcessor (OMP) system, which is under construction at the University of Southern California with research funding from NSF and assistance from several industrial partners. The prototype OMP is being built with 16 Intel i860 RISC microprocessors and 256 parallel memory modules using custom-designed spanning buses, which are 2-D interleaved and orthogonally accessed without conflicts. The 16-processor OMP prototype is targeted to achieve 430 MIPS and 600 Mflops, which have been verified by simulation experiments based on the design parameters used. The prototype OMP machine will be initially applied for image processing, computer vision, and neural network simulation applications. We summarize important vision and imaging algorithms that can be restructured with neural network models. These algorithms can efficiently run on the OMP hardware with linear speedup. The ultimate goal is to develop a high-performance Visual Computer (Viscom) for integrated low- and high-level image processing and vision tasks.

Cascade Optimization Strategy with Neural Network and Regression Approximations Demonstrated on a Preliminary Aircraft Engine Design

NASA Technical Reports Server (NTRS)

Hopkins, Dale A.; Patnaik, Surya N.

2000-01-01

A preliminary aircraft engine design methodology is being developed that utilizes a cascade optimization strategy together with neural network and regression approximation methods. The cascade strategy employs different optimization algorithms in a specified sequence. The neural network and regression methods are used to approximate solutions obtained from the NASA Engine Performance Program (NEPP), which implements engine thermodynamic cycle and performance analysis models. The new methodology is proving to be more robust and computationally efficient than the conventional optimization approach of using a single optimization algorithm with direct reanalysis. The methodology has been demonstrated on a preliminary design problem for a novel subsonic turbofan engine concept that incorporates a wave rotor as a cycle-topping device. Computations of maximum thrust were obtained for a specific design point in the engine mission profile. The results (depicted in the figure) show a significant improvement in the maximum thrust obtained using the new methodology in comparison to benchmark solutions obtained using NEPP in a manual design mode.

A more secure parallel keyed hash function based on chaotic neural network

NASA Astrophysics Data System (ADS)

Huang, Zhongquan

2011-08-01

Although various hash functions based on chaos or chaotic neural network were proposed, most of them can not work efficiently in parallel computing environment. Recently, an algorithm for parallel keyed hash function construction based on chaotic neural network was proposed [13]. However, there is a strict limitation in this scheme that its secret keys must be nonce numbers. In other words, if the keys are used more than once in this scheme, there will be some potential security flaw. In this paper, we analyze the cause of vulnerability of the original one in detail, and then propose the corresponding enhancement measures, which can remove the limitation on the secret keys. Theoretical analysis and computer simulation indicate that the modified hash function is more secure and practical than the original one. At the same time, it can keep the parallel merit and satisfy the other performance requirements of hash function, such as good statistical properties, high message and key sensitivity, and strong collision resistance, etc.

Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data

PubMed Central

Ching, Travers; Zhu, Xun

2018-01-01

Artificial neural networks (ANN) are computing architectures with many interconnections of simple neural-inspired computing elements, and have been applied to biomedical fields such as imaging analysis and diagnosis. We have developed a new ANN framework called Cox-nnet to predict patient prognosis from high throughput transcriptomics data. In 10 TCGA RNA-Seq data sets, Cox-nnet achieves the same or better predictive accuracy compared to other methods, including Cox-proportional hazards regression (with LASSO, ridge, and mimimax concave penalty), Random Forests Survival and CoxBoost. Cox-nnet also reveals richer biological information, at both the pathway and gene levels. The outputs from the hidden layer node provide an alternative approach for survival-sensitive dimension reduction. In summary, we have developed a new method for accurate and efficient prognosis prediction on high throughput data, with functional biological insights. The source code is freely available at https://github.com/lanagarmire/cox-nnet. PMID:29634719

Artificial intelligence-based computer modeling tools for controlling slag foaming in electric arc furnaces

NASA Astrophysics Data System (ADS)

Wilson, Eric Lee

Due to increased competition in a world economy, steel companies are currently interested in developing techniques that will allow for the improvement of the steelmaking process, either by increasing output efficiency or by improving the quality of their product, or both. Slag foaming is one practice that has been shown to contribute to both these goals. However, slag foaming is highly dynamic and difficult to model or control. This dissertation describes an effort to use artificial intelligence-based tools (genetic algorithms, fuzzy logic, and neural networks) to both model and control the slag foaming process. Specifically, a neural network is trained and tested on slag foaming data provided by a steel plant. This neural network model is then controlled by a fuzzy logic controller, which in turn is optimized by a genetic algorithm. This tuned controller is then installed at a steel plant and given control be a more efficient slag foaming controller than what was previously used by the steel plant.

A fast new algorithm for a robot neurocontroller using inverse QR decomposition

DOE Office of Scientific and Technical Information (OSTI.GOV)

Morris, A.S.; Khemaissia, S.

2000-01-01

A new adaptive neural network controller for robots is presented. The controller is based on direct adaptive techniques. Unlike many neural network controllers in the literature, inverse dynamical model evaluation is not required. A numerically robust, computationally efficient processing scheme for neutral network weight estimation is described, namely, the inverse QR decomposition (INVQR). The inverse QR decomposition and a weighted recursive least-squares (WRLS) method for neural network weight estimation is derived using Cholesky factorization of the data matrix. The algorithm that performs the efficient INVQR of the underlying space-time data matrix may be implemented in parallel on a triangular array.more » Furthermore, its systolic architecture is well suited for VLSI implementation. Another important benefit is well suited for VLSI implementation. Another important benefit of the INVQR decomposition is that it solves directly for the time-recursive least-squares filter vector, while avoiding the sequential back-substitution step required by the QR decomposition approaches.« less

SoftLab: A Soft-Computing Software for Experimental Research with Commercialization Aspects

NASA Technical Reports Server (NTRS)

Akbarzadeh-T, M.-R.; Shaikh, T. S.; Ren, J.; Hubbell, Rob; Kumbla, K. K.; Jamshidi, M

1998-01-01

SoftLab is a software environment for research and development in intelligent modeling/control using soft-computing paradigms such as fuzzy logic, neural networks, genetic algorithms, and genetic programs. SoftLab addresses the inadequacies of the existing soft-computing software by supporting comprehensive multidisciplinary functionalities from management tools to engineering systems. Furthermore, the built-in features help the user process/analyze information more efficiently by a friendly yet powerful interface, and will allow the user to specify user-specific processing modules, hence adding to the standard configuration of the software environment.

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

DOE PAGES

James, Conrad D.; Aimone, James B.; Miner, Nadine E.; ...

2017-01-04

In this study, biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classesmore » such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.« less

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

DOE Office of Scientific and Technical Information (OSTI.GOV)

James, Conrad D.; Aimone, James B.; Miner, Nadine E.

In this study, biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classesmore » such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.« less

Laser Fluence Recognition Using Computationally Intelligent Pulsed Photoacoustics Within the Trace Gases Analysis

NASA Astrophysics Data System (ADS)

Lukić, M.; Ćojbašić, Ž.; Rabasović, M. D.; Markushev, D. D.; Todorović, D. M.

2017-11-01

In this paper, the possibilities of computational intelligence applications for trace gas monitoring are discussed. For this, pulsed infrared photoacoustics is used to investigate SF6-Ar mixtures in a multiphoton regime, assisted by artificial neural networks. Feedforward multilayer perceptron networks are applied in order to recognize both the spatial characteristics of the laser beam and the values of laser fluence Φ from the given photoacoustic signal and prevent changes. Neural networks are trained in an offline batch training regime to simultaneously estimate four parameters from theoretical or experimental photoacoustic signals: the laser beam spatial profile R(r), vibrational-to-translational relaxation time τ _{V-T} , distance from the laser beam to the absorption molecules in the photoacoustic cell r* and laser fluence Φ . The results presented in this paper show that neural networks can estimate an unknown laser beam spatial profile and the parameters of photoacoustic signals in real time and with high precision. Real-time operation, high accuracy and the possibility of application for higher intensities of radiation for a wide range of laser fluencies are factors that classify the computational intelligence approach as efficient and powerful for the in situ measurement of atmospheric pollutants.

Feature extraction using extrema sampling of discrete derivatives for spike sorting in implantable upper-limb neural prostheses.

PubMed

Zamani, Majid; Demosthenous, Andreas

2014-07-01

Next generation neural interfaces for upper-limb (and other) prostheses aim to develop implantable interfaces for one or more nerves, each interface having many neural signal channels that work reliably in the stump without harming the nerves. To achieve real-time multi-channel processing it is important to integrate spike sorting on-chip to overcome limitations in transmission bandwidth. This requires computationally efficient algorithms for feature extraction and clustering suitable for low-power hardware implementation. This paper describes a new feature extraction method for real-time spike sorting based on extrema analysis (namely positive peaks and negative peaks) of spike shapes and their discrete derivatives at different frequency bands. Employing simulation across different datasets, the accuracy and computational complexity of the proposed method are assessed and compared with other methods. The average classification accuracy of the proposed method in conjunction with online sorting (O-Sort) is 91.6%, outperforming all the other methods tested with the O-Sort clustering algorithm. The proposed method offers a better tradeoff between classification error and computational complexity, making it a particularly strong choice for on-chip spike sorting.

High-Density Liquid-State Machine Circuitry for Time-Series Forecasting.

PubMed

Rosselló, Josep L; Alomar, Miquel L; Morro, Antoni; Oliver, Antoni; Canals, Vincent

2016-08-01

Spiking neural networks (SNN) are the last neural network generation that try to mimic the real behavior of biological neurons. Although most research in this area is done through software applications, it is in hardware implementations in which the intrinsic parallelism of these computing systems are more efficiently exploited. Liquid state machines (LSM) have arisen as a strategic technique to implement recurrent designs of SNN with a simple learning methodology. In this work, we show a new low-cost methodology to implement high-density LSM by using Boolean gates. The proposed method is based on the use of probabilistic computing concepts to reduce hardware requirements, thus considerably increasing the neuron count per chip. The result is a highly functional system that is applied to high-speed time series forecasting.

Modulation Depth Estimation and Variable Selection in State-Space Models for Neural Interfaces

PubMed Central

Hochberg, Leigh R.; Donoghue, John P.; Brown, Emery N.

2015-01-01

Rapid developments in neural interface technology are making it possible to record increasingly large signal sets of neural activity. Various factors such as asymmetrical information distribution and across-channel redundancy may, however, limit the benefit of high-dimensional signal sets, and the increased computational complexity may not yield corresponding improvement in system performance. High-dimensional system models may also lead to overfitting and lack of generalizability. To address these issues, we present a generalized modulation depth measure using the state-space framework that quantifies the tuning of a neural signal channel to relevant behavioral covariates. For a dynamical system, we develop computationally efficient procedures for estimating modulation depth from multivariate data. We show that this measure can be used to rank neural signals and select an optimal channel subset for inclusion in the neural decoding algorithm. We present a scheme for choosing the optimal subset based on model order selection criteria. We apply this method to neuronal ensemble spike-rate decoding in neural interfaces, using our framework to relate motor cortical activity with intended movement kinematics. With offline analysis of intracortical motor imagery data obtained from individuals with tetraplegia using the BrainGate neural interface, we demonstrate that our variable selection scheme is useful for identifying and ranking the most information-rich neural signals. We demonstrate that our approach offers several orders of magnitude lower complexity but virtually identical decoding performance compared to greedy search and other selection schemes. Our statistical analysis shows that the modulation depth of human motor cortical single-unit signals is well characterized by the generalized Pareto distribution. Our variable selection scheme has wide applicability in problems involving multisensor signal modeling and estimation in biomedical engineering systems. PMID:25265627

Efficient Monte Carlo sampling of inverse problems using a neural network-based forward—applied to GPR crosshole traveltime inversion

NASA Astrophysics Data System (ADS)

Hansen, T. M.; Cordua, K. S.

2017-12-01

Probabilistically formulated inverse problems can be solved using Monte Carlo-based sampling methods. In principle, both advanced prior information, based on for example, complex geostatistical models and non-linear forward models can be considered using such methods. However, Monte Carlo methods may be associated with huge computational costs that, in practice, limit their application. This is not least due to the computational requirements related to solving the forward problem, where the physical forward response of some earth model has to be evaluated. Here, it is suggested to replace a numerical complex evaluation of the forward problem, with a trained neural network that can be evaluated very fast. This will introduce a modeling error that is quantified probabilistically such that it can be accounted for during inversion. This allows a very fast and efficient Monte Carlo sampling of the solution to an inverse problem. We demonstrate the methodology for first arrival traveltime inversion of crosshole ground penetrating radar data. An accurate forward model, based on 2-D full-waveform modeling followed by automatic traveltime picking, is replaced by a fast neural network. This provides a sampling algorithm three orders of magnitude faster than using the accurate and computationally expensive forward model, and also considerably faster and more accurate (i.e. with better resolution), than commonly used approximate forward models. The methodology has the potential to dramatically change the complexity of non-linear and non-Gaussian inverse problems that have to be solved using Monte Carlo sampling techniques.

Using Stochastic Spiking Neural Networks on SpiNNaker to Solve Constraint Satisfaction Problems

PubMed Central

Fonseca Guerra, Gabriel A.; Furber, Steve B.

2017-01-01

Constraint satisfaction problems (CSP) are at the core of numerous scientific and technological applications. However, CSPs belong to the NP-complete complexity class, for which the existence (or not) of efficient algorithms remains a major unsolved question in computational complexity theory. In the face of this fundamental difficulty heuristics and approximation methods are used to approach instances of NP (e.g., decision and hard optimization problems). The human brain efficiently handles CSPs both in perception and behavior using spiking neural networks (SNNs), and recent studies have demonstrated that the noise embedded within an SNN can be used as a computational resource to solve CSPs. Here, we provide a software framework for the implementation of such noisy neural solvers on the SpiNNaker massively parallel neuromorphic hardware, further demonstrating their potential to implement a stochastic search that solves instances of P and NP problems expressed as CSPs. This facilitates the exploration of new optimization strategies and the understanding of the computational abilities of SNNs. We demonstrate the basic principles of the framework by solving difficult instances of the Sudoku puzzle and of the map color problem, and explore its application to spin glasses. The solver works as a stochastic dynamical system, which is attracted by the configuration that solves the CSP. The noise allows an optimal exploration of the space of configurations, looking for the satisfiability of all the constraints; if applied discontinuously, it can also force the system to leap to a new random configuration effectively causing a restart. PMID:29311791

SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method

PubMed Central

Bernal, Javier; Torres-Jimenez, Jose

2015-01-01

SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller’s scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller’s algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller’s algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller’s algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data. PMID:26958442

Using deep learning in image hyper spectral segmentation, classification, and detection

NASA Astrophysics Data System (ADS)

Zhao, Xiuying; Su, Zhenyu

2018-02-01

Recent years have shown that deep learning neural networks are a valuable tool in the field of computer vision. Deep learning method can be used in applications like remote sensing such as Land cover Classification, Detection of Vehicle in Satellite Images, Hyper spectral Image classification. This paper addresses the use of the deep learning artificial neural network in Satellite image segmentation. Image segmentation plays an important role in image processing. The hue of the remote sensing image often has a large hue difference, which will result in the poor display of the images in the VR environment. Image segmentation is a pre processing technique applied to the original images and splits the image into many parts which have different hue to unify the color. Several computational models based on supervised, unsupervised, parametric, probabilistic region based image segmentation techniques have been proposed. Recently, one of the machine learning technique known as, deep learning with convolution neural network has been widely used for development of efficient and automatic image segmentation models. In this paper, we focus on study of deep neural convolution network and its variants for automatic image segmentation rather than traditional image segmentation strategies.

Processing of chromatic information in a deep convolutional neural network.

PubMed

Flachot, Alban; Gegenfurtner, Karl R

2018-04-01

Deep convolutional neural networks are a class of machine-learning algorithms capable of solving non-trivial tasks, such as object recognition, with human-like performance. Little is known about the exact computations that deep neural networks learn, and to what extent these computations are similar to the ones performed by the primate brain. Here, we investigate how color information is processed in the different layers of the AlexNet deep neural network, originally trained on object classification of over 1.2M images of objects in their natural contexts. We found that the color-responsive units in the first layer of AlexNet learned linear features and were broadly tuned to two directions in color space, analogously to what is known of color responsive cells in the primate thalamus. Moreover, these directions are decorrelated and lead to statistically efficient representations, similar to the cardinal directions of the second-stage color mechanisms in primates. We also found, in analogy to the early stages of the primate visual system, that chromatic and achromatic information were segregated in the early layers of the network. Units in the higher layers of AlexNet exhibit on average a lower responsivity for color than units at earlier stages.

Computing Generalized Matrix Inverse on Spiking Neural Substrate.

PubMed

Shukla, Rohit; Khoram, Soroosh; Jorgensen, Erik; Li, Jing; Lipasti, Mikko; Wright, Stephen

2018-01-01

Emerging neural hardware substrates, such as IBM's TrueNorth Neurosynaptic System, can provide an appealing platform for deploying numerical algorithms. For example, a recurrent Hopfield neural network can be used to find the Moore-Penrose generalized inverse of a matrix, thus enabling a broad class of linear optimizations to be solved efficiently, at low energy cost. However, deploying numerical algorithms on hardware platforms that severely limit the range and precision of representation for numeric quantities can be quite challenging. This paper discusses these challenges and proposes a rigorous mathematical framework for reasoning about range and precision on such substrates. The paper derives techniques for normalizing inputs and properly quantizing synaptic weights originating from arbitrary systems of linear equations, so that solvers for those systems can be implemented in a provably correct manner on hardware-constrained neural substrates. The analytical model is empirically validated on the IBM TrueNorth platform, and results show that the guarantees provided by the framework for range and precision hold under experimental conditions. Experiments with optical flow demonstrate the energy benefits of deploying a reduced-precision and energy-efficient generalized matrix inverse engine on the IBM TrueNorth platform, reflecting 10× to 100× improvement over FPGA and ARM core baselines.

Artificial neural network detects human uncertainty

NASA Astrophysics Data System (ADS)

Hramov, Alexander E.; Frolov, Nikita S.; Maksimenko, Vladimir A.; Makarov, Vladimir V.; Koronovskii, Alexey A.; Garcia-Prieto, Juan; Antón-Toro, Luis Fernando; Maestú, Fernando; Pisarchik, Alexander N.

2018-03-01

Artificial neural networks (ANNs) are known to be a powerful tool for data analysis. They are used in social science, robotics, and neurophysiology for solving tasks of classification, forecasting, pattern recognition, etc. In neuroscience, ANNs allow the recognition of specific forms of brain activity from multichannel EEG or MEG data. This makes the ANN an efficient computational core for brain-machine systems. However, despite significant achievements of artificial intelligence in recognition and classification of well-reproducible patterns of neural activity, the use of ANNs for recognition and classification of patterns in neural networks still requires additional attention, especially in ambiguous situations. According to this, in this research, we demonstrate the efficiency of application of the ANN for classification of human MEG trials corresponding to the perception of bistable visual stimuli with different degrees of ambiguity. We show that along with classification of brain states associated with multistable image interpretations, in the case of significant ambiguity, the ANN can detect an uncertain state when the observer doubts about the image interpretation. With the obtained results, we describe the possible application of ANNs for detection of bistable brain activity associated with difficulties in the decision-making process.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei

2017-07-01

Considering that the manual inspection of the yarn-dyed fabric can be time consuming and less efficient, a convolutional neural network (CNN) solution based on the modified AlexNet structure for the classification of the yarn-dyed fabric defect is proposed. CNN has powerful ability of feature extraction and feature fusion which can simulate the learning mechanism of the human brain. In order to enhance computational efficiency and detection accuracy, the local response normalization (LRN) layers in AlexNet are replaced by the batch normalization (BN) layers. In the process of the network training, through several convolution operations, the characteristics of the image are extracted step by step, and the essential features of the image can be obtained from the edge features. And the max pooling layers, the dropout layers, the fully connected layers are also employed in the classification model to reduce the computation cost and acquire more precise features of fabric defect. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show the capability of defect classification via the modified Alexnet model and indicate its robustness.

Gradient-free MCMC methods for dynamic causal modelling.

PubMed

Sengupta, Biswa; Friston, Karl J; Penny, Will D

2015-05-15

In this technical note we compare the performance of four gradient-free MCMC samplers (random walk Metropolis sampling, slice-sampling, adaptive MCMC sampling and population-based MCMC sampling with tempering) in terms of the number of independent samples they can produce per unit computational time. For the Bayesian inversion of a single-node neural mass model, both adaptive and population-based samplers are more efficient compared with random walk Metropolis sampler or slice-sampling; yet adaptive MCMC sampling is more promising in terms of compute time. Slice-sampling yields the highest number of independent samples from the target density - albeit at almost 1000% increase in computational time, in comparison to the most efficient algorithm (i.e., the adaptive MCMC sampler). Copyright © 2015 The Authors. Published by Elsevier Inc. All rights reserved.

Three-Dimensional Terahertz Coded-Aperture Imaging Based on Matched Filtering and Convolutional Neural Network.

PubMed

Chen, Shuo; Luo, Chenggao; Wang, Hongqiang; Deng, Bin; Cheng, Yongqiang; Zhuang, Zhaowen

2018-04-26

As a promising radar imaging technique, terahertz coded-aperture imaging (TCAI) can achieve high-resolution, forward-looking, and staring imaging by producing spatiotemporal independent signals with coded apertures. However, there are still two problems in three-dimensional (3D) TCAI. Firstly, the large-scale reference-signal matrix based on meshing the 3D imaging area creates a heavy computational burden, thus leading to unsatisfactory efficiency. Secondly, it is difficult to resolve the target under low signal-to-noise ratio (SNR). In this paper, we propose a 3D imaging method based on matched filtering (MF) and convolutional neural network (CNN), which can reduce the computational burden and achieve high-resolution imaging for low SNR targets. In terms of the frequency-hopping (FH) signal, the original echo is processed with MF. By extracting the processed echo in different spike pulses separately, targets in different imaging planes are reconstructed simultaneously to decompose the global computational complexity, and then are synthesized together to reconstruct the 3D target. Based on the conventional TCAI model, we deduce and build a new TCAI model based on MF. Furthermore, the convolutional neural network (CNN) is designed to teach the MF-TCAI how to reconstruct the low SNR target better. The experimental results demonstrate that the MF-TCAI achieves impressive performance on imaging ability and efficiency under low SNR. Moreover, the MF-TCAI has learned to better resolve the low-SNR 3D target with the help of CNN. In summary, the proposed 3D TCAI can achieve: (1) low-SNR high-resolution imaging by using MF; (2) efficient 3D imaging by downsizing the large-scale reference-signal matrix; and (3) intelligent imaging with CNN. Therefore, the TCAI based on MF and CNN has great potential in applications such as security screening, nondestructive detection, medical diagnosis, etc.

A computational model of pattern separation efficiency in the dentate gyrus with implications in schizophrenia

PubMed Central

Faghihi, Faramarz; Moustafa, Ahmed A.

2015-01-01

Information processing in the hippocampus begins by transferring spiking activity of the entorhinal cortex (EC) into the dentate gyrus (DG). Activity pattern in the EC is separated by the DG such that it plays an important role in hippocampal functions including memory. The structural and physiological parameters of these neural networks enable the hippocampus to be efficient in encoding a large number of inputs that animals receive and process in their life time. The neural encoding capacity of the DG depends on its single neurons encoding and pattern separation efficiency. In this study, encoding by the DG is modeled such that single neurons and pattern separation efficiency are measured using simulations of different parameter values. For this purpose, a probabilistic model of single neurons efficiency is presented to study the role of structural and physiological parameters. Known neurons number of the EC and the DG is used to construct a neural network by electrophysiological features of granule cells of the DG. Separated inputs as activated neurons in the EC with different firing probabilities are presented into the DG. For different connectivity rates between the EC and DG, pattern separation efficiency of the DG is measured. The results show that in the absence of feedback inhibition on the DG neurons, the DG demonstrates low separation efficiency and high firing frequency. Feedback inhibition can increase separation efficiency while resulting in very low single neuron’s encoding efficiency in the DG and very low firing frequency of neurons in the DG (sparse spiking). This work presents a mechanistic explanation for experimental observations in the hippocampus, in combination with theoretical measures. Moreover, the model predicts a critical role for impaired inhibitory neurons in schizophrenia where deficiency in pattern separation of the DG has been observed. PMID:25859189

Predicting CYP2C19 Catalytic Parameters for Enantioselective Oxidations Using Artificial Neural Networks and a Chirality Code

PubMed Central

Hartman, Jessica H.; Cothren, Steven D.; Park, Sun-Ha; Yun, Chul-Ho; Darsey, Jerry A.; Miller, Grover P.

2013-01-01

Cytochromes P450 (CYP for isoforms) play a central role in biological processes especially metabolism of chiral molecules; thus, development of computational methods to predict parameters for chiral reactions is important for advancing this field. In this study, we identified the most optimal artificial neural networks using conformation-independent chirality codes to predict CYP2C19 catalytic parameters for enantioselective reactions. Optimization of the neural networks required identifying the most suitable representation of structure among a diverse array of training substrates, normalizing distribution of the corresponding catalytic parameters (kcat, Km, and kcat/Km), and determining the best topology for networks to make predictions. Among different structural descriptors, the use of partial atomic charges according to the CHelpG scheme and inclusion of hydrogens yielded the most optimal artificial neural networks. Their training also required resolution of poorly distributed output catalytic parameters using a Box-Cox transformation. End point leave-one-out cross correlations of the best neural networks revealed that predictions for individual catalytic parameters (kcat and Km) were more consistent with experimental values than those for catalytic efficiency (kcat/Km). Lastly, neural networks predicted correctly enantioselectivity and comparable catalytic parameters measured in this study for previously uncharacterized CYP2C19 substrates, R- and S-propranolol. Taken together, these seminal computational studies for CYP2C19 are the first to predict all catalytic parameters for enantioselective reactions using artificial neural networks and thus provide a foundation for expanding the prediction of cytochrome P450 reactions to chiral drugs, pollutants, and other biologically active compounds. PMID:23673224

Dendritic nonlinearities are tuned for efficient spike-based computations in cortical circuits.

PubMed

Ujfalussy, Balázs B; Makara, Judit K; Branco, Tiago; Lengyel, Máté

2015-12-24

Cortical neurons integrate thousands of synaptic inputs in their dendrites in highly nonlinear ways. It is unknown how these dendritic nonlinearities in individual cells contribute to computations at the level of neural circuits. Here, we show that dendritic nonlinearities are critical for the efficient integration of synaptic inputs in circuits performing analog computations with spiking neurons. We developed a theory that formalizes how a neuron's dendritic nonlinearity that is optimal for integrating synaptic inputs depends on the statistics of its presynaptic activity patterns. Based on their in vivo preynaptic population statistics (firing rates, membrane potential fluctuations, and correlations due to ensemble dynamics), our theory accurately predicted the responses of two different types of cortical pyramidal cells to patterned stimulation by two-photon glutamate uncaging. These results reveal a new computational principle underlying dendritic integration in cortical neurons by suggesting a functional link between cellular and systems--level properties of cortical circuits.

A fast identification algorithm for Box-Cox transformation based radial basis function neural network.

PubMed

Hong, Xia

2006-07-01

In this letter, a Box-Cox transformation-based radial basis function (RBF) neural network is introduced using the RBF neural network to represent the transformed system output. Initially a fixed and moderate sized RBF model base is derived based on a rank revealing orthogonal matrix triangularization (QR decomposition). Then a new fast identification algorithm is introduced using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator. The main contribution of this letter is to explore the special structure of the proposed RBF neural network for computational efficiency by utilizing the inverse of matrix block decomposition lemma. Finally, the Box-Cox transformation-based RBF neural network, with good generalization and sparsity, is identified based on the derived optimal Box-Cox transformation and a D-optimality-based orthogonal forward regression algorithm. The proposed algorithm and its efficacy are demonstrated with an illustrative example in comparison with support vector machine regression.

Neural network-based feature point descriptors for registration of optical and SAR images

NASA Astrophysics Data System (ADS)

Abulkhanov, Dmitry; Konovalenko, Ivan; Nikolaev, Dmitry; Savchik, Alexey; Shvets, Evgeny; Sidorchuk, Dmitry

2018-04-01

Registration of images of different nature is an important technique used in image fusion, change detection, efficient information representation and other problems of computer vision. Solving this task using feature-based approaches is usually more complex than registration of several optical images because traditional feature descriptors (SIFT, SURF, etc.) perform poorly when images have different nature. In this paper we consider the problem of registration of SAR and optical images. We train neural network to build feature point descriptors and use RANSAC algorithm to align found matches. Experimental results are presented that confirm the method's effectiveness.

Dynamic interactions in neural networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Arbib, M.A.; Amari, S.

The study of neural networks is enjoying a great renaissance, both in computational neuroscience, the development of information processing models of living brains, and in neural computing, the use of neurally inspired concepts in the construction of intelligent machines. This volume presents models and data on the dynamic interactions occurring in the brain, and exhibits the dynamic interactions between research in computational neuroscience and in neural computing. The authors present current research, future trends and open problems.

Model-based decoding, information estimation, and change-point detection techniques for multineuron spike trains.

PubMed

Pillow, Jonathan W; Ahmadian, Yashar; Paninski, Liam

2011-01-01

One of the central problems in systems neuroscience is to understand how neural spike trains convey sensory information. Decoding methods, which provide an explicit means for reading out the information contained in neural spike responses, offer a powerful set of tools for studying the neural coding problem. Here we develop several decoding methods based on point-process neural encoding models, or forward models that predict spike responses to stimuli. These models have concave log-likelihood functions, which allow efficient maximum-likelihood model fitting and stimulus decoding. We present several applications of the encoding model framework to the problem of decoding stimulus information from population spike responses: (1) a tractable algorithm for computing the maximum a posteriori (MAP) estimate of the stimulus, the most probable stimulus to have generated an observed single- or multiple-neuron spike train response, given some prior distribution over the stimulus; (2) a gaussian approximation to the posterior stimulus distribution that can be used to quantify the fidelity with which various stimulus features are encoded; (3) an efficient method for estimating the mutual information between the stimulus and the spike trains emitted by a neural population; and (4) a framework for the detection of change-point times (the time at which the stimulus undergoes a change in mean or variance) by marginalizing over the posterior stimulus distribution. We provide several examples illustrating the performance of these estimators with simulated and real neural data.

Architecture and biological applications of artificial neural networks: a tuberculosis perspective.

PubMed

Darsey, Jerry A; Griffin, William O; Joginipelli, Sravanthi; Melapu, Venkata Kiran

2015-01-01

Advancement of science and technology has prompted researchers to develop new intelligent systems that can solve a variety of problems such as pattern recognition, prediction, and optimization. The ability of the human brain to learn in a fashion that tolerates noise and error has attracted many researchers and provided the starting point for the development of artificial neural networks: the intelligent systems. Intelligent systems can acclimatize to the environment or data and can maximize the chances of success or improve the efficiency of a search. Due to massive parallelism with large numbers of interconnected processers and their ability to learn from the data, neural networks can solve a variety of challenging computational problems. Neural networks have the ability to derive meaning from complicated and imprecise data; they are used in detecting patterns, and trends that are too complex for humans, or other computer systems. Solutions to the toughest problems will not be found through one narrow specialization; therefore we need to combine interdisciplinary approaches to discover the solutions to a variety of problems. Many researchers in different disciplines such as medicine, bioinformatics, molecular biology, and pharmacology have successfully applied artificial neural networks. This chapter helps the reader in understanding the basics of artificial neural networks, their applications, and methodology; it also outlines the network learning process and architecture. We present a brief outline of the application of neural networks to medical diagnosis, drug discovery, gene identification, and protein structure prediction. We conclude with a summary of the results from our study on tuberculosis data using neural networks, in diagnosing active tuberculosis, and predicting chronic vs. infiltrative forms of tuberculosis.

A forecast-based STDP rule suitable for neuromorphic implementation.

PubMed

Davies, S; Galluppi, F; Rast, A D; Furber, S B

2012-08-01

Artificial neural networks increasingly involve spiking dynamics to permit greater computational efficiency. This becomes especially attractive for on-chip implementation using dedicated neuromorphic hardware. However, both spiking neural networks and neuromorphic hardware have historically found difficulties in implementing efficient, effective learning rules. The best-known spiking neural network learning paradigm is Spike Timing Dependent Plasticity (STDP) which adjusts the strength of a connection in response to the time difference between the pre- and post-synaptic spikes. Approaches that relate learning features to the membrane potential of the post-synaptic neuron have emerged as possible alternatives to the more common STDP rule, with various implementations and approximations. Here we use a new type of neuromorphic hardware, SpiNNaker, which represents the flexible "neuromimetic" architecture, to demonstrate a new approach to this problem. Based on the standard STDP algorithm with modifications and approximations, a new rule, called STDP TTS (Time-To-Spike) relates the membrane potential with the Long Term Potentiation (LTP) part of the basic STDP rule. Meanwhile, we use the standard STDP rule for the Long Term Depression (LTD) part of the algorithm. We show that on the basis of the membrane potential it is possible to make a statistical prediction of the time needed by the neuron to reach the threshold, and therefore the LTP part of the STDP algorithm can be triggered when the neuron receives a spike. In our system these approximations allow efficient memory access, reducing the overall computational time and the memory bandwidth required. The improvements here presented are significant for real-time applications such as the ones for which the SpiNNaker system has been designed. We present simulation results that show the efficacy of this algorithm using one or more input patterns repeated over the whole time of the simulation. On-chip results show that the STDP TTS algorithm allows the neural network to adapt and detect the incoming pattern with improvements both in the reliability of, and the time required for, consistent output. Through the approximations we suggest in this paper, we introduce a learning rule that is easy to implement both in event-driven simulators and in dedicated hardware, reducing computational complexity relative to the standard STDP rule. Such a rule offers a promising solution, complementary to standard STDP evaluation algorithms, for real-time learning using spiking neural networks in time-critical applications. Copyright © 2012 Elsevier Ltd. All rights reserved.

Neural dynamics of image representation in the primary visual cortex

PubMed Central

Yan, Xiaogang; Khambhati, Ankit; Liu, Lei; Lee, Tai Sing

2013-01-01

Horizontal connections in the primary visual cortex have been hypothesized to play a number of computational roles: association field for contour completion, surface interpolation, surround suppression, and saliency computation. Here, we argue that horizontal connections might also serve a critical role of computing the appropriate codes for image representation. That the early visual cortex or V1 explicitly represents the image we perceive has been a common assumption on computational theories of efficient coding (Olshausen and Field 1996), yet such a framework for understanding the circuitry in V1 has not been seriously entertained in the neurophysiological community. In fact, a number of recent fMRI and neurophysiological studies cast doubt on the neural validity of such an isomorphic representation (Cornelissen et al. 2006, von der Heydt et al. 2003). In this study, we investigated, neurophysiologically, how V1 neurons respond to uniform color surfaces and show that spiking activities of neurons can be decomposed into three components: a bottom-up feedforward input, an articulation of color tuning and a contextual modulation signal that is inversely proportional to the distance away from the bounding contrast border. We demonstrate through computational simulations that the behaviors of a model for image representation are consistent with many aspects of our neural observations. We conclude that the hypothesis of isomorphic representation of images in V1 remains viable and this hypothesis suggests an additional new interpretation of the functional roles of horizontal connections in the primary visual cortex. PMID:22944076

Evolution of the cerebellum as a neuronal machine for Bayesian state estimation

NASA Astrophysics Data System (ADS)

Paulin, M. G.

2005-09-01

The cerebellum evolved in association with the electric sense and vestibular sense of the earliest vertebrates. Accurate information provided by these sensory systems would have been essential for precise control of orienting behavior in predation. A simple model shows that individual spikes in electrosensory primary afferent neurons can be interpreted as measurements of prey location. Using this result, I construct a computational neural model in which the spatial distribution of spikes in a secondary electrosensory map forms a Monte Carlo approximation to the Bayesian posterior distribution of prey locations given the sense data. The neural circuit that emerges naturally to perform this task resembles the cerebellar-like hindbrain electrosensory filtering circuitry of sharks and other electrosensory vertebrates. The optimal filtering mechanism can be extended to handle dynamical targets observed from a dynamical platform; that is, to construct an optimal dynamical state estimator using spiking neurons. This may provide a generic model of cerebellar computation. Vertebrate motion-sensing neurons have specific fractional-order dynamical characteristics that allow Bayesian state estimators to be implemented elegantly and efficiently, using simple operations with asynchronous pulses, i.e. spikes. The computational neural models described in this paper represent a novel kind of particle filter, using spikes as particles. The models are specific and make testable predictions about computational mechanisms in cerebellar circuitry, while providing a plausible explanation of cerebellar contributions to aspects of motor control, perception and cognition.

Adaptive regularization network based neural modeling paradigm for nonlinear adaptive estimation of cerebral evoked potentials.

PubMed

Zhang, Jian-Hua; Böhme, Johann F

2007-11-01

In this paper we report an adaptive regularization network (ARN) approach to realizing fast blind separation of cerebral evoked potentials (EPs) from background electroencephalogram (EEG) activity with no need to make any explicit assumption on the statistical (or deterministic) signal model. The ARNs are proposed to construct nonlinear EEG and EP signal models. A novel adaptive regularization training (ART) algorithm is proposed to improve the generalization performance of the ARN. Two adaptive neural modeling methods based on the ARN are developed and their implementation and performance analysis are also presented. The computer experiments using simulated and measured visual evoked potential (VEP) data have shown that the proposed ARN modeling paradigm yields computationally efficient and more accurate VEP signal estimation owing to its intrinsic model-free and nonlinear processing characteristics.

Towards a theory of cortical columns: From spiking neurons to interacting neural populations of finite size.

PubMed

Schwalger, Tilo; Deger, Moritz; Gerstner, Wulfram

2017-04-01

Neural population equations such as neural mass or field models are widely used to study brain activity on a large scale. However, the relation of these models to the properties of single neurons is unclear. Here we derive an equation for several interacting populations at the mesoscopic scale starting from a microscopic model of randomly connected generalized integrate-and-fire neuron models. Each population consists of 50-2000 neurons of the same type but different populations account for different neuron types. The stochastic population equations that we find reveal how spike-history effects in single-neuron dynamics such as refractoriness and adaptation interact with finite-size fluctuations on the population level. Efficient integration of the stochastic mesoscopic equations reproduces the statistical behavior of the population activities obtained from microscopic simulations of a full spiking neural network model. The theory describes nonlinear emergent dynamics such as finite-size-induced stochastic transitions in multistable networks and synchronization in balanced networks of excitatory and inhibitory neurons. The mesoscopic equations are employed to rapidly integrate a model of a cortical microcircuit consisting of eight neuron types, which allows us to predict spontaneous population activities as well as evoked responses to thalamic input. Our theory establishes a general framework for modeling finite-size neural population dynamics based on single cell and synapse parameters and offers an efficient approach to analyzing cortical circuits and computations.

The quadriceps muscle of knee joint modelling Using Hybrid Particle Swarm Optimization-Neural Network (PSO-NN)

NASA Astrophysics Data System (ADS)

Kamaruddin, Saadi Bin Ahmad; Marponga Tolos, Siti; Hee, Pah Chin; Ghani, Nor Azura Md; Ramli, Norazan Mohamed; Nasir, Noorhamizah Binti Mohamed; Ksm Kader, Babul Salam Bin; Saiful Huq, Mohammad

2017-03-01

Neural framework has for quite a while been known for its ability to handle a complex nonlinear system without a logical model and can learn refined nonlinear associations gives. Theoretically, the most surely understood computation to set up the framework is the backpropagation (BP) count which relies on upon the minimization of the mean square error (MSE). However, this algorithm is not totally efficient in the presence of outliers which usually exist in dynamic data. This paper exhibits the modelling of quadriceps muscle model by utilizing counterfeit smart procedures named consolidated backpropagation neural network nonlinear autoregressive (BPNN-NAR) and backpropagation neural network nonlinear autoregressive moving average (BPNN-NARMA) models in view of utilitarian electrical incitement (FES). We adapted particle swarm optimization (PSO) approach to enhance the performance of backpropagation algorithm. In this research, a progression of tests utilizing FES was led. The information that is gotten is utilized to build up the quadriceps muscle model. 934 preparing information, 200 testing and 200 approval information set are utilized as a part of the improvement of muscle model. It was found that both BPNN-NAR and BPNN-NARMA performed well in modelling this type of data. As a conclusion, the neural network time series models performed reasonably efficient for non-linear modelling such as active properties of the quadriceps muscle with one input, namely output namely muscle force.

Computational modeling of neural plasticity for self-organization of neural networks.

PubMed

Chrol-Cannon, Joseph; Jin, Yaochu

2014-11-01

Self-organization in biological nervous systems during the lifetime is known to largely occur through a process of plasticity that is dependent upon the spike-timing activity in connected neurons. In the field of computational neuroscience, much effort has been dedicated to building up computational models of neural plasticity to replicate experimental data. Most recently, increasing attention has been paid to understanding the role of neural plasticity in functional and structural neural self-organization, as well as its influence on the learning performance of neural networks for accomplishing machine learning tasks such as classification and regression. Although many ideas and hypothesis have been suggested, the relationship between the structure, dynamics and learning performance of neural networks remains elusive. The purpose of this article is to review the most important computational models for neural plasticity and discuss various ideas about neural plasticity's role. Finally, we suggest a few promising research directions, in particular those along the line that combines findings in computational neuroscience and systems biology, and their synergetic roles in understanding learning, memory and cognition, thereby bridging the gap between computational neuroscience, systems biology and computational intelligence. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Modeling of an intelligent pressure sensor using functional link artificial neural networks.

PubMed

Patra, J C; van den Bos, A

2000-01-01

A capacitor pressure sensor (CPS) is modeled for accurate readout of applied pressure using a novel artificial neural network (ANN). The proposed functional link ANN (FLANN) is a computationally efficient nonlinear network and is capable of complex nonlinear mapping between its input and output pattern space. The nonlinearity is introduced into the FLANN by passing the input pattern through a functional expansion unit. Three different polynomials such as, Chebyschev, Legendre and power series have been employed in the FLANN. The FLANN offers computational advantage over a multilayer perceptron (MLP) for similar performance in modeling of the CPS. The prime aim of the present paper is to develop an intelligent model of the CPS involving less computational complexity, so that its implementation can be economical and robust. It is shown that, over a wide temperature variation ranging from -50 to 150 degrees C, the maximum error of estimation of pressure remains within +/- 3%. With the help of computer simulation, the performance of the three types of FLANN models has been compared to that of an MLP based model.

Probabilistic inference in discrete spaces can be implemented into networks of LIF neurons.

PubMed

Probst, Dimitri; Petrovici, Mihai A; Bytschok, Ilja; Bill, Johannes; Pecevski, Dejan; Schemmel, Johannes; Meier, Karlheinz

2015-01-01

The means by which cortical neural networks are able to efficiently solve inference problems remains an open question in computational neuroscience. Recently, abstract models of Bayesian computation in neural circuits have been proposed, but they lack a mechanistic interpretation at the single-cell level. In this article, we describe a complete theoretical framework for building networks of leaky integrate-and-fire neurons that can sample from arbitrary probability distributions over binary random variables. We test our framework for a model inference task based on a psychophysical phenomenon (the Knill-Kersten optical illusion) and further assess its performance when applied to randomly generated distributions. As the local computations performed by the network strongly depend on the interaction between neurons, we compare several types of couplings mediated by either single synapses or interneuron chains. Due to its robustness to substrate imperfections such as parameter noise and background noise correlations, our model is particularly interesting for implementation on novel, neuro-inspired computing architectures, which can thereby serve as a fast, low-power substrate for solving real-world inference problems.

Computer aided detection of ureteral stones in thin slice computed tomography volumes using Convolutional Neural Networks.

PubMed

Längkvist, Martin; Jendeberg, Johan; Thunberg, Per; Loutfi, Amy; Lidén, Mats

2018-06-01

Computed tomography (CT) is the method of choice for diagnosing ureteral stones - kidney stones that obstruct the ureter. The purpose of this study is to develop a computer aided detection (CAD) algorithm for identifying a ureteral stone in thin slice CT volumes. The challenge in CAD for urinary stones lies in the similarity in shape and intensity of stones with non-stone structures and how to efficiently deal with large high-resolution CT volumes. We address these challenges by using a Convolutional Neural Network (CNN) that works directly on the high resolution CT volumes. The method is evaluated on a large data base of 465 clinically acquired high-resolution CT volumes of the urinary tract with labeling of ureteral stones performed by a radiologist. The best model using 2.5D input data and anatomical information achieved a sensitivity of 100% and an average of 2.68 false-positives per patient on a test set of 88 scans. Copyright © 2018 The Authors. Published by Elsevier Ltd.. All rights reserved.

Probabilistic inference in discrete spaces can be implemented into networks of LIF neurons

PubMed Central

Probst, Dimitri; Petrovici, Mihai A.; Bytschok, Ilja; Bill, Johannes; Pecevski, Dejan; Schemmel, Johannes; Meier, Karlheinz

2015-01-01

The means by which cortical neural networks are able to efficiently solve inference problems remains an open question in computational neuroscience. Recently, abstract models of Bayesian computation in neural circuits have been proposed, but they lack a mechanistic interpretation at the single-cell level. In this article, we describe a complete theoretical framework for building networks of leaky integrate-and-fire neurons that can sample from arbitrary probability distributions over binary random variables. We test our framework for a model inference task based on a psychophysical phenomenon (the Knill-Kersten optical illusion) and further assess its performance when applied to randomly generated distributions. As the local computations performed by the network strongly depend on the interaction between neurons, we compare several types of couplings mediated by either single synapses or interneuron chains. Due to its robustness to substrate imperfections such as parameter noise and background noise correlations, our model is particularly interesting for implementation on novel, neuro-inspired computing architectures, which can thereby serve as a fast, low-power substrate for solving real-world inference problems. PMID:25729361

APPLICATION OF NEURAL NETWORK ALGORITHMS FOR BPM LINEARIZATION

DOE Office of Scientific and Technical Information (OSTI.GOV)

Musson, John C.; Seaton, Chad; Spata, Mike F.

2012-11-01

Stripline BPM sensors contain inherent non-linearities, as a result of field distortions from the pickup elements. Many methods have been devised to facilitate corrections, often employing polynomial fitting. The cost of computation makes real-time correction difficult, particulalry when integer math is utilized. The application of neural-network technology, particularly the multi-layer perceptron algorithm, is proposed as an efficient alternative for electrode linearization. A process of supervised learning is initially used to determine the weighting coefficients, which are subsequently applied to the incoming electrode data. A non-linear layer, known as an activation layer, is responsible for the removal of saturation effects. Implementationmore » of a perceptron in an FPGA-based software-defined radio (SDR) is presented, along with performance comparisons. In addition, efficient calculation of the sigmoidal activation function via the CORDIC algorithm is presented.« less

A Comparison of Several Artificial Neural Network Classifiers for CT Images of Hardwood Logs

Treesearch

Daniel L. Schmoldt; Jing He; A. Lynn Abbott

1998-01-01

Knowledge of internal log defects, obtained by scanning, is critical to efficiency improvements for future hardwood sawmills. Nevertheless, before computed tomography (CT) scanning can be applied in industrial operations, we need to automatically interpret scan information so that it can provide the saw operator with the information necessary to make proper sawing...

Global Sensory Qualities and Aesthetic Experience in Music.

PubMed

Brattico, Pauli; Brattico, Elvira; Vuust, Peter

2017-01-01

A well-known tradition in the study of visual aesthetics holds that the experience of visual beauty is grounded in global computational or statistical properties of the stimulus, for example, scale-invariant Fourier spectrum or self-similarity. Some approaches rely on neural mechanisms, such as efficient computation, processing fluency, or the responsiveness of the cells in the primary visual cortex. These proposals are united by the fact that the contributing factors are hypothesized to be global (i.e., they concern the percept as a whole), formal or non-conceptual (i.e., they concern form instead of content), computational and/or statistical, and based on relatively low-level sensory properties. Here we consider that the study of aesthetic responses to music could benefit from the same approach. Thus, along with local features such as pitch, tuning, consonance/dissonance, harmony, timbre, or beat, also global sonic properties could be viewed as contributing toward creating an aesthetic musical experience. Several such properties are discussed and their neural implementation is reviewed in the light of recent advances in neuroaesthetics.

Compact VLSI neural computer integrated with active pixel sensor for real-time ATR applications

NASA Astrophysics Data System (ADS)

Fang, Wai-Chi; Udomkesmalee, Gabriel; Alkalai, Leon

1997-04-01

A compact VLSI neural computer integrated with an active pixel sensor has been under development to mimic what is inherent in biological vision systems. This electronic eye- brain computer is targeted for real-time machine vision applications which require both high-bandwidth communication and high-performance computing for data sensing, synergy of multiple types of sensory information, feature extraction, target detection, target recognition, and control functions. The neural computer is based on a composite structure which combines Annealing Cellular Neural Network (ACNN) and Hierarchical Self-Organization Neural Network (HSONN). The ACNN architecture is a programmable and scalable multi- dimensional array of annealing neurons which are locally connected with their local neurons. Meanwhile, the HSONN adopts a hierarchical structure with nonlinear basis functions. The ACNN+HSONN neural computer is effectively designed to perform programmable functions for machine vision processing in all levels with its embedded host processor. It provides a two order-of-magnitude increase in computation power over the state-of-the-art microcomputer and DSP microelectronics. A compact current-mode VLSI design feasibility of the ACNN+HSONN neural computer is demonstrated by a 3D 16X8X9-cube neural processor chip design in a 2-micrometers CMOS technology. Integration of this neural computer as one slice of a 4'X4' multichip module into the 3D MCM based avionics architecture for NASA's New Millennium Program is also described.

Low-complexity nonlinear adaptive filter based on a pipelined bilinear recurrent neural network.

PubMed

Zhao, Haiquan; Zeng, Xiangping; He, Zhengyou

2011-09-01

To reduce the computational complexity of the bilinear recurrent neural network (BLRNN), a novel low-complexity nonlinear adaptive filter with a pipelined bilinear recurrent neural network (PBLRNN) is presented in this paper. The PBLRNN, inheriting the modular architectures of the pipelined RNN proposed by Haykin and Li, comprises a number of BLRNN modules that are cascaded in a chained form. Each module is implemented by a small-scale BLRNN with internal dynamics. Since those modules of the PBLRNN can be performed simultaneously in a pipelined parallelism fashion, it would result in a significant improvement of computational efficiency. Moreover, due to nesting module, the performance of the PBLRNN can be further improved. To suit for the modular architectures, a modified adaptive amplitude real-time recurrent learning algorithm is derived on the gradient descent approach. Extensive simulations are carried out to evaluate the performance of the PBLRNN on nonlinear system identification, nonlinear channel equalization, and chaotic time series prediction. Experimental results show that the PBLRNN provides considerably better performance compared to the single BLRNN and RNN models.

Motor-Skill Learning in an Insect Inspired Neuro-Computational Control System

PubMed Central

Arena, Eleonora; Arena, Paolo; Strauss, Roland; Patané, Luca

2017-01-01

In nature, insects show impressive adaptation and learning capabilities. The proposed computational model takes inspiration from specific structures of the insect brain: after proposing key hypotheses on the direct involvement of the mushroom bodies (MBs) and on their neural organization, we developed a new architecture for motor learning to be applied in insect-like walking robots. The proposed model is a nonlinear control system based on spiking neurons. MBs are modeled as a nonlinear recurrent spiking neural network (SNN) with novel characteristics, able to memorize time evolutions of key parameters of the neural motor controller, so that existing motor primitives can be improved. The adopted control scheme enables the structure to efficiently cope with goal-oriented behavioral motor tasks. Here, a six-legged structure, showing a steady-state exponentially stable locomotion pattern, is exposed to the need of learning new motor skills: moving through the environment, the structure is able to modulate motor commands and implements an obstacle climbing procedure. Experimental results on a simulated hexapod robot are reported; they are obtained in a dynamic simulation environment and the robot mimicks the structures of Drosophila melanogaster. PMID:28337138

Dynamical information encoding in neural adaptation.

PubMed

Luozheng Li; Wenhao Zhang; Yuanyuan Mi; Dahui Wang; Xiaohan Lin; Si Wu

2016-08-01

Adaptation refers to the general phenomenon that a neural system dynamically adjusts its response property according to the statistics of external inputs. In response to a prolonged constant stimulation, neuronal firing rates always first increase dramatically at the onset of the stimulation; and afterwards, they decrease rapidly to a low level close to background activity. This attenuation of neural activity seems to be contradictory to our experience that we can still sense the stimulus after the neural system is adapted. Thus, it prompts a question: where is the stimulus information encoded during the adaptation? Here, we investigate a computational model in which the neural system employs a dynamical encoding strategy during the neural adaptation: at the early stage of the adaptation, the stimulus information is mainly encoded in the strong independent firings; and as time goes on, the information is shifted into the weak but concerted responses of neurons. We find that short-term plasticity, a general feature of synapses, provides a natural mechanism to achieve this goal. Furthermore, we demonstrate that with balanced excitatory and inhibitory inputs, this correlation-based information can be read out efficiently. The implications of this study on our understanding of neural information encoding are discussed.

Reduced-Order Modeling for Flutter/LCO Using Recurrent Artificial Neural Network

NASA Technical Reports Server (NTRS)

Yao, Weigang; Liou, Meng-Sing

2012-01-01

The present study demonstrates the efficacy of a recurrent artificial neural network to provide a high fidelity time-dependent nonlinear reduced-order model (ROM) for flutter/limit-cycle oscillation (LCO) modeling. An artificial neural network is a relatively straightforward nonlinear method for modeling an input-output relationship from a set of known data, for which we use the radial basis function (RBF) with its parameters determined through a training process. The resulting RBF neural network, however, is only static and is not yet adequate for an application to problems of dynamic nature. The recurrent neural network method [1] is applied to construct a reduced order model resulting from a series of high-fidelity time-dependent data of aero-elastic simulations. Once the RBF neural network ROM is constructed properly, an accurate approximate solution can be obtained at a fraction of the cost of a full-order computation. The method derived during the study has been validated for predicting nonlinear aerodynamic forces in transonic flow and is capable of accurate flutter/LCO simulations. The obtained results indicate that the present recurrent RBF neural network is accurate and efficient for nonlinear aero-elastic system analysis

Neurally and ocularly informed graph-based models for searching 3D environments.

PubMed

Jangraw, David C; Wang, Jun; Lance, Brent J; Chang, Shih-Fu; Sajda, Paul

2014-08-01

As we move through an environment, we are constantly making assessments, judgments and decisions about the things we encounter. Some are acted upon immediately, but many more become mental notes or fleeting impressions-our implicit 'labeling' of the world. In this paper, we use physiological correlates of this labeling to construct a hybrid brain-computer interface (hBCI) system for efficient navigation of a 3D environment. First, we record electroencephalographic (EEG), saccadic and pupillary data from subjects as they move through a small part of a 3D virtual city under free-viewing conditions. Using machine learning, we integrate the neural and ocular signals evoked by the objects they encounter to infer which ones are of subjective interest to them. These inferred labels are propagated through a large computer vision graph of objects in the city, using semi-supervised learning to identify other, unseen objects that are visually similar to the labeled ones. Finally, the system plots an efficient route to help the subjects visit the 'similar' objects it identifies. We show that by exploiting the subjects' implicit labeling to find objects of interest instead of exploring naively, the median search precision is increased from 25% to 97%, and the median subject need only travel 40% of the distance to see 84% of the objects of interest. We also find that the neural and ocular signals contribute in a complementary fashion to the classifiers' inference of subjects' implicit labeling. In summary, we show that neural and ocular signals reflecting subjective assessment of objects in a 3D environment can be used to inform a graph-based learning model of that environment, resulting in an hBCI system that improves navigation and information delivery specific to the user's interests.

Neurally and ocularly informed graph-based models for searching 3D environments

NASA Astrophysics Data System (ADS)

Jangraw, David C.; Wang, Jun; Lance, Brent J.; Chang, Shih-Fu; Sajda, Paul

2014-08-01

Objective. As we move through an environment, we are constantly making assessments, judgments and decisions about the things we encounter. Some are acted upon immediately, but many more become mental notes or fleeting impressions—our implicit ‘labeling’ of the world. In this paper, we use physiological correlates of this labeling to construct a hybrid brain-computer interface (hBCI) system for efficient navigation of a 3D environment. Approach. First, we record electroencephalographic (EEG), saccadic and pupillary data from subjects as they move through a small part of a 3D virtual city under free-viewing conditions. Using machine learning, we integrate the neural and ocular signals evoked by the objects they encounter to infer which ones are of subjective interest to them. These inferred labels are propagated through a large computer vision graph of objects in the city, using semi-supervised learning to identify other, unseen objects that are visually similar to the labeled ones. Finally, the system plots an efficient route to help the subjects visit the ‘similar’ objects it identifies. Main results. We show that by exploiting the subjects’ implicit labeling to find objects of interest instead of exploring naively, the median search precision is increased from 25% to 97%, and the median subject need only travel 40% of the distance to see 84% of the objects of interest. We also find that the neural and ocular signals contribute in a complementary fashion to the classifiers’ inference of subjects’ implicit labeling. Significance. In summary, we show that neural and ocular signals reflecting subjective assessment of objects in a 3D environment can be used to inform a graph-based learning model of that environment, resulting in an hBCI system that improves navigation and information delivery specific to the user’s interests.

Accelerating global optimization of aerodynamic shapes using a new surrogate-assisted parallel genetic algorithm

NASA Astrophysics Data System (ADS)

Ebrahimi, Mehdi; Jahangirian, Alireza

2017-12-01

An efficient strategy is presented for global shape optimization of wing sections with a parallel genetic algorithm. Several computational techniques are applied to increase the convergence rate and the efficiency of the method. A variable fidelity computational evaluation method is applied in which the expensive Navier-Stokes flow solver is complemented by an inexpensive multi-layer perceptron neural network for the objective function evaluations. A population dispersion method that consists of two phases, of exploration and refinement, is developed to improve the convergence rate and the robustness of the genetic algorithm. Owing to the nature of the optimization problem, a parallel framework based on the master/slave approach is used. The outcomes indicate that the method is able to find the global optimum with significantly lower computational time in comparison to the conventional genetic algorithm.

Efficient organ localization using multi-label convolutional neural networks in thorax-abdomen CT scans

NASA Astrophysics Data System (ADS)

Efrain Humpire-Mamani, Gabriel; Arindra Adiyoso Setio, Arnaud; van Ginneken, Bram; Jacobs, Colin

2018-04-01

Automatic localization of organs and other structures in medical images is an important preprocessing step that can improve and speed up other algorithms such as organ segmentation, lesion detection, and registration. This work presents an efficient method for simultaneous localization of multiple structures in 3D thorax-abdomen CT scans. Our approach predicts the location of multiple structures using a single multi-label convolutional neural network for each orthogonal view. Each network takes extra slices around the current slice as input to provide extra context. A sigmoid layer is used to perform multi-label classification. The output of the three networks is subsequently combined to compute a 3D bounding box for each structure. We used our approach to locate 11 structures of interest. The neural network was trained and evaluated on a large set of 1884 thorax-abdomen CT scans from patients undergoing oncological workup. Reference bounding boxes were annotated by human observers. The performance of our method was evaluated by computing the wall distance to the reference bounding boxes. The bounding boxes annotated by the first human observer were used as the reference standard for the test set. Using the best configuration, we obtained an average wall distance of 3.20~+/-~7.33 mm in the test set. The second human observer achieved 1.23~+/-~3.39 mm. For all structures, the results were better than those reported in previously published studies. In conclusion, we proposed an efficient method for the accurate localization of multiple organs. Our method uses multiple slices as input to provide more context around the slice under analysis, and we have shown that this improves performance. This method can easily be adapted to handle more organs.

Advancing interconnect density for spiking neural network hardware implementations using traffic-aware adaptive network-on-chip routers.

PubMed

Carrillo, Snaider; Harkin, Jim; McDaid, Liam; Pande, Sandeep; Cawley, Seamus; McGinley, Brian; Morgan, Fearghal

2012-09-01

The brain is highly efficient in how it processes information and tolerates faults. Arguably, the basic processing units are neurons and synapses that are interconnected in a complex pattern. Computer scientists and engineers aim to harness this efficiency and build artificial neural systems that can emulate the key information processing principles of the brain. However, existing approaches cannot provide the dense interconnect for the billions of neurons and synapses that are required. Recently a reconfigurable and biologically inspired paradigm based on network-on-chip (NoC) and spiking neural networks (SNNs) has been proposed as a new method of realising an efficient, robust computing platform. However, the use of the NoC as an interconnection fabric for large-scale SNNs demands a good trade-off between scalability, throughput, neuron/synapse ratio and power consumption. This paper presents a novel traffic-aware, adaptive NoC router, which forms part of a proposed embedded mixed-signal SNN architecture called EMBRACE (EMulating Biologically-inspiRed ArChitectures in hardwarE). The proposed adaptive NoC router provides the inter-neuron connectivity for EMBRACE, maintaining router communication and avoiding dropped router packets by adapting to router traffic congestion. Results are presented on throughput, power and area performance analysis of the adaptive router using a 90 nm CMOS technology which outperforms existing NoCs in this domain. The adaptive behaviour of the router is also verified on a Stratix II FPGA implementation of a 4 × 2 router array with real-time traffic congestion. The presented results demonstrate the feasibility of using the proposed adaptive NoC router within the EMBRACE architecture to realise large-scale SNNs on embedded hardware. Copyright © 2012 Elsevier Ltd. All rights reserved.

Neural Network Based Sensory Fusion for Landmark Detection

NASA Technical Reports Server (NTRS)

Kumbla, Kishan -K.; Akbarzadeh, Mohammad R.

1997-01-01

NASA is planning to send numerous unmanned planetary missions to explore the space. This requires autonomous robotic vehicles which can navigate in an unstructured, unknown, and uncertain environment. Landmark based navigation is a new area of research which differs from the traditional goal-oriented navigation, where a mobile robot starts from an initial point and reaches a destination in accordance with a pre-planned path. The landmark based navigation has the advantage of allowing the robot to find its way without communication with the mission control station and without exact knowledge of its coordinates. Current algorithms based on landmark navigation however pose several constraints. First, they require large memories to store the images. Second, the task of comparing the images using traditional methods is computationally intensive and consequently real-time implementation is difficult. The method proposed here consists of three stages, First stage utilizes a heuristic-based algorithm to identify significant objects. The second stage utilizes a neural network (NN) to efficiently classify images of the identified objects. The third stage combines distance information with the classification results of neural networks for efficient and intelligent navigation.

Vibration control of building structures using self-organizing and self-learning neural networks

NASA Astrophysics Data System (ADS)

Madan, Alok

2005-11-01

Past research in artificial intelligence establishes that artificial neural networks (ANN) are effective and efficient computational processors for performing a variety of tasks including pattern recognition, classification, associative recall, combinatorial problem solving, adaptive control, multi-sensor data fusion, noise filtering and data compression, modelling and forecasting. The paper presents a potentially feasible approach for training ANN in active control of earthquake-induced vibrations in building structures without the aid of teacher signals (i.e. target control forces). A counter-propagation neural network is trained to output the control forces that are required to reduce the structural vibrations in the absence of any feedback on the correctness of the output control forces (i.e. without any information on the errors in output activations of the network). The present study shows that, in principle, the counter-propagation network (CPN) can learn from the control environment to compute the required control forces without the supervision of a teacher (unsupervised learning). Simulated case studies are presented to demonstrate the feasibility of implementing the unsupervised learning approach in ANN for effective vibration control of structures under the influence of earthquake ground motions. The proposed learning methodology obviates the need for developing a mathematical model of structural dynamics or training a separate neural network to emulate the structural response for implementation in practice.

Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification.

PubMed

Rueckauer, Bodo; Lungu, Iulia-Alexandra; Hu, Yuhuang; Pfeiffer, Michael; Liu, Shih-Chii

2017-01-01

Spiking neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs) can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset. SNNs can trade off classification error rate against the number of available operations whereas deep continuous-valued neural networks require a fixed number of operations to achieve their classification error rate. From the examples of LeNet for MNIST and BinaryNet for CIFAR-10, we show that with an increase in error rate of a few percentage points, the SNNs can achieve more than 2x reductions in operations compared to the original CNNs. This highlights the potential of SNNs in particular when deployed on power-efficient neuromorphic spiking neuron chips, for use in embedded applications.

Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification

PubMed Central

Rueckauer, Bodo; Lungu, Iulia-Alexandra; Hu, Yuhuang; Pfeiffer, Michael; Liu, Shih-Chii

2017-01-01

Spiking neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs) can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset. SNNs can trade off classification error rate against the number of available operations whereas deep continuous-valued neural networks require a fixed number of operations to achieve their classification error rate. From the examples of LeNet for MNIST and BinaryNet for CIFAR-10, we show that with an increase in error rate of a few percentage points, the SNNs can achieve more than 2x reductions in operations compared to the original CNNs. This highlights the potential of SNNs in particular when deployed on power-efficient neuromorphic spiking neuron chips, for use in embedded applications. PMID:29375284

Rapid Optimization of External Quantum Efficiency of Thin Film Solar Cells Using Surrogate Modeling of Absorptivity.

PubMed

Kaya, Mine; Hajimirza, Shima

2018-05-25

This paper uses surrogate modeling for very fast design of thin film solar cells with improved solar-to-electricity conversion efficiency. We demonstrate that the wavelength-specific optical absorptivity of a thin film multi-layered amorphous-silicon-based solar cell can be modeled accurately with Neural Networks and can be efficiently approximated as a function of cell geometry and wavelength. Consequently, the external quantum efficiency can be computed by averaging surrogate absorption and carrier recombination contributions over the entire irradiance spectrum in an efficient way. Using this framework, we optimize a multi-layer structure consisting of ITO front coating, metallic back-reflector and oxide layers for achieving maximum efficiency. Our required computation time for an entire model fitting and optimization is 5 to 20 times less than the best previous optimization results based on direct Finite Difference Time Domain (FDTD) simulations, therefore proving the value of surrogate modeling. The resulting optimization solution suggests at least 50% improvement in the external quantum efficiency compared to bare silicon, and 25% improvement compared to a random design.

Computing with Neural Synchrony

PubMed Central

Brette, Romain

2012-01-01

Neurons communicate primarily with spikes, but most theories of neural computation are based on firing rates. Yet, many experimental observations suggest that the temporal coordination of spikes plays a role in sensory processing. Among potential spike-based codes, synchrony appears as a good candidate because neural firing and plasticity are sensitive to fine input correlations. However, it is unclear what role synchrony may play in neural computation, and what functional advantage it may provide. With a theoretical approach, I show that the computational interest of neural synchrony appears when neurons have heterogeneous properties. In this context, the relationship between stimuli and neural synchrony is captured by the concept of synchrony receptive field, the set of stimuli which induce synchronous responses in a group of neurons. In a heterogeneous neural population, it appears that synchrony patterns represent structure or sensory invariants in stimuli, which can then be detected by postsynaptic neurons. The required neural circuitry can spontaneously emerge with spike-timing-dependent plasticity. Using examples in different sensory modalities, I show that this allows simple neural circuits to extract relevant information from realistic sensory stimuli, for example to identify a fluctuating odor in the presence of distractors. This theory of synchrony-based computation shows that relative spike timing may indeed have computational relevance, and suggests new types of neural network models for sensory processing with appealing computational properties. PMID:22719243

Computing Generalized Matrix Inverse on Spiking Neural Substrate

PubMed Central

Shukla, Rohit; Khoram, Soroosh; Jorgensen, Erik; Li, Jing; Lipasti, Mikko; Wright, Stephen

2018-01-01

Emerging neural hardware substrates, such as IBM's TrueNorth Neurosynaptic System, can provide an appealing platform for deploying numerical algorithms. For example, a recurrent Hopfield neural network can be used to find the Moore-Penrose generalized inverse of a matrix, thus enabling a broad class of linear optimizations to be solved efficiently, at low energy cost. However, deploying numerical algorithms on hardware platforms that severely limit the range and precision of representation for numeric quantities can be quite challenging. This paper discusses these challenges and proposes a rigorous mathematical framework for reasoning about range and precision on such substrates. The paper derives techniques for normalizing inputs and properly quantizing synaptic weights originating from arbitrary systems of linear equations, so that solvers for those systems can be implemented in a provably correct manner on hardware-constrained neural substrates. The analytical model is empirically validated on the IBM TrueNorth platform, and results show that the guarantees provided by the framework for range and precision hold under experimental conditions. Experiments with optical flow demonstrate the energy benefits of deploying a reduced-precision and energy-efficient generalized matrix inverse engine on the IBM TrueNorth platform, reflecting 10× to 100× improvement over FPGA and ARM core baselines. PMID:29593483

The silicon synapse or, neural net computing.

PubMed

Frenger, P

1989-01-01

Recent developments have rekindled interest in the electronic neural network, a form of parallel computer architecture loosely based on the nervous system of living creatures. This paper describes the elements of neural net computers, reviews the historical milestones in their development, and lists the advantages and disadvantages of their use. Methods for software simulation of neural network systems on existing computers, as well as creation of hardware analogues, are given. The most successful applications of these techniques, involving emulation of biological system responses, are presented. The author's experiences with neural net systems are discussed.

Toward an Integration of Deep Learning and Neuroscience

PubMed Central

Marblestone, Adam H.; Wayne, Greg; Kording, Konrad P.

2016-01-01

Neuroscience has focused on the detailed implementation of computation, studying neural codes, dynamics and circuits. In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively uniform initial architectures. Two recent developments have emerged within machine learning that create an opportunity to connect these seemingly divergent perspectives. First, structured architectures are used, including dedicated systems for attention, recursion and various forms of short- and long-term memory storage. Second, cost functions and training procedures have become more complex and are varied across layers and over time. Here we think about the brain in terms of these ideas. We hypothesize that (1) the brain optimizes cost functions, (2) the cost functions are diverse and differ across brain locations and over development, and (3) optimization operates within a pre-structured architecture matched to the computational problems posed by behavior. In support of these hypotheses, we argue that a range of implementations of credit assignment through multiple layers of neurons are compatible with our current knowledge of neural circuitry, and that the brain's specialized systems can be interpreted as enabling efficient optimization for specific problem classes. Such a heterogeneously optimized system, enabled by a series of interacting cost functions, serves to make learning data-efficient and precisely targeted to the needs of the organism. We suggest directions by which neuroscience could seek to refine and test these hypotheses. PMID:27683554

Modeling fMRI signals can provide insights into neural processing in the cerebral cortex

PubMed Central

Sharifian, Fariba; Heikkinen, Hanna; Vigário, Ricardo

2015-01-01

Every stimulus or task activates multiple areas in the mammalian cortex. These distributed activations can be measured with functional magnetic resonance imaging (fMRI), which has the best spatial resolution among the noninvasive brain imaging methods. Unfortunately, the relationship between the fMRI activations and distributed cortical processing has remained unclear, both because the coupling between neural and fMRI activations has remained poorly understood and because fMRI voxels are too large to directly sense the local neural events. To get an idea of the local processing given the macroscopic data, we need models to simulate the neural activity and to provide output that can be compared with fMRI data. Such models can describe neural mechanisms as mathematical functions between input and output in a specific system, with little correspondence to physiological mechanisms. Alternatively, models can be biomimetic, including biological details with straightforward correspondence to experimental data. After careful balancing between complexity, computational efficiency, and realism, a biomimetic simulation should be able to provide insight into how biological structures or functions contribute to actual data processing as well as to promote theory-driven neuroscience experiments. This review analyzes the requirements for validating system-level computational models with fMRI. In particular, we study mesoscopic biomimetic models, which include a limited set of details from real-life networks and enable system-level simulations of neural mass action. In addition, we discuss how recent developments in neurophysiology and biophysics may significantly advance the modelling of fMRI signals. PMID:25972586

Modeling fMRI signals can provide insights into neural processing in the cerebral cortex.

PubMed

Vanni, Simo; Sharifian, Fariba; Heikkinen, Hanna; Vigário, Ricardo

2015-08-01

Every stimulus or task activates multiple areas in the mammalian cortex. These distributed activations can be measured with functional magnetic resonance imaging (fMRI), which has the best spatial resolution among the noninvasive brain imaging methods. Unfortunately, the relationship between the fMRI activations and distributed cortical processing has remained unclear, both because the coupling between neural and fMRI activations has remained poorly understood and because fMRI voxels are too large to directly sense the local neural events. To get an idea of the local processing given the macroscopic data, we need models to simulate the neural activity and to provide output that can be compared with fMRI data. Such models can describe neural mechanisms as mathematical functions between input and output in a specific system, with little correspondence to physiological mechanisms. Alternatively, models can be biomimetic, including biological details with straightforward correspondence to experimental data. After careful balancing between complexity, computational efficiency, and realism, a biomimetic simulation should be able to provide insight into how biological structures or functions contribute to actual data processing as well as to promote theory-driven neuroscience experiments. This review analyzes the requirements for validating system-level computational models with fMRI. In particular, we study mesoscopic biomimetic models, which include a limited set of details from real-life networks and enable system-level simulations of neural mass action. In addition, we discuss how recent developments in neurophysiology and biophysics may significantly advance the modelling of fMRI signals. Copyright © 2015 the American Physiological Society.

Neural correlates and neural computations in posterior parietal cortex during perceptual decision-making

PubMed Central

Huk, Alexander C.; Meister, Miriam L. R.

2012-01-01

A recent line of work has found remarkable success in relating perceptual decision-making and the spiking activity in the macaque lateral intraparietal area (LIP). In this review, we focus on questions about the neural computations in LIP that are not answered by demonstrations of neural correlates of psychological processes. We highlight three areas of limitations in our current understanding of the precise neural computations that might underlie neural correlates of decisions: (1) empirical questions not yet answered by existing data; (2) implementation issues related to how neural circuits could actually implement the mechanisms suggested by both extracellular neurophysiology and psychophysics; and (3) ecological constraints related to the use of well-controlled laboratory tasks and whether they provide an accurate window on sensorimotor computation. These issues motivate the adoption of a more general “encoding-decoding framework” that will be fruitful for more detailed contemplation of how neural computations in LIP relate to the formation of perceptual decisions. PMID:23087623

Collective Computation of Neural Network

DTIC Science & Technology

1990-03-15

Sciences, Beijing ABSTRACT Computational neuroscience is a new branch of neuroscience originating from current research on the theory of computer...scientists working in artificial intelligence engineering and neuroscience . The paper introduces the collective computational properties of model neural...vision research. On this basis, the authors analyzed the significance of the Hopfield model. Key phrases: Computational Neuroscience , Neural Network, Model

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images †

PubMed Central

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

2017-01-01

Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the “navigation via classification” task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications. PMID:28604624

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images.

PubMed

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

2017-06-12

Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the "navigation via classification" task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications.

A Computational Framework for Realistic Retina Modeling.

PubMed

Martínez-Cañada, Pablo; Morillas, Christian; Pino, Begoña; Ros, Eduardo; Pelayo, Francisco

2016-11-01

Computational simulations of the retina have led to valuable insights about the biophysics of its neuronal activity and processing principles. A great number of retina models have been proposed to reproduce the behavioral diversity of the different visual processing pathways. While many of these models share common computational stages, previous efforts have been more focused on fitting specific retina functions rather than generalizing them beyond a particular model. Here, we define a set of computational retinal microcircuits that can be used as basic building blocks for the modeling of different retina mechanisms. To validate the hypothesis that similar processing structures may be repeatedly found in different retina functions, we implemented a series of retina models simply by combining these computational retinal microcircuits. Accuracy of the retina models for capturing neural behavior was assessed by fitting published electrophysiological recordings that characterize some of the best-known phenomena observed in the retina: adaptation to the mean light intensity and temporal contrast, and differential motion sensitivity. The retinal microcircuits are part of a new software platform for efficient computational retina modeling from single-cell to large-scale levels. It includes an interface with spiking neural networks that allows simulation of the spiking response of ganglion cells and integration with models of higher visual areas.

Prediction of Classroom Reverberation Time using Neural Network

NASA Astrophysics Data System (ADS)

Liyana Zainudin, Fathin; Kadir Mahamad, Abd; Saon, Sharifah; Nizam Yahya, Musli

2018-04-01

In this paper, an alternative method for predicting the reverberation time (RT) using neural network (NN) for classroom was designed and explored. Classroom models were created using Google SketchUp software. The NN applied training dataset from the classroom models with RT values that were computed from ODEON 12.10 software. The NN was conducted separately for 500Hz, 1000Hz, and 2000Hz as absorption coefficient that is one of the prominent input variable is frequency dependent. Mean squared error (MSE) and regression (R) values were obtained to examine the NN efficiency. Overall, the NN shows a good result with MSE < 0.005 and R > 0.9. The NN also managed to achieve a percentage of accuracy of 92.53% for 500Hz, 93.66% for 1000Hz, and 93.18% for 2000Hz and thus displays a good and efficient performance. Nevertheless, the optimum RT value is range between 0.75 – 0.9 seconds.

Acoustic emission data assisted process monitoring.

PubMed

Yen, Gary G; Lu, Haiming

2002-07-01

Gas-liquid two-phase flows are widely used in the chemical industry. Accurate measurements of flow parameters, such as flow regimes, are the key of operating efficiency. Due to the interface complexity of a two-phase flow, it is very difficult to monitor and distinguish flow regimes on-line and real time. In this paper we propose a cost-effective and computation-efficient acoustic emission (AE) detection system combined with artificial neural network technology to recognize four major patterns in an air-water vertical two-phase flow column. Several crucial AE parameters are explored and validated, and we found that the density of acoustic emission events and ring-down counts are two excellent indicators for the flow pattern recognition problems. Instead of the traditional Fair map, a hit-count map is developed and a multilayer Perceptron neural network is designed as a decision maker to describe an approximate transmission stage of a given two-phase flow system.

Ship detection in optical remote sensing images based on deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Yao, Yuan; Jiang, Zhiguo; Zhang, Haopeng; Zhao, Danpei; Cai, Bowen

2017-10-01

Automatic ship detection in optical remote sensing images has attracted wide attention for its broad applications. Major challenges for this task include the interference of cloud, wave, wake, and the high computational expenses. We propose a fast and robust ship detection algorithm to solve these issues. The framework for ship detection is designed based on deep convolutional neural networks (CNNs), which provide the accurate locations of ship targets in an efficient way. First, the deep CNN is designed to extract features. Then, a region proposal network (RPN) is applied to discriminate ship targets and regress the detection bounding boxes, in which the anchors are designed by intrinsic shape of ship targets. Experimental results on numerous panchromatic images demonstrate that, in comparison with other state-of-the-art ship detection methods, our method is more efficient and achieves higher detection accuracy and more precise bounding boxes in different complex backgrounds.

Machine learning on-a-chip: a high-performance low-power reusable neuron architecture for artificial neural networks in ECG classifications.

PubMed

Sun, Yuwen; Cheng, Allen C

2012-07-01

Artificial neural networks (ANNs) are a promising machine learning technique in classifying non-linear electrocardiogram (ECG) signals and recognizing abnormal patterns suggesting risks of cardiovascular diseases (CVDs). In this paper, we propose a new reusable neuron architecture (RNA) enabling a performance-efficient and cost-effective silicon implementation for ANN. The RNA architecture consists of a single layer of physical RNA neurons, each of which is designed to use minimal hardware resource (e.g., a single 2-input multiplier-accumulator is used to compute the dot product of two vectors). By carefully applying the principal of time sharing, RNA can multiplexs this single layer of physical neurons to efficiently execute both feed-forward and back-propagation computations of an ANN while conserving the area and reducing the power dissipation of the silicon. A three-layer 51-30-12 ANN is implemented in RNA to perform the ECG classification for CVD detection. This RNA hardware also allows on-chip automatic training update. A quantitative design space exploration in area, power dissipation, and execution speed between RNA and three other implementations representative of different reusable hardware strategies is presented and discussed. Compared with an equivalent software implementation in C executed on an embedded microprocessor, the RNA ASIC achieves three orders of magnitude improvements in both the execution speed and the energy efficiency. Copyright © 2012 Elsevier Ltd. All rights reserved.

High-Speed Photonic Reservoir Computing Using a Time-Delay-Based Architecture: Million Words per Second Classification

NASA Astrophysics Data System (ADS)

Larger, Laurent; Baylón-Fuentes, Antonio; Martinenghi, Romain; Udaltsov, Vladimir S.; Chembo, Yanne K.; Jacquot, Maxime

2017-01-01

Reservoir computing, originally referred to as an echo state network or a liquid state machine, is a brain-inspired paradigm for processing temporal information. It involves learning a "read-out" interpretation for nonlinear transients developed by high-dimensional dynamics when the latter is excited by the information signal to be processed. This novel computational paradigm is derived from recurrent neural network and machine learning techniques. It has recently been implemented in photonic hardware for a dynamical system, which opens the path to ultrafast brain-inspired computing. We report on a novel implementation involving an electro-optic phase-delay dynamics designed with off-the-shelf optoelectronic telecom devices, thus providing the targeted wide bandwidth. Computational efficiency is demonstrated experimentally with speech-recognition tasks. State-of-the-art speed performances reach one million words per second, with very low word error rate. Additionally, to record speed processing, our investigations have revealed computing-efficiency improvements through yet-unexplored temporal-information-processing techniques, such as simultaneous multisample injection and pitched sampling at the read-out compared to information "write-in".

Optimal size of stochastic Hodgkin-Huxley neuronal systems for maximal energy efficiency in coding pulse signals

NASA Astrophysics Data System (ADS)

Yu, Lianchun; Liu, Liwei

2014-03-01

The generation and conduction of action potentials (APs) represents a fundamental means of communication in the nervous system and is a metabolically expensive process. In this paper, we investigate the energy efficiency of neural systems in transferring pulse signals with APs. By analytically solving a bistable neuron model that mimics the AP generation with a particle crossing the barrier of a double well, we find the optimal number of ion channels that maximizes the energy efficiency of a neuron. We also investigate the energy efficiency of a neuron population in which the input pulse signals are represented with synchronized spikes and read out with a downstream coincidence detector neuron. We find an optimal number of neurons in neuron population, as well as the number of ion channels in each neuron that maximizes the energy efficiency. The energy efficiency also depends on the characters of the input signals, e.g., the pulse strength and the interpulse intervals. These results are confirmed by computer simulation of the stochastic Hodgkin-Huxley model with a detailed description of the ion channel random gating. We argue that the tradeoff between signal transmission reliability and energy cost may influence the size of the neural systems when energy use is constrained.

Optimal size of stochastic Hodgkin-Huxley neuronal systems for maximal energy efficiency in coding pulse signals.

PubMed

Yu, Lianchun; Liu, Liwei

2014-03-01

The generation and conduction of action potentials (APs) represents a fundamental means of communication in the nervous system and is a metabolically expensive process. In this paper, we investigate the energy efficiency of neural systems in transferring pulse signals with APs. By analytically solving a bistable neuron model that mimics the AP generation with a particle crossing the barrier of a double well, we find the optimal number of ion channels that maximizes the energy efficiency of a neuron. We also investigate the energy efficiency of a neuron population in which the input pulse signals are represented with synchronized spikes and read out with a downstream coincidence detector neuron. We find an optimal number of neurons in neuron population, as well as the number of ion channels in each neuron that maximizes the energy efficiency. The energy efficiency also depends on the characters of the input signals, e.g., the pulse strength and the interpulse intervals. These results are confirmed by computer simulation of the stochastic Hodgkin-Huxley model with a detailed description of the ion channel random gating. We argue that the tradeoff between signal transmission reliability and energy cost may influence the size of the neural systems when energy use is constrained.

Training Deep Spiking Neural Networks Using Backpropagation.

PubMed

Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael

2016-01-01

Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.

Reconstruction of three-dimensional porous media using generative adversarial neural networks

NASA Astrophysics Data System (ADS)

Mosser, Lukas; Dubrule, Olivier; Blunt, Martin J.

2017-10-01

To evaluate the variability of multiphase flow properties of porous media at the pore scale, it is necessary to acquire a number of representative samples of the void-solid structure. While modern x-ray computer tomography has made it possible to extract three-dimensional images of the pore space, assessment of the variability in the inherent material properties is often experimentally not feasible. We present a method to reconstruct the solid-void structure of porous media by applying a generative neural network that allows an implicit description of the probability distribution represented by three-dimensional image data sets. We show, by using an adversarial learning approach for neural networks, that this method of unsupervised learning is able to generate representative samples of porous media that honor their statistics. We successfully compare measures of pore morphology, such as the Euler characteristic, two-point statistics, and directional single-phase permeability of synthetic realizations with the calculated properties of a bead pack, Berea sandstone, and Ketton limestone. Results show that generative adversarial networks can be used to reconstruct high-resolution three-dimensional images of porous media at different scales that are representative of the morphology of the images used to train the neural network. The fully convolutional nature of the trained neural network allows the generation of large samples while maintaining computational efficiency. Compared to classical stochastic methods of image reconstruction, the implicit representation of the learned data distribution can be stored and reused to generate multiple realizations of the pore structure very rapidly.

Localizing Tortoise Nests by Neural Networks.

PubMed

Barbuti, Roberto; Chessa, Stefano; Micheli, Alessio; Pucci, Rita

2016-01-01

The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating). Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS) which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN). We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours), the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition.

Neuromorphic Hardware Architecture Using the Neural Engineering Framework for Pattern Recognition.

PubMed

Wang, Runchun; Thakur, Chetan Singh; Cohen, Gregory; Hamilton, Tara Julia; Tapson, Jonathan; van Schaik, Andre

2017-06-01

We present a hardware architecture that uses the neural engineering framework (NEF) to implement large-scale neural networks on field programmable gate arrays (FPGAs) for performing massively parallel real-time pattern recognition. NEF is a framework that is capable of synthesising large-scale cognitive systems from subnetworks and we have previously presented an FPGA implementation of the NEF that successfully performs nonlinear mathematical computations. That work was developed based on a compact digital neural core, which consists of 64 neurons that are instantiated by a single physical neuron using a time-multiplexing approach. We have now scaled this approach up to build a pattern recognition system by combining identical neural cores together. As a proof of concept, we have developed a handwritten digit recognition system using the MNIST database and achieved a recognition rate of 96.55%. The system is implemented on a state-of-the-art FPGA and can process 5.12 million digits per second. The architecture and hardware optimisations presented offer high-speed and resource-efficient means for performing high-speed, neuromorphic, and massively parallel pattern recognition and classification tasks.

Prediction and control of neural responses to pulsatile electrical stimulation

NASA Astrophysics Data System (ADS)

Campbell, Luke J.; Sly, David James; O'Leary, Stephen John

2012-04-01

This paper aims to predict and control the probability of firing of a neuron in response to pulsatile electrical stimulation of the type delivered by neural prostheses such as the cochlear implant, bionic eye or in deep brain stimulation. Using the cochlear implant as a model, we developed an efficient computational model that predicts the responses of auditory nerve fibers to electrical stimulation and evaluated the model's accuracy by comparing the model output with pooled responses from a group of guinea pig auditory nerve fibers. It was found that the model accurately predicted the changes in neural firing probability over time to constant and variable amplitude electrical pulse trains, including speech-derived signals, delivered at rates up to 889 pulses s-1. A simplified version of the model that did not incorporate adaptation was used to adaptively predict, within its limitations, the pulsatile electrical stimulus required to cause a desired response from neurons up to 250 pulses s-1. Future stimulation strategies for cochlear implants and other neural prostheses may be enhanced using similar models that account for the way that neural responses are altered by previous stimulation.

Towards multifocal ultrasonic neural stimulation: pattern generation algorithms

NASA Astrophysics Data System (ADS)

Hertzberg, Yoni; Naor, Omer; Volovick, Alexander; Shoham, Shy

2010-10-01

Focused ultrasound (FUS) waves directed onto neural structures have been shown to dynamically modulate neural activity and excitability, opening up a range of possible systems and applications where the non-invasiveness, safety, mm-range resolution and other characteristics of FUS are advantageous. As in other neuro-stimulation and modulation modalities, the highly distributed and parallel nature of neural systems and neural information processing call for the development of appropriately patterned stimulation strategies which could simultaneously address multiple sites in flexible patterns. Here, we study the generation of sparse multi-focal ultrasonic distributions using phase-only modulation in ultrasonic phased arrays. We analyse the relative performance of an existing algorithm for generating multifocal ultrasonic distributions and new algorithms that we adapt from the field of optical digital holography, and find that generally the weighted Gerchberg-Saxton algorithm leads to overall superior efficiency and uniformity in the focal spots, without significantly increasing the computational burden. By combining phased-array FUS and magnetic-resonance thermometry we experimentally demonstrate the simultaneous generation of tightly focused multifocal distributions in a tissue phantom, a first step towards patterned FUS neuro-modulation systems and devices.

A robust cloud registration method based on redundant data reduction using backpropagation neural network and shift window

NASA Astrophysics Data System (ADS)

Xin, Meiting; Li, Bing; Yan, Xiao; Chen, Lei; Wei, Xiang

2018-02-01

A robust coarse-to-fine registration method based on the backpropagation (BP) neural network and shift window technology is proposed in this study. Specifically, there are three steps: coarse alignment between the model data and measured data, data simplification based on the BP neural network and point reservation in the contour region of point clouds, and fine registration with the reweighted iterative closest point algorithm. In the process of rough alignment, the initial rotation matrix and the translation vector between the two datasets are obtained. After performing subsequent simplification operations, the number of points can be reduced greatly. Therefore, the time and space complexity of the accurate registration can be significantly reduced. The experimental results show that the proposed method improves the computational efficiency without loss of accuracy.

Artificial neuron operations and spike-timing-dependent plasticity using memristive devices for brain-inspired computing

NASA Astrophysics Data System (ADS)

Marukame, Takao; Nishi, Yoshifumi; Yasuda, Shin-ichi; Tanamoto, Tetsufumi

2018-04-01

The use of memristive devices for creating artificial neurons is promising for brain-inspired computing from the viewpoints of computation architecture and learning protocol. We present an energy-efficient multiplier accumulator based on a memristive array architecture incorporating both analog and digital circuitries. The analog circuitry is used to full advantage for neural networks, as demonstrated by the spike-timing-dependent plasticity (STDP) in fabricated AlO x /TiO x -based metal-oxide memristive devices. STDP protocols for controlling periodic analog resistance with long-range stability were experimentally verified using a variety of voltage amplitudes and spike timings.

Performance/price estimates for cortex-scale hardware: a design space exploration.

PubMed

Zaveri, Mazad S; Hammerstrom, Dan

2011-04-01

In this paper, we revisit the concept of virtualization. Virtualization is useful for understanding and investigating the performance/price and other trade-offs related to the hardware design space. Moreover, it is perhaps the most important aspect of a hardware design space exploration. Such a design space exploration is a necessary part of the study of hardware architectures for large-scale computational models for intelligent computing, including AI, Bayesian, bio-inspired and neural models. A methodical exploration is needed to identify potentially interesting regions in the design space, and to assess the relative performance/price points of these implementations. As an example, in this paper we investigate the performance/price of (digital and mixed-signal) CMOS and hypothetical CMOL (nanogrid) technology based hardware implementations of human cortex-scale spiking neural systems. Through this analysis, and the resulting performance/price points, we demonstrate, in general, the importance of virtualization, and of doing these kinds of design space explorations. The specific results suggest that hybrid nanotechnology such as CMOL is a promising candidate to implement very large-scale spiking neural systems, providing a more efficient utilization of the density and storage benefits of emerging nano-scale technologies. In general, we believe that the study of such hypothetical designs/architectures will guide the neuromorphic hardware community towards building large-scale systems, and help guide research trends in intelligent computing, and computer engineering. Copyright © 2010 Elsevier Ltd. All rights reserved.

Neural network based load and price forecasting and confidence interval estimation in deregulated power markets

NASA Astrophysics Data System (ADS)

Zhang, Li

With the deregulation of the electric power market in New England, an independent system operator (ISO) has been separated from the New England Power Pool (NEPOOL). The ISO provides a regional spot market, with bids on various electricity-related products and services submitted by utilities and independent power producers. A utility can bid on the spot market and buy or sell electricity via bilateral transactions. Good estimation of market clearing prices (MCP) will help utilities and independent power producers determine bidding and transaction strategies with low risks, and this is crucial for utilities to compete in the deregulated environment. MCP prediction, however, is difficult since bidding strategies used by participants are complicated and MCP is a non-stationary process. The main objective of this research is to provide efficient short-term load and MCP forecasting and corresponding confidence interval estimation methodologies. In this research, the complexity of load and MCP with other factors is investigated, and neural networks are used to model the complex relationship between input and output. With improved learning algorithm and on-line update features for load forecasting, a neural network based load forecaster was developed, and has been in daily industry use since summer 1998 with good performance. MCP is volatile because of the complexity of market behaviors. In practice, neural network based MCP predictors usually have a cascaded structure, as several key input factors need to be estimated first. In this research, the uncertainties involved in a cascaded neural network structure for MCP prediction are analyzed, and prediction distribution under the Bayesian framework is developed. A fast algorithm to evaluate the confidence intervals by using the memoryless Quasi-Newton method is also developed. The traditional back-propagation algorithm for neural network learning needs to be improved since MCP is a non-stationary process. The extended Kalman filter (EKF) can be used as an integrated adaptive learning and confidence interval estimation algorithm for neural networks, with fast convergence and small confidence intervals. However, EKF learning is computationally expensive because it involves high dimensional matrix manipulations. A modified U-D factorization within the decoupled EKF (DEKF-UD) framework is developed in this research. The computational efficiency and numerical stability are significantly improved.

Towards a theory of cortical columns: From spiking neurons to interacting neural populations of finite size

PubMed Central

Gerstner, Wulfram

2017-01-01

Neural population equations such as neural mass or field models are widely used to study brain activity on a large scale. However, the relation of these models to the properties of single neurons is unclear. Here we derive an equation for several interacting populations at the mesoscopic scale starting from a microscopic model of randomly connected generalized integrate-and-fire neuron models. Each population consists of 50–2000 neurons of the same type but different populations account for different neuron types. The stochastic population equations that we find reveal how spike-history effects in single-neuron dynamics such as refractoriness and adaptation interact with finite-size fluctuations on the population level. Efficient integration of the stochastic mesoscopic equations reproduces the statistical behavior of the population activities obtained from microscopic simulations of a full spiking neural network model. The theory describes nonlinear emergent dynamics such as finite-size-induced stochastic transitions in multistable networks and synchronization in balanced networks of excitatory and inhibitory neurons. The mesoscopic equations are employed to rapidly integrate a model of a cortical microcircuit consisting of eight neuron types, which allows us to predict spontaneous population activities as well as evoked responses to thalamic input. Our theory establishes a general framework for modeling finite-size neural population dynamics based on single cell and synapse parameters and offers an efficient approach to analyzing cortical circuits and computations. PMID:28422957

A network of spiking neurons for computing sparse representations in an energy efficient way

PubMed Central

Hu, Tao; Genkin, Alexander; Chklovskii, Dmitri B.

2013-01-01

Computing sparse redundant representations is an important problem both in applied mathematics and neuroscience. In many applications, this problem must be solved in an energy efficient way. Here, we propose a hybrid distributed algorithm (HDA), which solves this problem on a network of simple nodes communicating via low-bandwidth channels. HDA nodes perform both gradient-descent-like steps on analog internal variables and coordinate-descent-like steps via quantized external variables communicated to each other. Interestingly, such operation is equivalent to a network of integrate-and-fire neurons, suggesting that HDA may serve as a model of neural computation. We compare the numerical performance of HDA with existing algorithms and show that in the asymptotic regime the representation error of HDA decays with time, t, as 1/t. We show that HDA is stable against time-varying noise, specifically, the representation error decays as 1/t for Gaussian white noise. PMID:22920853

A network of spiking neurons for computing sparse representations in an energy-efficient way.

PubMed

Hu, Tao; Genkin, Alexander; Chklovskii, Dmitri B

2012-11-01

Computing sparse redundant representations is an important problem in both applied mathematics and neuroscience. In many applications, this problem must be solved in an energy-efficient way. Here, we propose a hybrid distributed algorithm (HDA), which solves this problem on a network of simple nodes communicating by low-bandwidth channels. HDA nodes perform both gradient-descent-like steps on analog internal variables and coordinate-descent-like steps via quantized external variables communicated to each other. Interestingly, the operation is equivalent to a network of integrate-and-fire neurons, suggesting that HDA may serve as a model of neural computation. We show that the numerical performance of HDA is on par with existing algorithms. In the asymptotic regime, the representation error of HDA decays with time, t, as 1/t. HDA is stable against time-varying noise; specifically, the representation error decays as 1/√t for gaussian white noise.

Neural assembly computing.

PubMed

Ranhel, João

2012-06-01

Spiking neurons can realize several computational operations when firing cooperatively. This is a prevalent notion, although the mechanisms are not yet understood. A way by which neural assemblies compute is proposed in this paper. It is shown how neural coalitions represent things (and world states), memorize them, and control their hierarchical relations in order to perform algorithms. It is described how neural groups perform statistic logic functions as they form assemblies. Neural coalitions can reverberate, becoming bistable loops. Such bistable neural assemblies become short- or long-term memories that represent the event that triggers them. In addition, assemblies can branch and dismantle other neural groups generating new events that trigger other coalitions. Hence, such capabilities and the interaction among assemblies allow neural networks to create and control hierarchical cascades of causal activities, giving rise to parallel algorithms. Computing and algorithms are used here as in a nonstandard computation approach. In this sense, neural assembly computing (NAC) can be seen as a new class of spiking neural network machines. NAC can explain the following points: 1) how neuron groups represent things and states; 2) how they retain binary states in memories that do not require any plasticity mechanism; and 3) how branching, disbanding, and interaction among assemblies may result in algorithms and behavioral responses. Simulations were carried out and the results are in agreement with the hypothesis presented. A MATLAB code is available as a supplementary material.

On-board fault diagnostics for fly-by-light flight control systems using neural network flight processors

NASA Astrophysics Data System (ADS)

Urnes, James M., Sr.; Cushing, John; Bond, William E.; Nunes, Steve

1996-10-01

Fly-by-Light control systems offer higher performance for fighter and transport aircraft, with efficient fiber optic data transmission, electric control surface actuation, and multi-channel high capacity centralized processing combining to provide maximum aircraft flight control system handling qualities and safety. The key to efficient support for these vehicles is timely and accurate fault diagnostics of all control system components. These diagnostic tests are best conducted during flight when all facts relating to the failure are present. The resulting data can be used by the ground crew for efficient repair and turnaround of the aircraft, saving time and money in support costs. These difficult to diagnose (Cannot Duplicate) fault indications average 40 - 50% of maintenance activities on today's fighter and transport aircraft, adding significantly to fleet support cost. Fiber optic data transmission can support a wealth of data for fault monitoring; the most efficient method of fault diagnostics is accurate modeling of the component response under normal and failed conditions for use in comparison with the actual component flight data. Neural Network hardware processors offer an efficient and cost-effective method to install fault diagnostics in flight systems, permitting on-board diagnostic modeling of very complex subsystems. Task 2C of the ARPA FLASH program is a design demonstration of this diagnostics approach, using the very high speed computation of the Adaptive Solutions Neural Network processor to monitor an advanced Electrohydrostatic control surface actuator linked through a AS-1773A fiber optic bus. This paper describes the design approach and projected performance of this on-line diagnostics system.

A computational model of conditioning inspired by Drosophila olfactory system.

PubMed

Faghihi, Faramarz; Moustafa, Ahmed A; Heinrich, Ralf; Wörgötter, Florentin

2017-03-01

Recent studies have demonstrated that Drosophila melanogaster (briefly Drosophila) can successfully perform higher cognitive processes including second order olfactory conditioning. Understanding the neural mechanism of this behavior can help neuroscientists to unravel the principles of information processing in complex neural systems (e.g. the human brain) and to create efficient and robust robotic systems. In this work, we have developed a biologically-inspired spiking neural network which is able to execute both first and second order conditioning. Experimental studies demonstrated that volume signaling (e.g. by the gaseous transmitter nitric oxide) contributes to memory formation in vertebrates and invertebrates including insects. Based on the existing knowledge of odor encoding in Drosophila, the role of retrograde signaling in memory function, and the integration of synaptic and non-synaptic neural signaling, a neural system is implemented as Simulated fly. Simulated fly navigates in a two-dimensional environment in which it receives odors and electric shocks as sensory stimuli. The model suggests some experimental research on retrograde signaling to investigate neural mechanisms of conditioning in insects and other animals. Moreover, it illustrates a simple strategy to implement higher cognitive capabilities in machines including robots. Copyright © 2016 Elsevier Ltd. All rights reserved.

Energy consumption analysis for various memristive networks under different learning strategies

NASA Astrophysics Data System (ADS)

Deng, Lei; Wang, Dong; Zhang, Ziyang; Tang, Pei; Li, Guoqi; Pei, Jing

2016-02-01

Recently, various memristive systems emerge to emulate the efficient computing paradigm of the brain cortex; whereas, how to make them energy efficient still remains unclear, especially from an overall perspective. Here, a systematical and bottom-up energy consumption analysis is demonstrated, including the memristor device level and the network learning level. We propose an energy estimating methodology when modulating the memristive synapses, which is simulated in three typical neural networks with different synaptic structures and learning strategies for both offline and online learning. These results provide an in-depth insight to create energy efficient brain-inspired neuromorphic devices in the future.

Optimal channel efficiency in a sensory network

NASA Astrophysics Data System (ADS)

Mosqueiro, Thiago S.; Maia, Leonardo P.

2013-07-01

Spontaneous neural activity has been increasingly recognized as a subject of key relevance in neuroscience. It exhibits nontrivial spatiotemporal structure reflecting the organization of the underlying neural network and has proved to be closely intertwined with stimulus-induced activity patterns. As an additional contribution in this regard, we report computational studies that strongly suggest that a stimulus-free feature rules the behavior of an important psychophysical measure of the sensibility of a sensory system to a stimulus, the so-called dynamic range. Indeed in this paper we show that the entropy of the distribution of avalanche lifetimes (information efficiency, since it can be interpreted as the efficiency of the network seen as a communication channel) always accompanies the dynamic range in the benchmark model for sensory systems. Specifically, by simulating the Kinouchi-Copelli (KC) model on two broad families of model networks, we generically observed that both quantities always increase or decrease together as functions of the average branching ratio (the control parameter of the KC model) and that the information efficiency typically exhibits critical optimization jointly with the dynamic range (i.e., both quantities are optimized at the same value of that control parameter, that turns out to be the critical point of a nonequilibrium phase transition). In contrast with the practice of taking power laws to identify critical points in most studies describing measured neuronal avalanches, we rely on data collapses as more robust signatures of criticality to claim that critical optimization may happen even when the distribution of avalanche lifetimes is not a power law, as suggested by a recent experiment. Finally, we note that the entropy of the size distribution of avalanches (information capacity) does not always follow the dynamic range and the information efficiency when they are critically optimized, despite being more widely used than the latter to describe the computational capabilities of a neural network. This strongly suggests that dynamical rules allowing a proper temporal matching of the states of the interacting neurons is the key for achieving good performance in information processing, rather than increasing the number of available units.

Artificial neural networks for modeling time series of beach litter in the southern North Sea.

PubMed

Schulz, Marcus; Matthies, Michael

2014-07-01

In European marine waters, existing monitoring programs of beach litter need to be improved concerning litter items used as indicators of pollution levels, efficiency, and effectiveness. In order to ease and focus future monitoring of beach litter on few important litter items, feed-forward neural networks consisting of three layers were developed to relate single litter items to general categories of marine litter. The neural networks developed were applied to seven beaches in the southern North Sea and modeled time series of five general categories of marine litter, such as litter from fishing, shipping, and tourism. Results of regression analyses show that general categories were predicted significantly moderately to well. Measured and modeled data were in the same order of magnitude, and minima and maxima overlapped well. Neural networks were found to be eligible tools to deliver reliable predictions of marine litter with low computational effort and little input of information. Copyright © 2014 Elsevier Ltd. All rights reserved.

A Pruning Neural Network Model in Credit Classification Analysis

PubMed Central

Tang, Yajiao; Ji, Junkai; Dai, Hongwei; Yu, Yang; Todo, Yuki

2018-01-01

Nowadays, credit classification models are widely applied because they can help financial decision-makers to handle credit classification issues. Among them, artificial neural networks (ANNs) have been widely accepted as the convincing methods in the credit industry. In this paper, we propose a pruning neural network (PNN) and apply it to solve credit classification problem by adopting the well-known Australian and Japanese credit datasets. The model is inspired by synaptic nonlinearity of a dendritic tree in a biological neural model. And it is trained by an error back-propagation algorithm. The model is capable of realizing a neuronal pruning function by removing the superfluous synapses and useless dendrites and forms a tidy dendritic morphology at the end of learning. Furthermore, we utilize logic circuits (LCs) to simulate the dendritic structures successfully which makes PNN be implemented on the hardware effectively. The statistical results of our experiments have verified that PNN obtains superior performance in comparison with other classical algorithms in terms of accuracy and computational efficiency. PMID:29606961

Dendritic nonlinearities are tuned for efficient spike-based computations in cortical circuits

PubMed Central

Ujfalussy, Balázs B; Makara, Judit K; Branco, Tiago; Lengyel, Máté

2015-01-01

Cortical neurons integrate thousands of synaptic inputs in their dendrites in highly nonlinear ways. It is unknown how these dendritic nonlinearities in individual cells contribute to computations at the level of neural circuits. Here, we show that dendritic nonlinearities are critical for the efficient integration of synaptic inputs in circuits performing analog computations with spiking neurons. We developed a theory that formalizes how a neuron's dendritic nonlinearity that is optimal for integrating synaptic inputs depends on the statistics of its presynaptic activity patterns. Based on their in vivo preynaptic population statistics (firing rates, membrane potential fluctuations, and correlations due to ensemble dynamics), our theory accurately predicted the responses of two different types of cortical pyramidal cells to patterned stimulation by two-photon glutamate uncaging. These results reveal a new computational principle underlying dendritic integration in cortical neurons by suggesting a functional link between cellular and systems--level properties of cortical circuits. DOI: http://dx.doi.org/10.7554/eLife.10056.001 PMID:26705334

Devices and circuits for nanoelectronic implementation of artificial neural networks

NASA Astrophysics Data System (ADS)

Turel, Ozgur

Biological neural networks perform complicated information processing tasks at speeds better than conventional computers based on conventional algorithms. This has inspired researchers to look into the way these networks function, and propose artificial networks that mimic their behavior. Unfortunately, most artificial neural networks, either software or hardware, do not provide either the speed or the complexity of a human brain. Nanoelectronics, with high density and low power dissipation that it provides, may be used in developing more efficient artificial neural networks. This work consists of two major contributions in this direction. First is the proposal of the CMOL concept, hybrid CMOS-molecular hardware [1-8]. CMOL may circumvent most of the problems in posed by molecular devices, such as low yield, vet provide high active device density, ˜1012/cm 2. The second contribution is CrossNets, artificial neural networks that are based on CMOL. We showed that CrossNets, with their fault tolerance, exceptional speed (˜ 4 to 6 orders of magnitude faster than biological neural networks) can perform any task any artificial neural network can perform. Moreover, there is a hope that if their integration scale is increased to that of human cerebral cortex (˜ 1010 neurons and ˜ 1014 synapses), they may be capable of performing more advanced tasks.

PyNEST: A Convenient Interface to the NEST Simulator.

PubMed

Eppler, Jochen Martin; Helias, Moritz; Muller, Eilif; Diesmann, Markus; Gewaltig, Marc-Oliver

2008-01-01

The neural simulation tool NEST (http://www.nest-initiative.org) is a simulator for heterogeneous networks of point neurons or neurons with a small number of compartments. It aims at simulations of large neural systems with more than 10(4) neurons and 10(7) to 10(9) synapses. NEST is implemented in C++ and can be used on a large range of architectures from single-core laptops over multi-core desktop computers to super-computers with thousands of processor cores. Python (http://www.python.org) is a modern programming language that has recently received considerable attention in Computational Neuroscience. Python is easy to learn and has many extension modules for scientific computing (e.g. http://www.scipy.org). In this contribution we describe PyNEST, the new user interface to NEST. PyNEST combines NEST's efficient simulation kernel with the simplicity and flexibility of Python. Compared to NEST's native simulation language SLI, PyNEST makes it easier to set up simulations, generate stimuli, and analyze simulation results. We describe how PyNEST connects NEST and Python and how it is implemented. With a number of examples, we illustrate how it is used.

A practical comparison of algorithms for the measurement of multiscale entropy in neural time series data.

PubMed

Kuntzelman, Karl; Jack Rhodes, L; Harrington, Lillian N; Miskovic, Vladimir

2018-06-01

There is a broad family of statistical methods for capturing time series regularity, with increasingly widespread adoption by the neuroscientific community. A common feature of these methods is that they permit investigators to quantify the entropy of brain signals - an index of unpredictability/complexity. Despite the proliferation of algorithms for computing entropy from neural time series data there is scant evidence concerning their relative stability and efficiency. Here we evaluated several different algorithmic implementations (sample, fuzzy, dispersion and permutation) of multiscale entropy in terms of their stability across sessions, internal consistency and computational speed, accuracy and precision using a combination of electroencephalogram (EEG) and synthetic 1/ƒ noise signals. Overall, we report fair to excellent internal consistency and longitudinal stability over a one-week period for the majority of entropy estimates, with several caveats. Computational timing estimates suggest distinct advantages for dispersion and permutation entropy over other entropy estimates. Considered alongside the psychometric evidence, we suggest several ways in which researchers can maximize computational resources (without sacrificing reliability), especially when working with high-density M/EEG data or multivoxel BOLD time series signals. Copyright © 2018 Elsevier Inc. All rights reserved.

PyNEST: A Convenient Interface to the NEST Simulator

PubMed Central

Eppler, Jochen Martin; Helias, Moritz; Muller, Eilif; Diesmann, Markus; Gewaltig, Marc-Oliver

2008-01-01

The neural simulation tool NEST (http://www.nest-initiative.org) is a simulator for heterogeneous networks of point neurons or neurons with a small number of compartments. It aims at simulations of large neural systems with more than 104 neurons and 107 to 109 synapses. NEST is implemented in C++ and can be used on a large range of architectures from single-core laptops over multi-core desktop computers to super-computers with thousands of processor cores. Python (http://www.python.org) is a modern programming language that has recently received considerable attention in Computational Neuroscience. Python is easy to learn and has many extension modules for scientific computing (e.g. http://www.scipy.org). In this contribution we describe PyNEST, the new user interface to NEST. PyNEST combines NEST's efficient simulation kernel with the simplicity and flexibility of Python. Compared to NEST's native simulation language SLI, PyNEST makes it easier to set up simulations, generate stimuli, and analyze simulation results. We describe how PyNEST connects NEST and Python and how it is implemented. With a number of examples, we illustrate how it is used. PMID:19198667

Toward Petascale Biologically Plausible Neural Networks

NASA Astrophysics Data System (ADS)

Long, Lyle

This talk will describe an approach to achieving petascale neural networks. Artificial intelligence has been oversold for many decades. Computers in the beginning could only do about 16,000 operations per second. Computer processing power, however, has been doubling every two years thanks to Moore's law, and growing even faster due to massively parallel architectures. Finally, 60 years after the first AI conference we have computers on the order of the performance of the human brain (1016 operations per second). The main issues now are algorithms, software, and learning. We have excellent models of neurons, such as the Hodgkin-Huxley model, but we do not know how the human neurons are wired together. With careful attention to efficient parallel computing, event-driven programming, table lookups, and memory minimization massive scale simulations can be performed. The code that will be described was written in C + + and uses the Message Passing Interface (MPI). It uses the full Hodgkin-Huxley neuron model, not a simplified model. It also allows arbitrary network structures (deep, recurrent, convolutional, all-to-all, etc.). The code is scalable, and has, so far, been tested on up to 2,048 processor cores using 107 neurons and 109 synapses.

Artificial Neural Network Metamodels of Stochastic Computer Simulations

DTIC Science & Technology

1994-08-10

SUBTITLE r 5. FUNDING NUMBERS Artificial Neural Network Metamodels of Stochastic I () Computer Simulations 6. AUTHOR(S) AD- A285 951 Robert Allen...8217!298*1C2 ARTIFICIAL NEURAL NETWORK METAMODELS OF STOCHASTIC COMPUTER SIMULATIONS by Robert Allen Kilmer B.S. in Education Mathematics, Indiana...dedicate this document to the memory of my father, William Ralph Kilmer. mi ABSTRACT Signature ARTIFICIAL NEURAL NETWORK METAMODELS OF STOCHASTIC

Towards a 'siliconeural computer': technological successes and challenges.

PubMed

Hughes, Mark A; Shipston, Mike J; Murray, Alan F

2015-07-28

Electronic signals govern the function of both nervous systems and computers, albeit in different ways. As such, hybridizing both systems to create an iono-electric brain-computer interface is a realistic goal; and one that promises exciting advances in both heterotic computing and neuroprosthetics capable of circumventing devastating neuropathology. 'Neural networks' were, in the 1980s, viewed naively as a potential panacea for all computational problems that did not fit well with conventional computing. The field bifurcated during the 1990s into a highly successful and much more realistic machine learning community and an equally pragmatic, biologically oriented 'neuromorphic computing' community. Algorithms found in nature that use the non-synchronous, spiking nature of neuronal signals have been found to be (i) implementable efficiently in silicon and (ii) computationally useful. As a result, interest has grown in techniques that could create mixed 'siliconeural' computers. Here, we discuss potential approaches and focus on one particular platform using parylene-patterned silicon dioxide.

Fish and chips: implementation of a neural network model into computer chips to maximize swimming efficiency in autonomous underwater vehicles.

PubMed

Blake, R W; Ng, H; Chan, K H S; Li, J

2008-09-01

Recent developments in the design and propulsion of biomimetic autonomous underwater vehicles (AUVs) have focused on boxfish as models (e.g. Deng and Avadhanula 2005 Biomimetic micro underwater vehicle with oscillating fin propulsion: system design and force measurement Proc. 2005 IEEE Int. Conf. Robot. Auto. (Barcelona, Spain) pp 3312-7). Whilst such vehicles have many potential advantages in operating in complex environments (e.g. high manoeuvrability and stability), limited battery life and payload capacity are likely functional disadvantages. Boxfish employ undulatory median and paired fins during routine swimming which are characterized by high hydromechanical Froude efficiencies (approximately 0.9) at low forward speeds. Current boxfish-inspired vehicles are propelled by a low aspect ratio, 'plate-like' caudal fin (ostraciiform tail) which can be shown to operate at a relatively low maximum Froude efficiency (approximately 0.5) and is mainly employed as a rudder for steering and in rapid swimming bouts (e.g. escape responses). Given this and the fact that bioinspired engineering designs are not obligated to wholly duplicate a biological model, computer chips were developed using a multilayer perception neural network model of undulatory fin propulsion in the knifefish Xenomystus nigri that would potentially allow an AUV to achieve high optimum values of propulsive efficiency at any given forward velocity, giving a minimum energy drain on the battery. We envisage that externally monitored information on flow velocity (sensory system) would be conveyed to the chips residing in the vehicle's control unit, which in turn would signal the locomotor unit to adopt kinematics (e.g. fin frequency, amplitude) associated with optimal propulsion efficiency. Power savings could protract vehicle operational life and/or provide more power to other functions (e.g. communications).

Global Sensory Qualities and Aesthetic Experience in Music

PubMed Central

Brattico, Pauli; Brattico, Elvira; Vuust, Peter

2017-01-01

A well-known tradition in the study of visual aesthetics holds that the experience of visual beauty is grounded in global computational or statistical properties of the stimulus, for example, scale-invariant Fourier spectrum or self-similarity. Some approaches rely on neural mechanisms, such as efficient computation, processing fluency, or the responsiveness of the cells in the primary visual cortex. These proposals are united by the fact that the contributing factors are hypothesized to be global (i.e., they concern the percept as a whole), formal or non-conceptual (i.e., they concern form instead of content), computational and/or statistical, and based on relatively low-level sensory properties. Here we consider that the study of aesthetic responses to music could benefit from the same approach. Thus, along with local features such as pitch, tuning, consonance/dissonance, harmony, timbre, or beat, also global sonic properties could be viewed as contributing toward creating an aesthetic musical experience. Several such properties are discussed and their neural implementation is reviewed in the light of recent advances in neuroaesthetics. PMID:28424573

Emergence of Adaptive Computation by Single Neurons in the Developing Cortex

PubMed Central

Famulare, Michael; Gjorgjieva, Julijana; Moody, William J.

2013-01-01

Adaptation is a fundamental computational motif in neural processing. To maintain stable perception in the face of rapidly shifting input, neural systems must extract relevant information from background fluctuations under many different contexts. Many neural systems are able to adjust their input–output properties such that an input's ability to trigger a response depends on the size of that input relative to its local statistical context. This “gain-scaling” strategy has been shown to be an efficient coding strategy. We report here that this property emerges during early development as an intrinsic property of single neurons in mouse sensorimotor cortex, coinciding with the disappearance of spontaneous waves of network activity, and can be modulated by changing the balance of spike-generating currents. Simultaneously, developing neurons move toward a common intrinsic operating point and a stable ratio of spike-generating currents. This developmental trajectory occurs in the absence of sensory input or spontaneous network activity. Through a combination of electrophysiology and modeling, we demonstrate that developing cortical neurons develop the ability to perform nearly perfect gain scaling by virtue of the maturing spike-generating currents alone. We use reduced single neuron models to identify the conditions for this property to hold. PMID:23884925

Updated energy budgets for neural computation in the neocortex and cerebellum

PubMed Central

Howarth, Clare; Gleeson, Padraig; Attwell, David

2012-01-01

The brain's energy supply determines its information processing power, and generates functional imaging signals. The energy use on the different subcellular processes underlying neural information processing has been estimated previously for the grey matter of the cerebral and cerebellar cortex. However, these estimates need reevaluating following recent work demonstrating that action potentials in mammalian neurons are much more energy efficient than was previously thought. Using this new knowledge, this paper provides revised estimates for the energy expenditure on neural computation in a simple model for the cerebral cortex and a detailed model of the cerebellar cortex. In cerebral cortex, most signaling energy (50%) is used on postsynaptic glutamate receptors, 21% is used on action potentials, 20% on resting potentials, 5% on presynaptic transmitter release, and 4% on transmitter recycling. In the cerebellar cortex, excitatory neurons use 75% and inhibitory neurons 25% of the signaling energy, and most energy is used on information processing by non-principal neurons: Purkinje cells use only 15% of the signaling energy. The majority of cerebellar signaling energy use is on the maintenance of resting potentials (54%) and postsynaptic receptors (22%), while action potentials account for only 17% of the signaling energy use. PMID:22434069

Computational modeling of spiking neural network with learning rules from STDP and intrinsic plasticity

NASA Astrophysics Data System (ADS)

Li, Xiumin; Wang, Wei; Xue, Fangzheng; Song, Yongduan

2018-02-01

Recently there has been continuously increasing interest in building up computational models of spiking neural networks (SNN), such as the Liquid State Machine (LSM). The biologically inspired self-organized neural networks with neural plasticity can enhance the capability of computational performance, with the characteristic features of dynamical memory and recurrent connection cycles which distinguish them from the more widely used feedforward neural networks. Despite a variety of computational models for brain-like learning and information processing have been proposed, the modeling of self-organized neural networks with multi-neural plasticity is still an important open challenge. The main difficulties lie in the interplay among different forms of neural plasticity rules and understanding how structures and dynamics of neural networks shape the computational performance. In this paper, we propose a novel approach to develop the models of LSM with a biologically inspired self-organizing network based on two neural plasticity learning rules. The connectivity among excitatory neurons is adapted by spike-timing-dependent plasticity (STDP) learning; meanwhile, the degrees of neuronal excitability are regulated to maintain a moderate average activity level by another learning rule: intrinsic plasticity (IP). Our study shows that LSM with STDP+IP performs better than LSM with a random SNN or SNN obtained by STDP alone. The noticeable improvement with the proposed method is due to the better reflected competition among different neurons in the developed SNN model, as well as the more effectively encoded and processed relevant dynamic information with its learning and self-organizing mechanism. This result gives insights to the optimization of computational models of spiking neural networks with neural plasticity.

A Fast Neural Network Approach to Predict Lung Tumor Motion during Respiration for Radiation Therapy Applications

PubMed Central

Slama, Matous; Benes, Peter M.; Bila, Jiri

2015-01-01

During radiotherapy treatment for thoracic and abdomen cancers, for example, lung cancers, respiratory motion moves the target tumor and thus badly affects the accuracy of radiation dose delivery into the target. A real-time image-guided technique can be used to monitor such lung tumor motion for accurate dose delivery, but the system latency up to several hundred milliseconds for repositioning the radiation beam also affects the accuracy. In order to compensate the latency, neural network prediction technique with real-time retraining can be used. We have investigated real-time prediction of 3D time series of lung tumor motion on a classical linear model, perceptron model, and on a class of higher-order neural network model that has more attractive attributes regarding its optimization convergence and computational efficiency. The implemented static feed-forward neural architectures are compared when using gradient descent adaptation and primarily the Levenberg-Marquardt batch algorithm as the ones of the most common and most comprehensible learning algorithms. The proposed technique resulted in fast real-time retraining, so the total computational time on a PC platform was equal to or even less than the real treatment time. For one-second prediction horizon, the proposed techniques achieved accuracy less than one millimeter of 3D mean absolute error in one hundred seconds of total treatment time. PMID:25893194

Hermite Functional Link Neural Network for Solving the Van der Pol-Duffing Oscillator Equation.

PubMed

Mall, Susmita; Chakraverty, S

2016-08-01

Hermite polynomial-based functional link artificial neural network (FLANN) is proposed here to solve the Van der Pol-Duffing oscillator equation. A single-layer hermite neural network (HeNN) model is used, where a hidden layer is replaced by expansion block of input pattern using Hermite orthogonal polynomials. A feedforward neural network model with the unsupervised error backpropagation principle is used for modifying the network parameters and minimizing the computed error function. The Van der Pol-Duffing and Duffing oscillator equations may not be solved exactly. Here, approximate solutions of these types of equations have been obtained by applying the HeNN model for the first time. Three mathematical example problems and two real-life application problems of Van der Pol-Duffing oscillator equation, extracting the features of early mechanical failure signal and weak signal detection problems, are solved using the proposed HeNN method. HeNN approximate solutions have been compared with results obtained by the well known Runge-Kutta method. Computed results are depicted in term of graphs. After training the HeNN model, we may use it as a black box to get numerical results at any arbitrary point in the domain. Thus, the proposed HeNN method is efficient. The results reveal that this method is reliable and can be applied to other nonlinear problems too.

FPGA implementation of a biological neural network based on the Hodgkin-Huxley neuron model.

PubMed

Yaghini Bonabi, Safa; Asgharian, Hassan; Safari, Saeed; Nili Ahmadabadi, Majid

2014-01-01

A set of techniques for efficient implementation of Hodgkin-Huxley-based (H-H) model of a neural network on FPGA (Field Programmable Gate Array) is presented. The central implementation challenge is H-H model complexity that puts limits on the network size and on the execution speed. However, basics of the original model cannot be compromised when effect of synaptic specifications on the network behavior is the subject of study. To solve the problem, we used computational techniques such as CORDIC (Coordinate Rotation Digital Computer) algorithm and step-by-step integration in the implementation of arithmetic circuits. In addition, we employed different techniques such as sharing resources to preserve the details of model as well as increasing the network size in addition to keeping the network execution speed close to real time while having high precision. Implementation of a two mini-columns network with 120/30 excitatory/inhibitory neurons is provided to investigate the characteristic of our method in practice. The implementation techniques provide an opportunity to construct large FPGA-based network models to investigate the effect of different neurophysiological mechanisms, like voltage-gated channels and synaptic activities, on the behavior of a neural network in an appropriate execution time. Additional to inherent properties of FPGA, like parallelism and re-configurability, our approach makes the FPGA-based system a proper candidate for study on neural control of cognitive robots and systems as well.

A fast neural network approach to predict lung tumor motion during respiration for radiation therapy applications.

PubMed

Bukovsky, Ivo; Homma, Noriyasu; Ichiji, Kei; Cejnek, Matous; Slama, Matous; Benes, Peter M; Bila, Jiri

2015-01-01

During radiotherapy treatment for thoracic and abdomen cancers, for example, lung cancers, respiratory motion moves the target tumor and thus badly affects the accuracy of radiation dose delivery into the target. A real-time image-guided technique can be used to monitor such lung tumor motion for accurate dose delivery, but the system latency up to several hundred milliseconds for repositioning the radiation beam also affects the accuracy. In order to compensate the latency, neural network prediction technique with real-time retraining can be used. We have investigated real-time prediction of 3D time series of lung tumor motion on a classical linear model, perceptron model, and on a class of higher-order neural network model that has more attractive attributes regarding its optimization convergence and computational efficiency. The implemented static feed-forward neural architectures are compared when using gradient descent adaptation and primarily the Levenberg-Marquardt batch algorithm as the ones of the most common and most comprehensible learning algorithms. The proposed technique resulted in fast real-time retraining, so the total computational time on a PC platform was equal to or even less than the real treatment time. For one-second prediction horizon, the proposed techniques achieved accuracy less than one millimeter of 3D mean absolute error in one hundred seconds of total treatment time.

On the Computational Power of Spiking Neural P Systems with Self-Organization.

PubMed

Wang, Xun; Song, Tao; Gong, Faming; Zheng, Pan

2016-06-10

Neural-like computing models are versatile computing mechanisms in the field of artificial intelligence. Spiking neural P systems (SN P systems for short) are one of the recently developed spiking neural network models inspired by the way neurons communicate. The communications among neurons are essentially achieved by spikes, i. e. short electrical pulses. In terms of motivation, SN P systems fall into the third generation of neural network models. In this study, a novel variant of SN P systems, namely SN P systems with self-organization, is introduced, and the computational power of the system is investigated and evaluated. It is proved that SN P systems with self-organization are capable of computing and accept the family of sets of Turing computable natural numbers. Moreover, with 87 neurons the system can compute any Turing computable recursive function, thus achieves Turing universality. These results demonstrate promising initiatives to solve an open problem arisen by Gh Păun.

On the Computational Power of Spiking Neural P Systems with Self-Organization

PubMed Central

Wang, Xun; Song, Tao; Gong, Faming; Zheng, Pan

2016-01-01

Neural-like computing models are versatile computing mechanisms in the field of artificial intelligence. Spiking neural P systems (SN P systems for short) are one of the recently developed spiking neural network models inspired by the way neurons communicate. The communications among neurons are essentially achieved by spikes, i. e. short electrical pulses. In terms of motivation, SN P systems fall into the third generation of neural network models. In this study, a novel variant of SN P systems, namely SN P systems with self-organization, is introduced, and the computational power of the system is investigated and evaluated. It is proved that SN P systems with self-organization are capable of computing and accept the family of sets of Turing computable natural numbers. Moreover, with 87 neurons the system can compute any Turing computable recursive function, thus achieves Turing universality. These results demonstrate promising initiatives to solve an open problem arisen by Gh Păun. PMID:27283843

On the Computational Power of Spiking Neural P Systems with Self-Organization

NASA Astrophysics Data System (ADS)

Wang, Xun; Song, Tao; Gong, Faming; Zheng, Pan

2016-06-01

Neural-like computing models are versatile computing mechanisms in the field of artificial intelligence. Spiking neural P systems (SN P systems for short) are one of the recently developed spiking neural network models inspired by the way neurons communicate. The communications among neurons are essentially achieved by spikes, i. e. short electrical pulses. In terms of motivation, SN P systems fall into the third generation of neural network models. In this study, a novel variant of SN P systems, namely SN P systems with self-organization, is introduced, and the computational power of the system is investigated and evaluated. It is proved that SN P systems with self-organization are capable of computing and accept the family of sets of Turing computable natural numbers. Moreover, with 87 neurons the system can compute any Turing computable recursive function, thus achieves Turing universality. These results demonstrate promising initiatives to solve an open problem arisen by Gh Păun.

A framework for plasticity implementation on the SpiNNaker neural architecture.

PubMed

Galluppi, Francesco; Lagorce, Xavier; Stromatias, Evangelos; Pfeiffer, Michael; Plana, Luis A; Furber, Steve B; Benosman, Ryad B

2014-01-01

Many of the precise biological mechanisms of synaptic plasticity remain elusive, but simulations of neural networks have greatly enhanced our understanding of how specific global functions arise from the massively parallel computation of neurons and local Hebbian or spike-timing dependent plasticity rules. For simulating large portions of neural tissue, this has created an increasingly strong need for large scale simulations of plastic neural networks on special purpose hardware platforms, because synaptic transmissions and updates are badly matched to computing style supported by current architectures. Because of the great diversity of biological plasticity phenomena and the corresponding diversity of models, there is a great need for testing various hypotheses about plasticity before committing to one hardware implementation. Here we present a novel framework for investigating different plasticity approaches on the SpiNNaker distributed digital neural simulation platform. The key innovation of the proposed architecture is to exploit the reconfigurability of the ARM processors inside SpiNNaker, dedicating a subset of them exclusively to process synaptic plasticity updates, while the rest perform the usual neural and synaptic simulations. We demonstrate the flexibility of the proposed approach by showing the implementation of a variety of spike- and rate-based learning rules, including standard Spike-Timing dependent plasticity (STDP), voltage-dependent STDP, and the rate-based BCM rule. We analyze their performance and validate them by running classical learning experiments in real time on a 4-chip SpiNNaker board. The result is an efficient, modular, flexible and scalable framework, which provides a valuable tool for the fast and easy exploration of learning models of very different kinds on the parallel and reconfigurable SpiNNaker system.

A framework for plasticity implementation on the SpiNNaker neural architecture

PubMed Central

Galluppi, Francesco; Lagorce, Xavier; Stromatias, Evangelos; Pfeiffer, Michael; Plana, Luis A.; Furber, Steve B.; Benosman, Ryad B.

2015-01-01

Many of the precise biological mechanisms of synaptic plasticity remain elusive, but simulations of neural networks have greatly enhanced our understanding of how specific global functions arise from the massively parallel computation of neurons and local Hebbian or spike-timing dependent plasticity rules. For simulating large portions of neural tissue, this has created an increasingly strong need for large scale simulations of plastic neural networks on special purpose hardware platforms, because synaptic transmissions and updates are badly matched to computing style supported by current architectures. Because of the great diversity of biological plasticity phenomena and the corresponding diversity of models, there is a great need for testing various hypotheses about plasticity before committing to one hardware implementation. Here we present a novel framework for investigating different plasticity approaches on the SpiNNaker distributed digital neural simulation platform. The key innovation of the proposed architecture is to exploit the reconfigurability of the ARM processors inside SpiNNaker, dedicating a subset of them exclusively to process synaptic plasticity updates, while the rest perform the usual neural and synaptic simulations. We demonstrate the flexibility of the proposed approach by showing the implementation of a variety of spike- and rate-based learning rules, including standard Spike-Timing dependent plasticity (STDP), voltage-dependent STDP, and the rate-based BCM rule. We analyze their performance and validate them by running classical learning experiments in real time on a 4-chip SpiNNaker board. The result is an efficient, modular, flexible and scalable framework, which provides a valuable tool for the fast and easy exploration of learning models of very different kinds on the parallel and reconfigurable SpiNNaker system. PMID:25653580

Neural Computation and the Computational Theory of Cognition

ERIC Educational Resources Information Center

Piccinini, Gualtiero; Bahar, Sonya

2013-01-01

We begin by distinguishing computationalism from a number of other theses that are sometimes conflated with it. We also distinguish between several important kinds of computation: computation in a generic sense, digital computation, and analog computation. Then, we defend a weak version of computationalism--neural processes are computations in the…

An integrated modelling framework for neural circuits with multiple neuromodulators.

PubMed

Joshi, Alok; Youssofzadeh, Vahab; Vemana, Vinith; McGinnity, T M; Prasad, Girijesh; Wong-Lin, KongFatt

2017-01-01

Neuromodulators are endogenous neurochemicals that regulate biophysical and biochemical processes, which control brain function and behaviour, and are often the targets of neuropharmacological drugs. Neuromodulator effects are generally complex partly owing to the involvement of broad innervation, co-release of neuromodulators, complex intra- and extrasynaptic mechanism, existence of multiple receptor subtypes and high interconnectivity within the brain. In this work, we propose an efficient yet sufficiently realistic computational neural modelling framework to study some of these complex behaviours. Specifically, we propose a novel dynamical neural circuit model that integrates the effective neuromodulator-induced currents based on various experimental data (e.g. electrophysiology, neuropharmacology and voltammetry). The model can incorporate multiple interacting brain regions, including neuromodulator sources, simulate efficiently and easily extendable to large-scale brain models, e.g. for neuroimaging purposes. As an example, we model a network of mutually interacting neural populations in the lateral hypothalamus, dorsal raphe nucleus and locus coeruleus, which are major sources of neuromodulator orexin/hypocretin, serotonin and norepinephrine/noradrenaline, respectively, and which play significant roles in regulating many physiological functions. We demonstrate that such a model can provide predictions of systemic drug effects of the popular antidepressants (e.g. reuptake inhibitors), neuromodulator antagonists or their combinations. Finally, we developed user-friendly graphical user interface software for model simulation and visualization for both fundamental sciences and pharmacological studies. © 2017 The Authors.

An integrated modelling framework for neural circuits with multiple neuromodulators

PubMed Central

Vemana, Vinith

2017-01-01

Neuromodulators are endogenous neurochemicals that regulate biophysical and biochemical processes, which control brain function and behaviour, and are often the targets of neuropharmacological drugs. Neuromodulator effects are generally complex partly owing to the involvement of broad innervation, co-release of neuromodulators, complex intra- and extrasynaptic mechanism, existence of multiple receptor subtypes and high interconnectivity within the brain. In this work, we propose an efficient yet sufficiently realistic computational neural modelling framework to study some of these complex behaviours. Specifically, we propose a novel dynamical neural circuit model that integrates the effective neuromodulator-induced currents based on various experimental data (e.g. electrophysiology, neuropharmacology and voltammetry). The model can incorporate multiple interacting brain regions, including neuromodulator sources, simulate efficiently and easily extendable to large-scale brain models, e.g. for neuroimaging purposes. As an example, we model a network of mutually interacting neural populations in the lateral hypothalamus, dorsal raphe nucleus and locus coeruleus, which are major sources of neuromodulator orexin/hypocretin, serotonin and norepinephrine/noradrenaline, respectively, and which play significant roles in regulating many physiological functions. We demonstrate that such a model can provide predictions of systemic drug effects of the popular antidepressants (e.g. reuptake inhibitors), neuromodulator antagonists or their combinations. Finally, we developed user-friendly graphical user interface software for model simulation and visualization for both fundamental sciences and pharmacological studies. PMID:28100828

Reducing the computational footprint for real-time BCPNN learning

PubMed Central

Vogginger, Bernhard; Schüffny, René; Lansner, Anders; Cederström, Love; Partzsch, Johannes; Höppner, Sebastian

2015-01-01

The implementation of synaptic plasticity in neural simulation or neuromorphic hardware is usually very resource-intensive, often requiring a compromise between efficiency and flexibility. A versatile, but computationally-expensive plasticity mechanism is provided by the Bayesian Confidence Propagation Neural Network (BCPNN) paradigm. Building upon Bayesian statistics, and having clear links to biological plasticity processes, the BCPNN learning rule has been applied in many fields, ranging from data classification, associative memory, reward-based learning, probabilistic inference to cortical attractor memory networks. In the spike-based version of this learning rule the pre-, postsynaptic and coincident activity is traced in three low-pass-filtering stages, requiring a total of eight state variables, whose dynamics are typically simulated with the fixed step size Euler method. We derive analytic solutions allowing an efficient event-driven implementation of this learning rule. Further speedup is achieved by first rewriting the model which reduces the number of basic arithmetic operations per update to one half, and second by using look-up tables for the frequently calculated exponential decay. Ultimately, in a typical use case, the simulation using our approach is more than one order of magnitude faster than with the fixed step size Euler method. Aiming for a small memory footprint per BCPNN synapse, we also evaluate the use of fixed-point numbers for the state variables, and assess the number of bits required to achieve same or better accuracy than with the conventional explicit Euler method. All of this will allow a real-time simulation of a reduced cortex model based on BCPNN in high performance computing. More important, with the analytic solution at hand and due to the reduced memory bandwidth, the learning rule can be efficiently implemented in dedicated or existing digital neuromorphic hardware. PMID:25657618

Reducing the computational footprint for real-time BCPNN learning.

PubMed

Vogginger, Bernhard; Schüffny, René; Lansner, Anders; Cederström, Love; Partzsch, Johannes; Höppner, Sebastian

2015-01-01

The implementation of synaptic plasticity in neural simulation or neuromorphic hardware is usually very resource-intensive, often requiring a compromise between efficiency and flexibility. A versatile, but computationally-expensive plasticity mechanism is provided by the Bayesian Confidence Propagation Neural Network (BCPNN) paradigm. Building upon Bayesian statistics, and having clear links to biological plasticity processes, the BCPNN learning rule has been applied in many fields, ranging from data classification, associative memory, reward-based learning, probabilistic inference to cortical attractor memory networks. In the spike-based version of this learning rule the pre-, postsynaptic and coincident activity is traced in three low-pass-filtering stages, requiring a total of eight state variables, whose dynamics are typically simulated with the fixed step size Euler method. We derive analytic solutions allowing an efficient event-driven implementation of this learning rule. Further speedup is achieved by first rewriting the model which reduces the number of basic arithmetic operations per update to one half, and second by using look-up tables for the frequently calculated exponential decay. Ultimately, in a typical use case, the simulation using our approach is more than one order of magnitude faster than with the fixed step size Euler method. Aiming for a small memory footprint per BCPNN synapse, we also evaluate the use of fixed-point numbers for the state variables, and assess the number of bits required to achieve same or better accuracy than with the conventional explicit Euler method. All of this will allow a real-time simulation of a reduced cortex model based on BCPNN in high performance computing. More important, with the analytic solution at hand and due to the reduced memory bandwidth, the learning rule can be efficiently implemented in dedicated or existing digital neuromorphic hardware.

An Energy Model of Place Cell Network in Three Dimensional Space.

PubMed

Wang, Yihong; Xu, Xuying; Wang, Rubin

2018-01-01

Place cells are important elements in the spatial representation system of the brain. A considerable amount of experimental data and classical models are achieved in this area. However, an important question has not been addressed, which is how the three dimensional space is represented by the place cells. This question is preliminarily surveyed by energy coding method in this research. Energy coding method argues that neural information can be expressed by neural energy and it is convenient to model and compute for neural systems due to the global and linearly addable properties of neural energy. Nevertheless, the models of functional neural networks based on energy coding method have not been established. In this work, we construct a place cell network model to represent three dimensional space on an energy level. Then we define the place field and place field center and test the locating performance in three dimensional space. The results imply that the model successfully simulates the basic properties of place cells. The individual place cell obtains unique spatial selectivity. The place fields in three dimensional space vary in size and energy consumption. Furthermore, the locating error is limited to a certain level and the simulated place field agrees to the experimental results. In conclusion, this is an effective model to represent three dimensional space by energy method. The research verifies the energy efficiency principle of the brain during the neural coding for three dimensional spatial information. It is the first step to complete the three dimensional spatial representing system of the brain, and helps us further understand how the energy efficiency principle directs the locating, navigating, and path planning function of the brain.

Feature extraction using first and second derivative extrema (FSDE) for real-time and hardware-efficient spike sorting.

PubMed

Paraskevopoulou, Sivylla E; Barsakcioglu, Deren Y; Saberi, Mohammed R; Eftekhar, Amir; Constandinou, Timothy G

2013-04-30

Next generation neural interfaces aspire to achieve real-time multi-channel systems by integrating spike sorting on chip to overcome limitations in communication channel capacity. The feasibility of this approach relies on developing highly efficient algorithms for feature extraction and clustering with the potential of low-power hardware implementation. We are proposing a feature extraction method, not requiring any calibration, based on first and second derivative features of the spike waveform. The accuracy and computational complexity of the proposed method are quantified and compared against commonly used feature extraction methods, through simulation across four datasets (with different single units) at multiple noise levels (ranging from 5 to 20% of the signal amplitude). The average classification error is shown to be below 7% with a computational complexity of 2N-3, where N is the number of sample points of each spike. Overall, this method presents a good trade-off between accuracy and computational complexity and is thus particularly well-suited for hardware-efficient implementation. Copyright © 2013 Elsevier B.V. All rights reserved.

Optical information-processing systems and architectures II; Proceedings of the Meeting, San Diego, CA, July 9-13, 1990

NASA Astrophysics Data System (ADS)

Javidi, Bahram

The present conference discusses topics in the fields of neural networks, acoustooptic signal processing, pattern recognition, phase-only processing, nonlinear signal processing, image processing, optical computing, and optical information processing. Attention is given to the optical implementation of an inner-product neural associative memory, optoelectronic associative recall via motionless-head/parallel-readout optical disk, a compact real-time acoustooptic image correlator, a multidimensional synthetic estimation filter, and a light-efficient joint transform optical correlator. Also discussed are a high-resolution spatial light modulator, compact real-time interferometric Fourier-transform processors, a fast decorrelation algorithm for permutation arrays, the optical interconnection of optical modules, and carry-free optical binary adders.

Spatiotemporal Computations of an Excitable and Plastic Brain: Neuronal Plasticity Leads to Noise-Robust and Noise-Constructive Computations

PubMed Central

Toutounji, Hazem; Pipa, Gordon

2014-01-01

It is a long-established fact that neuronal plasticity occupies the central role in generating neural function and computation. Nevertheless, no unifying account exists of how neurons in a recurrent cortical network learn to compute on temporally and spatially extended stimuli. However, these stimuli constitute the norm, rather than the exception, of the brain's input. Here, we introduce a geometric theory of learning spatiotemporal computations through neuronal plasticity. To that end, we rigorously formulate the problem of neural representations as a relation in space between stimulus-induced neural activity and the asymptotic dynamics of excitable cortical networks. Backed up by computer simulations and numerical analysis, we show that two canonical and widely spread forms of neuronal plasticity, that is, spike-timing-dependent synaptic plasticity and intrinsic plasticity, are both necessary for creating neural representations, such that these computations become realizable. Interestingly, the effects of these forms of plasticity on the emerging neural code relate to properties necessary for both combating and utilizing noise. The neural dynamics also exhibits features of the most likely stimulus in the network's spontaneous activity. These properties of the spatiotemporal neural code resulting from plasticity, having their grounding in nature, further consolidate the biological relevance of our findings. PMID:24651447

Implementing Signature Neural Networks with Spiking Neurons

PubMed Central

Carrillo-Medina, José Luis; Latorre, Roberto

2016-01-01

Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm—i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data—to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the absence of inhibitory connections. These parameters also modulate the memory capabilities of the network. The dynamical modes observed in the different informational dimensions in a given moment are independent and they only depend on the parameters shaping the information processing in this dimension. In view of these results, we argue that plasticity mechanisms inside individual cells and multicoding strategies can provide additional computational properties to spiking neural networks, which could enhance their capacity and performance in a wide variety of real-world tasks. PMID:28066221

Implementing Signature Neural Networks with Spiking Neurons.

PubMed

Carrillo-Medina, José Luis; Latorre, Roberto

2016-01-01

Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm-i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data-to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the absence of inhibitory connections. These parameters also modulate the memory capabilities of the network. The dynamical modes observed in the different informational dimensions in a given moment are independent and they only depend on the parameters shaping the information processing in this dimension. In view of these results, we argue that plasticity mechanisms inside individual cells and multicoding strategies can provide additional computational properties to spiking neural networks, which could enhance their capacity and performance in a wide variety of real-world tasks.

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence

PubMed Central

Cichy, Radoslaw Martin; Khosla, Aditya; Pantazis, Dimitrios; Torralba, Antonio; Oliva, Aude

2016-01-01

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain. PMID:27282108

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence.

PubMed

Cichy, Radoslaw Martin; Khosla, Aditya; Pantazis, Dimitrios; Torralba, Antonio; Oliva, Aude

2016-06-10

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain.

Biological modelling of a computational spiking neural network with neuronal avalanches.

PubMed

Li, Xiumin; Chen, Qing; Xue, Fangzheng

2017-06-28

In recent years, an increasing number of studies have demonstrated that networks in the brain can self-organize into a critical state where dynamics exhibit a mixture of ordered and disordered patterns. This critical branching phenomenon is termed neuronal avalanches. It has been hypothesized that the homeostatic level balanced between stability and plasticity of this critical state may be the optimal state for performing diverse neural computational tasks. However, the critical region for high performance is narrow and sensitive for spiking neural networks (SNNs). In this paper, we investigated the role of the critical state in neural computations based on liquid-state machines, a biologically plausible computational neural network model for real-time computing. The computational performance of an SNN when operating at the critical state and, in particular, with spike-timing-dependent plasticity for updating synaptic weights is investigated. The network is found to show the best computational performance when it is subjected to critical dynamic states. Moreover, the active-neuron-dominant structure refined from synaptic learning can remarkably enhance the robustness of the critical state and further improve computational accuracy. These results may have important implications in the modelling of spiking neural networks with optimal computational performance.This article is part of the themed issue 'Mathematical methods in medicine: neuroscience, cardiology and pathology'. © 2017 The Author(s).

Biological modelling of a computational spiking neural network with neuronal avalanches

NASA Astrophysics Data System (ADS)

Li, Xiumin; Chen, Qing; Xue, Fangzheng

2017-05-01

In recent years, an increasing number of studies have demonstrated that networks in the brain can self-organize into a critical state where dynamics exhibit a mixture of ordered and disordered patterns. This critical branching phenomenon is termed neuronal avalanches. It has been hypothesized that the homeostatic level balanced between stability and plasticity of this critical state may be the optimal state for performing diverse neural computational tasks. However, the critical region for high performance is narrow and sensitive for spiking neural networks (SNNs). In this paper, we investigated the role of the critical state in neural computations based on liquid-state machines, a biologically plausible computational neural network model for real-time computing. The computational performance of an SNN when operating at the critical state and, in particular, with spike-timing-dependent plasticity for updating synaptic weights is investigated. The network is found to show the best computational performance when it is subjected to critical dynamic states. Moreover, the active-neuron-dominant structure refined from synaptic learning can remarkably enhance the robustness of the critical state and further improve computational accuracy. These results may have important implications in the modelling of spiking neural networks with optimal computational performance. This article is part of the themed issue `Mathematical methods in medicine: neuroscience, cardiology and pathology'.

Computational model for perception of objects and motions.

PubMed

Yang, WenLu; Zhang, LiQing; Ma, LiBo

2008-06-01

Perception of objects and motions in the visual scene is one of the basic problems in the visual system. There exist 'What' and 'Where' pathways in the superior visual cortex, starting from the simple cells in the primary visual cortex. The former is able to perceive objects such as forms, color, and texture, and the latter perceives 'where', for example, velocity and direction of spatial movement of objects. This paper explores brain-like computational architectures of visual information processing. We propose a visual perceptual model and computational mechanism for training the perceptual model. The computational model is a three-layer network. The first layer is the input layer which is used to receive the stimuli from natural environments. The second layer is designed for representing the internal neural information. The connections between the first layer and the second layer, called the receptive fields of neurons, are self-adaptively learned based on principle of sparse neural representation. To this end, we introduce Kullback-Leibler divergence as the measure of independence between neural responses and derive the learning algorithm based on minimizing the cost function. The proposed algorithm is applied to train the basis functions, namely receptive fields, which are localized, oriented, and bandpassed. The resultant receptive fields of neurons in the second layer have the characteristics resembling that of simple cells in the primary visual cortex. Based on these basis functions, we further construct the third layer for perception of what and where in the superior visual cortex. The proposed model is able to perceive objects and their motions with a high accuracy and strong robustness against additive noise. Computer simulation results in the final section show the feasibility of the proposed perceptual model and high efficiency of the learning algorithm.

Databases, data integration, and expert systems: new directions in mineral resource assessment and mineral exploration

USGS Publications Warehouse

McCammon, Richard B.; Ramani, Raja V.; Mozumdar, Bijoy K.; Samaddar, Arun B.

1994-01-01

Overcoming future difficulties in searching for ore deposits deeper in the earth's crust will require closer attention to the collection and analysis of more diverse types of data and to more efficient use of current computer technologies. Computer technologies of greatest interest include methods of storage and retrieval of resource information, methods for integrating geologic, geochemical, and geophysical data, and the introduction of advanced computer technologies such as expert systems, multivariate techniques, and neural networks. Much experience has been gained in the past few years in applying these technologies. More experience is needed if they are to be implemented for everyday use in future assessments and exploration.

A High-Performance Neural Prosthesis Incorporating Discrete State Selection With Hidden Markov Models.

PubMed

Kao, Jonathan C; Nuyujukian, Paul; Ryu, Stephen I; Shenoy, Krishna V

2017-04-01

Communication neural prostheses aim to restore efficient communication to people with motor neurological injury or disease by decoding neural activity into control signals. These control signals are both analog (e.g., the velocity of a computer mouse) and discrete (e.g., clicking an icon with a computer mouse) in nature. Effective, high-performing, and intuitive-to-use communication prostheses should be capable of decoding both analog and discrete state variables seamlessly. However, to date, the highest-performing autonomous communication prostheses rely on precise analog decoding and typically do not incorporate high-performance discrete decoding. In this report, we incorporated a hidden Markov model (HMM) into an intracortical communication prosthesis to enable accurate and fast discrete state decoding in parallel with analog decoding. In closed-loop experiments with nonhuman primates implanted with multielectrode arrays, we demonstrate that incorporating an HMM into a neural prosthesis can increase state-of-the-art achieved bitrate by 13.9% and 4.2% in two monkeys ( ). We found that the transition model of the HMM is critical to achieving this performance increase. Further, we found that using an HMM resulted in the highest achieved peak performance we have ever observed for these monkeys, achieving peak bitrates of 6.5, 5.7, and 4.7 bps in Monkeys J, R, and L, respectively. Finally, we found that this neural prosthesis was robustly controllable for the duration of entire experimental sessions. These results demonstrate that high-performance discrete decoding can be beneficially combined with analog decoding to achieve new state-of-the-art levels of performance.

LLNL Partners with IBM on Brain-Like Computing Chip

DOE Office of Scientific and Technical Information (OSTI.GOV)

Van Essen, Brian

Lawrence Livermore National Laboratory (LLNL) will receive a first-of-a-kind brain-inspired supercomputing platform for deep learning developed by IBM Research. Based on a breakthrough neurosynaptic computer chip called IBM TrueNorth, the scalable platform will process the equivalent of 16 million neurons and 4 billion synapses and consume the energy equivalent of a hearing aid battery – a mere 2.5 watts of power. The brain-like, neural network design of the IBM Neuromorphic System is able to infer complex cognitive tasks such as pattern recognition and integrated sensory processing far more efficiently than conventional chips.

LLNL Partners with IBM on Brain-Like Computing Chip

ScienceCinema

Van Essen, Brian

2018-06-25

Lawrence Livermore National Laboratory (LLNL) will receive a first-of-a-kind brain-inspired supercomputing platform for deep learning developed by IBM Research. Based on a breakthrough neurosynaptic computer chip called IBM TrueNorth, the scalable platform will process the equivalent of 16 million neurons and 4 billion synapses and consume the energy equivalent of a hearing aid battery – a mere 2.5 watts of power. The brain-like, neural network design of the IBM Neuromorphic System is able to infer complex cognitive tasks such as pattern recognition and integrated sensory processing far more efficiently than conventional chips.

A lightweight QRS detector for single lead ECG signals using a max-min difference algorithm.

PubMed

Pandit, Diptangshu; Zhang, Li; Liu, Chengyu; Chattopadhyay, Samiran; Aslam, Nauman; Lim, Chee Peng

2017-06-01

Detection of the R-peak pertaining to the QRS complex of an ECG signal plays an important role for the diagnosis of a patient's heart condition. To accurately identify the QRS locations from the acquired raw ECG signals, we need to handle a number of challenges, which include noise, baseline wander, varying peak amplitudes, and signal abnormality. This research aims to address these challenges by developing an efficient lightweight algorithm for QRS (i.e., R-peak) detection from raw ECG signals. A lightweight real-time sliding window-based Max-Min Difference (MMD) algorithm for QRS detection from Lead II ECG signals is proposed. Targeting to achieve the best trade-off between computational efficiency and detection accuracy, the proposed algorithm consists of five key steps for QRS detection, namely, baseline correction, MMD curve generation, dynamic threshold computation, R-peak detection, and error correction. Five annotated databases from Physionet are used for evaluating the proposed algorithm in R-peak detection. Integrated with a feature extraction technique and a neural network classifier, the proposed ORS detection algorithm has also been extended to undertake normal and abnormal heartbeat detection from ECG signals. The proposed algorithm exhibits a high degree of robustness in QRS detection and achieves an average sensitivity of 99.62% and an average positive predictivity of 99.67%. Its performance compares favorably with those from the existing state-of-the-art models reported in the literature. In regards to normal and abnormal heartbeat detection, the proposed QRS detection algorithm in combination with the feature extraction technique and neural network classifier achieves an overall accuracy rate of 93.44% based on an empirical evaluation using the MIT-BIH Arrhythmia data set with 10-fold cross validation. In comparison with other related studies, the proposed algorithm offers a lightweight adaptive alternative for R-peak detection with good computational efficiency. The empirical results indicate that it not only yields a high accuracy rate in QRS detection, but also exhibits efficient computational complexity at the order of O(n), where n is the length of an ECG signal. Copyright © 2017 Elsevier B.V. All rights reserved.

Forecasting sea cliff retreat in Southern California using process-based models and artificial neural networks

NASA Astrophysics Data System (ADS)

Limber, P. W.; Barnard, P.; Erikson, L. H.

2016-02-01

Modeling coastal geomorphic change over multi-decadal time and regional spatial scales (i.e. >20 km alongshore) is in high demand due to rising global sea levels and heavily populated coastal zones, but is challenging for several reasons: adequate geomorphic and oceanographic data often does not exist over the entire study area or time period; models can be too computationally expensive; and model uncertainty is high. In the absence of rich datasets and unlimited computer processing power, researchers are forced to leverage existing data, however sparse, and find analytical methods that minimize computation time without sacrificing (too much) model reliability. Machine learning techniques, such as artificial neural networks, can assimilate and efficiently extrapolate geomorphic model behavior over large areas. They can also facilitate ensemble model forecasts over a broad range of parameter space, which is useful when a paucity of observational data inhibits the constraint of model parameters. Here, we assimilate the behavior of two established process-based sea cliff erosion and retreat models into a neural network to forecast the impacts of sea level rise on sea cliff retreat in Southern California ( 400 km) through the 21st century. Using inputs such as historical cliff retreat rates, mean wave power, and whether or not a beach is present, the neural network independently reproduces modeled sea cliff retreat as a function of sea level rise with a high degree of confidence (R2 > 0.9, mean squared error < 0.1 m yr-1). Results will continuously improve as more model scenarios are assimilated into the neural network, and more field data (i.e., cliff composition and rock hardness) becomes available to tune the cliff retreat models. Preliminary results suggest that sea level rise rates of 2 to 20 mm yr-1 during the next century could accelerate historical cliff retreat rates in Southern California by an average of 0.10 - 0.56 m yr-1.

A Neurocomputational Model of Goal-Directed Navigation in Insect-Inspired Artificial Agents

PubMed Central

Goldschmidt, Dennis; Manoonpong, Poramate; Dasgupta, Sakyasingha

2017-01-01

Despite their small size, insect brains are able to produce robust and efficient navigation in complex environments. Specifically in social insects, such as ants and bees, these navigational capabilities are guided by orientation directing vectors generated by a process called path integration. During this process, they integrate compass and odometric cues to estimate their current location as a vector, called the home vector for guiding them back home on a straight path. They further acquire and retrieve path integration-based vector memories globally to the nest or based on visual landmarks. Although existing computational models reproduced similar behaviors, a neurocomputational model of vector navigation including the acquisition of vector representations has not been described before. Here we present a model of neural mechanisms in a modular closed-loop control—enabling vector navigation in artificial agents. The model consists of a path integration mechanism, reward-modulated global learning, random search, and action selection. The path integration mechanism integrates compass and odometric cues to compute a vectorial representation of the agent's current location as neural activity patterns in circular arrays. A reward-modulated learning rule enables the acquisition of vector memories by associating the local food reward with the path integration state. A motor output is computed based on the combination of vector memories and random exploration. In simulation, we show that the neural mechanisms enable robust homing and localization, even in the presence of external sensory noise. The proposed learning rules lead to goal-directed navigation and route formation performed under realistic conditions. Consequently, we provide a novel approach for vector learning and navigation in a simulated, situated agent linking behavioral observations to their possible underlying neural substrates. PMID:28446872

A Neurocomputational Model of Goal-Directed Navigation in Insect-Inspired Artificial Agents.

PubMed

Goldschmidt, Dennis; Manoonpong, Poramate; Dasgupta, Sakyasingha

2017-01-01

Despite their small size, insect brains are able to produce robust and efficient navigation in complex environments. Specifically in social insects, such as ants and bees, these navigational capabilities are guided by orientation directing vectors generated by a process called path integration. During this process, they integrate compass and odometric cues to estimate their current location as a vector, called the home vector for guiding them back home on a straight path. They further acquire and retrieve path integration-based vector memories globally to the nest or based on visual landmarks. Although existing computational models reproduced similar behaviors, a neurocomputational model of vector navigation including the acquisition of vector representations has not been described before. Here we present a model of neural mechanisms in a modular closed-loop control-enabling vector navigation in artificial agents. The model consists of a path integration mechanism, reward-modulated global learning, random search, and action selection. The path integration mechanism integrates compass and odometric cues to compute a vectorial representation of the agent's current location as neural activity patterns in circular arrays. A reward-modulated learning rule enables the acquisition of vector memories by associating the local food reward with the path integration state. A motor output is computed based on the combination of vector memories and random exploration. In simulation, we show that the neural mechanisms enable robust homing and localization, even in the presence of external sensory noise. The proposed learning rules lead to goal-directed navigation and route formation performed under realistic conditions. Consequently, we provide a novel approach for vector learning and navigation in a simulated, situated agent linking behavioral observations to their possible underlying neural substrates.

Fast maximum likelihood estimation using continuous-time neural point process models.

PubMed

Lepage, Kyle Q; MacDonald, Christopher J

2015-06-01

A recent report estimates that the number of simultaneously recorded neurons is growing exponentially. A commonly employed statistical paradigm using discrete-time point process models of neural activity involves the computation of a maximum-likelihood estimate. The time to computate this estimate, per neuron, is proportional to the number of bins in a finely spaced discretization of time. By using continuous-time models of neural activity and the optimally efficient Gaussian quadrature, memory requirements and computation times are dramatically decreased in the commonly encountered situation where the number of parameters p is much less than the number of time-bins n. In this regime, with q equal to the quadrature order, memory requirements are decreased from O(np) to O(qp), and the number of floating-point operations are decreased from O(np(2)) to O(qp(2)). Accuracy of the proposed estimates is assessed based upon physiological consideration, error bounds, and mathematical results describing the relation between numerical integration error and numerical error affecting both parameter estimates and the observed Fisher information. A check is provided which is used to adapt the order of numerical integration. The procedure is verified in simulation and for hippocampal recordings. It is found that in 95 % of hippocampal recordings a q of 60 yields numerical error negligible with respect to parameter estimate standard error. Statistical inference using the proposed methodology is a fast and convenient alternative to statistical inference performed using a discrete-time point process model of neural activity. It enables the employment of the statistical methodology available with discrete-time inference, but is faster, uses less memory, and avoids any error due to discretization.

A Feasibility Study of Synthesizing Subsurfaces Modeled with Computational Neural Networks

NASA Technical Reports Server (NTRS)

Wang, John T.; Housner, Jerrold M.; Szewczyk, Z. Peter

1998-01-01

This paper investigates the feasibility of synthesizing substructures modeled with computational neural networks. Substructures are modeled individually with computational neural networks and the response of the assembled structure is predicted by synthesizing the neural networks. A superposition approach is applied to synthesize models for statically determinate substructures while an interface displacement collocation approach is used to synthesize statically indeterminate substructure models. Beam and plate substructures along with components of a complicated Next Generation Space Telescope (NGST) model are used in this feasibility study. In this paper, the limitations and difficulties of synthesizing substructures modeled with neural networks are also discussed.

Neural-Network Simulator

NASA Technical Reports Server (NTRS)

Mitchell, Paul H.

1991-01-01

F77NNS (FORTRAN 77 Neural Network Simulator) computer program simulates popular back-error-propagation neural network. Designed to take advantage of vectorization when used on computers having this capability, also used on any computer equipped with ANSI-77 FORTRAN Compiler. Problems involving matching of patterns or mathematical modeling of systems fit class of problems F77NNS designed to solve. Program has restart capability so neural network solved in stages suitable to user's resources and desires. Enables user to customize patterns of connections between layers of network. Size of neural network F77NNS applied to limited only by amount of random-access memory available to user.

Obstacle Avoidance and Target Acquisition for Robot Navigation Using a Mixed Signal Analog/Digital Neuromorphic Processing System

PubMed Central

Milde, Moritz B.; Blum, Hermann; Dietmüller, Alexander; Sumislawska, Dora; Conradt, Jörg; Indiveri, Giacomo; Sandamirskaya, Yulia

2017-01-01

Neuromorphic hardware emulates dynamics of biological neural networks in electronic circuits offering an alternative to the von Neumann computing architecture that is low-power, inherently parallel, and event-driven. This hardware allows to implement neural-network based robotic controllers in an energy-efficient way with low latency, but requires solving the problem of device variability, characteristic for analog electronic circuits. In this work, we interfaced a mixed-signal analog-digital neuromorphic processor ROLLS to a neuromorphic dynamic vision sensor (DVS) mounted on a robotic vehicle and developed an autonomous neuromorphic agent that is able to perform neurally inspired obstacle-avoidance and target acquisition. We developed a neural network architecture that can cope with device variability and verified its robustness in different environmental situations, e.g., moving obstacles, moving target, clutter, and poor light conditions. We demonstrate how this network, combined with the properties of the DVS, allows the robot to avoid obstacles using a simple biologically-inspired dynamics. We also show how a Dynamic Neural Field for target acquisition can be implemented in spiking neuromorphic hardware. This work demonstrates an implementation of working obstacle avoidance and target acquisition using mixed signal analog/digital neuromorphic hardware. PMID:28747883

A limit-cycle self-organizing map architecture for stable arm control.

PubMed

Huang, Di-Wei; Gentili, Rodolphe J; Katz, Garrett E; Reggia, James A

2017-01-01

Inspired by the oscillatory nature of cerebral cortex activity, we recently proposed and studied self-organizing maps (SOMs) based on limit cycle neural activity in an attempt to improve the information efficiency and robustness of conventional single-node, single-pattern representations. Here we explore for the first time the use of limit cycle SOMs to build a neural architecture that controls a robotic arm by solving inverse kinematics in reach-and-hold tasks. This multi-map architecture integrates open-loop and closed-loop controls that learn to self-organize oscillatory neural representations and to harness non-fixed-point neural activity even for fixed-point arm reaching tasks. We show through computer simulations that our architecture generalizes well, achieves accurate, fast, and smooth arm movements, and is robust in the face of arm perturbations, map damage, and variations of internal timing parameters controlling the flow of activity. A robotic implementation is evaluated successfully without further training, demonstrating for the first time that limit cycle maps can control a physical robot arm. We conclude that architectures based on limit cycle maps can be organized to function effectively as neural controllers. Copyright © 2016 Elsevier Ltd. All rights reserved.

Obstacle Avoidance and Target Acquisition for Robot Navigation Using a Mixed Signal Analog/Digital Neuromorphic Processing System.

PubMed

Milde, Moritz B; Blum, Hermann; Dietmüller, Alexander; Sumislawska, Dora; Conradt, Jörg; Indiveri, Giacomo; Sandamirskaya, Yulia

2017-01-01

Neuromorphic hardware emulates dynamics of biological neural networks in electronic circuits offering an alternative to the von Neumann computing architecture that is low-power, inherently parallel, and event-driven. This hardware allows to implement neural-network based robotic controllers in an energy-efficient way with low latency, but requires solving the problem of device variability, characteristic for analog electronic circuits. In this work, we interfaced a mixed-signal analog-digital neuromorphic processor ROLLS to a neuromorphic dynamic vision sensor (DVS) mounted on a robotic vehicle and developed an autonomous neuromorphic agent that is able to perform neurally inspired obstacle-avoidance and target acquisition. We developed a neural network architecture that can cope with device variability and verified its robustness in different environmental situations, e.g., moving obstacles, moving target, clutter, and poor light conditions. We demonstrate how this network, combined with the properties of the DVS, allows the robot to avoid obstacles using a simple biologically-inspired dynamics. We also show how a Dynamic Neural Field for target acquisition can be implemented in spiking neuromorphic hardware. This work demonstrates an implementation of working obstacle avoidance and target acquisition using mixed signal analog/digital neuromorphic hardware.

An adaptable neural-network model for recursive nonlinear traffic prediction and modeling of MPEG video sources.

PubMed

Doulamis, A D; Doulamis, N D; Kollias, S D

2003-01-01

Multimedia services and especially digital video is expected to be the major traffic component transmitted over communication networks [such as internet protocol (IP)-based networks]. For this reason, traffic characterization and modeling of such services are required for an efficient network operation. The generated models can be used as traffic rate predictors, during the network operation phase (online traffic modeling), or as video generators for estimating the network resources, during the network design phase (offline traffic modeling). In this paper, an adaptable neural-network architecture is proposed covering both cases. The scheme is based on an efficient recursive weight estimation algorithm, which adapts the network response to current conditions. In particular, the algorithm updates the network weights so that 1) the network output, after the adaptation, is approximately equal to current bit rates (current traffic statistics) and 2) a minimal degradation over the obtained network knowledge is provided. It can be shown that the proposed adaptable neural-network architecture simulates a recursive nonlinear autoregressive model (RNAR) similar to the notation used in the linear case. The algorithm presents low computational complexity and high efficiency in tracking traffic rates in contrast to conventional retraining schemes. Furthermore, for the problem of offline traffic modeling, a novel correlation mechanism is proposed for capturing the burstness of the actual MPEG video traffic. The performance of the model is evaluated using several real-life MPEG coded video sources of long duration and compared with other linear/nonlinear techniques used for both cases. The results indicate that the proposed adaptable neural-network architecture presents better performance than other examined techniques.

Training-free compressed sensing for wireless neural recording using analysis model and group weighted {{\\ell}_{1}} -minimization

NASA Astrophysics Data System (ADS)

Sun, Biao; Zhao, Wenfeng; Zhu, Xinshan

2017-06-01

Objective. Data compression is crucial for resource-constrained wireless neural recording applications with limited data bandwidth, and compressed sensing (CS) theory has successfully demonstrated its potential in neural recording applications. In this paper, an analytical, training-free CS recovery method, termed group weighted analysis {{\\ell}1} -minimization (GWALM), is proposed for wireless neural recording. Approach. The GWALM method consists of three parts: (1) the analysis model is adopted to enforce sparsity of the neural signals, therefore overcoming the drawbacks of conventional synthesis models and enhancing the recovery performance. (2) A multi-fractional-order difference matrix is constructed as the analysis operator, thus avoiding the dictionary learning procedure and reducing the need for previously acquired data and computational complexities. (3) By exploiting the statistical properties of the analysis coefficients, a group weighting approach is developed to enhance the performance of analysis {{\\ell}1} -minimization. Main results. Experimental results on synthetic and real datasets reveal that the proposed approach outperforms state-of-the-art CS-based methods in terms of both spike recovery quality and classification accuracy. Significance. Energy and area efficiency of the GWALM make it an ideal candidate for resource-constrained, large scale wireless neural recording applications. The training-free feature of the GWALM further improves its robustness to spike shape variation, thus making it more practical for long term wireless neural recording.

Training-free compressed sensing for wireless neural recording using analysis model and group weighted [Formula: see text]-minimization.

PubMed

Sun, Biao; Zhao, Wenfeng; Zhu, Xinshan

2017-06-01

Data compression is crucial for resource-constrained wireless neural recording applications with limited data bandwidth, and compressed sensing (CS) theory has successfully demonstrated its potential in neural recording applications. In this paper, an analytical, training-free CS recovery method, termed group weighted analysis [Formula: see text]-minimization (GWALM), is proposed for wireless neural recording. The GWALM method consists of three parts: (1) the analysis model is adopted to enforce sparsity of the neural signals, therefore overcoming the drawbacks of conventional synthesis models and enhancing the recovery performance. (2) A multi-fractional-order difference matrix is constructed as the analysis operator, thus avoiding the dictionary learning procedure and reducing the need for previously acquired data and computational complexities. (3) By exploiting the statistical properties of the analysis coefficients, a group weighting approach is developed to enhance the performance of analysis [Formula: see text]-minimization. Experimental results on synthetic and real datasets reveal that the proposed approach outperforms state-of-the-art CS-based methods in terms of both spike recovery quality and classification accuracy. Energy and area efficiency of the GWALM make it an ideal candidate for resource-constrained, large scale wireless neural recording applications. The training-free feature of the GWALM further improves its robustness to spike shape variation, thus making it more practical for long term wireless neural recording.

A Novel Stimulus Artifact Removal Technique for High-Rate Electrical Stimulation

PubMed Central

Heffer, Leon F; Fallon, James B

2008-01-01

Electrical stimulus artifact corrupting electrophysiological recordings often make the subsequent analysis of the underlying neural response difficult. This is particularly evident when investigating short-latency neural activity in response to high-rate electrical stimulation. We developed and evaluated an off-line technique for the removal of stimulus artifact from electrophysiological recordings. Pulsatile electrical stimulation was presented at rates of up to 5000 pulses/s during extracellular recordings of guinea pig auditory nerve fibers. Stimulus artifact was removed by replacing the sample points at each stimulus artifact event with values interpolated along a straight line, computed from neighbouring sample points. This technique required only that artifact events be identifiable and that the artifact duration remained less than both the inter-stimulus interval and the time course of the action potential. We have demonstrated that this computationally efficient sample-and-interpolate technique removes the stimulus artifact with minimal distortion of the action potential waveform. We suggest that this technique may have potential applications in a range of electrophysiological recording systems. PMID:18339428

Nonlinear channel equalization for QAM signal constellation using artificial neural networks.

PubMed

Patra, J C; Pal, R N; Baliarsingh, R; Panda, G

1999-01-01

Application of artificial neural networks (ANN's) to adaptive channel equalization in a digital communication system with 4-QAM signal constellation is reported in this paper. A novel computationally efficient single layer functional link ANN (FLANN) is proposed for this purpose. This network has a simple structure in which the nonlinearity is introduced by functional expansion of the input pattern by trigonometric polynomials. Because of input pattern enhancement, the FLANN is capable of forming arbitrarily nonlinear decision boundaries and can perform complex pattern classification tasks. Considering channel equalization as a nonlinear classification problem, the FLANN has been utilized for nonlinear channel equalization. The performance of the FLANN is compared with two other ANN structures [a multilayer perceptron (MLP) and a polynomial perceptron network (PPN)] along with a conventional linear LMS-based equalizer for different linear and nonlinear channel models. The effect of eigenvalue ratio (EVR) of input correlation matrix on the equalizer performance has been studied. The comparison of computational complexity involved for the three ANN structures is also provided.

Muon Trigger for Mobile Phones

NASA Astrophysics Data System (ADS)

Borisyak, M.; Usvyatsov, M.; Mulhearn, M.; Shimmin, C.; Ustyuzhanin, A.

2017-10-01

The CRAYFIS experiment proposes to use privately owned mobile phones as a ground detector array for Ultra High Energy Cosmic Rays. Upon interacting with Earth’s atmosphere, these events produce extensive particle showers which can be detected by cameras on mobile phones. A typical shower contains minimally-ionizing particles such as muons. As these particles interact with CMOS image sensors, they may leave tracks of faintly-activated pixels that are sometimes hard to distinguish from random detector noise. Triggers that rely on the presence of very bright pixels within an image frame are not efficient in this case. We present a trigger algorithm based on Convolutional Neural Networks which selects images containing such tracks and are evaluated in a lazy manner: the response of each successive layer is computed only if activation of the current layer satisfies a continuation criterion. Usage of neural networks increases the sensitivity considerably comparable with image thresholding, while the lazy evaluation allows for execution of the trigger under the limited computational power of mobile phones.

Neural network feedforward control of a closed-circuit wind tunnel

NASA Astrophysics Data System (ADS)

Sutcliffe, Peter

Accurate control of wind-tunnel test conditions can be dramatically enhanced using feedforward control architectures which allow operating conditions to be maintained at a desired setpoint through the use of mathematical models as the primary source of prediction. However, as the desired accuracy of the feedforward prediction increases, the model complexity also increases, so that an ever increasing computational load is incurred. This drawback can be avoided by employing a neural network that is trained offline using the output of a high fidelity wind-tunnel mathematical model, so that the neural network can rapidly reproduce the predictions of the model with a greatly reduced computational overhead. A novel neural network database generation method, developed through the use of fractional factorial arrays, was employed such that a neural network can accurately predict wind-tunnel parameters across a wide range of operating conditions whilst trained upon a highly efficient database. The subsequent network was incorporated into a Neural Network Model Predictive Control (NNMPC) framework to allow an optimised output schedule capable of providing accurate control of the wind-tunnel operating parameters. Facilitation of an optimised path through the solution space is achieved through the use of a chaos optimisation algorithm such that a more globally optimum solution is likely to be found with less computational expense than the gradient descent method. The parameters associated with the NNMPC such as the control horizon are determined through the use of a Taguchi methodology enabling the minimum number of experiments to be carried out to determine the optimal combination. The resultant NNMPC scheme was employed upon the Hessert Low Speed Wind Tunnel at the University of Notre Dame to control the test-section temperature such that it follows a pre-determined reference trajectory during changes in the test-section velocity. Experimental testing revealed that the derived NNMPC controller provided an excellent level of control over the test-section temperature in adherence to a reference trajectory even when faced with unforeseen disturbances such as rapid changes in the operating environment.

Integration of nanoscale memristor synapses in neuromorphic computing architectures

NASA Astrophysics Data System (ADS)

Indiveri, Giacomo; Linares-Barranco, Bernabé; Legenstein, Robert; Deligeorgis, George; Prodromakis, Themistoklis

2013-09-01

Conventional neuro-computing architectures and artificial neural networks have often been developed with no or loose connections to neuroscience. As a consequence, they have largely ignored key features of biological neural processing systems, such as their extremely low-power consumption features or their ability to carry out robust and efficient computation using massively parallel arrays of limited precision, highly variable, and unreliable components. Recent developments in nano-technologies are making available extremely compact and low power, but also variable and unreliable solid-state devices that can potentially extend the offerings of availing CMOS technologies. In particular, memristors are regarded as a promising solution for modeling key features of biological synapses due to their nanoscale dimensions, their capacity to store multiple bits of information per element and the low energy required to write distinct states. In this paper, we first review the neuro- and neuromorphic computing approaches that can best exploit the properties of memristor and scale devices, and then propose a novel hybrid memristor-CMOS neuromorphic circuit which represents a radical departure from conventional neuro-computing approaches, as it uses memristors to directly emulate the biophysics and temporal dynamics of real synapses. We point out the differences between the use of memristors in conventional neuro-computing architectures and the hybrid memristor-CMOS circuit proposed, and argue how this circuit represents an ideal building block for implementing brain-inspired probabilistic computing paradigms that are robust to variability and fault tolerant by design.

Hybrid soft computing systems for electromyographic signals analysis: a review.

PubMed

Xie, Hong-Bo; Guo, Tianruo; Bai, Siwei; Dokos, Socrates

2014-02-03

Electromyographic (EMG) is a bio-signal collected on human skeletal muscle. Analysis of EMG signals has been widely used to detect human movement intent, control various human-machine interfaces, diagnose neuromuscular diseases, and model neuromusculoskeletal system. With the advances of artificial intelligence and soft computing, many sophisticated techniques have been proposed for such purpose. Hybrid soft computing system (HSCS), the integration of these different techniques, aims to further improve the effectiveness, efficiency, and accuracy of EMG analysis. This paper reviews and compares key combinations of neural network, support vector machine, fuzzy logic, evolutionary computing, and swarm intelligence for EMG analysis. Our suggestions on the possible future development of HSCS in EMG analysis are also given in terms of basic soft computing techniques, further combination of these techniques, and their other applications in EMG analysis.

Hybrid soft computing systems for electromyographic signals analysis: a review

PubMed Central

2014-01-01

Electromyographic (EMG) is a bio-signal collected on human skeletal muscle. Analysis of EMG signals has been widely used to detect human movement intent, control various human-machine interfaces, diagnose neuromuscular diseases, and model neuromusculoskeletal system. With the advances of artificial intelligence and soft computing, many sophisticated techniques have been proposed for such purpose. Hybrid soft computing system (HSCS), the integration of these different techniques, aims to further improve the effectiveness, efficiency, and accuracy of EMG analysis. This paper reviews and compares key combinations of neural network, support vector machine, fuzzy logic, evolutionary computing, and swarm intelligence for EMG analysis. Our suggestions on the possible future development of HSCS in EMG analysis are also given in terms of basic soft computing techniques, further combination of these techniques, and their other applications in EMG analysis. PMID:24490979

Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study

NASA Astrophysics Data System (ADS)

Sheikhan, Mansour; Abbasnezhad Arabi, Mahdi; Gharavian, Davood

2015-10-01

Artificial neural networks are efficient models in pattern recognition applications, but their performance is dependent on employing suitable structure and connection weights. This study used a hybrid method for obtaining the optimal weight set and architecture of a recurrent neural emotion classifier based on gravitational search algorithm (GSA) and its binary version (BGSA), respectively. By considering the features of speech signal that were related to prosody, voice quality, and spectrum, a rich feature set was constructed. To select more efficient features, a fast feature selection method was employed. The performance of the proposed hybrid GSA-BGSA method was compared with similar hybrid methods based on particle swarm optimisation (PSO) algorithm and its binary version, PSO and discrete firefly algorithm, and hybrid of error back-propagation and genetic algorithm that were used for optimisation. Experimental tests on Berlin emotional database demonstrated the superior performance of the proposed method using a lighter network structure.

Neuronal couplings between retinal ganglion cells inferred by efficient inverse statistical physics methods

PubMed Central

Cocco, Simona; Leibler, Stanislas; Monasson, Rémi

2009-01-01

Complexity of neural systems often makes impracticable explicit measurements of all interactions between their constituents. Inverse statistical physics approaches, which infer effective couplings between neurons from their spiking activity, have been so far hindered by their computational complexity. Here, we present 2 complementary, computationally efficient inverse algorithms based on the Ising and “leaky integrate-and-fire” models. We apply those algorithms to reanalyze multielectrode recordings in the salamander retina in darkness and under random visual stimulus. We find strong positive couplings between nearby ganglion cells common to both stimuli, whereas long-range couplings appear under random stimulus only. The uncertainty on the inferred couplings due to limitations in the recordings (duration, small area covered on the retina) is discussed. Our methods will allow real-time evaluation of couplings for large assemblies of neurons. PMID:19666487

Deep learning for computational chemistry

DOE Office of Scientific and Technical Information (OSTI.GOV)

Goh, Garrett B.; Hodas, Nathan O.; Vishnu, Abhinav

The rise and fall of artificial neural networks is well documented in the scientific literature of both the fields of computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on “deep” neural networks. Within the last few years, we have seen the transformative impact of deep learning the computer science domain, notably in speech recognition and computer vision, to the extent that the majority of practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. Inmore » this review, we provide an introductory overview into the theory of deep neural networks and their unique properties as compared to traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including QSAR, virtual screening, protein structure modeling, QM calculations, materials synthesis and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non neural networks state-of-the-art models across disparate research topics, and deep neural network based models often exceeded the “glass ceiling” expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a useful tool and may grow into a pivotal role for various challenges in the computational chemistry field.« less

The dynamical analysis of modified two-compartment neuron model and FPGA implementation

NASA Astrophysics Data System (ADS)

Lin, Qianjin; Wang, Jiang; Yang, Shuangming; Yi, Guosheng; Deng, Bin; Wei, Xile; Yu, Haitao

2017-10-01

The complexity of neural models is increasing with the investigation of larger biological neural network, more various ionic channels and more detailed morphologies, and the implementation of biological neural network is a task with huge computational complexity and power consumption. This paper presents an efficient digital design using piecewise linearization on field programmable gate array (FPGA), to succinctly implement the reduced two-compartment model which retains essential features of more complicated models. The design proposes an approximate neuron model which is composed of a set of piecewise linear equations, and it can reproduce different dynamical behaviors to depict the mechanisms of a single neuron model. The consistency of hardware implementation is verified in terms of dynamical behaviors and bifurcation analysis, and the simulation results including varied ion channel characteristics coincide with the biological neuron model with a high accuracy. Hardware synthesis on FPGA demonstrates that the proposed model has reliable performance and lower hardware resource compared with the original two-compartment model. These investigations are conducive to scalability of biological neural network in reconfigurable large-scale neuromorphic system.

Instrumentation for Scientific Computing in Neural Networks, Information Science, Artificial Intelligence, and Applied Mathematics.

DTIC Science & Technology

1987-10-01

include Security Classification) Instrumentation for scientific computing in neural networks, information science, artificial intelligence, and...instrumentation grant to purchase equipment for support of research in neural networks, information science, artificail intellignece , and applied mathematics...in Neural Networks, Information Science, Artificial Intelligence, and Applied Mathematics Contract AFOSR 86-0282 Principal Investigator: Stephen

Tools for Atmospheric Radiative Transfer: Streamer and FluxNet. Revised

NASA Technical Reports Server (NTRS)

Key, Jeffrey R.; Schweiger, Axel J.

1998-01-01

Two tools for the solution of radiative transfer problems are presented. Streamer is a highly flexible medium spectral resolution radiative transfer model based on the plane-parallel theory of radiative transfer. Capable of computing either fluxes or radiances, it is suitable for studying radiative processes at the surface or within the atmosphere and for the development of remote-sensing algorithms. FluxNet is a fast neural network-based implementation of Streamer for computing surface fluxes. It allows for a sophisticated treatment of radiative processes in the analysis of large data sets and potential integration into geophysical models where computational efficiency is an issue. Documentation and tools for the development of alternative versions of Fluxnet are available. Collectively, Streamer and FluxNet solve a wide variety of problems related to radiative transfer: Streamer provides the detail and sophistication needed to perform basic research on most aspects of complex radiative processes while the efficiency and simplicity of FluxNet make it ideal for operational use.

NEURAL NETWORK MODELLING OF CARDIAC DOSE CONVERSION COEFFICIENT FOR ARBITRARY X-RAY SPECTRA.

PubMed

Kadri, O; Manai, K

2016-12-01

In this article, an approach to compute the dose conversion coefficients (DCCs) is described for the computational voxel phantom 'High-Definition Reference Korean-Man' (HDRK-Man) using artificial neural networks (ANN). For this purpose, the voxel phantom was implemented into the Monte Carlo (MC) transport toolkit GEANT4, and the DCCs for more than 30 tissues and organs, due to a broad parallel beam of monoenergetic photons with energy ranging from 15 to 150 keV by a step of 5 keV, were calculated. To study the influence of patient size on DCC values, DCC calculation was performed, for a representative body size population, using five different sizes covering the range of 80-120 % magnification of the original HDRK-Man. The focus of the present study was on the computation of DCC for the human heart. ANN calculation and MC simulation results were compared, and good agreement was observed showing that ANNs can be used as an efficient tool for modelling DCCs for the computational voxel phantom. ANN approach appears to be a significant advance over the time-consuming MC methods for DCC calculation. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Understanding the Convolutional Neural Networks with Gradient Descent and Backpropagation

NASA Astrophysics Data System (ADS)

Zhou, XueFei

2018-04-01

With the development of computer technology, the applications of machine learning are more and more extensive. And machine learning is providing endless opportunities to develop new applications. One of those applications is image recognition by using Convolutional Neural Networks (CNNs). CNN is one of the most common algorithms in image recognition. It is significant to understand its theory and structure for every scholar who is interested in this field. CNN is mainly used in computer identification, especially in voice, text recognition and other aspects of the application. It utilizes hierarchical structure with different layers to accelerate computing speed. In addition, the greatest features of CNNs are the weight sharing and dimension reduction. And all of these consolidate the high effectiveness and efficiency of CNNs with idea computing speed and error rate. With the help of other learning altruisms, CNNs could be used in several scenarios for machine learning, especially for deep learning. Based on the general introduction to the background and the core solution CNN, this paper is going to focus on summarizing how Gradient Descent and Backpropagation work, and how they contribute to the high performances of CNNs. Also, some practical applications will be discussed in the following parts. The last section exhibits the conclusion and some perspectives of future work.

Real-time encoding and compression of neuronal spikes by metal-oxide memristors

NASA Astrophysics Data System (ADS)

Gupta, Isha; Serb, Alexantrou; Khiat, Ali; Zeitler, Ralf; Vassanelli, Stefano; Prodromakis, Themistoklis

2016-09-01

Advanced brain-chip interfaces with numerous recording sites bear great potential for investigation of neuroprosthetic applications. The bottleneck towards achieving an efficient bio-electronic link is the real-time processing of neuronal signals, which imposes excessive requirements on bandwidth, energy and computation capacity. Here we present a unique concept where the intrinsic properties of memristive devices are exploited to compress information on neural spikes in real-time. We demonstrate that the inherent voltage thresholds of metal-oxide memristors can be used for discriminating recorded spiking events from background activity and without resorting to computationally heavy off-line processing. We prove that information on spike amplitude and frequency can be transduced and stored in single devices as non-volatile resistive state transitions. Finally, we show that a memristive device array allows for efficient data compression of signals recorded by a multi-electrode array, demonstrating the technology's potential for building scalable, yet energy-efficient on-node processors for brain-chip interfaces.

Real-time encoding and compression of neuronal spikes by metal-oxide memristors

PubMed Central

Gupta, Isha; Serb, Alexantrou; Khiat, Ali; Zeitler, Ralf; Vassanelli, Stefano; Prodromakis, Themistoklis

2016-01-01

Advanced brain-chip interfaces with numerous recording sites bear great potential for investigation of neuroprosthetic applications. The bottleneck towards achieving an efficient bio-electronic link is the real-time processing of neuronal signals, which imposes excessive requirements on bandwidth, energy and computation capacity. Here we present a unique concept where the intrinsic properties of memristive devices are exploited to compress information on neural spikes in real-time. We demonstrate that the inherent voltage thresholds of metal-oxide memristors can be used for discriminating recorded spiking events from background activity and without resorting to computationally heavy off-line processing. We prove that information on spike amplitude and frequency can be transduced and stored in single devices as non-volatile resistive state transitions. Finally, we show that a memristive device array allows for efficient data compression of signals recorded by a multi-electrode array, demonstrating the technology's potential for building scalable, yet energy-efficient on-node processors for brain-chip interfaces. PMID:27666698

Modeling of frost crystal growth over a flat plate using artificial neural networks and fractal geometries

NASA Astrophysics Data System (ADS)

Tahavvor, Ali Reza

2017-03-01

In the present study artificial neural network and fractal geometry are used to predict frost thickness and density on a cold flat plate having constant surface temperature under forced convection for different ambient conditions. These methods are very applicable in this area because phase changes such as melting and solidification are simulated by conventional methods but frost formation is a most complicated phase change phenomenon consists of coupled heat and mass transfer. Therefore conventional mathematical techniques cannot capture the effects of all parameters on its growth and development because this process influenced by many factors and it is a time dependent process. Therefore, in this work soft computing method such as artificial neural network and fractal geometry are used to do this manner. The databases for modeling are generated from the experimental measurements. First, multilayer perceptron network is used and it is found that the back-propagation algorithm with Levenberg-Marquardt learning rule is the best choice to estimate frost growth properties due to accurate and faster training procedure. Second, fractal geometry based on the Von-Koch curve is used to model frost growth procedure especially in frost thickness and density. Comparison is performed between experimental measurements and soft computing methods. Results show that soft computing methods can be used more efficiently to determine frost properties over a flat plate. Based on the developed models, wide range of frost formation over flat plates can be determined for various conditions.

Computational modeling of an endovascular approach to deep brain stimulation

NASA Astrophysics Data System (ADS)

Teplitzky, Benjamin A.; Connolly, Allison T.; Bajwa, Jawad A.; Johnson, Matthew D.

2014-04-01

Objective. Deep brain stimulation (DBS) therapy currently relies on a transcranial neurosurgical technique to implant one or more electrode leads into the brain parenchyma. In this study, we used computational modeling to investigate the feasibility of using an endovascular approach to target DBS therapy. Approach. Image-based anatomical reconstructions of the human brain and vasculature were used to identify 17 established and hypothesized anatomical targets of DBS, of which five were found adjacent to a vein or artery with intraluminal diameter ≥1 mm. Two of these targets, the fornix and subgenual cingulate white matter (SgCwm) tracts, were further investigated using a computational modeling framework that combined segmented volumes of the vascularized brain, finite element models of the tissue voltage during DBS, and multi-compartment axon models to predict the direct electrophysiological effects of endovascular DBS. Main results. The models showed that: (1) a ring-electrode conforming to the vessel wall was more efficient at neural activation than a guidewire design, (2) increasing the length of a ring-electrode had minimal effect on neural activation thresholds, (3) large variability in neural activation occurred with suboptimal placement of a ring-electrode along the targeted vessel, and (4) activation thresholds for the fornix and SgCwm tracts were comparable for endovascular and stereotactic DBS, though endovascular DBS was able to produce significantly larger contralateral activation for a unilateral implantation. Significance. Together, these results suggest that endovascular DBS can serve as a complementary approach to stereotactic DBS in select cases.

Surfing a spike wave down the ventral stream.

PubMed

VanRullen, Rufin; Thorpe, Simon J

2002-10-01

Numerous theories of neural processing, often motivated by experimental observations, have explored the computational properties of neural codes based on the absolute or relative timing of spikes in spike trains. Spiking neuron models and theories however, as well as their experimental counterparts, have generally been limited to the simulation or observation of isolated neurons, isolated spike trains, or reduced neural populations. Such theories would therefore seem inappropriate to capture the properties of a neural code relying on temporal spike patterns distributed across large neuronal populations. Here we report a range of computer simulations and theoretical considerations that were designed to explore the possibilities of one such code and its relevance for visual processing. In a unified framework where the relation between stimulus saliency and spike relative timing plays the central role, we describe how the ventral stream of the visual system could process natural input scenes and extract meaningful information, both rapidly and reliably. The first wave of spikes generated in the retina in response to a visual stimulation carries information explicitly in its spatio-temporal structure: the most salient information is represented by the first spikes over the population. This spike wave, propagating through a hierarchy of visual areas, is regenerated at each processing stage, where its temporal structure can be modified by (i). the selectivity of the cortical neurons, (ii). lateral interactions and (iii). top-down attentional influences from higher order cortical areas. The resulting model could account for the remarkable efficiency and rapidity of processing observed in the primate visual system.

FPGA implementation of a biological neural network based on the Hodgkin-Huxley neuron model

PubMed Central

Yaghini Bonabi, Safa; Asgharian, Hassan; Safari, Saeed; Nili Ahmadabadi, Majid

2014-01-01

A set of techniques for efficient implementation of Hodgkin-Huxley-based (H-H) model of a neural network on FPGA (Field Programmable Gate Array) is presented. The central implementation challenge is H-H model complexity that puts limits on the network size and on the execution speed. However, basics of the original model cannot be compromised when effect of synaptic specifications on the network behavior is the subject of study. To solve the problem, we used computational techniques such as CORDIC (Coordinate Rotation Digital Computer) algorithm and step-by-step integration in the implementation of arithmetic circuits. In addition, we employed different techniques such as sharing resources to preserve the details of model as well as increasing the network size in addition to keeping the network execution speed close to real time while having high precision. Implementation of a two mini-columns network with 120/30 excitatory/inhibitory neurons is provided to investigate the characteristic of our method in practice. The implementation techniques provide an opportunity to construct large FPGA-based network models to investigate the effect of different neurophysiological mechanisms, like voltage-gated channels and synaptic activities, on the behavior of a neural network in an appropriate execution time. Additional to inherent properties of FPGA, like parallelism and re-configurability, our approach makes the FPGA-based system a proper candidate for study on neural control of cognitive robots and systems as well. PMID:25484854

Analysis of Power Laws, Shape Collapses, and Neural Complexity: New Techniques and MATLAB Support via the NCC Toolbox

PubMed Central

Marshall, Najja; Timme, Nicholas M.; Bennett, Nicholas; Ripp, Monica; Lautzenhiser, Edward; Beggs, John M.

2016-01-01

Neural systems include interactions that occur across many scales. Two divergent methods for characterizing such interactions have drawn on the physical analysis of critical phenomena and the mathematical study of information. Inferring criticality in neural systems has traditionally rested on fitting power laws to the property distributions of “neural avalanches” (contiguous bursts of activity), but the fractal nature of avalanche shapes has recently emerged as another signature of criticality. On the other hand, neural complexity, an information theoretic measure, has been used to capture the interplay between the functional localization of brain regions and their integration for higher cognitive functions. Unfortunately, treatments of all three methods—power-law fitting, avalanche shape collapse, and neural complexity—have suffered from shortcomings. Empirical data often contain biases that introduce deviations from true power law in the tail and head of the distribution, but deviations in the tail have often been unconsidered; avalanche shape collapse has required manual parameter tuning; and the estimation of neural complexity has relied on small data sets or statistical assumptions for the sake of computational efficiency. In this paper we present technical advancements in the analysis of criticality and complexity in neural systems. We use maximum-likelihood estimation to automatically fit power laws with left and right cutoffs, present the first automated shape collapse algorithm, and describe new techniques to account for large numbers of neural variables and small data sets in the calculation of neural complexity. In order to facilitate future research in criticality and complexity, we have made the software utilized in this analysis freely available online in the MATLAB NCC (Neural Complexity and Criticality) Toolbox. PMID:27445842

Analysis of Power Laws, Shape Collapses, and Neural Complexity: New Techniques and MATLAB Support via the NCC Toolbox.

PubMed

Marshall, Najja; Timme, Nicholas M; Bennett, Nicholas; Ripp, Monica; Lautzenhiser, Edward; Beggs, John M

2016-01-01

Neural systems include interactions that occur across many scales. Two divergent methods for characterizing such interactions have drawn on the physical analysis of critical phenomena and the mathematical study of information. Inferring criticality in neural systems has traditionally rested on fitting power laws to the property distributions of "neural avalanches" (contiguous bursts of activity), but the fractal nature of avalanche shapes has recently emerged as another signature of criticality. On the other hand, neural complexity, an information theoretic measure, has been used to capture the interplay between the functional localization of brain regions and their integration for higher cognitive functions. Unfortunately, treatments of all three methods-power-law fitting, avalanche shape collapse, and neural complexity-have suffered from shortcomings. Empirical data often contain biases that introduce deviations from true power law in the tail and head of the distribution, but deviations in the tail have often been unconsidered; avalanche shape collapse has required manual parameter tuning; and the estimation of neural complexity has relied on small data sets or statistical assumptions for the sake of computational efficiency. In this paper we present technical advancements in the analysis of criticality and complexity in neural systems. We use maximum-likelihood estimation to automatically fit power laws with left and right cutoffs, present the first automated shape collapse algorithm, and describe new techniques to account for large numbers of neural variables and small data sets in the calculation of neural complexity. In order to facilitate future research in criticality and complexity, we have made the software utilized in this analysis freely available online in the MATLAB NCC (Neural Complexity and Criticality) Toolbox.

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines

PubMed Central

Neftci, Emre O.; Augustine, Charles; Paul, Somnath; Detorakis, Georgios

2017-01-01

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning. PMID:28680387

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines.

PubMed

Neftci, Emre O; Augustine, Charles; Paul, Somnath; Detorakis, Georgios

2017-01-01

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning.

A FPGA-Based, Granularity-Variable Neuromorphic Processor and Its Application in a MIMO Real-Time Control System.

PubMed

Zhang, Zhen; Ma, Cheng; Zhu, Rong

2017-08-23

Artificial Neural Networks (ANNs), including Deep Neural Networks (DNNs), have become the state-of-the-art methods in machine learning and achieved amazing success in speech recognition, visual object recognition, and many other domains. There are several hardware platforms for developing accelerated implementation of ANN models. Since Field Programmable Gate Array (FPGA) architectures are flexible and can provide high performance per watt of power consumption, they have drawn a number of applications from scientists. In this paper, we propose a FPGA-based, granularity-variable neuromorphic processor (FBGVNP). The traits of FBGVNP can be summarized as granularity variability, scalability, integrated computing, and addressing ability: first, the number of neurons is variable rather than constant in one core; second, the multi-core network scale can be extended in various forms; third, the neuron addressing and computing processes are executed simultaneously. These make the processor more flexible and better suited for different applications. Moreover, a neural network-based controller is mapped to FBGVNP and applied in a multi-input, multi-output, (MIMO) real-time, temperature-sensing and control system. Experiments validate the effectiveness of the neuromorphic processor. The FBGVNP provides a new scheme for building ANNs, which is flexible, highly energy-efficient, and can be applied in many areas.

A FPGA-Based, Granularity-Variable Neuromorphic Processor and Its Application in a MIMO Real-Time Control System

PubMed Central

Zhang, Zhen; Zhu, Rong

2017-01-01

Artificial Neural Networks (ANNs), including Deep Neural Networks (DNNs), have become the state-of-the-art methods in machine learning and achieved amazing success in speech recognition, visual object recognition, and many other domains. There are several hardware platforms for developing accelerated implementation of ANN models. Since Field Programmable Gate Array (FPGA) architectures are flexible and can provide high performance per watt of power consumption, they have drawn a number of applications from scientists. In this paper, we propose a FPGA-based, granularity-variable neuromorphic processor (FBGVNP). The traits of FBGVNP can be summarized as granularity variability, scalability, integrated computing, and addressing ability: first, the number of neurons is variable rather than constant in one core; second, the multi-core network scale can be extended in various forms; third, the neuron addressing and computing processes are executed simultaneously. These make the processor more flexible and better suited for different applications. Moreover, a neural network-based controller is mapped to FBGVNP and applied in a multi-input, multi-output, (MIMO) real-time, temperature-sensing and control system. Experiments validate the effectiveness of the neuromorphic processor. The FBGVNP provides a new scheme for building ANNs, which is flexible, highly energy-efficient, and can be applied in many areas. PMID:28832522

Your eyes give you away: pupillary responses, EEG dynamics, and applications for BCI (Conference Presentation)

NASA Astrophysics Data System (ADS)

Sajda, Paul

2017-05-01

As we move through an environment, we are constantly making assessments, judgments, and decisions about the things we encounter. Some are acted upon immediately, but many more become mental notes or fleeting impressions - our implicit "labeling" of the world. In this talk I will describe our work using physiological correlates of this labeling to construct a hybrid brain-computer interface (hBCI) system for efficient navigation of a 3-D environment. Specifically, we record electroencephalographic (EEG), saccadic, and pupillary data from subjects as they move through a small part of a 3-D virtual city under free-viewing conditions. Using machine learning, we integrate the neural and ocular signals evoked by the objects they encounter to infer which ones are of subjective interest. These inferred labels are propagated through a large computer vision graph of objects in the city, using semi-supervised learning to identify other, unseen objects that are visually similar to those that are labelled. Finally, the system plots an efficient route so that subjects visit similar objects of interest. We show that by exploiting the subjects' implicit labeling, the median search precision is increased from 25% to 97%, and the median subject need only travel 40% of the distance to see 84% of the objects of interest. We also find that the neural and ocular signals contribute in a complementary fashion to the classifiers' inference of subjects' implicit labeling. In summary, we show that neural and ocular signals reflecting subjective assessment of objects in a 3-D environment can be used to inform a graph-based learning model of that environment, resulting in an hBCI system that improves navigation and information delivery specific to the user's interests.

Limits to high-speed simulations of spiking neural networks using general-purpose computers.

PubMed

Zenke, Friedemann; Gerstner, Wulfram

2014-01-01

To understand how the central nervous system performs computations using recurrent neuronal circuitry, simulations have become an indispensable tool for theoretical neuroscience. To study neuronal circuits and their ability to self-organize, increasing attention has been directed toward synaptic plasticity. In particular spike-timing-dependent plasticity (STDP) creates specific demands for simulations of spiking neural networks. On the one hand a high temporal resolution is required to capture the millisecond timescale of typical STDP windows. On the other hand network simulations have to evolve over hours up to days, to capture the timescale of long-term plasticity. To do this efficiently, fast simulation speed is the crucial ingredient rather than large neuron numbers. Using different medium-sized network models consisting of several thousands of neurons and off-the-shelf hardware, we compare the simulation speed of the simulators: Brian, NEST and Neuron as well as our own simulator Auryn. Our results show that real-time simulations of different plastic network models are possible in parallel simulations in which numerical precision is not a primary concern. Even so, the speed-up margin of parallelism is limited and boosting simulation speeds beyond one tenth of real-time is difficult. By profiling simulation code we show that the run times of typical plastic network simulations encounter a hard boundary. This limit is partly due to latencies in the inter-process communications and thus cannot be overcome by increased parallelism. Overall, these results show that to study plasticity in medium-sized spiking neural networks, adequate simulation tools are readily available which run efficiently on small clusters. However, to run simulations substantially faster than real-time, special hardware is a prerequisite.

The application of improved NeuroEvolution of Augmenting Topologies neural network in Marcellus Shale lithofacies prediction

NASA Astrophysics Data System (ADS)

Wang, Guochang; Cheng, Guojian; Carr, Timothy R.

2013-04-01

The organic-rich Marcellus Shale was deposited in a foreland basin during Middle Devonian. In terms of mineral composition and organic matter richness, we define seven mudrock lithofacies: three organic-rich lithofacies and four organic-poor lithofacies. The 3D lithofacies model is very helpful to determine geologic and engineering sweet spots, and consequently useful for designing horizontal well trajectories and stimulation strategies. The NeuroEvolution of Augmenting Topologies (NEAT) is relatively new idea in the design of neural networks, and shed light on classification (i.e., Marcellus Shale lithofacies prediction). We have successfully enhanced the capability and efficiency of NEAT in three aspects. First, we introduced two new attributes of node gene, the node location and recurrent connection (RCC), to increase the calculation efficiency. Second, we evolved the population size from an initial small value to big, instead of using the constant value, which saves time and computer memory, especially for complex learning tasks. Third, in multiclass pattern recognition problems, we combined feature selection of input variables and modular neural network to automatically select input variables and optimize network topology for each binary classifier. These improvements were tested and verified by true if an odd number of its arguments are true and false otherwise (XOR) experiments, and were powerful for classification.

Bio-inspired spiking neural network for nonlinear systems control.

PubMed

Pérez, Javier; Cabrera, Juan A; Castillo, Juan J; Velasco, Juan M

2018-08-01

Spiking neural networks (SNN) are the third generation of artificial neural networks. SNN are the closest approximation to biological neural networks. SNNs make use of temporal spike trains to command inputs and outputs, allowing a faster and more complex computation. As demonstrated by biological organisms, they are a potentially good approach to designing controllers for highly nonlinear dynamic systems in which the performance of controllers developed by conventional techniques is not satisfactory or difficult to implement. SNN-based controllers exploit their ability for online learning and self-adaptation to evolve when transferred from simulations to the real world. SNN's inherent binary and temporary way of information codification facilitates their hardware implementation compared to analog neurons. Biological neural networks often require a lower number of neurons compared to other controllers based on artificial neural networks. In this work, these neuronal systems are imitated to perform the control of non-linear dynamic systems. For this purpose, a control structure based on spiking neural networks has been designed. Particular attention has been paid to optimizing the structure and size of the neural network. The proposed structure is able to control dynamic systems with a reduced number of neurons and connections. A supervised learning process using evolutionary algorithms has been carried out to perform controller training. The efficiency of the proposed network has been verified in two examples of dynamic systems control. Simulations show that the proposed control based on SNN exhibits superior performance compared to other approaches based on Neural Networks and SNNs. Copyright © 2018 Elsevier Ltd. All rights reserved.

Research in Computational Astrobiology

NASA Technical Reports Server (NTRS)

Chaban, Galina; Jaffe, Richard; Liang, Shoudan; New, Michael H.; Pohorille, Andrew; Wilson, Michael A.

2002-01-01

We present results from several projects in the new field of computational astrobiology, which is devoted to advancing our understanding of the origin, evolution and distribution of life in the Universe using theoretical and computational tools. We have developed a procedure for calculating long-range effects in molecular dynamics using a plane wave expansion of the electrostatic potential. This method is expected to be highly efficient for simulating biological systems on massively parallel supercomputers. We have perform genomics analysis on a family of actin binding proteins. We have performed quantum mechanical calculations on carbon nanotubes and nucleic acids, which simulations will allow us to investigate possible sources of organic material on the early earth. Finally, we have developed a model of protobiological chemistry using neural networks.

Decreasing-Rate Pruning Optimizes the Construction of Efficient and Robust Distributed Networks.

PubMed

Navlakha, Saket; Barth, Alison L; Bar-Joseph, Ziv

2015-07-01

Robust, efficient, and low-cost networks are advantageous in both biological and engineered systems. During neural network development in the brain, synapses are massively over-produced and then pruned-back over time. This strategy is not commonly used when designing engineered networks, since adding connections that will soon be removed is considered wasteful. Here, we show that for large distributed routing networks, network function is markedly enhanced by hyper-connectivity followed by aggressive pruning and that the global rate of pruning, a developmental parameter not previously studied by experimentalists, plays a critical role in optimizing network structure. We first used high-throughput image analysis techniques to quantify the rate of pruning in the mammalian neocortex across a broad developmental time window and found that the rate is decreasing over time. Based on these results, we analyzed a model of computational routing networks and show using both theoretical analysis and simulations that decreasing rates lead to more robust and efficient networks compared to other rates. We also present an application of this strategy to improve the distributed design of airline networks. Thus, inspiration from neural network formation suggests effective ways to design distributed networks across several domains.

Decreasing-Rate Pruning Optimizes the Construction of Efficient and Robust Distributed Networks

PubMed Central

Navlakha, Saket; Barth, Alison L.; Bar-Joseph, Ziv

2015-01-01

Robust, efficient, and low-cost networks are advantageous in both biological and engineered systems. During neural network development in the brain, synapses are massively over-produced and then pruned-back over time. This strategy is not commonly used when designing engineered networks, since adding connections that will soon be removed is considered wasteful. Here, we show that for large distributed routing networks, network function is markedly enhanced by hyper-connectivity followed by aggressive pruning and that the global rate of pruning, a developmental parameter not previously studied by experimentalists, plays a critical role in optimizing network structure. We first used high-throughput image analysis techniques to quantify the rate of pruning in the mammalian neocortex across a broad developmental time window and found that the rate is decreasing over time. Based on these results, we analyzed a model of computational routing networks and show using both theoretical analysis and simulations that decreasing rates lead to more robust and efficient networks compared to other rates. We also present an application of this strategy to improve the distributed design of airline networks. Thus, inspiration from neural network formation suggests effective ways to design distributed networks across several domains. PMID:26217933

Artificial Neural Network L* from different magnetospheric field models

NASA Astrophysics Data System (ADS)

Yu, Y.; Koller, J.; Zaharia, S. G.; Jordanova, V. K.

2011-12-01

The third adiabatic invariant L* plays an important role in modeling and understanding the radiation belt dynamics. The popular way to numerically obtain the L* value follows the recipe described by Roederer [1970], which is, however, slow and computational expensive. This work focuses on a new technique, which can compute the L* value in microseconds without losing much accuracy: artificial neural networks. Since L* is related to the magnetic flux enclosed by a particle drift shell, global magnetic field information needed to trace the drift shell is required. A series of currently popular empirical magnetic field models are applied to create the L* data pool using 1 million data samples which are randomly selected within a solar cycle and within the global magnetosphere. The networks, trained from the above L* data pool, can thereby be used for fairly efficient L* calculation given input parameters valid within the trained temporal and spatial range. Besides the empirical magnetospheric models, a physics-based self-consistent inner magnetosphere model (RAM-SCB) developed at LANL is also utilized to calculate L* values and then to train the L* neural network. This model better predicts the magnetospheric configuration and therefore can significantly improve the L*. The above neural network L* technique will enable, for the first time, comprehensive solar-cycle long studies of radiation belt processes. However, neural networks trained from different magnetic field models can result in different L* values, which could cause mis-interpretation of radiation belt dynamics, such as where the source of the radiation belt charged particle is and which mechanism is dominant in accelerating the particles. Such a fact calls for attention to cautiously choose a magnetospheric field model for the L* calculation.

Robust optimization with transiently chaotic dynamical systems

NASA Astrophysics Data System (ADS)

Sumi, R.; Molnár, B.; Ercsey-Ravasz, M.

2014-05-01

Efficiently solving hard optimization problems has been a strong motivation for progress in analog computing. In a recent study we presented a continuous-time dynamical system for solving the NP-complete Boolean satisfiability (SAT) problem, with a one-to-one correspondence between its stable attractors and the SAT solutions. While physical implementations could offer great efficiency, the transiently chaotic dynamics raises the question of operability in the presence of noise, unavoidable on analog devices. Here we show that the probability of finding solutions is robust to noise intensities well above those present on real hardware. We also developed a cellular neural network model realizable with analog circuits, which tolerates even larger noise intensities. These methods represent an opportunity for robust and efficient physical implementations.

Three-Dimensional Stereoscopic Tracking Velocimetry and Experimental/Numerical Comparison of Directional Solidification

NASA Technical Reports Server (NTRS)

Lee, David; Ge, Yi; Cha, Soyoung Stephen; Ramachandran, Narayanan; Rose, M. Franklin (Technical Monitor)

2001-01-01

Measurement of three-dimensional (3-D) three-component velocity fields is of great importance in both ground and space experiments for understanding materials processing and fluid physics. The experiments in these fields most likely inhibit the application of conventional planar probes for observing 3-D phenomena. Here, we present the investigation results of stereoscopic tracking velocimetry (STV) for measuring 3-D velocity fields, which include diagnostic technology development, experimental velocity measurement, and comparison with analytical and numerical computation. STV is advantageous in system simplicity for building compact hardware and in software efficiency for continual near-real-time monitoring. It has great freedom in illuminating and observing volumetric fields from arbitrary directions. STV is based on stereoscopic observation of particles-Seeded in a flow by CCD sensors. In the approach, part of the individual particle images that provide data points is likely to be lost or cause errors when their images overlap and crisscross each other especially under a high particle density. In order to maximize the valid recovery of data points, neural networks are implemented for these two important processes. For the step of particle overlap decomposition, the back propagation neural network is utilized because of its ability in pattern recognition with pertinent particle image feature parameters. For the step of particle tracking, the Hopfield neural network is employed to find appropriate particle tracks based on global optimization. Our investigation indicates that the neural networks are very efficient and useful for stereoscopically tracking particles. As an initial assessment of the diagnostic technology performance, laminar water jets with and without pulsation are measured. The jet tip velocity profiles are in good agreement with analytical predictions. Finally, for testing in material processing applications, a simple directional solidification apparatus is built for experimenting with a metal analog of succinonitrile. Its 3-D velocity field at the liquid phase is then measured to be compared with those from numerical computation. Our theoretical, numerical, and experimental investigations have proven STV to be a viable candidate for reliably measuring 3-D flow velocities. With current activities are focused on further improving the processing efficiency, overall accuracy, and automation, the eventual efforts of broad experimental applications and concurrent numerical modeling validation will be vital to many areas in fluid flow and materials processing.

Neural Network Computing and Natural Language Processing.

ERIC Educational Resources Information Center

Borchardt, Frank

1988-01-01

Considers the application of neural network concepts to traditional natural language processing and demonstrates that neural network computing architecture can: (1) learn from actual spoken language; (2) observe rules of pronunciation; and (3) reproduce sounds from the patterns derived by its own processes. (Author/CB)

Learning of embodied interaction dynamics with recurrent neural networks: some exploratory experiments.

PubMed

Oubbati, Mohamed; Kord, Bahram; Koprinkova-Hristova, Petia; Palm, Günther

2014-04-01

The new tendency of artificial intelligence suggests that intelligence must be seen as a result of the interaction between brains, bodies and environments. This view implies that designing sophisticated behaviour requires a primary focus on how agents are functionally coupled to their environments. Under this perspective, we present early results with the application of reservoir computing as an efficient tool to understand how behaviour emerges from interaction. Specifically, we present reservoir computing models, that are inspired by imitation learning designs, to extract the essential components of behaviour that results from agent-environment interaction dynamics. Experimental results using a mobile robot are reported to validate the learning architectures.

Learning of embodied interaction dynamics with recurrent neural networks: some exploratory experiments

NASA Astrophysics Data System (ADS)

Oubbati, Mohamed; Kord, Bahram; Koprinkova-Hristova, Petia; Palm, Günther

2014-04-01

The new tendency of artificial intelligence suggests that intelligence must be seen as a result of the interaction between brains, bodies and environments. This view implies that designing sophisticated behaviour requires a primary focus on how agents are functionally coupled to their environments. Under this perspective, we present early results with the application of reservoir computing as an efficient tool to understand how behaviour emerges from interaction. Specifically, we present reservoir computing models, that are inspired by imitation learning designs, to extract the essential components of behaviour that results from agent-environment interaction dynamics. Experimental results using a mobile robot are reported to validate the learning architectures.

The brian simulator.

PubMed

Goodman, Dan F M; Brette, Romain

2009-09-01

"Brian" is a simulator for spiking neural networks (http://www.briansimulator.org). The focus is on making the writing of simulation code as quick and easy as possible for the user, and on flexibility: new and non-standard models are no more difficult to define than standard ones. This allows scientists to spend more time on the details of their models, and less on their implementation. Neuron models are defined by writing differential equations in standard mathematical notation, facilitating scientific communication. Brian is written in the Python programming language, and uses vector-based computation to allow for efficient simulations. It is particularly useful for neuroscientific modelling at the systems level, and for teaching computational neuroscience.

Event- and Time-Driven Techniques Using Parallel CPU-GPU Co-processing for Spiking Neural Networks

PubMed Central

Naveros, Francisco; Garrido, Jesus A.; Carrillo, Richard R.; Ros, Eduardo; Luque, Niceto R.

2017-01-01

Modeling and simulating the neural structures which make up our central neural system is instrumental for deciphering the computational neural cues beneath. Higher levels of biological plausibility usually impose higher levels of complexity in mathematical modeling, from neural to behavioral levels. This paper focuses on overcoming the simulation problems (accuracy and performance) derived from using higher levels of mathematical complexity at a neural level. This study proposes different techniques for simulating neural models that hold incremental levels of mathematical complexity: leaky integrate-and-fire (LIF), adaptive exponential integrate-and-fire (AdEx), and Hodgkin-Huxley (HH) neural models (ranged from low to high neural complexity). The studied techniques are classified into two main families depending on how the neural-model dynamic evaluation is computed: the event-driven or the time-driven families. Whilst event-driven techniques pre-compile and store the neural dynamics within look-up tables, time-driven techniques compute the neural dynamics iteratively during the simulation time. We propose two modifications for the event-driven family: a look-up table recombination to better cope with the incremental neural complexity together with a better handling of the synchronous input activity. Regarding the time-driven family, we propose a modification in computing the neural dynamics: the bi-fixed-step integration method. This method automatically adjusts the simulation step size to better cope with the stiffness of the neural model dynamics running in CPU platforms. One version of this method is also implemented for hybrid CPU-GPU platforms. Finally, we analyze how the performance and accuracy of these modifications evolve with increasing levels of neural complexity. We also demonstrate how the proposed modifications which constitute the main contribution of this study systematically outperform the traditional event- and time-driven techniques under increasing levels of neural complexity. PMID:28223930

An Algebra-Based Introductory Computational Neuroscience Course with Lab.

PubMed

Fink, Christian G

2017-01-01

A course in computational neuroscience has been developed at Ohio Wesleyan University which requires no previous experience with calculus or computer programming, and which exposes students to theoretical models of neural information processing and techniques for analyzing neural data. The exploration of theoretical models of neural processes is conducted in the classroom portion of the course, while data analysis techniques are covered in lab. Students learn to program in MATLAB and are offered the opportunity to conclude the course with a final project in which they explore a topic of their choice within computational neuroscience. Results from a questionnaire administered at the beginning and end of the course indicate significant gains in student facility with core concepts in computational neuroscience, as well as with analysis techniques applied to neural data.

Deep learning for computational chemistry.

PubMed

Goh, Garrett B; Hodas, Nathan O; Vishnu, Abhinav

2017-06-15

The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on multilayer neural networks. Within the last few years, we have seen the transformative impact of deep learning in many domains, particularly in speech recognition and computer vision, to the extent that the majority of expert practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties that distinguish them from traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including quantitative structure activity relationship, virtual screening, protein structure prediction, quantum chemistry, materials design, and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non-neural networks state-of-the-art models across disparate research topics, and deep neural network-based models often exceeded the "glass ceiling" expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a valuable tool for computational chemistry. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

Real-time immune-inspired optimum state-of-charge trajectory estimation using upcoming route information preview and neural networks for plug-in hybrid electric vehicles fuel economy

NASA Astrophysics Data System (ADS)

Mozaffari, Ahmad; Vajedi, Mahyar; Azad, Nasser L.

2015-06-01

The main proposition of the current investigation is to develop a computational intelligence-based framework which can be used for the real-time estimation of optimum battery state-of-charge (SOC) trajectory in plug-in hybrid electric vehicles (PHEVs). The estimated SOC trajectory can be then employed for an intelligent power management to significantly improve the fuel economy of the vehicle. The devised intelligent SOC trajectory builder takes advantage of the upcoming route information preview to achieve the lowest possible total cost of electricity and fossil fuel. To reduce the complexity of real-time optimization, the authors propose an immune system-based clustering approach which allows categorizing the route information into a predefined number of segments. The intelligent real-time optimizer is also inspired on the basis of interactions in biological immune systems, and is called artificial immune algorithm (AIA). The objective function of the optimizer is derived from a computationally efficient artificial neural network (ANN) which is trained by a database obtained from a high-fidelity model of the vehicle built in the Autonomie software. The simulation results demonstrate that the integration of immune inspired clustering tool, AIA and ANN, will result in a powerful framework which can generate a near global optimum SOC trajectory for the baseline vehicle, that is, the Toyota Prius PHEV. The outcomes of the current investigation prove that by taking advantage of intelligent approaches, it is possible to design a computationally efficient and powerful SOC trajectory builder for the intelligent power management of PHEVs.

Neuromodulation and Synaptic Plasticity for the Control of Fast Periodic Movement: Energy Efficiency in Coupled Compliant Joints via PCA.

PubMed

Stratmann, Philipp; Lakatos, Dominic; Albu-Schäffer, Alin

2016-01-01

There are multiple indications that the nervous system of animals tunes muscle output to exploit natural dynamics of the elastic locomotor system and the environment. This is an advantageous strategy especially in fast periodic movements, since the elastic elements store energy and increase energy efficiency and movement speed. Experimental evidence suggests that coordination among joints involves proprioceptive input and neuromodulatory influence originating in the brain stem. However, the neural strategies underlying the coordination of fast periodic movements remain poorly understood. Based on robotics control theory, we suggest that the nervous system implements a mechanism to accomplish coordination between joints by a linear coordinate transformation from the multi-dimensional space representing proprioceptive input at the joint level into a one-dimensional controller space. In this one-dimensional subspace, the movements of a whole limb can be driven by a single oscillating unit as simple as a reflex interneuron. The output of the oscillating unit is transformed back to joint space via the same transformation. The transformation weights correspond to the dominant principal component of the movement. In this study, we propose a biologically plausible neural network to exemplify that the central nervous system (CNS) may encode our controller design. Using theoretical considerations and computer simulations, we demonstrate that spike-timing-dependent plasticity (STDP) for the input mapping and serotonergic neuromodulation for the output mapping can extract the dominant principal component of sensory signals. Our simulations show that our network can reliably control mechanical systems of different complexity and increase the energy efficiency of ongoing cyclic movements. The proposed network is simple and consistent with previous biologic experiments. Thus, our controller could serve as a candidate to describe the neural control of fast, energy-efficient, periodic movements involving multiple coupled joints.

Neuromodulation and Synaptic Plasticity for the Control of Fast Periodic Movement: Energy Efficiency in Coupled Compliant Joints via PCA

PubMed Central

Stratmann, Philipp; Lakatos, Dominic; Albu-Schäffer, Alin

2016-01-01

There are multiple indications that the nervous system of animals tunes muscle output to exploit natural dynamics of the elastic locomotor system and the environment. This is an advantageous strategy especially in fast periodic movements, since the elastic elements store energy and increase energy efficiency and movement speed. Experimental evidence suggests that coordination among joints involves proprioceptive input and neuromodulatory influence originating in the brain stem. However, the neural strategies underlying the coordination of fast periodic movements remain poorly understood. Based on robotics control theory, we suggest that the nervous system implements a mechanism to accomplish coordination between joints by a linear coordinate transformation from the multi-dimensional space representing proprioceptive input at the joint level into a one-dimensional controller space. In this one-dimensional subspace, the movements of a whole limb can be driven by a single oscillating unit as simple as a reflex interneuron. The output of the oscillating unit is transformed back to joint space via the same transformation. The transformation weights correspond to the dominant principal component of the movement. In this study, we propose a biologically plausible neural network to exemplify that the central nervous system (CNS) may encode our controller design. Using theoretical considerations and computer simulations, we demonstrate that spike-timing-dependent plasticity (STDP) for the input mapping and serotonergic neuromodulation for the output mapping can extract the dominant principal component of sensory signals. Our simulations show that our network can reliably control mechanical systems of different complexity and increase the energy efficiency of ongoing cyclic movements. The proposed network is simple and consistent with previous biologic experiments. Thus, our controller could serve as a candidate to describe the neural control of fast, energy-efficient, periodic movements involving multiple coupled joints. PMID:27014051

Data mining in soft computing framework: a survey.

PubMed

Mitra, S; Pal, S K; Mitra, P

2002-01-01

The present article provides a survey of the available literature on data mining using soft computing. A categorization has been provided based on the different soft computing tools and their hybridizations used, the data mining function implemented, and the preference criterion selected by the model. The utility of the different soft computing methodologies is highlighted. Generally fuzzy sets are suitable for handling the issues related to understandability of patterns, incomplete/noisy data, mixed media information and human interaction, and can provide approximate solutions faster. Neural networks are nonparametric, robust, and exhibit good learning and generalization capabilities in data-rich environments. Genetic algorithms provide efficient search algorithms to select a model, from mixed media data, based on some preference criterion/objective function. Rough sets are suitable for handling different types of uncertainty in data. Some challenges to data mining and the application of soft computing methodologies are indicated. An extensive bibliography is also included.

Connecting Neural Coding to Number Cognition: A Computational Account

ERIC Educational Resources Information Center

Prather, Richard W.

2012-01-01

The current study presents a series of computational simulations that demonstrate how the neural coding of numerical magnitude may influence number cognition and development. This includes behavioral phenomena cataloged in cognitive literature such as the development of numerical estimation and operational momentum. Though neural research has…

Modelling formulations using gene expression programming--a comparative analysis with artificial neural networks.

PubMed

Colbourn, E A; Roskilly, S J; Rowe, R C; York, P

2011-10-09

This study has investigated the utility and potential advantages of gene expression programming (GEP)--a new development in evolutionary computing for modelling data and automatically generating equations that describe the cause-and-effect relationships in a system--to four types of pharmaceutical formulation and compared the models with those generated by neural networks, a technique now widely used in the formulation development. Both methods were capable of discovering subtle and non-linear relationships within the data, with no requirement from the user to specify the functional forms that should be used. Although the neural networks rapidly developed models with higher values for the ANOVA R(2) these were black box and provided little insight into the key relationships. However, GEP, although significantly slower at developing models, generated relatively simple equations describing the relationships that could be interpreted directly. The results indicate that GEP can be considered an effective and efficient modelling technique for formulation data. Copyright © 2011 Elsevier B.V. All rights reserved.

Robust model predictive control of nonlinear systems with unmodeled dynamics and bounded uncertainties based on neural networks.

PubMed

Yan, Zheng; Wang, Jun

2014-03-01

This paper presents a neural network approach to robust model predictive control (MPC) for constrained discrete-time nonlinear systems with unmodeled dynamics affected by bounded uncertainties. The exact nonlinear model of underlying process is not precisely known, but a partially known nominal model is available. This partially known nonlinear model is first decomposed to an affine term plus an unknown high-order term via Jacobian linearization. The linearization residue combined with unmodeled dynamics is then modeled using an extreme learning machine via supervised learning. The minimax methodology is exploited to deal with bounded uncertainties. The minimax optimization problem is reformulated as a convex minimization problem and is iteratively solved by a two-layer recurrent neural network. The proposed neurodynamic approach to nonlinear MPC improves the computational efficiency and sheds a light for real-time implementability of MPC technology. Simulation results are provided to substantiate the effectiveness and characteristics of the proposed approach.

ANNA: A Convolutional Neural Network Code for Spectroscopic Analysis

NASA Astrophysics Data System (ADS)

Lee-Brown, Donald; Anthony-Twarog, Barbara J.; Twarog, Bruce A.

2018-01-01

We present ANNA, a Python-based convolutional neural network code for the automated analysis of stellar spectra. ANNA provides a flexible framework that allows atmospheric parameters such as temperature and metallicity to be determined with accuracies comparable to those of established but less efficient techniques. ANNA performs its parameterization extremely quickly; typically several thousand spectra can be analyzed in less than a second. Additionally, the code incorporates features which greatly speed up the training process necessary for the neural network to measure spectra accurately, resulting in a tool that can easily be run on a single desktop or laptop computer. Thus, ANNA is useful in an era when spectrographs increasingly have the capability to collect dozens to hundreds of spectra each night. This talk will cover the basic features included in ANNA and demonstrate its performance in two use cases: an open cluster abundance analysis involving several hundred spectra, and a metal-rich field star study. Applicability of the code to large survey datasets will also be discussed.

Processing short-term and long-term information with a combination of polynomial approximation techniques and time-delay neural networks.

PubMed

Fuchs, Erich; Gruber, Christian; Reitmaier, Tobias; Sick, Bernhard

2009-09-01

Neural networks are often used to process temporal information, i.e., any kind of information related to time series. In many cases, time series contain short-term and long-term trends or behavior. This paper presents a new approach to capture temporal information with various reference periods simultaneously. A least squares approximation of the time series with orthogonal polynomials will be used to describe short-term trends contained in a signal (average, increase, curvature, etc.). Long-term behavior will be modeled with the tapped delay lines of a time-delay neural network (TDNN). This network takes the coefficients of the orthogonal expansion of the approximating polynomial as inputs such considering short-term and long-term information efficiently. The advantages of the method will be demonstrated by means of artificial data and two real-world application examples, the prediction of the user number in a computer network and online tool wear classification in turning.

Condition monitoring of 3G cellular networks through competitive neural models.

PubMed

Barreto, Guilherme A; Mota, João C M; Souza, Luis G M; Frota, Rewbenio A; Aguayo, Leonardo

2005-09-01

We develop an unsupervised approach to condition monitoring of cellular networks using competitive neural algorithms. Training is carried out with state vectors representing the normal functioning of a simulated CDMA2000 network. Once training is completed, global and local normality profiles (NPs) are built from the distribution of quantization errors of the training state vectors and their components, respectively. The global NP is used to evaluate the overall condition of the cellular system. If abnormal behavior is detected, local NPs are used in a component-wise fashion to find abnormal state variables. Anomaly detection tests are performed via percentile-based confidence intervals computed over the global and local NPs. We compared the performance of four competitive algorithms [winner-take-all (WTA), frequency-sensitive competitive learning (FSCL), self-organizing map (SOM), and neural-gas algorithm (NGA)] and the results suggest that the joint use of global and local NPs is more efficient and more robust than current single-threshold methods.

An experimental vestibular neural prosthesis: design and preliminary results with rhesus monkeys stimulated with modulated pulses.

PubMed

Nie, Kaibao; Ling, Leo; Bierer, Steven M; Kaneko, Chris R S; Fuchs, Albert F; Oxford, Trey; Rubinstein, Jay T; Phillips, James O

2013-06-01

A vestibular neural prosthesis was designed on the basis of a cochlear implant for treatment of Meniere's disease and other vestibular disorders. Computer control software was developed to generate patterned pulse stimuli for exploring optimal parameters to activate the vestibular nerve. Two rhesus monkeys were implanted with the prototype vestibular prosthesis and they were behaviorally evaluated post implantation surgery. Horizontal and vertical eye movement responses to patterned electrical pulse stimulations were collected on both monkeys. Pulse amplitude modulated (PAM) and pulse rate modulated (PRM) trains were applied to the lateral canal of each implanted animal. Robust slow-phase nystagmus responses following the PAM or PRM modulation pattern were observed in both implanted monkeys in the direction consistent with the activation of the implanted canal. Both PAM and PRM pulse trains can elicit a significant amount of in-phase modulated eye velocity changes and they could potentially be used for efficiently coding head rotational signals in future vestibular neural prostheses.

Memory Efficient Evaluations of Nonlinear Stochastic Equations and C3 Applications.

DTIC Science & Technology

1987-12-01

time. In the 1960’s, when Massachusetts Institute of Technology’s Marvin Minsky [16] and others criticized the concept on the grounds of .nsufficient...recognize letters of the alphabet [231. Minsky and Papert [16] criticized the perceptron, asserting that too little is known of the human brain to...1987). [15] Kinoshita, J. and Palevsky, N. G., "Computing with neural networks," High Technology (May 1987). . [16] Minsky , M. and Papert, S

Artificial neural networks for efficient clustering of conformational ensembles and their potential for medicinal chemistry.

PubMed

Pandini, Alessandro; Fraccalvieri, Domenico; Bonati, Laura

2013-01-01

The biological function of proteins is strictly related to their molecular flexibility and dynamics: enzymatic activity, protein-protein interactions, ligand binding and allosteric regulation are important mechanisms involving protein motions. Computational approaches, such as Molecular Dynamics (MD) simulations, are now routinely used to study the intrinsic dynamics of target proteins as well as to complement molecular docking approaches. These methods have also successfully supported the process of rational design and discovery of new drugs. Identification of functionally relevant conformations is a key step in these studies. This is generally done by cluster analysis of the ensemble of structures in the MD trajectory. Recently Artificial Neural Network (ANN) approaches, in particular methods based on Self-Organising Maps (SOMs), have been reported performing more accurately and providing more consistent results than traditional clustering algorithms in various data-mining problems. In the specific case of conformational analysis, SOMs have been successfully used to compare multiple ensembles of protein conformations demonstrating a potential in efficiently detecting the dynamic signatures central to biological function. Moreover, examples of the use of SOMs to address problems relevant to other stages of the drug-design process, including clustering of docking poses, have been reported. In this contribution we review recent applications of ANN algorithms in analysing conformational and structural ensembles and we discuss their potential in computer-based approaches for medicinal chemistry.

Force Field for Water Based on Neural Network.

PubMed

Wang, Hao; Yang, Weitao

2018-05-18

We developed a novel neural network based force field for water based on training with high level ab initio theory. The force field was built based on electrostatically embedded many-body expansion method truncated at binary interactions. Many-body expansion method is a common strategy to partition the total Hamiltonian of large systems into a hierarchy of few-body terms. Neural networks were trained to represent electrostatically embedded one-body and two-body interactions, which require as input only one and two water molecule calculations at the level of ab initio electronic structure method CCSD/aug-cc-pVDZ embedded in the molecular mechanics water environment, making it efficient as a general force field construction approach. Structural and dynamic properties of liquid water calculated with our force field show good agreement with experimental results. We constructed two sets of neural network based force fields: non-polarizable and polarizable force fields. Simulation results show that the non-polarizable force field using fixed TIP3P charges has already behaved well, since polarization effects and many-body effects are implicitly included due to the electrostatic embedding scheme. Our results demonstrate that the electrostatically embedded many-body expansion combined with neural network provides a promising and systematic way to build the next generation force fields at high accuracy and low computational costs, especially for large systems.

Improved Adjoint-Operator Learning For A Neural Network

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad; Barhen, Jacob

1995-01-01

Improved method of adjoint-operator learning reduces amount of computation and associated computational memory needed to make electronic neural network learn temporally varying pattern (e.g., to recognize moving object in image) in real time. Method extension of method described in "Adjoint-Operator Learning for a Neural Network" (NPO-18352).

Brains--Computers--Machines: Neural Engineering in Science Classrooms

ERIC Educational Resources Information Center

Chudler, Eric H.; Bergsman, Kristen Clapper

2016-01-01

Neural engineering is an emerging field of high relevance to students, teachers, and the general public. This feature presents online resources that educators and scientists can use to introduce students to neural engineering and to integrate core ideas from the life sciences, physical sciences, social sciences, computer science, and engineering…

A Decade of Neural Networks: Practical Applications and Prospects

NASA Technical Reports Server (NTRS)

Kemeny, Sabrina E.

1994-01-01

The Jet Propulsion Laboratory Neural Network Workshop, sponsored by NASA and DOD, brings together sponsoring agencies, active researchers, and the user community to formulate a vision for the next decade of neural network research and application prospects. While the speed and computing power of microprocessors continue to grow at an ever-increasing pace, the demand to intelligently and adaptively deal with the complex, fuzzy, and often ill-defined world around us remains to a large extent unaddressed. Powerful, highly parallel computing paradigms such as neural networks promise to have a major impact in addressing these needs. Papers in the workshop proceedings highlight benefits of neural networks in real-world applications compared to conventional computing techniques. Topics include fault diagnosis, pattern recognition, and multiparameter optimization.

Brian: a simulator for spiking neural networks in python.

PubMed

Goodman, Dan; Brette, Romain

2008-01-01

"Brian" is a new simulator for spiking neural networks, written in Python (http://brian. di.ens.fr). It is an intuitive and highly flexible tool for rapidly developing new models, especially networks of single-compartment neurons. In addition to using standard types of neuron models, users can define models by writing arbitrary differential equations in ordinary mathematical notation. Python scientific libraries can also be used for defining models and analysing data. Vectorisation techniques allow efficient simulations despite the overheads of an interpreted language. Brian will be especially valuable for working on non-standard neuron models not easily covered by existing software, and as an alternative to using Matlab or C for simulations. With its easy and intuitive syntax, Brian is also very well suited for teaching computational neuroscience.

Online graphic symbol recognition using neural network and ARG matching

NASA Astrophysics Data System (ADS)

Yang, Bing; Li, Changhua; Xie, Weixing

2001-09-01

This paper proposes a novel method for on-line recognition of line-based graphic symbol. The input strokes are usually warped into a cursive form due to the sundry drawing style, and classifying them is very difficult. To deal with this, an ART-2 neural network is used to classify the input strokes. It has the advantages of high recognition rate, less recognition time and forming classes in a self-organized manner. The symbol recognition is achieved by an Attribute Relational Graph (ARG) matching algorithm. The ARG is very efficient for representing complex objects, but computation cost is very high. To over come this, we suggest a fast graph matching algorithm using symbol structure information. The experimental results show that the proposed method is effective for recognition of symbols with hierarchical structure.

Neural architecture design based on extreme learning machine.

PubMed

Bueno-Crespo, Andrés; García-Laencina, Pedro J; Sancho-Gómez, José-Luis

2013-12-01

Selection of the optimal neural architecture to solve a pattern classification problem entails to choose the relevant input units, the number of hidden neurons and its corresponding interconnection weights. This problem has been widely studied in many research works but their solutions usually involve excessive computational cost in most of the problems and they do not provide a unique solution. This paper proposes a new technique to efficiently design the MultiLayer Perceptron (MLP) architecture for classification using the Extreme Learning Machine (ELM) algorithm. The proposed method provides a high generalization capability and a unique solution for the architecture design. Moreover, the selected final network only retains those input connections that are relevant for the classification task. Experimental results show these advantages. Copyright © 2013 Elsevier Ltd. All rights reserved.

Boolean and brain-inspired computing using spin-transfer torque devices

NASA Astrophysics Data System (ADS)

Fan, Deliang

Several completely new approaches (such as spintronic, carbon nanotube, graphene, TFETs, etc.) to information processing and data storage technologies are emerging to address the time frame beyond current Complementary Metal-Oxide-Semiconductor (CMOS) roadmap. The high speed magnetization switching of a nano-magnet due to current induced spin-transfer torque (STT) have been demonstrated in recent experiments. Such STT devices can be explored in compact, low power memory and logic design. In order to truly leverage STT devices based computing, researchers require a re-think of circuit, architecture, and computing model, since the STT devices are unlikely to be drop-in replacements for CMOS. The potential of STT devices based computing will be best realized by considering new computing models that are inherently suited to the characteristics of STT devices, and new applications that are enabled by their unique capabilities, thereby attaining performance that CMOS cannot achieve. The goal of this research is to conduct synergistic exploration in architecture, circuit and device levels for Boolean and brain-inspired computing using nanoscale STT devices. Specifically, we first show that the non-volatile STT devices can be used in designing configurable Boolean logic blocks. We propose a spin-memristor threshold logic (SMTL) gate design, where memristive cross-bar array is used to perform current mode summation of binary inputs and the low power current mode spintronic threshold device carries out the energy efficient threshold operation. Next, for brain-inspired computing, we have exploited different spin-transfer torque device structures that can implement the hard-limiting and soft-limiting artificial neuron transfer functions respectively. We apply such STT based neuron (or 'spin-neuron') in various neural network architectures, such as hierarchical temporal memory and feed-forward neural network, for performing "human-like" cognitive computing, which show more than two orders of lower energy consumption compared to state of the art CMOS implementation. Finally, we show the dynamics of injection locked Spin Hall Effect Spin-Torque Oscillator (SHE-STO) cluster can be exploited as a robust multi-dimensional distance metric for associative computing, image/ video analysis, etc. Our simulation results show that the proposed system architecture with injection locked SHE-STOs and the associated CMOS interface circuits can be suitable for robust and energy efficient associative computing and pattern matching.

Multiple neural network approaches to clinical expert systems

NASA Astrophysics Data System (ADS)

Stubbs, Derek F.

1990-08-01

We briefly review the concept of computer aided medical diagnosis and more extensively review the the existing literature on neural network applications in the field. Neural networks can function as simple expert systems for diagnosis or prognosis. Using a public database we develop a neural network for the diagnosis of a major presenting symptom while discussing the development process and possible approaches. MEDICAL EXPERTS SYSTEMS COMPUTER AIDED DIAGNOSIS Biomedicine is an incredibly diverse and multidisciplinary field and it is not surprising that neural networks with their many applications are finding more and more applications in the highly non-linear field of biomedicine. I want to concentrate on neural networks as medical expert systems for clinical diagnosis or prognosis. Expert Systems started out as a set of computerized " ifthen" rules. Everything was reduced to boolean logic and the promised land of computer experts was said to be in sight. It never came. Why? First the computer code explodes as the number of " ifs" increases. All the " ifs" have to interact. Second experts are not very good at reducing expertise to language. It turns out that experts recognize patterns and have non-verbal left-brain intuition decision processes. Third learning by example rather than learning by rule is the way natural brains works and making computers work by rule-learning is hideously labor intensive. Neural networks can learn from example. They learn the results

Single- and Multiple-Objective Optimization with Differential Evolution and Neural Networks

NASA Technical Reports Server (NTRS)

Rai, Man Mohan

2006-01-01

Genetic and evolutionary algorithms have been applied to solve numerous problems in engineering design where they have been used primarily as optimization procedures. These methods have an advantage over conventional gradient-based search procedures became they are capable of finding global optima of multi-modal functions and searching design spaces with disjoint feasible regions. They are also robust in the presence of noisy data. Another desirable feature of these methods is that they can efficiently use distributed and parallel computing resources since multiple function evaluations (flow simulations in aerodynamics design) can be performed simultaneously and independently on ultiple processors. For these reasons genetic and evolutionary algorithms are being used more frequently in design optimization. Examples include airfoil and wing design and compressor and turbine airfoil design. They are also finding increasing use in multiple-objective and multidisciplinary optimization. This lecture will focus on an evolutionary method that is a relatively new member to the general class of evolutionary methods called differential evolution (DE). This method is easy to use and program and it requires relatively few user-specified constants. These constants are easily determined for a wide class of problems. Fine-tuning the constants will off course yield the solution to the optimization problem at hand more rapidly. DE can be efficiently implemented on parallel computers and can be used for continuous, discrete and mixed discrete/continuous optimization problems. It does not require the objective function to be continuous and is noise tolerant. DE and applications to single and multiple-objective optimization will be included in the presentation and lecture notes. A method for aerodynamic design optimization that is based on neural networks will also be included as a part of this lecture. The method offers advantages over traditional optimization methods. It is more flexible than other methods in dealing with design in the context of both steady and unsteady flows, partial and complete data sets, combined experimental and numerical data, inclusion of various constraints and rules of thumb, and other issues that characterize the aerodynamic design process. Neural networks provide a natural framework within which a succession of numerical solutions of increasing fidelity, incorporating more realistic flow physics, can be represented and utilized for optimization. Neural networks also offer an excellent framework for multiple-objective and multi-disciplinary design optimization. Simulation tools from various disciplines can be integrated within this framework and rapid trade-off studies involving one or many disciplines can be performed. The prospect of combining neural network based optimization methods and evolutionary algorithms to obtain a hybrid method with the best properties of both methods will be included in this presentation. Achieving solution diversity and accurate convergence to the exact Pareto front in multiple objective optimization usually requires a significant computational effort with evolutionary algorithms. In this lecture we will also explore the possibility of using neural networks to obtain estimates of the Pareto optimal front using non-dominated solutions generated by DE as training data. Neural network estimators have the potential advantage of reducing the number of function evaluations required to obtain solution accuracy and diversity, thus reducing cost to design.

An Attractor-Based Complexity Measurement for Boolean Recurrent Neural Networks

PubMed Central

Cabessa, Jérémie; Villa, Alessandro E. P.

2014-01-01

We provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their attractor dynamics. This complexity measurement is achieved by first proving a computational equivalence between Boolean recurrent neural networks and some specific class of -automata, and then translating the most refined classification of -automata to the Boolean neural network context. As a result, a hierarchical classification of Boolean neural networks based on their attractive dynamics is obtained, thus providing a novel refined attractor-based complexity measurement for Boolean recurrent neural networks. These results provide new theoretical insights to the computational and dynamical capabilities of neural networks according to their attractive potentialities. An application of our findings is illustrated by the analysis of the dynamics of a simplified model of the basal ganglia-thalamocortical network simulated by a Boolean recurrent neural network. This example shows the significance of measuring network complexity, and how our results bear new founding elements for the understanding of the complexity of real brain circuits. PMID:24727866

Neural networks applications to control and computations

NASA Technical Reports Server (NTRS)

Luxemburg, Leon A.

1994-01-01

Several interrelated problems in the area of neural network computations are described. First an interpolation problem is considered, then a control problem is reduced to a problem of interpolation by a neural network via Lyapunov function approach, and finally a new, faster method of learning as compared with the gradient descent method, was introduced.

Real-space mapping of topological invariants using artificial neural networks

NASA Astrophysics Data System (ADS)

Carvalho, D.; García-Martínez, N. A.; Lado, J. L.; Fernández-Rossier, J.

2018-03-01

Topological invariants allow one to characterize Hamiltonians, predicting the existence of topologically protected in-gap modes. Those invariants can be computed by tracing the evolution of the occupied wave functions under twisted boundary conditions. However, those procedures do not allow one to calculate a topological invariant by evaluating the system locally, and thus require information about the wave functions in the whole system. Here we show that artificial neural networks can be trained to identify the topological order by evaluating a local projection of the density matrix. We demonstrate this for two different models, a one-dimensional topological superconductor and a two-dimensional quantum anomalous Hall state, both with spatially modulated parameters. Our neural network correctly identifies the different topological domains in real space, predicting the location of in-gap states. By combining a neural network with a calculation of the electronic states that uses the kernel polynomial method, we show that the local evaluation of the invariant can be carried out by evaluating a local quantity, in particular for systems without translational symmetry consisting of tens of thousands of atoms. Our results show that supervised learning is an efficient methodology to characterize the local topology of a system.

Robust hepatic vessel segmentation using multi deep convolution network

NASA Astrophysics Data System (ADS)

Kitrungrotsakul, Titinunt; Han, Xian-Hua; Iwamoto, Yutaro; Foruzan, Amir Hossein; Lin, Lanfen; Chen, Yen-Wei

2017-03-01

Extraction of blood vessels of the organ is a challenging task in the area of medical image processing. It is really difficult to get accurate vessel segmentation results even with manually labeling by human being. The difficulty of vessels segmentation is the complicated structure of blood vessels and its large variations that make them hard to recognize. In this paper, we present deep artificial neural network architecture to automatically segment the hepatic vessels from computed tomography (CT) image. We proposed novel deep neural network (DNN) architecture for vessel segmentation from a medical CT volume, which consists of three deep convolution neural networks to extract features from difference planes of CT data. The three networks have share features at the first convolution layer but will separately learn their own features in the second layer. All three networks will join again at the top layer. To validate effectiveness and efficiency of our proposed method, we conduct experiments on 12 CT volumes which training data are randomly generate from 5 CT volumes and 7 using for test. Our network can yield an average dice coefficient 0.830, while 3D deep convolution neural network can yield around 0.7 and multi-scale can yield only 0.6.

Detection, location, and quantification of structural damage by neural-net-processed moiré profilometry

NASA Astrophysics Data System (ADS)

Grossman, Barry G.; Gonzalez, Frank S.; Blatt, Joel H.; Hooker, Jeffery A.

1992-03-01

The development of efficient high speed techniques to recognize, locate, and quantify damage is vitally important for successful automated inspection systems such as ones used for the inspection of undersea pipelines. Two critical problems must be solved to achieve these goals: the reduction of nonuseful information present in the video image and automatic recognition and quantification of extent and location of damage. Artificial neural network processed moire profilometry appears to be a promising technique to accomplish this. Real time video moire techniques have been developed which clearly distinguish damaged and undamaged areas on structures, thus reducing the amount of extraneous information input into an inspection system. Artificial neural networks have demonstrated advantages for image processing, since they can learn the desired response to a given input and are inherently fast when implemented in hardware due to their parallel computing architecture. Video moire images of pipes with dents of different depths were used to train a neural network, with the desired output being the location and severity of the damage. The system was then successfully tested with a second series of moire images. The techniques employed and the results obtained are discussed.

Effects of Pulse Shape and Polarity on Sensitivity to Cochlear Implant Stimulation: A Chronic Study in Guinea Pigs.

PubMed

Macherey, Olivier; Cazals, Yves

2016-01-01

Most cochlear implants (CIs) stimulate the auditory nerve with trains of symmetric biphasic pulses consisting of two phases of opposite polarity. Animal and human studies have shown that both polarities can elicit neural responses. In human CI listeners, studies have shown that at suprathreshold levels, the anodic phase is more effective than the cathodic phase. In contrast, animal studies usually show the opposite trend. Although the reason for this discrepancy remains unclear, computational modelling results have proposed that the degeneration of the peripheral processes of the neurons could lead to a higher efficiency of anodic stimulation. We tested this hypothesis in ten guinea pigs who were deafened with an injection of sysomycin and implanted with a single ball electrode inserted in the first turn of the cochlea. Animals were tested at regular intervals between 1 week after deafening and up to 1 year for some of them. Our hypothesis was that if the effect of polarity is determined by the presence or absence of peripheral processes, the difference in polarity efficiency should change over time because of a progressive neural degeneration. Stimuli consisted of charge-balanced symmetric and asymmetric pulses allowing us to observe the response to each polarity individually. For all stimuli, the inferior colliculus evoked potential was measured. Results show that the cathodic phase was more effective than the anodic phase and that this remained so even several months after deafening. This suggests that neural degeneration cannot entirely account for the higher efficiency of anodic stimulation observed in human CI listeners.

Cerebellum-inspired neural network solution of the inverse kinematics problem.

PubMed

Asadi-Eydivand, Mitra; Ebadzadeh, Mohammad Mehdi; Solati-Hashjin, Mehran; Darlot, Christian; Abu Osman, Noor Azuan

2015-12-01

The demand today for more complex robots that have manipulators with higher degrees of freedom is increasing because of technological advances. Obtaining the precise movement for a desired trajectory or a sequence of arm and positions requires the computation of the inverse kinematic (IK) function, which is a major problem in robotics. The solution of the IK problem leads robots to the precise position and orientation of their end-effector. We developed a bioinspired solution comparable with the cerebellar anatomy and function to solve the said problem. The proposed model is stable under all conditions merely by parameter determination, in contrast to recursive model-based solutions, which remain stable only under certain conditions. We modified the proposed model for the simple two-segmented arm to prove the feasibility of the model under a basic condition. A fuzzy neural network through its learning method was used to compute the parameters of the system. Simulation results show the practical feasibility and efficiency of the proposed model in robotics. The main advantage of the proposed model is its generalizability and potential use in any robot.

An alternative respiratory sounds classification system utilizing artificial neural networks.

PubMed

Oweis, Rami J; Abdulhay, Enas W; Khayal, Amer; Awad, Areen

2015-01-01

Computerized lung sound analysis involves recording lung sound via an electronic device, followed by computer analysis and classification based on specific signal characteristics as non-linearity and nonstationarity caused by air turbulence. An automatic analysis is necessary to avoid dependence on expert skills. This work revolves around exploiting autocorrelation in the feature extraction stage. All process stages were implemented in MATLAB. The classification process was performed comparatively using both artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS) toolboxes. The methods have been applied to 10 different respiratory sounds for classification. The ANN was superior to the ANFIS system and returned superior performance parameters. Its accuracy, specificity, and sensitivity were 98.6%, 100%, and 97.8%, respectively. The obtained parameters showed superiority to many recent approaches. The promising proposed method is an efficient fast tool for the intended purpose as manifested in the performance parameters, specifically, accuracy, specificity, and sensitivity. Furthermore, it may be added that utilizing the autocorrelation function in the feature extraction in such applications results in enhanced performance and avoids undesired computation complexities compared to other techniques.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei; Zhang, Kaibing

2017-09-01

Considering that manual inspection of the yarn-dyed fabric can be time consuming and inefficient, we propose a yarn-dyed fabric defect classification method by using a convolutional neural network (CNN) based on a modified AlexNet. CNN shows powerful ability in performing feature extraction and fusion by simulating the learning mechanism of human brain. The local response normalization layers in AlexNet are replaced by the batch normalization layers, which can enhance both the computational efficiency and classification accuracy. In the training process of the network, the characteristics of the defect are extracted step by step and the essential features of the image can be obtained from the fusion of the edge details with several convolution operations. Then the max-pooling layers, the dropout layers, and the fully connected layers are employed in the classification model to reduce the computation cost and extract more precise features of the defective fabric. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show promising performance with an acceptable average classification rate and strong robustness on yarn-dyed fabric defect classification.

Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles

NASA Astrophysics Data System (ADS)

Ha, Jin Gwan; Moon, Hyeonjoon; Kwak, Jin Tae; Hassan, Syed Ibrahim; Dang, Minh; Lee, O. New; Park, Han Yong

2017-10-01

Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.

Seismic activity prediction using computational intelligence techniques in northern Pakistan

NASA Astrophysics Data System (ADS)

Asim, Khawaja M.; Awais, Muhammad; Martínez-Álvarez, F.; Iqbal, Talat

2017-10-01

Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar's statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.

A non-volatile organic electrochemical device as a low-voltage artificial synapse for neuromorphic computing

DOE PAGES

van de Burgt, Yoeri; Lubberman, Ewout; Fuller, Elliot J.; ...

2017-02-20

The brain is capable of massively parallel information processing while consuming only ~1- 100 fJ per synaptic event. Inspired by the efficiency of the brain, CMOS-based neural architectures and memristors are being developed for pattern recognition and machine learning. However, the volatility, design complexity and high supply voltages for CMOS architectures, and the stochastic and energy-costly switching of memristors complicate the path to achieve the interconnectivity, information density, and energy efficiency of the brain using either approach. Here we describe an electrochemical neuromorphic organic device (ENODe) operating with a fundamentally different mechanism from existing memristors. ENODe switches at low energymore » (<10 pJ for 10 3 μm 2 devices) and voltage, displays >500 distinct, non-volatile conductance states within a ~1 V range, and achieves high classification accuracy when implemented in neural network simulations. Plastic ENODEs are also fabricated on flexible substrates enabling the integration of neuromorphic functionality in stretchable electronic systems. Mechanical flexibility makes ENODes compatible with 3D architectures, opening a path towards extreme interconnectivity comparable to the human brain.« less

A non-volatile organic electrochemical device as a low-voltage artificial synapse for neuromorphic computing

NASA Astrophysics Data System (ADS)

van de Burgt, Yoeri; Lubberman, Ewout; Fuller, Elliot J.; Keene, Scott T.; Faria, Grégorio C.; Agarwal, Sapan; Marinella, Matthew J.; Alec Talin, A.; Salleo, Alberto

2017-04-01

The brain is capable of massively parallel information processing while consuming only ~1-100 fJ per synaptic event. Inspired by the efficiency of the brain, CMOS-based neural architectures and memristors are being developed for pattern recognition and machine learning. However, the volatility, design complexity and high supply voltages for CMOS architectures, and the stochastic and energy-costly switching of memristors complicate the path to achieve the interconnectivity, information density, and energy efficiency of the brain using either approach. Here we describe an electrochemical neuromorphic organic device (ENODe) operating with a fundamentally different mechanism from existing memristors. ENODe switches at low voltage and energy (<10 pJ for 103 μm2 devices), displays >500 distinct, non-volatile conductance states within a ~1 V range, and achieves high classification accuracy when implemented in neural network simulations. Plastic ENODes are also fabricated on flexible substrates enabling the integration of neuromorphic functionality in stretchable electronic systems. Mechanical flexibility makes ENODes compatible with three-dimensional architectures, opening a path towards extreme interconnectivity comparable to the human brain.

A non-volatile organic electrochemical device as a low-voltage artificial synapse for neuromorphic computing.

PubMed

van de Burgt, Yoeri; Lubberman, Ewout; Fuller, Elliot J; Keene, Scott T; Faria, Grégorio C; Agarwal, Sapan; Marinella, Matthew J; Alec Talin, A; Salleo, Alberto

2017-04-01

The brain is capable of massively parallel information processing while consuming only ∼1-100 fJ per synaptic event. Inspired by the efficiency of the brain, CMOS-based neural architectures and memristors are being developed for pattern recognition and machine learning. However, the volatility, design complexity and high supply voltages for CMOS architectures, and the stochastic and energy-costly switching of memristors complicate the path to achieve the interconnectivity, information density, and energy efficiency of the brain using either approach. Here we describe an electrochemical neuromorphic organic device (ENODe) operating with a fundamentally different mechanism from existing memristors. ENODe switches at low voltage and energy (<10 pJ for 10 3  μm 2 devices), displays >500 distinct, non-volatile conductance states within a ∼1 V range, and achieves high classification accuracy when implemented in neural network simulations. Plastic ENODes are also fabricated on flexible substrates enabling the integration of neuromorphic functionality in stretchable electronic systems. Mechanical flexibility makes ENODes compatible with three-dimensional architectures, opening a path towards extreme interconnectivity comparable to the human brain.

Training trajectories by continuous recurrent multilayer networks.

PubMed

Leistritz, L; Galicki, M; Witte, H; Kochs, E

2002-01-01

This paper addresses the problem of training trajectories by means of continuous recurrent neural networks whose feedforward parts are multilayer perceptrons. Such networks can approximate a general nonlinear dynamic system with arbitrary accuracy. The learning process is transformed into an optimal control framework where the weights are the controls to be determined. A training algorithm based upon a variational formulation of Pontryagin's maximum principle is proposed for such networks. Computer examples demonstrating the efficiency of the given approach are also presented.

Comparisons of a Quantum Annealing and Classical Computer Neural Net Approach for Inferring Global Annual CO2 Fluxes over Land

NASA Astrophysics Data System (ADS)

Halem, M.; Radov, A.; Singh, D.

2017-12-01

Investigations of mid to high latitude atmospheric CO2 show growing amplitudes in seasonal variations over the past several decades. Recent high-resolution satellite measurements of CO2 concentration are now available for three years from the Orbiting Carbon Observatory-2. The Atmospheric Radiation Measurement (ARM) program of DOE has been making long-term CO2-flux measurements (in addition to CO2 concentration and an array of other meteorological quantities) at several towers and mobile sites located around the globe at half-hour frequencies. Recent papers have shown CO2 fluxes inferred by assimilating CO2 observations into ecosystem models are largely inconsistent with station observations. An investigation of how the biosphere has reacted to changes in atmospheric CO2 is essential to our understanding of potential climate-vegetation feedbacks. Thus, new approaches for calculating CO2-flux for assimilation into land surface models are necessary for improving the prediction of annual carbon uptake. In this study, we calculate and compare the predicted CO2 fluxes results employing a Feed Forward Backward Propagation Neural Network model on two architectures, (i) an IBM Minsky Computer node and (ii) a hybrid version of the ARC D-Wave quantum annealing computer. We compare the neural net results of predictions of CO2 flux from ARM station data for three different DOE ecosystem sites; an arid plains near Oklahoma City, a northern arctic site at Barrows AL, and a tropical rainforest site in the Amazon. Training times and predictive results for the calculating annual CO2 flux for the two architectures for each of the three sites are presented. Comparative results of predictions as measured by RMSE and MAE are discussed. Plots and correlations of observed vs predicted CO2 flux are also presented for all three sites. We show the estimated training times for quantum and classical calculations when extended to calculating global annual Carbon Uptake over land. We also examine the efficiency, dependability and resilience of the quantum neural net approach relative to classical computer systems in predicting annual CO2 flux globally.

Optical Neural Classification Of Binary Patterns

NASA Astrophysics Data System (ADS)

Gustafson, Steven C.; Little, Gordon R.

1988-05-01

Binary pattern classification that may be implemented using optical hardware and neural network algorithms is considered. Pattern classification problems that have no concise description (as in classifying handwritten characters) or no concise computation (as in NP-complete problems) are expected to be particularly amenable to this approach. For example, optical processors that efficiently classify binary patterns in accordance with their Boolean function complexity might be designed. As a candidate for such a design, an optical neural network model is discussed that is designed for binary pattern classification and that consists of an optical resonator with a dynamic multiplex-recorded reflection hologram and a phase conjugate mirror with thresholding and gain. In this model, learning or training examples of binary patterns may be recorded on the hologram such that one bit in each pattern marks the pattern class. Any input pattern, including one with an unknown class or marker bit, will be modified by a large number of parallel interactions with the reflection hologram and nonlinear mirror. After perhaps several seconds and 100 billion interactions, a steady-state pattern may develop with a marker bit that represents a minimum-Boolean-complexity classification of the input pattern. Computer simulations are presented that illustrate progress in understanding the behavior of this model and in developing a processor design that could have commanding and enduring performance advantages compared to current pattern classification techniques.

A neuron-astrocyte transistor-like model for neuromorphic dressed neurons.

PubMed

Valenza, G; Pioggia, G; Armato, A; Ferro, M; Scilingo, E P; De Rossi, D

2011-09-01

Experimental evidences on the role of the synaptic glia as an active partner together with the bold synapse in neuronal signaling and dynamics of neural tissue strongly suggest to investigate on a more realistic neuron-glia model for better understanding human brain processing. Among the glial cells, the astrocytes play a crucial role in the tripartite synapsis, i.e. the dressed neuron. A well-known two-way astrocyte-neuron interaction can be found in the literature, completely revising the purely supportive role for the glia. The aim of this study is to provide a computationally efficient model for neuron-glia interaction. The neuron-glia interactions were simulated by implementing the Li-Rinzel model for an astrocyte and the Izhikevich model for a neuron. Assuming the dressed neuron dynamics similar to the nonlinear input-output characteristics of a bipolar junction transistor, we derived our computationally efficient model. This model may represent the fundamental computational unit for the development of real-time artificial neuron-glia networks opening new perspectives in pattern recognition systems and in brain neurophysiology. Copyright © 2011 Elsevier Ltd. All rights reserved.

Design and Analysis of a Neuromemristive Reservoir Computing Architecture for Biosignal Processing

PubMed Central

Kudithipudi, Dhireesha; Saleh, Qutaiba; Merkel, Cory; Thesing, James; Wysocki, Bryant

2016-01-01

Reservoir computing (RC) is gaining traction in several signal processing domains, owing to its non-linear stateful computation, spatiotemporal encoding, and reduced training complexity over recurrent neural networks (RNNs). Previous studies have shown the effectiveness of software-based RCs for a wide spectrum of applications. A parallel body of work indicates that realizing RNN architectures using custom integrated circuits and reconfigurable hardware platforms yields significant improvements in power and latency. In this research, we propose a neuromemristive RC architecture, with doubly twisted toroidal structure, that is validated for biosignal processing applications. We exploit the device mismatch to implement the random weight distributions within the reservoir and propose mixed-signal subthreshold circuits for energy efficiency. A comprehensive analysis is performed to compare the efficiency of the neuromemristive RC architecture in both digital(reconfigurable) and subthreshold mixed-signal realizations. Both Electroencephalogram (EEG) and Electromyogram (EMG) biosignal benchmarks are used for validating the RC designs. The proposed RC architecture demonstrated an accuracy of 90 and 84% for epileptic seizure detection and EMG prosthetic finger control, respectively. PMID:26869876

Prediction of the Thermal Conductivity of Refrigerants by Computational Methods and Artificial Neural Network.

PubMed

Ghaderi, Forouzan; Ghaderi, Amir H; Ghaderi, Noushin; Najafi, Bijan

2017-01-01

Background: The thermal conductivity of fluids can be calculated by several computational methods. However, these methods are reliable only at the confined levels of density, and there is no specific computational method for calculating thermal conductivity in the wide ranges of density. Methods: In this paper, two methods, an Artificial Neural Network (ANN) approach and a computational method established upon the Rainwater-Friend theory, were used to predict the value of thermal conductivity in all ranges of density. The thermal conductivity of six refrigerants, R12, R14, R32, R115, R143, and R152 was predicted by these methods and the effectiveness of models was specified and compared. Results: The results show that the computational method is a usable method for predicting thermal conductivity at low levels of density. However, the efficiency of this model is considerably reduced in the mid-range of density. It means that this model cannot be used at density levels which are higher than 6. On the other hand, the ANN approach is a reliable method for thermal conductivity prediction in all ranges of density. The best accuracy of ANN is achieved when the number of units is increased in the hidden layer. Conclusion: The results of the computational method indicate that the regular dependence between thermal conductivity and density at higher densities is eliminated. It can develop a nonlinear problem. Therefore, analytical approaches are not able to predict thermal conductivity in wide ranges of density. Instead, a nonlinear approach such as, ANN is a valuable method for this purpose.

Prediction of the Thermal Conductivity of Refrigerants by Computational Methods and Artificial Neural Network

PubMed Central

Ghaderi, Forouzan; Ghaderi, Amir H.; Ghaderi, Noushin; Najafi, Bijan

2017-01-01

Background: The thermal conductivity of fluids can be calculated by several computational methods. However, these methods are reliable only at the confined levels of density, and there is no specific computational method for calculating thermal conductivity in the wide ranges of density. Methods: In this paper, two methods, an Artificial Neural Network (ANN) approach and a computational method established upon the Rainwater-Friend theory, were used to predict the value of thermal conductivity in all ranges of density. The thermal conductivity of six refrigerants, R12, R14, R32, R115, R143, and R152 was predicted by these methods and the effectiveness of models was specified and compared. Results: The results show that the computational method is a usable method for predicting thermal conductivity at low levels of density. However, the efficiency of this model is considerably reduced in the mid-range of density. It means that this model cannot be used at density levels which are higher than 6. On the other hand, the ANN approach is a reliable method for thermal conductivity prediction in all ranges of density. The best accuracy of ANN is achieved when the number of units is increased in the hidden layer. Conclusion: The results of the computational method indicate that the regular dependence between thermal conductivity and density at higher densities is eliminated. It can develop a nonlinear problem. Therefore, analytical approaches are not able to predict thermal conductivity in wide ranges of density. Instead, a nonlinear approach such as, ANN is a valuable method for this purpose. PMID:29188217

Representation of Muscle Synergies in the Primate Brain.

PubMed

Overduin, Simon A; d'Avella, Andrea; Roh, Jinsook; Carmena, Jose M; Bizzi, Emilio

2015-09-16

Evidence suggests that the CNS uses motor primitives to simplify movement control, but whether it actually stores primitives instead of computing solutions on the fly to satisfy task demands is a controversial and still-unanswered possibility. Also in contention is whether these primitives take the form of time-invariant muscle coactivations ("spatial" synergies) or time-varying muscle commands ("spatiotemporal" synergies). Here, we examined forelimb muscle patterns and motor cortical spiking data in rhesus macaques (Macaca mulatta) handling objects of variable shape and size. From these data, we extracted both spatiotemporal and spatial synergies using non-negative decomposition. Each spatiotemporal synergy represents a sequence of muscular or neural activations that appeared to recur frequently during the animals' behavior. Key features of the spatiotemporal synergies (including their dimensionality, timing, and amplitude modulation) were independently observed in the muscular and neural data. In addition, both at the muscular and neural levels, these spatiotemporal synergies could be readily reconstructed as sequential activations of spatial synergies (a subset of those extracted independently from the task data), suggestive of a hierarchical relationship between the two levels of synergies. The possibility that motor cortex may execute even complex skill using spatiotemporal synergies has novel implications for the design of neuroprosthetic devices, which could gain computational efficiency by adopting the discrete and low-dimensional control that these primitives imply. We studied the motor cortical and forearm muscular activity of rhesus macaques (Macaca mulatta) as they reached, grasped, and carried objects of varied shape and size. We applied non-negative matrix factorization separately to the cortical and muscular data to reduce their dimensionality to a smaller set of time-varying "spatiotemporal" synergies. Each synergy represents a sequence of cortical or muscular activity that recurred frequently during the animals' behavior. Salient features of the synergies (including their dimensionality, timing, and amplitude modulation) were observed at both the cortical and muscular levels. The possibility that the brain may execute even complex behaviors using spatiotemporal synergies has implications for neuroprosthetic algorithm design, which could become more computationally efficient by adopting the discrete and low-dimensional control that they afford. Copyright © 2015 the authors 0270-6474/15/3512615-10$15.00/0.

The Brian Simulator

PubMed Central

Goodman, Dan F. M.; Brette, Romain

2009-01-01

“Brian” is a simulator for spiking neural networks (http://www.briansimulator.org). The focus is on making the writing of simulation code as quick and easy as possible for the user, and on flexibility: new and non-standard models are no more difficult to define than standard ones. This allows scientists to spend more time on the details of their models, and less on their implementation. Neuron models are defined by writing differential equations in standard mathematical notation, facilitating scientific communication. Brian is written in the Python programming language, and uses vector-based computation to allow for efficient simulations. It is particularly useful for neuroscientific modelling at the systems level, and for teaching computational neuroscience. PMID:20011141

Neural-Network Computer Transforms Coordinates

NASA Technical Reports Server (NTRS)

Josin, Gary M.

1990-01-01

Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.

Artificial Neuron Based on Integrated Semiconductor Quantum Dot Mode-Locked Lasers

NASA Astrophysics Data System (ADS)

Mesaritakis, Charis; Kapsalis, Alexandros; Bogris, Adonis; Syvridis, Dimitris

2016-12-01

Neuro-inspired implementations have attracted strong interest as a power efficient and robust alternative to the digital model of computation with a broad range of applications. Especially, neuro-mimetic systems able to produce and process spike-encoding schemes can offer merits like high noise-resiliency and increased computational efficiency. Towards this direction, integrated photonics can be an auspicious platform due to its multi-GHz bandwidth, its high wall-plug efficiency and the strong similarity of its dynamics under excitation with biological spiking neurons. Here, we propose an integrated all-optical neuron based on an InAs/InGaAs semiconductor quantum-dot passively mode-locked laser. The multi-band emission capabilities of these lasers allows, through waveband switching, the emulation of the excitation and inhibition modes of operation. Frequency-response effects, similar to biological neural circuits, are observed just as in a typical two-section excitable laser. The demonstrated optical building block can pave the way for high-speed photonic integrated systems able to address tasks ranging from pattern recognition to cognitive spectrum management and multi-sensory data processing.

Artificial Neuron Based on Integrated Semiconductor Quantum Dot Mode-Locked Lasers

PubMed Central

Mesaritakis, Charis; Kapsalis, Alexandros; Bogris, Adonis; Syvridis, Dimitris

2016-01-01

Neuro-inspired implementations have attracted strong interest as a power efficient and robust alternative to the digital model of computation with a broad range of applications. Especially, neuro-mimetic systems able to produce and process spike-encoding schemes can offer merits like high noise-resiliency and increased computational efficiency. Towards this direction, integrated photonics can be an auspicious platform due to its multi-GHz bandwidth, its high wall-plug efficiency and the strong similarity of its dynamics under excitation with biological spiking neurons. Here, we propose an integrated all-optical neuron based on an InAs/InGaAs semiconductor quantum-dot passively mode-locked laser. The multi-band emission capabilities of these lasers allows, through waveband switching, the emulation of the excitation and inhibition modes of operation. Frequency-response effects, similar to biological neural circuits, are observed just as in a typical two-section excitable laser. The demonstrated optical building block can pave the way for high-speed photonic integrated systems able to address tasks ranging from pattern recognition to cognitive spectrum management and multi-sensory data processing. PMID:27991574

Sex differences in neural efficiency: Are they due to the stereotype threat effect?☆

PubMed Central

Dunst, Beate; Benedek, Mathias; Bergner, Sabine; Athenstaedt, Ursula; Neubauer, Aljoscha C.

2013-01-01

The neural efficiency hypothesis postulates a more efficient use of brain resources in more intelligent people as compared to less intelligent ones. However, this relationship was found to be moderated by sex and task content. While the phenomenon of neural efficiency was previously supported for men when performing visuo-spatial tasks it occurred for women only when performing verbal tasks. One possible explanation for this finding could be provided by the well-studied phenomenon called stereotype threat. Stereotype threat arises when a negative stereotype of one’s own group is made salient and can result in behavior that confirms the stereotype. Overall, 32 boys and 31 girls of varying intellectual ability were tested with a mental rotation task, either under a stereotype exposure or a no-stereotype exposure condition while measuring their EEG. The behavioral results show that an activated negative stereotype not necessarily hampers the performance of girls. Physiologically, a confirmation of the neural efficiency phenomenon was only obtained for boys working under a no-stereotype exposure condition. This result pattern replicates previous findings without threat and thus suggests that sex differences in neural efficiency during visuo-spatial tasks may not be due to the stereotype threat effect. PMID:24092950

Hardware Acceleration of Adaptive Neural Algorithms.

DOE Office of Scientific and Technical Information (OSTI.GOV)

James, Conrad D.

As tradit ional numerical computing has faced challenges, researchers have turned towards alternative computing approaches to reduce power - per - computation metrics and improve algorithm performance. Here, we describe an approach towards non - conventional computing that strengthens the connection between machine learning and neuroscience concepts. The Hardware Acceleration of Adaptive Neural Algorithms (HAANA) project ha s develop ed neural machine learning algorithms and hardware for applications in image processing and cybersecurity. While machine learning methods are effective at extracting relevant features from many types of data, the effectiveness of these algorithms degrades when subjected to real - worldmore » conditions. Our team has generated novel neural - inspired approa ches to improve the resiliency and adaptability of machine learning algorithms. In addition, we have also designed and fabricated hardware architectures and microelectronic devices specifically tuned towards the training and inference operations of neural - inspired algorithms. Finally, our multi - scale simulation framework allows us to assess the impact of microelectronic device properties on algorithm performance.« less

Solving Constraint Satisfaction Problems with Networks of Spiking Neurons

PubMed Central

Jonke, Zeno; Habenschuss, Stefan; Maass, Wolfgang

2016-01-01

Network of neurons in the brain apply—unlike processors in our current generation of computer hardware—an event-based processing strategy, where short pulses (spikes) are emitted sparsely by neurons to signal the occurrence of an event at a particular point in time. Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes. However, it turns out to be surprisingly difficult to design networks of spiking neurons that can solve difficult computational problems on the level of single spikes, rather than rates of spikes. We present here a new method for designing networks of spiking neurons via an energy function. Furthermore, we show how the energy function of a network of stochastically firing neurons can be shaped in a transparent manner by composing the networks of simple stereotypical network motifs. We show that this design approach enables networks of spiking neurons to produce approximate solutions to difficult (NP-hard) constraint satisfaction problems from the domains of planning/optimization and verification/logical inference. The resulting networks employ noise as a computational resource. Nevertheless, the timing of spikes plays an essential role in their computations. Furthermore, networks of spiking neurons carry out for the Traveling Salesman Problem a more efficient stochastic search for good solutions compared with stochastic artificial neural networks (Boltzmann machines) and Gibbs sampling. PMID:27065785

Efficiency turns the table on neural encoding, decoding and noise.

PubMed

Deneve, Sophie; Chalk, Matthew

2016-04-01

Sensory neurons are usually described with an encoding model, for example, a function that predicts their response from the sensory stimulus using a receptive field (RF) or a tuning curve. However, central to theories of sensory processing is the notion of 'efficient coding'. We argue here that efficient coding implies a completely different neural coding strategy. Instead of a fixed encoding model, neural populations would be described by a fixed decoding model (i.e. a model reconstructing the stimulus from the neural responses). Because the population solves a global optimization problem, individual neurons are variable, but not noisy, and have no truly invariant tuning curve or receptive field. We review recent experimental evidence and implications for neural noise correlations, robustness and adaptation. Copyright © 2016. Published by Elsevier Ltd.

Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets.

PubMed

Hu, Peijun; Wu, Fa; Peng, Jialin; Bao, Yuanyuan; Chen, Feng; Kong, Dexing

2017-03-01

Multi-organ segmentation from CT images is an essential step for computer-aided diagnosis and surgery planning. However, manual delineation of the organs by radiologists is tedious, time-consuming and poorly reproducible. Therefore, we propose a fully automatic method for the segmentation of multiple organs from three-dimensional abdominal CT images. The proposed method employs deep fully convolutional neural networks (CNNs) for organ detection and segmentation, which is further refined by a time-implicit multi-phase evolution method. Firstly, a 3D CNN is trained to automatically localize and delineate the organs of interest with a probability prediction map. The learned probability map provides both subject-specific spatial priors and initialization for subsequent fine segmentation. Then, for the refinement of the multi-organ segmentation, image intensity models, probability priors as well as a disjoint region constraint are incorporated into an unified energy functional. Finally, a novel time-implicit multi-phase level-set algorithm is utilized to efficiently optimize the proposed energy functional model. Our method has been evaluated on 140 abdominal CT scans for the segmentation of four organs (liver, spleen and both kidneys). With respect to the ground truth, average Dice overlap ratios for the liver, spleen and both kidneys are 96.0, 94.2 and 95.4%, respectively, and average symmetric surface distance is less than 1.3 mm for all the segmented organs. The computation time for a CT volume is 125 s in average. The achieved accuracy compares well to state-of-the-art methods with much higher efficiency. A fully automatic method for multi-organ segmentation from abdominal CT images was developed and evaluated. The results demonstrated its potential in clinical usage with high effectiveness, robustness and efficiency.

Natural language acquisition in large scale neural semantic networks

NASA Astrophysics Data System (ADS)

Ealey, Douglas

This thesis puts forward the view that a purely signal- based approach to natural language processing is both plausible and desirable. By questioning the veracity of symbolic representations of meaning, it argues for a unified, non-symbolic model of knowledge representation that is both biologically plausible and, potentially, highly efficient. Processes to generate a grounded, neural form of this model-dubbed the semantic filter-are discussed. The combined effects of local neural organisation, coincident with perceptual maturation, are used to hypothesise its nature. This theoretical model is then validated in light of a number of fundamental neurological constraints and milestones. The mechanisms of semantic and episodic development that the model predicts are then used to explain linguistic properties, such as propositions and verbs, syntax and scripting. To mimic the growth of locally densely connected structures upon an unbounded neural substrate, a system is developed that can grow arbitrarily large, data- dependant structures composed of individual self- organising neural networks. The maturational nature of the data used results in a structure in which the perception of concepts is refined by the networks, but demarcated by subsequent structure. As a consequence, the overall structure shows significant memory and computational benefits, as predicted by the cognitive and neural models. Furthermore, the localised nature of the neural architecture also avoids the increasing error sensitivity and redundancy of traditional systems as the training domain grows. The semantic and episodic filters have been demonstrated to perform as well, or better, than more specialist networks, whilst using significantly larger vocabularies, more complex sentence forms and more natural corpora.

Streamflow Forecasting Using Nuero-Fuzzy Inference System

NASA Astrophysics Data System (ADS)

Nanduri, U. V.; Swain, P. C.

2005-12-01

The prediction of flow into a reservoir is fundamental in water resources planning and management. The need for timely and accurate streamflow forecasting is widely recognized and emphasized by many in water resources fraternity. Real-time forecasts of natural inflows to reservoirs are of particular interest for operation and scheduling. The physical system of the river basin that takes the rainfall as an input and produces the runoff is highly nonlinear, complicated and very difficult to fully comprehend. The system is influenced by large number of factors and variables. The large spatial extent of the systems forces the uncertainty into the hydrologic information. A variety of methods have been proposed for forecasting reservoir inflows including conceptual (physical) and empirical (statistical) models (WMO 1994), but none of them can be considered as unique superior model (Shamseldin 1997). Owing to difficulties of formulating reasonable non-linear watershed models, recent attempts have resorted to Neural Network (NN) approach for complex hydrologic modeling. In recent years the use of soft computing in the field of hydrological forecasting is gaining ground. The relatively new soft computing technique of Adaptive Neuro-Fuzzy Inference System (ANFIS), developed by Jang (1993) is able to take care of the non-linearity, uncertainty, and vagueness embedded in the system. It is a judicious combination of the Neural Networks and fuzzy systems. It can learn and generalize highly nonlinear and uncertain phenomena due to the embedded neural network (NN). NN is efficient in learning and generalization, and the fuzzy system mimics the cognitive capability of human brain. Hence, ANFIS can learn the complicated processes involved in the basin and correlate the precipitation to the corresponding discharge. In the present study, one step ahead forecasts are made for ten-daily flows, which are mostly required for short term operational planning of multipurpose reservoirs. A Neuro-Fuzzy model is developed to forecast ten-daily flows into the Hirakud reservoir on River Mahanadi in the state of Orissa in India. Correlation analysis is carried out to find out the most influential variables on the ten daily flow at Hirakud. Based on this analysis, four variables, namely, flow during the previous time period, ql1, rainfall during the previous two time periods, rl1 and rl2, and flow during the same period in previous year, qpy, are identified as the most influential variables to forecast the ten daily flow. Performance measures such as Root Mean Square Error (RMSE), Correlation Coefficient (CORR) and coefficient of efficiency R2 are computed for training and testing phases of the model to evaluate its performance. The results indicate that the ten-daily forecasting model is efficient in predicting the high and medium flows with reasonable accuracy. The forecast of low flows is associated with less efficiency. REFERENCES Jang, J.S.R. (1993). "ANFIS: Adaptive - network- based fuzzy inference system." IEEE Trans. on Systems, Man and Cybernetics, 23 (3), 665-685. Shamseldin, A.Y. (1997). "Application of a neural network technique to rainfall-runoff modeling." Journal of Hydrology, 199, 272-294. World Meteorological Organization (1975). Intercomparison of conceptual models used in operational hydrological forecasting. World Meteorological Organization, Technical Report No.429, Geneva, Switzerland.

Generation of H1 PAX6WT/EGFP reporter cells to purify PAX6 positive neural stem/progenitor cells.

PubMed

Wu, Wei; Liu, Juli; Su, Zhenghui; Li, Zhonghao; Ma, Ning; Huang, Ke; Zhou, Tiancheng; Wang, Linli

2018-08-25

Neural conversion from human pluripotent cells (hPSCs) is a potential therapy to neurological disease in the future. However, this is still limited by efficiency and stability of existed protocols used for neural induction from hPSCs. To overcome this obstacle, we developed a reporter system to screen PAX6 + neural progenitor/stem cells using transcription activator like effector nuclease (TALEN). We found that knock-in 2 A-EGFP cassette into PAX6 exon of human embryonic stem cells H1 with TALEN-based homology recombination could establish PAX6 WT/EGFP H1 reporter cell line fast and efficiently. This reporter cell line could differentiate into PAX6 and EGFP double positive neural progenitor/stem cells (NPCs/NSCs) after neural induction. Those PAX6 WT/EGFP NPCs could be purified, expanded and specified to post-mitotic neurons in vitro efficiently. With this reporter cell line, we also screened out 1 NPC-specific microRNA, hsa-miR-99a-5p, and 3 ESCs-enriched miRNAs, hsa-miR-302c-5p, hsa-miR-512-3p and hsa-miR-518 b. In conclusion, the TALEN-based neural stem cell screening system is safe and efficient and could help researcher to acquire adequate and pure neural progenitor cells for further application. Copyright © 2018 Elsevier Inc. All rights reserved.

Automated selection of computed tomography display parameters using neural networks

NASA Astrophysics Data System (ADS)

Zhang, Di; Neu, Scott; Valentino, Daniel J.

2001-07-01

A collection of artificial neural networks (ANN's) was trained to identify simple anatomical structures in a set of x-ray computed tomography (CT) images. These neural networks learned to associate a point in an image with the anatomical structure containing the point by using the image pixels located on the horizontal and vertical lines that ran through the point. The neural networks were integrated into a computer software tool whose function is to select an index into a list of CT window/level values from the location of the user's mouse cursor. Based upon the anatomical structure selected by the user, the software tool automatically adjusts the image display to optimally view the structure.

Normalization as a canonical neural computation

PubMed Central

Carandini, Matteo; Heeger, David J.

2012-01-01

There is increasing evidence that the brain relies on a set of canonical neural computations, repeating them across brain regions and modalities to apply similar operations to different problems. A promising candidate for such a computation is normalization, in which the responses of neurons are divided by a common factor that typically includes the summed activity of a pool of neurons. Normalization was developed to explain responses in the primary visual cortex and is now thought to operate throughout the visual system, and in many other sensory modalities and brain regions. Normalization may underlie operations such as the representation of odours, the modulatory effects of visual attention, the encoding of value and the integration of multisensory information. Its presence in such a diversity of neural systems in multiple species, from invertebrates to mammals, suggests that it serves as a canonical neural computation. PMID:22108672

Random noise effects in pulse-mode digital multilayer neural networks.

PubMed

Kim, Y C; Shanblatt, M A

1995-01-01

A pulse-mode digital multilayer neural network (DMNN) based on stochastic computing techniques is implemented with simple logic gates as basic computing elements. The pulse-mode signal representation and the use of simple logic gates for neural operations lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Algebraic neural operations are replaced by stochastic processes using pseudorandom pulse sequences. The distributions of the results from the stochastic processes are approximated using the hypergeometric distribution. Synaptic weights and neuron states are represented as probabilities and estimated as average pulse occurrence rates in corresponding pulse sequences. A statistical model of the noise (error) is developed to estimate the relative accuracy associated with stochastic computing in terms of mean and variance. Computational differences are then explained by comparison to deterministic neural computations. DMNN feedforward architectures are modeled in VHDL using character recognition problems as testbeds. Computational accuracy is analyzed, and the results of the statistical model are compared with the actual simulation results. Experiments show that the calculations performed in the DMNN are more accurate than those anticipated when Bernoulli sequences are assumed, as is common in the literature. Furthermore, the statistical model successfully predicts the accuracy of the operations performed in the DMNN.

The super-Turing computational power of plastic recurrent neural networks.

PubMed

Cabessa, Jérémie; Siegelmann, Hava T

2014-12-01

We study the computational capabilities of a biologically inspired neural model where the synaptic weights, the connectivity pattern, and the number of neurons can evolve over time rather than stay static. Our study focuses on the mere concept of plasticity of the model so that the nature of the updates is assumed to be not constrained. In this context, we show that the so-called plastic recurrent neural networks (RNNs) are capable of the precise super-Turing computational power--as the static analog neural networks--irrespective of whether their synaptic weights are modeled by rational or real numbers, and moreover, irrespective of whether their patterns of plasticity are restricted to bi-valued updates or expressed by any other more general form of updating. Consequently, the incorporation of only bi-valued plastic capabilities in a basic model of RNNs suffices to break the Turing barrier and achieve the super-Turing level of computation. The consideration of more general mechanisms of architectural plasticity or of real synaptic weights does not further increase the capabilities of the networks. These results support the claim that the general mechanism of plasticity is crucially involved in the computational and dynamical capabilities of biological neural networks. They further show that the super-Turing level of computation reflects in a suitable way the capabilities of brain-like models of computation.

A dual estimate method for aeromagnetic compensation

NASA Astrophysics Data System (ADS)

Ma, Ming; Zhou, Zhijian; Cheng, Defu

2017-11-01

Scalar aeromagnetic surveys have played a vital role in prospecting. However, before analysis of the surveys’ aeromagnetic data is possible, the aircraft’s magnetic interference should be removed. The extensively adopted linear model for aeromagnetic compensation is computationally efficient but faces an underfitting problem. On the other hand, the neural model proposed by Williams is more powerful at fitting but always suffers from an overfitting problem. This paper starts off with an analysis of these two models and then proposes a dual estimate method to combine them together to improve accuracy. This method is based on an unscented Kalman filter, but a gradient descent method is implemented over the iteration so that the parameters of the linear model are adjustable during flight. The noise caused by the neural model’s overfitting problem is suppressed by introducing an observation noise.

Egg production forecasting: Determining efficient modeling approaches.

PubMed

Ahmad, H A

2011-12-01

Several mathematical or statistical and artificial intelligence models were developed to compare egg production forecasts in commercial layers. Initial data for these models were collected from a comparative layer trial on commercial strains conducted at the Poultry Research Farms, Auburn University. Simulated data were produced to represent new scenarios by using means and SD of egg production of the 22 commercial strains. From the simulated data, random examples were generated for neural network training and testing for the weekly egg production prediction from wk 22 to 36. Three neural network architectures-back-propagation-3, Ward-5, and the general regression neural network-were compared for their efficiency to forecast egg production, along with other traditional models. The general regression neural network gave the best-fitting line, which almost overlapped with the commercial egg production data, with an R(2) of 0.71. The general regression neural network-predicted curve was compared with original egg production data, the average curves of white-shelled and brown-shelled strains, linear regression predictions, and the Gompertz nonlinear model. The general regression neural network was superior in all these comparisons and may be the model of choice if the initial overprediction is managed efficiently. In general, neural network models are efficient, are easy to use, require fewer data, and are practical under farm management conditions to forecast egg production.

Evolution of a designless nanoparticle network into reconfigurable Boolean logic

NASA Astrophysics Data System (ADS)

Bose, S. K.; Lawrence, C. P.; Liu, Z.; Makarenko, K. S.; van Damme, R. M. J.; Broersma, H. J.; van der Wiel, W. G.

2015-12-01

Natural computers exploit the emergent properties and massive parallelism of interconnected networks of locally active components. Evolution has resulted in systems that compute quickly and that use energy efficiently, utilizing whatever physical properties are exploitable. Man-made computers, on the other hand, are based on circuits of functional units that follow given design rules. Hence, potentially exploitable physical processes, such as capacitive crosstalk, to solve a problem are left out. Until now, designless nanoscale networks of inanimate matter that exhibit robust computational functionality had not been realized. Here we artificially evolve the electrical properties of a disordered nanomaterials system (by optimizing the values of control voltages using a genetic algorithm) to perform computational tasks reconfigurably. We exploit the rich behaviour that emerges from interconnected metal nanoparticles, which act as strongly nonlinear single-electron transistors, and find that this nanoscale architecture can be configured in situ into any Boolean logic gate. This universal, reconfigurable gate would require about ten transistors in a conventional circuit. Our system meets the criteria for the physical realization of (cellular) neural networks: universality (arbitrary Boolean functions), compactness, robustness and evolvability, which implies scalability to perform more advanced tasks. Our evolutionary approach works around device-to-device variations and the accompanying uncertainties in performance. Moreover, it bears a great potential for more energy-efficient computation, and for solving problems that are very hard to tackle in conventional architectures.

Application of artificial neural networks to chemostratigraphy

NASA Astrophysics Data System (ADS)

Malmgren, BjöRn A.; Nordlund, Ulf

1996-08-01

Artificial neural networks, a branch of artificial intelligence, are computer systems formed by a number of simple, highly interconnected processing units that have the ability to learn a set of target vectors from a set of associated input signals. Neural networks learn by self-adjusting a set of parameters, using some pertinent algorithm to minimize the error between the desired output and network output. We explore the potential of this approach in solving a problem involving classification of geochemical data. The data, taken from the literature, are derived from four late Quaternary zones of volcanic ash of basaltic and rhyolithic origin from the Norwegian Sea. These ash layers span the oxygen isotope zones 1, 5, 7, and 11, respectively (last 420,000 years). The data consist of nine geochemical variables (oxides) determined in each of 183 samples. We employed a three-layer back propagation neural network to assess its efficiency to optimally differentiate samples from the four ash zones on the basis of their geochemical composition. For comparison, three statistical pattern recognition techniques, linear discriminant analysis, the k-nearest neighbor (k-NN) technique, and SIMCA (soft independent modeling of class analogy), were applied to the same data. All of these showed considerably higher error rates than the artificial neural network, indicating that the back propagation network was indeed more powerful in correctly classifying the ash particles to the appropriate zone on the basis of their geochemical composition.

Neural network face recognition using wavelets

NASA Astrophysics Data System (ADS)

Karunaratne, Passant V.; Jouny, Ismail I.

1997-04-01

The recognition of human faces is a phenomenon that has been mastered by the human visual system and that has been researched extensively in the domain of computer neural networks and image processing. This research is involved in the study of neural networks and wavelet image processing techniques in the application of human face recognition. The objective of the system is to acquire a digitized still image of a human face, carry out pre-processing on the image as required, an then, given a prior database of images of possible individuals, be able to recognize the individual in the image. The pre-processing segment of the system includes several procedures, namely image compression, denoising, and feature extraction. The image processing is carried out using Daubechies wavelets. Once the images have been passed through the wavelet-based image processor they can be efficiently analyzed by means of a neural network. A back- propagation neural network is used for the recognition segment of the system. The main constraints of the system is with regard to the characteristics of the images being processed. The system should be able to carry out effective recognition of the human faces irrespective of the individual's facial-expression, presence of extraneous objects such as head-gear or spectacles, and face/head orientation. A potential application of this face recognition system would be as a secondary verification method in an automated teller machine.

Neural network approach to proximity effect corrections in electron-beam lithography

NASA Astrophysics Data System (ADS)

Frye, Robert C.; Cummings, Kevin D.; Rietman, Edward A.

1990-05-01

The proximity effect, caused by electron beam backscattering during resist exposure, is an important concern in writing submicron features. It can be compensated by appropriate local changes in the incident beam dose, but computation of the optimal correction usually requires a prohibitively long time. We present an example of such a computation on a small test pattern, which we performed by an iterative method. We then used this solution as a training set for an adaptive neural network. After training, the network computed the same correction as the iterative method, but in a much shorter time. Correcting the image with a software based neural network resulted in a decrease in the computation time by a factor of 30, and a hardware based network enhanced the computation speed by more than a factor of 1000. Both methods had an acceptably small error of 0.5% compared to the results of the iterative computation. Additionally, we verified that the neural network correctly generalized the solution of the problem to include patterns not contained in its training set.

Neural networks for calibration tomography

NASA Technical Reports Server (NTRS)

Decker, Arthur

1993-01-01

Artificial neural networks are suitable for performing pattern-to-pattern calibrations. These calibrations are potentially useful for facilities operations in aeronautics, the control of optical alignment, and the like. Computed tomography is compared with neural net calibration tomography for estimating density from its x-ray transform. X-ray transforms are measured, for example, in diffuse-illumination, holographic interferometry of fluids. Computed tomography and neural net calibration tomography are shown to have comparable performance for a 10 degree viewing cone and 29 interferograms within that cone. The system of tomography discussed is proposed as a relevant test of neural networks and other parallel processors intended for using flow visualization data.

Simulator for neural networks and action potentials.

PubMed

Baxter, Douglas A; Byrne, John H

2007-01-01

A key challenge for neuroinformatics is to devise methods for representing, accessing, and integrating vast amounts of diverse and complex data. A useful approach to represent and integrate complex data sets is to develop mathematical models [Arbib (The Handbook of Brain Theory and Neural Networks, pp. 741-745, 2003); Arbib and Grethe (Computing the Brain: A Guide to Neuroinformatics, 2001); Ascoli (Computational Neuroanatomy: Principles and Methods, 2002); Bower and Bolouri (Computational Modeling of Genetic and Biochemical Networks, 2001); Hines et al. (J. Comput. Neurosci. 17, 7-11, 2004); Shepherd et al. (Trends Neurosci. 21, 460-468, 1998); Sivakumaran et al. (Bioinformatics 19, 408-415, 2003); Smolen et al. (Neuron 26, 567-580, 2000); Vadigepalli et al. (OMICS 7, 235-252, 2003)]. Models of neural systems provide quantitative and modifiable frameworks for representing data and analyzing neural function. These models can be developed and solved using neurosimulators. One such neurosimulator is simulator for neural networks and action potentials (SNNAP) [Ziv (J. Neurophysiol. 71, 294-308, 1994)]. SNNAP is a versatile and user-friendly tool for developing and simulating models of neurons and neural networks. SNNAP simulates many features of neuronal function, including ionic currents and their modulation by intracellular ions and/or second messengers, and synaptic transmission and synaptic plasticity. SNNAP is written in Java and runs on most computers. Moreover, SNNAP provides a graphical user interface (GUI) and does not require programming skills. This chapter describes several capabilities of SNNAP and illustrates methods for simulating neurons and neural networks. SNNAP is available at http://snnap.uth.tmc.edu .

Unsupervised discrimination of patterns in spiking neural networks with excitatory and inhibitory synaptic plasticity

PubMed Central

Srinivasa, Narayan; Cho, Youngkwan

2014-01-01

A spiking neural network model is described for learning to discriminate among spatial patterns in an unsupervised manner. The network anatomy consists of source neurons that are activated by external inputs, a reservoir that resembles a generic cortical layer with an excitatory-inhibitory (EI) network and a sink layer of neurons for readout. Synaptic plasticity in the form of STDP is imposed on all the excitatory and inhibitory synapses at all times. While long-term excitatory STDP enables sparse and efficient learning of the salient features in inputs, inhibitory STDP enables this learning to be stable by establishing a balance between excitatory and inhibitory currents at each neuron in the network. The synaptic weights between source and reservoir neurons form a basis set for the input patterns. The neural trajectories generated in the reservoir due to input stimulation and lateral connections between reservoir neurons can be readout by the sink layer neurons. This activity is used for adaptation of synapses between reservoir and sink layer neurons. A new measure called the discriminability index (DI) is introduced to compute if the network can discriminate between old patterns already presented in an initial training session. The DI is also used to compute if the network adapts to new patterns without losing its ability to discriminate among old patterns. The final outcome is that the network is able to correctly discriminate between all patterns—both old and new. This result holds as long as inhibitory synapses employ STDP to continuously enable current balance in the network. The results suggest a possible direction for future investigation into how spiking neural networks could address the stability-plasticity question despite having continuous synaptic plasticity. PMID:25566045

Unsupervised discrimination of patterns in spiking neural networks with excitatory and inhibitory synaptic plasticity.

PubMed

Srinivasa, Narayan; Cho, Youngkwan

2014-01-01

A spiking neural network model is described for learning to discriminate among spatial patterns in an unsupervised manner. The network anatomy consists of source neurons that are activated by external inputs, a reservoir that resembles a generic cortical layer with an excitatory-inhibitory (EI) network and a sink layer of neurons for readout. Synaptic plasticity in the form of STDP is imposed on all the excitatory and inhibitory synapses at all times. While long-term excitatory STDP enables sparse and efficient learning of the salient features in inputs, inhibitory STDP enables this learning to be stable by establishing a balance between excitatory and inhibitory currents at each neuron in the network. The synaptic weights between source and reservoir neurons form a basis set for the input patterns. The neural trajectories generated in the reservoir due to input stimulation and lateral connections between reservoir neurons can be readout by the sink layer neurons. This activity is used for adaptation of synapses between reservoir and sink layer neurons. A new measure called the discriminability index (DI) is introduced to compute if the network can discriminate between old patterns already presented in an initial training session. The DI is also used to compute if the network adapts to new patterns without losing its ability to discriminate among old patterns. The final outcome is that the network is able to correctly discriminate between all patterns-both old and new. This result holds as long as inhibitory synapses employ STDP to continuously enable current balance in the network. The results suggest a possible direction for future investigation into how spiking neural networks could address the stability-plasticity question despite having continuous synaptic plasticity.

A novel constructive-optimizer neural network for the traveling salesman problem.

PubMed

Saadatmand-Tarzjan, Mahdi; Khademi, Morteza; Akbarzadeh-T, Mohammad-R; Moghaddam, Hamid Abrishami

2007-08-01

In this paper, a novel constructive-optimizer neural network (CONN) is proposed for the traveling salesman problem (TSP). CONN uses a feedback structure similar to Hopfield-type neural networks and a competitive training algorithm similar to the Kohonen-type self-organizing maps (K-SOMs). Consequently, CONN is composed of a constructive part, which grows the tour and an optimizer part to optimize it. In the training algorithm, an initial tour is created first and introduced to CONN. Then, it is trained in the constructive phase for adding a number of cities to the tour. Next, the training algorithm switches to the optimizer phase for optimizing the current tour by displacing the tour cities. After convergence in this phase, the training algorithm switches to the constructive phase anew and is continued until all cities are added to the tour. Furthermore, we investigate a relationship between the number of TSP cities and the number of cities to be added in each constructive phase. CONN was tested on nine sets of benchmark TSPs from TSPLIB to demonstrate its performance and efficiency. It performed better than several typical Neural networks (NNs), including KNIES_TSP_Local, KNIES_TSP_Global, Budinich's SOM, Co-Adaptive Net, and multivalued Hopfield network as wall as computationally comparable variants of the simulated annealing algorithm, in terms of both CPU time and accuracy. Furthermore, CONN converged considerably faster than expanding SOM and evolved integrated SOM and generated shorter tours compared to KNIES_DECOMPOSE. Although CONN is not yet comparable in terms of accuracy with some sophisticated computationally intensive algorithms, it converges significantly faster than they do. Generally speaking, CONN provides the best compromise between CPU time and accuracy among currently reported NNs for TSP.

Nondestructive pavement evaluation using ILLI-PAVE based artificial neural network models.

DOT National Transportation Integrated Search

2008-09-01

The overall objective in this research project is to develop advanced pavement structural analysis models for more accurate solutions with fast computation schemes. Soft computing and modeling approaches, specifically the Artificial Neural Network (A...

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems

PubMed Central

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-01

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems. PMID:28079187

Neural Network Model For Fast Learning And Retrieval

NASA Astrophysics Data System (ADS)

Arsenault, Henri H.; Macukow, Bohdan

1989-05-01

An approach to learning in a multilayer neural network is presented. The proposed network learns by creating interconnections between the input layer and the intermediate layer. In one of the new storage prescriptions proposed, interconnections are excitatory (positive) only and the weights depend on the stored patterns. In the intermediate layer each mother cell is responsible for one stored pattern. Mutually interconnected neurons in the intermediate layer perform a winner-take-all operation, taking into account correlations between stored vectors. The performance of networks using this interconnection prescription is compared with two previously proposed schemes, one using inhibitory connections at the output and one using all-or-nothing interconnections. The network can be used as a content-addressable memory or as a symbolic substitution system that yields an arbitrarily defined output for any input. The training of a model to perform Boolean logical operations is also described. Computer simulations using the network as an autoassociative content-addressable memory show the model to be efficient. Content-addressable associative memories and neural logic modules can be combined to perform logic operations on highly corrupted data.

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems.

PubMed

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-12

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems.

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems

NASA Astrophysics Data System (ADS)

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-01

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems.

Single-hidden-layer feed-forward quantum neural network based on Grover learning.

PubMed

Liu, Cheng-Yi; Chen, Chein; Chang, Ching-Ter; Shih, Lun-Min

2013-09-01

In this paper, a novel single-hidden-layer feed-forward quantum neural network model is proposed based on some concepts and principles in the quantum theory. By combining the quantum mechanism with the feed-forward neural network, we defined quantum hidden neurons and connected quantum weights, and used them as the fundamental information processing unit in a single-hidden-layer feed-forward neural network. The quantum neurons make a wide range of nonlinear functions serve as the activation functions in the hidden layer of the network, and the Grover searching algorithm outstands the optimal parameter setting iteratively and thus makes very efficient neural network learning possible. The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high efficient training and prospect application in future. Some simulations are taken to investigate the performance of the proposed quantum network and the result show that it can achieve accurate learning. Copyright © 2013 Elsevier Ltd. All rights reserved.

Computational Methods for Tracking, Quantitative Assessment, and Visualization of C. elegans Locomotory Behavior

PubMed Central

Moy, Kyle; Li, Weiyu; Tran, Huu Phuoc; Simonis, Valerie; Story, Evan; Brandon, Christopher; Furst, Jacob; Raicu, Daniela; Kim, Hongkyun

2015-01-01

The nematode Caenorhabditis elegans provides a unique opportunity to interrogate the neural basis of behavior at single neuron resolution. In C. elegans, neural circuits that control behaviors can be formulated based on its complete neural connection map, and easily assessed by applying advanced genetic tools that allow for modulation in the activity of specific neurons. Importantly, C. elegans exhibits several elaborate behaviors that can be empirically quantified and analyzed, thus providing a means to assess the contribution of specific neural circuits to behavioral output. Particularly, locomotory behavior can be recorded and analyzed with computational and mathematical tools. Here, we describe a robust single worm-tracking system, which is based on the open-source Python programming language, and an analysis system, which implements path-related algorithms. Our tracking system was designed to accommodate worms that explore a large area with frequent turns and reversals at high speeds. As a proof of principle, we used our tracker to record the movements of wild-type animals that were freshly removed from abundant bacterial food, and determined how wild-type animals change locomotory behavior over a long period of time. Consistent with previous findings, we observed that wild-type animals show a transition from area-restricted local search to global search over time. Intriguingly, we found that wild-type animals initially exhibit short, random movements interrupted by infrequent long trajectories. This movement pattern often coincides with local/global search behavior, and visually resembles Lévy flight search, a search behavior conserved across species. Our mathematical analysis showed that while most of the animals exhibited Brownian walks, approximately 20% of the animals exhibited Lévy flights, indicating that C. elegans can use Lévy flights for efficient food search. In summary, our tracker and analysis software will help analyze the neural basis of the alteration and transition of C. elegans locomotory behavior in a food-deprived condition. PMID:26713869

Recurrent Neural Network for Computing the Drazin Inverse.

PubMed

Stanimirović, Predrag S; Zivković, Ivan S; Wei, Yimin

2015-11-01

This paper presents a recurrent neural network (RNN) for computing the Drazin inverse of a real matrix in real time. This recurrent neural network (RNN) is composed of n independent parts (subnetworks), where n is the order of the input matrix. These subnetworks can operate concurrently, so parallel and distributed processing can be achieved. In this way, the computational advantages over the existing sequential algorithms can be attained in real-time applications. The RNN defined in this paper is convenient for an implementation in an electronic circuit. The number of neurons in the neural network is the same as the number of elements in the output matrix, which represents the Drazin inverse. The difference between the proposed RNN and the existing ones for the Drazin inverse computation lies in their network architecture and dynamics. The conditions that ensure the stability of the defined RNN as well as its convergence toward the Drazin inverse are considered. In addition, illustrative examples and examples of application to the practical engineering problems are discussed to show the efficacy of the proposed neural network.

Performance analysis and comparison of a minimum interconnections direct storage model with traditional neural bidirectional memories.

PubMed

Bhatti, A Aziz

2009-12-01

This study proposes an efficient and improved model of a direct storage bidirectional memory, improved bidirectional associative memory (IBAM), and emphasises the use of nanotechnology for efficient implementation of such large-scale neural network structures at a considerable lower cost reduced complexity, and less area required for implementation. This memory model directly stores the X and Y associated sets of M bipolar binary vectors in the form of (MxN(x)) and (MxN(y)) memory matrices, requires O(N) or about 30% of interconnections with weight strength ranging between +/-1, and is computationally very efficient as compared to sequential, intraconnected and other bidirectional associative memory (BAM) models of outer-product type that require O(N(2)) complex interconnections with weight strength ranging between +/-M. It is shown that it is functionally equivalent to and possesses all attributes of a BAM of outer-product type, and yet it is simple and robust in structure, very large scale integration (VLSI), optical and nanotechnology realisable, modular and expandable neural network bidirectional associative memory model in which the addition or deletion of a pair of vectors does not require changes in the strength of interconnections of the entire memory matrix. The analysis of retrieval process, signal-to-noise ratio, storage capacity and stability of the proposed model as well as of the traditional BAM has been carried out. Constraints on and characteristics of unipolar and bipolar binaries for improved storage and retrieval are discussed. The simulation results show that it has log(e) N times higher storage capacity, superior performance, faster convergence and retrieval time, when compared to traditional sequential and intraconnected bidirectional memories.

Effect of Heterogeneity on Decorrelation Mechanisms in Spiking Neural Networks: A Neuromorphic-Hardware Study

NASA Astrophysics Data System (ADS)

Pfeil, Thomas; Jordan, Jakob; Tetzlaff, Tom; Grübl, Andreas; Schemmel, Johannes; Diesmann, Markus; Meier, Karlheinz

2016-04-01

High-level brain function, such as memory, classification, or reasoning, can be realized by means of recurrent networks of simplified model neurons. Analog neuromorphic hardware constitutes a fast and energy-efficient substrate for the implementation of such neural computing architectures in technical applications and neuroscientific research. The functional performance of neural networks is often critically dependent on the level of correlations in the neural activity. In finite networks, correlations are typically inevitable due to shared presynaptic input. Recent theoretical studies have shown that inhibitory feedback, abundant in biological neural networks, can actively suppress these shared-input correlations and thereby enable neurons to fire nearly independently. For networks of spiking neurons, the decorrelating effect of inhibitory feedback has so far been explicitly demonstrated only for homogeneous networks of neurons with linear subthreshold dynamics. Theory, however, suggests that the effect is a general phenomenon, present in any system with sufficient inhibitory feedback, irrespective of the details of the network structure or the neuronal and synaptic properties. Here, we investigate the effect of network heterogeneity on correlations in sparse, random networks of inhibitory neurons with nonlinear, conductance-based synapses. Emulations of these networks on the analog neuromorphic-hardware system Spikey allow us to test the efficiency of decorrelation by inhibitory feedback in the presence of hardware-specific heterogeneities. The configurability of the hardware substrate enables us to modulate the extent of heterogeneity in a systematic manner. We selectively study the effects of shared input and recurrent connections on correlations in membrane potentials and spike trains. Our results confirm that shared-input correlations are actively suppressed by inhibitory feedback also in highly heterogeneous networks exhibiting broad, heavy-tailed firing-rate distributions. In line with former studies, cell heterogeneities reduce shared-input correlations. Overall, however, correlations in the recurrent system can increase with the level of heterogeneity as a consequence of diminished effective negative feedback.

Reformulated Neural Network (ReNN): a New Alternative for Data-driven Modelling in Hydrology and Water Resources Engineering

NASA Astrophysics Data System (ADS)

Razavi, S.; Tolson, B.; Burn, D.; Seglenieks, F.

2012-04-01

Reformulated Neural Network (ReNN) has been recently developed as an efficient and more effective alternative to feedforward multi-layer perceptron (MLP) neural networks [Razavi, S., and Tolson, B. A. (2011). "A new formulation for feedforward neural networks." IEEE Transactions on Neural Networks, 22(10), 1588-1598, DOI: 1510.1109/TNN.2011.2163169]. This presentation initially aims to introduce the ReNN to the water resources community and then demonstrates ReNN applications to water resources related problems. ReNN is essentially equivalent to a single-hidden-layer MLP neural network but defined on a new set of network variables which is more effective than the traditional set of network weights and biases. The main features of the new network variables are that they are geometrically interpretable and each variable has a distinct role in forming the network response. ReNN is more efficiently trained as it has a less complex error response surface. In addition to the ReNN training efficiency, the interpretability of the ReNN variables enables the users to monitor and understand the internal behaviour of the network while training. Regularization in the ReNN response can be also directly measured and controlled. This feature improves the generalization ability of the network. The appeal of the ReNN is demonstrated with two ReNN applications to water resources engineering problems. In the first application, the ReNN is used to model the rainfall-runoff relationships in multiple watersheds in the Great Lakes basin located in northeastern North America. Modelling inflows to the Great Lakes are of great importance to the management of the Great Lakes system. Due to the lack of some detailed physical data about existing control structures in many subwatersheds of this huge basin, the data-driven approach to modelling such as the ReNN are required to replace predictions from a physically-based rainfall runoff model. Unlike traditional MLPs, the ReNN does not necessarily require an independent set of data for validation as the ReNN has the capability to control and verify the network degree of regularization. As such, the ReNN can be very beneficial in this case study as the data available in this case study is limited. In the second application, ReNN is fitted on the response function of the SWAT hydrologic model to act as a fast-to-run response surface surrogate (i.e., metamodel) of the original computationally intensive SWAT model. Besides the training efficiency gains, the ReNN applications demonstrate how the ReNN interpretability could help users develop more reliable networks which perform predictably better in terms of generalization.

A universal concept based on cellular neural networks for ultrafast and flexible solving of differential equations.

PubMed

Chedjou, Jean Chamberlain; Kyamakya, Kyandoghere

2015-04-01

This paper develops and validates a comprehensive and universally applicable computational concept for solving nonlinear differential equations (NDEs) through a neurocomputing concept based on cellular neural networks (CNNs). High-precision, stability, convergence, and lowest-possible memory requirements are ensured by the CNN processor architecture. A significant challenge solved in this paper is that all these cited computing features are ensured in all system-states (regular or chaotic ones) and in all bifurcation conditions that may be experienced by NDEs.One particular quintessence of this paper is to develop and demonstrate a solver concept that shows and ensures that CNN processors (realized either in hardware or in software) are universal solvers of NDE models. The solving logic or algorithm of given NDEs (possible examples are: Duffing, Mathieu, Van der Pol, Jerk, Chua, Rössler, Lorenz, Burgers, and the transport equations) through a CNN processor system is provided by a set of templates that are computed by our comprehensive templates calculation technique that we call nonlinear adaptive optimization. This paper is therefore a significant contribution and represents a cutting-edge real-time computational engineering approach, especially while considering the various scientific and engineering applications of this ultrafast, energy-and-memory-efficient, and high-precise NDE solver concept. For illustration purposes, three NDE models are demonstratively solved, and related CNN templates are derived and used: the periodically excited Duffing equation, the Mathieu equation, and the transport equation.

Antenna analysis using neural networks

NASA Technical Reports Server (NTRS)

Smith, William T.

1992-01-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern shaping. The interesting thing about D-C synthesis is that the side lobes have the same amplitude. Five-element arrays were used. Again, 41 pattern samples were used for the input. Nine actual D-C patterns ranging from -10 dB to -30 dB side lobe levels were used to train the network. A comparison between simulated and actual D-C techniques for a pattern with -22 dB side lobe level is shown. The goal for this research was to evaluate the performance of neural network computing with antennas. Future applications will employ the backpropagation training algorithm to drastically reduce the computational complexity involved in performing EM compensation for surface errors in large space reflector antennas.

Antenna analysis using neural networks

NASA Astrophysics Data System (ADS)

Smith, William T.

1992-09-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary).

Spatiotemporal Dynamics and Reliable Computations in Recurrent Spiking Neural Networks

NASA Astrophysics Data System (ADS)

Pyle, Ryan; Rosenbaum, Robert

2017-01-01

Randomly connected networks of excitatory and inhibitory spiking neurons provide a parsimonious model of neural variability, but are notoriously unreliable for performing computations. We show that this difficulty is overcome by incorporating the well-documented dependence of connection probability on distance. Spatially extended spiking networks exhibit symmetry-breaking bifurcations and generate spatiotemporal patterns that can be trained to perform dynamical computations under a reservoir computing framework.

From biological neural networks to thinking machines: Transitioning biological organizational principles to computer technology

NASA Technical Reports Server (NTRS)

Ross, Muriel D.

1991-01-01

The three-dimensional organization of the vestibular macula is under study by computer assisted reconstruction and simulation methods as a model for more complex neural systems. One goal of this research is to transition knowledge of biological neural network architecture and functioning to computer technology, to contribute to the development of thinking computers. Maculas are organized as weighted neural networks for parallel distributed processing of information. The network is characterized by non-linearity of its terminal/receptive fields. Wiring appears to develop through constrained randomness. A further property is the presence of two main circuits, highly channeled and distributed modifying, that are connected through feedforward-feedback collaterals and biasing subcircuit. Computer simulations demonstrate that differences in geometry of the feedback (afferent) collaterals affects the timing and the magnitude of voltage changes delivered to the spike initiation zone. Feedforward (efferent) collaterals act as voltage followers and likely inhibit neurons of the distributed modifying circuit. These results illustrate the importance of feedforward-feedback loops, of timing, and of inhibition in refining neural network output. They also suggest that it is the distributed modifying network that is most involved in adaptation, memory, and learning. Tests of macular adaptation, through hyper- and microgravitational studies, support this hypothesis since synapses in the distributed modifying circuit, but not the channeled circuit, are altered. Transitioning knowledge of biological systems to computer technology, however, remains problematical.

Relaxed fault-tolerant hardware implementation of neural networks in the presence of multiple transient errors.

PubMed

Mahdiani, Hamid Reza; Fakhraie, Sied Mehdi; Lucas, Caro

2012-08-01

Reliability should be identified as the most important challenge in future nano-scale very large scale integration (VLSI) implementation technologies for the development of complex integrated systems. Normally, fault tolerance (FT) in a conventional system is achieved by increasing its redundancy, which also implies higher implementation costs and lower performance that sometimes makes it even infeasible. In contrast to custom approaches, a new class of applications is categorized in this paper, which is inherently capable of absorbing some degrees of vulnerability and providing FT based on their natural properties. Neural networks are good indicators of imprecision-tolerant applications. We have also proposed a new class of FT techniques called relaxed fault-tolerant (RFT) techniques which are developed for VLSI implementation of imprecision-tolerant applications. The main advantage of RFT techniques with respect to traditional FT solutions is that they exploit inherent FT of different applications to reduce their implementation costs while improving their performance. To show the applicability as well as the efficiency of the RFT method, the experimental results for implementation of a face-recognition computationally intensive neural network and its corresponding RFT realization are presented in this paper. The results demonstrate promising higher performance of artificial neural network VLSI solutions for complex applications in faulty nano-scale implementation environments.

Artificial Neural Networks-Based Software for Measuring Heat Collection Rate and Heat Loss Coefficient of Water-in-Glass Evacuated Tube Solar Water Heaters

PubMed Central

Liu, Zhijian; Liu, Kejun; Li, Hao; Zhang, Xinyu; Jin, Guangya; Cheng, Kewei

2015-01-01

Measurements of heat collection rate and heat loss coefficient are crucial for the evaluation of in service water-in-glass evacuated tube solar water heaters. However, conventional measurement requires expensive detection devices and undergoes a series of complicated procedures. To simplify the measurement and reduce the cost, software based on artificial neural networks for measuring heat collection rate and heat loss coefficient of water-in-glass evacuated tube solar water heaters was developed. Using multilayer feed-forward neural networks with back-propagation algorithm, we developed and tested our program on the basis of 915measuredsamples of water-in-glass evacuated tube solar water heaters. This artificial neural networks-based software program automatically obtained accurate heat collection rateand heat loss coefficient using simply "portable test instruments" acquired parameters, including tube length, number of tubes, tube center distance, heat water mass in tank, collector area, angle between tubes and ground and final temperature. Our results show that this software (on both personal computer and Android platforms) is efficient and convenient to predict the heat collection rate and heat loss coefficient due to it slow root mean square errors in prediction. The software now can be downloaded from http://t.cn/RLPKF08. PMID:26624613

Ultra-low-power and robust digital-signal-processing hardware for implantable neural interface microsystems.

PubMed

Narasimhan, S; Chiel, H J; Bhunia, S

2011-04-01

Implantable microsystems for monitoring or manipulating brain activity typically require on-chip real-time processing of multichannel neural data using ultra low-power, miniaturized electronics. In this paper, we propose an integrated-circuit/architecture-level hardware design framework for neural signal processing that exploits the nature of the signal-processing algorithm. First, we consider different power reduction techniques and compare the energy efficiency between the ultra-low frequency subthreshold and conventional superthreshold design. We show that the superthreshold design operating at a much higher frequency can achieve comparable energy dissipation by taking advantage of extensive power gating. It also provides significantly higher robustness of operation and yield under large process variations. Next, we propose an architecture level preferential design approach for further energy reduction by isolating the critical computation blocks (with respect to the quality of the output signal) and assigning them higher delay margins compared to the noncritical ones. Possible delay failures under parameter variations are confined to the noncritical components, allowing graceful degradation in quality under voltage scaling. Simulation results using prerecorded neural data from the sea-slug (Aplysia californica) show that the application of the proposed design approach can lead to significant improvement in total energy, without compromising the output signal quality under process variations, compared to conventional design approaches.

Measuring Fisher Information Accurately in Correlated Neural Populations

PubMed Central

Kohn, Adam; Pouget, Alexandre

2015-01-01

Neural responses are known to be variable. In order to understand how this neural variability constrains behavioral performance, we need to be able to measure the reliability with which a sensory stimulus is encoded in a given population. However, such measures are challenging for two reasons: First, they must take into account noise correlations which can have a large influence on reliability. Second, they need to be as efficient as possible, since the number of trials available in a set of neural recording is usually limited by experimental constraints. Traditionally, cross-validated decoding has been used as a reliability measure, but it only provides a lower bound on reliability and underestimates reliability substantially in small datasets. We show that, if the number of trials per condition is larger than the number of neurons, there is an alternative, direct estimate of reliability which consistently leads to smaller errors and is much faster to compute. The superior performance of the direct estimator is evident both for simulated data and for neuronal population recordings from macaque primary visual cortex. Furthermore we propose generalizations of the direct estimator which measure changes in stimulus encoding across conditions and the impact of correlations on encoding and decoding, typically denoted by Ishuffle and Idiag respectively. PMID:26030735

Artificial Neural Networks-Based Software for Measuring Heat Collection Rate and Heat Loss Coefficient of Water-in-Glass Evacuated Tube Solar Water Heaters.

PubMed

Liu, Zhijian; Liu, Kejun; Li, Hao; Zhang, Xinyu; Jin, Guangya; Cheng, Kewei

2015-01-01

Measurements of heat collection rate and heat loss coefficient are crucial for the evaluation of in service water-in-glass evacuated tube solar water heaters. However, conventional measurement requires expensive detection devices and undergoes a series of complicated procedures. To simplify the measurement and reduce the cost, software based on artificial neural networks for measuring heat collection rate and heat loss coefficient of water-in-glass evacuated tube solar water heaters was developed. Using multilayer feed-forward neural networks with back-propagation algorithm, we developed and tested our program on the basis of 915 measured samples of water-in-glass evacuated tube solar water heaters. This artificial neural networks-based software program automatically obtained accurate heat collection rate and heat loss coefficient using simply "portable test instruments" acquired parameters, including tube length, number of tubes, tube center distance, heat water mass in tank, collector area, angle between tubes and ground and final temperature. Our results show that this software (on both personal computer and Android platforms) is efficient and convenient to predict the heat collection rate and heat loss coefficient due to it slow root mean square errors in prediction. The software now can be downloaded from http://t.cn/RLPKF08.

GaAs Optoelectronic Integrated-Circuit Neurons

NASA Technical Reports Server (NTRS)

Lin, Steven H.; Kim, Jae H.; Psaltis, Demetri

1992-01-01

Monolithic GaAs optoelectronic integrated circuits developed for use as artificial neurons. Neural-network computer contains planar arrays of optoelectronic neurons, and variable synaptic connections between neurons effected by diffraction of light from volume hologram in photorefractive material. Basic principles of neural-network computers explained more fully in "Optoelectronic Integrated Circuits For Neural Networks" (NPO-17652). In present circuits, devices replaced by metal/semiconductor field effect transistors (MESFET's), which consume less power.

The use of self-organising maps for anomalous behaviour detection in a digital investigation.

PubMed

Fei, B K L; Eloff, J H P; Olivier, M S; Venter, H S

2006-10-16

The dramatic increase in crime relating to the Internet and computers has caused a growing need for digital forensics. Digital forensic tools have been developed to assist investigators in conducting a proper investigation into digital crimes. In general, the bulk of the digital forensic tools available on the market permit investigators to analyse data that has been gathered from a computer system. However, current state-of-the-art digital forensic tools simply cannot handle large volumes of data in an efficient manner. With the advent of the Internet, many employees have been given access to new and more interesting possibilities via their desktop. Consequently, excessive Internet usage for non-job purposes and even blatant misuse of the Internet have become a problem in many organisations. Since storage media are steadily growing in size, the process of analysing multiple computer systems during a digital investigation can easily consume an enormous amount of time. Identifying a single suspicious computer from a set of candidates can therefore reduce human processing time and monetary costs involved in gathering evidence. The focus of this paper is to demonstrate how, in a digital investigation, digital forensic tools and the self-organising map (SOM)--an unsupervised neural network model--can aid investigators to determine anomalous behaviours (or activities) among employees (or computer systems) in a far more efficient manner. By analysing the different SOMs (one for each computer system), anomalous behaviours are identified and investigators are assisted to conduct the analysis more efficiently. The paper will demonstrate how the easy visualisation of the SOM enhances the ability of the investigators to interpret and explore the data generated by digital forensic tools so as to determine anomalous behaviours.

Human Inspired Self-developmental Model of Neural Network (HIM): Introducing Content/Form Computing

NASA Astrophysics Data System (ADS)

Krajíček, Jiří

This paper presents cross-disciplinary research between medical/psychological evidence on human abilities and informatics needs to update current models in computer science to support alternative methods for computation and communication. In [10] we have already proposed hypothesis introducing concept of human information model (HIM) as cooperative system. Here we continue on HIM design in detail. In our design, first we introduce Content/Form computing system which is new principle of present methods in evolutionary computing (genetic algorithms, genetic programming). Then we apply this system on HIM (type of artificial neural network) model as basic network self-developmental paradigm. Main inspiration of our natural/human design comes from well known concept of artificial neural networks, medical/psychological evidence and Sheldrake theory of "Nature as Alive" [22].

Neuromorphic sensory systems.

PubMed

Liu, Shih-Chii; Delbruck, Tobi

2010-06-01

Biology provides examples of efficient machines which greatly outperform conventional technology. Designers in neuromorphic engineering aim to construct electronic systems with the same efficient style of computation. This task requires a melding of novel engineering principles with knowledge gleaned from neuroscience. We discuss recent progress in realizing neuromorphic sensory systems which mimic the biological retina and cochlea, and subsequent sensor processing. The main trends are the increasing number of sensors and sensory systems that communicate through asynchronous digital signals analogous to neural spikes; the improved performance and usability of these sensors; and novel sensory processing methods which capitalize on the timing of spikes from these sensors. Experiments using these sensors can impact how we think the brain processes sensory information. 2010 Elsevier Ltd. All rights reserved.

Synaptic E-I Balance Underlies Efficient Neural Coding.

PubMed

Zhou, Shanglin; Yu, Yuguo

2018-01-01

Both theoretical and experimental evidence indicate that synaptic excitation and inhibition in the cerebral cortex are well-balanced during the resting state and sensory processing. Here, we briefly summarize the evidence for how neural circuits are adjusted to achieve this balance. Then, we discuss how such excitatory and inhibitory balance shapes stimulus representation and information propagation, two basic functions of neural coding. We also point out the benefit of adopting such a balance during neural coding. We conclude that excitatory and inhibitory balance may be a fundamental mechanism underlying efficient coding.

Synaptic E-I Balance Underlies Efficient Neural Coding

PubMed Central

Zhou, Shanglin; Yu, Yuguo

2018-01-01

Both theoretical and experimental evidence indicate that synaptic excitation and inhibition in the cerebral cortex are well-balanced during the resting state and sensory processing. Here, we briefly summarize the evidence for how neural circuits are adjusted to achieve this balance. Then, we discuss how such excitatory and inhibitory balance shapes stimulus representation and information propagation, two basic functions of neural coding. We also point out the benefit of adopting such a balance during neural coding. We conclude that excitatory and inhibitory balance may be a fundamental mechanism underlying efficient coding. PMID:29456491

Whole-Volume Clustering of Time Series Data from Zebrafish Brain Calcium Images via Mixture Modeling.

PubMed

Nguyen, Hien D; Ullmann, Jeremy F P; McLachlan, Geoffrey J; Voleti, Venkatakaushik; Li, Wenze; Hillman, Elizabeth M C; Reutens, David C; Janke, Andrew L

2018-02-01

Calcium is a ubiquitous messenger in neural signaling events. An increasing number of techniques are enabling visualization of neurological activity in animal models via luminescent proteins that bind to calcium ions. These techniques generate large volumes of spatially correlated time series. A model-based functional data analysis methodology via Gaussian mixtures is suggested for the clustering of data from such visualizations is proposed. The methodology is theoretically justified and a computationally efficient approach to estimation is suggested. An example analysis of a zebrafish imaging experiment is presented.

Methods and Apparatus for Autonomous Robotic Control

NASA Technical Reports Server (NTRS)

Gorshechnikov, Anatoly (Inventor); Livitz, Gennady (Inventor); Versace, Massimiliano (Inventor); Palma, Jesse (Inventor)

2017-01-01

Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on "stovepiped," or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.

Behavioral modeling of VCSELs for high-speed optical interconnects

NASA Astrophysics Data System (ADS)

Szczerba, Krzysztof; Kocot, Chris

2018-02-01

Transition from on-off keying to 4-level pulse amplitude modulation (PAM) in VCSEL based optical interconnects allows for an increase of data rates, at the cost of 4.8 dB sensitivity penalty. The resulting strained link budget creates a need for accurate VCSEL models for driver integrated circuit (IC) design and system level simulations. Rate equation based equivalent circuit models are convenient for the IC design, but system level analysis requires computationally efficient closed form behavioral models based Volterra series and neural networks. In this paper we present and compare these models.

Application of two neural network paradigms to the study of voluntary employee turnover.

PubMed

Somers, M J

1999-04-01

Two neural network paradigms--multilayer perceptron and learning vector quantization--were used to study voluntary employee turnover with a sample of 577 hospital employees. The objectives of the study were twofold. The 1st was to assess whether neural computing techniques offered greater predictive accuracy than did conventional turnover methodologies. The 2nd was to explore whether computer models of turnover based on neural network technologies offered new insights into turnover processes. When compared with logistic regression analysis, both neural network paradigms provided considerably more accurate predictions of turnover behavior, particularly with respect to the correct classification of leavers. In addition, these neural network paradigms captured nonlinear relationships that are relevant for theory development. Results are discussed in terms of their implications for future research.

Neural simulations on multi-core architectures.

PubMed

Eichner, Hubert; Klug, Tobias; Borst, Alexander

2009-01-01

Neuroscience is witnessing increasing knowledge about the anatomy and electrophysiological properties of neurons and their connectivity, leading to an ever increasing computational complexity of neural simulations. At the same time, a rather radical change in personal computer technology emerges with the establishment of multi-cores: high-density, explicitly parallel processor architectures for both high performance as well as standard desktop computers. This work introduces strategies for the parallelization of biophysically realistic neural simulations based on the compartmental modeling technique and results of such an implementation, with a strong focus on multi-core architectures and automation, i.e. user-transparent load balancing.

Neural Simulations on Multi-Core Architectures

PubMed Central

Eichner, Hubert; Klug, Tobias; Borst, Alexander

2009-01-01

Neuroscience is witnessing increasing knowledge about the anatomy and electrophysiological properties of neurons and their connectivity, leading to an ever increasing computational complexity of neural simulations. At the same time, a rather radical change in personal computer technology emerges with the establishment of multi-cores: high-density, explicitly parallel processor architectures for both high performance as well as standard desktop computers. This work introduces strategies for the parallelization of biophysically realistic neural simulations based on the compartmental modeling technique and results of such an implementation, with a strong focus on multi-core architectures and automation, i.e. user-transparent load balancing. PMID:19636393

A memory efficient implementation scheme of Gauss error function in a Laguerre-Volterra network for neuroprosthetic devices

NASA Astrophysics Data System (ADS)

Li, Will X. Y.; Cui, Ke; Zhang, Wei

2017-04-01

Cognitive neural prosthesis is a manmade device which can be used to restore or compensate for lost human cognitive modalities. The generalized Laguerre-Volterra (GLV) network serves as a robust mathematical underpinning for the development of such prosthetic instrument. In this paper, a hardware implementation scheme of Gauss error function for the GLV network targeting reconfigurable platforms is reported. Numerical approximations are formulated which transform the computation of nonelementary function into combinational operations of elementary functions, and memory-intensive look-up table (LUT) based approaches can therefore be circumvented. The computational precision can be made adjustable with the utilization of an error compensation scheme, which is proposed based on the experimental observation of the mathematical characteristics of the error trajectory. The precision can be further customizable by exploiting the run-time characteristics of the reconfigurable system. Compared to the polynomial expansion based implementation scheme, the utilization of slice LUTs, occupied slices, and DSP48E1s on a Xilinx XC6VLX240T field-programmable gate array has decreased by 94.2%, 94.1%, and 90.0%, respectively. While compared to the look-up table based scheme, 1.0 ×1017 bits of storage can be spared under the maximum allowable error of 1.0 ×10-3 . The proposed implementation scheme can be employed in the study of large-scale neural ensemble activity and in the design and development of neural prosthetic device.

Cross hole GPR traveltime inversion using a fast and accurate neural network as a forward model

NASA Astrophysics Data System (ADS)

Mejer Hansen, Thomas

2017-04-01

Probabilistic formulated inverse problems can be solved using Monte Carlo based sampling methods. In principle both advanced prior information, such as based on geostatistics, and complex non-linear forward physical models can be considered. However, in practice these methods can be associated with huge computational costs that in practice limit their application. This is not least due to the computational requirements related to solving the forward problem, where the physical response of some earth model has to be evaluated. Here, it is suggested to replace a numerical complex evaluation of the forward problem, with a trained neural network that can be evaluated very fast. This will introduce a modeling error, that is quantified probabilistically such that it can be accounted for during inversion. This allows a very fast and efficient Monte Carlo sampling of the solution to an inverse problem. We demonstrate the methodology for first arrival travel time inversion of cross hole ground-penetrating radar (GPR) data. An accurate forward model, based on 2D full-waveform modeling followed by automatic travel time picking, is replaced by a fast neural network. This provides a sampling algorithm three orders of magnitude faster than using the full forward model, and considerably faster, and more accurate, than commonly used approximate forward models. The methodology has the potential to dramatically change the complexity of the types of inverse problems that can be solved using non-linear Monte Carlo sampling techniques.

Delay dynamics of neuromorphic optoelectronic nanoscale resonators: Perspectives and applications

NASA Astrophysics Data System (ADS)

Romeira, Bruno; Figueiredo, José M. L.; Javaloyes, Julien

2017-11-01

With the recent exponential growth of applications using artificial intelligence (AI), the development of efficient and ultrafast brain-like (neuromorphic) systems is crucial for future information and communication technologies. While the implementation of AI systems using computer algorithms of neural networks is emerging rapidly, scientists are just taking the very first steps in the development of the hardware elements of an artificial brain, specifically neuromorphic microchips. In this review article, we present the current state of the art of neuromorphic photonic circuits based on solid-state optoelectronic oscillators formed by nanoscale double barrier quantum well resonant tunneling diodes. We address, both experimentally and theoretically, the key dynamic properties of recently developed artificial solid-state neuron microchips with delayed perturbations and describe their role in the study of neural activity and regenerative memory. This review covers our recent research work on excitable and delay dynamic characteristics of both single and autaptic (delayed) artificial neurons including all-or-none response, spike-based data encoding, storage, signal regeneration and signal healing. Furthermore, the neural responses of these neuromorphic microchips display all the signatures of extended spatio-temporal localized structures (LSs) of light, which are reviewed here in detail. By taking advantage of the dissipative nature of LSs, we demonstrate potential applications in optical data reconfiguration and clock and timing at high-speeds and with short transients. The results reviewed in this article are a key enabler for the development of high-performance optoelectronic devices in future high-speed brain-inspired optical memories and neuromorphic computing.

Delay dynamics of neuromorphic optoelectronic nanoscale resonators: Perspectives and applications.

PubMed

Romeira, Bruno; Figueiredo, José M L; Javaloyes, Julien

2017-11-01

With the recent exponential growth of applications using artificial intelligence (AI), the development of efficient and ultrafast brain-like (neuromorphic) systems is crucial for future information and communication technologies. While the implementation of AI systems using computer algorithms of neural networks is emerging rapidly, scientists are just taking the very first steps in the development of the hardware elements of an artificial brain, specifically neuromorphic microchips. In this review article, we present the current state of the art of neuromorphic photonic circuits based on solid-state optoelectronic oscillators formed by nanoscale double barrier quantum well resonant tunneling diodes. We address, both experimentally and theoretically, the key dynamic properties of recently developed artificial solid-state neuron microchips with delayed perturbations and describe their role in the study of neural activity and regenerative memory. This review covers our recent research work on excitable and delay dynamic characteristics of both single and autaptic (delayed) artificial neurons including all-or-none response, spike-based data encoding, storage, signal regeneration and signal healing. Furthermore, the neural responses of these neuromorphic microchips display all the signatures of extended spatio-temporal localized structures (LSs) of light, which are reviewed here in detail. By taking advantage of the dissipative nature of LSs, we demonstrate potential applications in optical data reconfiguration and clock and timing at high-speeds and with short transients. The results reviewed in this article are a key enabler for the development of high-performance optoelectronic devices in future high-speed brain-inspired optical memories and neuromorphic computing.

A computational framework to detect normal and tuberculosis infected lung from H and E-stained whole slide images

NASA Astrophysics Data System (ADS)

Niazi, M. Khalid Khan; Beamer, Gillian; Gurcan, Metin N.

2017-03-01

Accurate detection and quantification of normal lung tissue in the context of Mycobacterium tuberculosis infection is of interest from a biological perspective. The automatic detection and quantification of normal lung will allow the biologists to focus more intensely on regions of interest within normal and infected tissues. We present a computational framework to extract individual tissue sections from whole slide images having multiple tissue sections. It automatically detects the background, red blood cells and handwritten digits to bring efficiency as well as accuracy in quantification of tissue sections. For efficiency, we model our framework with logical and morphological operations as they can be performed in linear time. We further divide these individual tissue sections into normal and infected areas using deep neural network. The computational framework was trained on 60 whole slide images. The proposed computational framework resulted in an overall accuracy of 99.2% when extracting individual tissue sections from 120 whole slide images in the test dataset. The framework resulted in a relatively higher accuracy (99.7%) while classifying individual lung sections into normal and infected areas. Our preliminary findings suggest that the proposed framework has good agreement with biologists on how define normal and infected lung areas.

Neural Computations in a Dynamical System with Multiple Time Scales.

PubMed

Mi, Yuanyuan; Lin, Xiaohan; Wu, Si

2016-01-01

Neural systems display rich short-term dynamics at various levels, e.g., spike-frequency adaptation (SFA) at the single-neuron level, and short-term facilitation (STF) and depression (STD) at the synapse level. These dynamical features typically cover a broad range of time scales and exhibit large diversity in different brain regions. It remains unclear what is the computational benefit for the brain to have such variability in short-term dynamics. In this study, we propose that the brain can exploit such dynamical features to implement multiple seemingly contradictory computations in a single neural circuit. To demonstrate this idea, we use continuous attractor neural network (CANN) as a working model and include STF, SFA and STD with increasing time constants in its dynamics. Three computational tasks are considered, which are persistent activity, adaptation, and anticipative tracking. These tasks require conflicting neural mechanisms, and hence cannot be implemented by a single dynamical feature or any combination with similar time constants. However, with properly coordinated STF, SFA and STD, we show that the network is able to implement the three computational tasks concurrently. We hope this study will shed light on the understanding of how the brain orchestrates its rich dynamics at various levels to realize diverse cognitive functions.

Coordinated within-trial dynamics of low-frequency neural rhythms controls evidence accumulation.

PubMed

Werkle-Bergner, Markus; Grandy, Thomas H; Chicherio, Christian; Schmiedek, Florian; Lövdén, Martin; Lindenberger, Ulman

2014-06-18

Higher cognitive functions, such as human perceptual decision making, require information processing and transmission across wide-spread cortical networks. Temporally synchronized neural firing patterns are advantageous for efficiently representing and transmitting information within and between assemblies. Computational, empirical, and conceptual considerations all lead to the expectation that the informational redundancy of neural firing rates is positively related to their synchronization. Recent theorizing and initial evidence also suggest that the coding of stimulus characteristics and their integration with behavioral goal states require neural interactions across a hierarchy of timescales. However, most studies thus have focused on neural activity in a single frequency range or on a restricted set of brain regions. Here we provide evidence for cooperative spatiotemporal dynamics of slow and fast EEG signals during perceptual decision making at the single-trial level. Participants performed three masked two-choice decision tasks, one each with numerical, verbal, or figural content. Decrements in posterior α power (8-14 Hz) were paralleled by increments in high-frequency (>30 Hz) signal entropy in trials demanding active sensory processing. Simultaneously, frontocentral θ power (4-7 Hz) increased, indicating evidence integration. The coordinated α/θ dynamics were tightly linked to decision speed and remarkably similar across tasks, suggesting a domain-general mechanism. In sum, we demonstrate an inverse association between decision-related changes in widespread low-frequency power and local high-frequency entropy. The cooperation among mechanisms captured by these changes enhances the informational density of neural response patterns and qualifies as a neural coding system in the service of perceptual decision making. Copyright © 2014 the authors 0270-6474/14/348519-10$15.00/0.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU.

PubMed

Lan, Qiang; Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU

PubMed Central

Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version. PMID:29250109

How Neural Networks Learn from Experience.

ERIC Educational Resources Information Center

Hinton, Geoffrey E.

1992-01-01

Discusses computational studies of learning in artificial neural networks and findings that may provide insights into the learning abilities of the human brain. Describes efforts to test theories about brain information processing, using artificial neural networks. Vignettes include information concerning how a neural network represents…

Accelerating deep neural network training with inconsistent stochastic gradient descent.

PubMed

Wang, Linnan; Yang, Yi; Min, Renqiang; Chakradhar, Srimat

2017-09-01

Stochastic Gradient Descent (SGD) updates Convolutional Neural Network (CNN) with a noisy gradient computed from a random batch, and each batch evenly updates the network once in an epoch. This model applies the same training effort to each batch, but it overlooks the fact that the gradient variance, induced by Sampling Bias and Intrinsic Image Difference, renders different training dynamics on batches. In this paper, we develop a new training strategy for SGD, referred to as Inconsistent Stochastic Gradient Descent (ISGD) to address this problem. The core concept of ISGD is the inconsistent training, which dynamically adjusts the training effort w.r.t the loss. ISGD models the training as a stochastic process that gradually reduces down the mean of batch's loss, and it utilizes a dynamic upper control limit to identify a large loss batch on the fly. ISGD stays on the identified batch to accelerate the training with additional gradient updates, and it also has a constraint to penalize drastic parameter changes. ISGD is straightforward, computationally efficient and without requiring auxiliary memories. A series of empirical evaluations on real world datasets and networks demonstrate the promising performance of inconsistent training. Copyright © 2017 Elsevier Ltd. All rights reserved.

Analytical modelling of temperature effects on an AMPA-type synapse.

PubMed

Kufel, Dominik S; Wojcik, Grzegorz M

2018-05-11

It was previously reported, that temperature may significantly influence neural dynamics on the different levels of brain function. Thus, in computational neuroscience, it would be useful to make models scalable for a wide range of various brain temperatures. However, lack of experimental data and an absence of temperature-dependent analytical models of synaptic conductance does not allow to include temperature effects at the multi-neuron modeling level. In this paper, we propose a first step to deal with this problem: A new analytical model of AMPA-type synaptic conductance, which is able to incorporate temperature effects in low-frequency stimulations. It was constructed based on Markov model description of AMPA receptor kinetics using the set of coupled ODEs. The closed-form solution for the set of differential equations was found using uncoupling assumption (introduced in the paper) with few simplifications motivated both from experimental data and from Monte Carlo simulation of synaptic transmission. The model may be used for computationally efficient and biologically accurate implementation of temperature effects on AMPA receptor conductance in large-scale neural network simulations. As a result, it may open a wide range of new possibilities for researching the influence of temperature on certain aspects of brain functioning.

Application of ANNs approach for wave-like and heat-like equations

NASA Astrophysics Data System (ADS)

Jafarian, Ahmad; Baleanu, Dumitru

2017-12-01

Artificial neural networks are data processing systems which originate from human brain tissue studies. The remarkable abilities of these networks help us to derive desired results from complicated raw data. In this study, we intend to duplicate an efficient iterative method to the numerical solution of two famous partial differential equations, namely the wave-like and heat-like problems. It should be noted that many physical phenomena such as coupling currents in a flat multi-strand two-layer super conducting cable, non-homogeneous elastic waves in soils and earthquake stresses, are described by initial-boundary value wave and heat partial differential equations with variable coefficients. To the numerical solution of these equations, a combination of the power series method and artificial neural networks approach, is used to seek an appropriate bivariate polynomial solution of the mentioned initial-boundary value problem. Finally, several computer simulations confirmed the theoretical results and demonstrating applicability of the method.

Adaptive neural control for dual-arm coordination of humanoid robot with unknown nonlinearities in output mechanism.

PubMed

Liu, Zhi; Chen, Ci; Zhang, Yun; Chen, C L P

2015-03-01

To achieve an excellent dual-arm coordination of the humanoid robot, it is essential to deal with the nonlinearities existing in the system dynamics. The literatures so far on the humanoid robot control have a common assumption that the problem of output hysteresis could be ignored. However, in the practical applications, the output hysteresis is widely spread; and its existing limits the motion/force performances of the robotic system. In this paper, an adaptive neural control scheme, which takes the unknown output hysteresis and computational efficiency into account, is presented and investigated. In the controller design, the prior knowledge of system dynamics is assumed to be unknown. The motion error is guaranteed to converge to a small neighborhood of the origin by Lyapunov's stability theory. Simultaneously, the internal force is kept bounded and its error can be made arbitrarily small.

LensFlow: A Convolutional Neural Network in Search of Strong Gravitational Lenses

NASA Astrophysics Data System (ADS)

Pourrahmani, Milad; Nayyeri, Hooshang; Cooray, Asantha

2018-03-01

In this work, we present our machine learning classification algorithm for identifying strong gravitational lenses from wide-area surveys using convolutional neural networks; LENSFLOW. We train and test the algorithm using a wide variety of strong gravitational lens configurations from simulations of lensing events. Images are processed through multiple convolutional layers that extract feature maps necessary to assign a lens probability to each image. LENSFLOW provides a ranking scheme for all sources that could be used to identify potential gravitational lens candidates by significantly reducing the number of images that have to be visually inspected. We apply our algorithm to the HST/ACS i-band observations of the COSMOS field and present our sample of identified lensing candidates. The developed machine learning algorithm is more computationally efficient and complimentary to classical lens identification algorithms and is ideal for discovering such events across wide areas from current and future surveys such as LSST and WFIRST.

Integrating probabilistic models of perception and interactive neural networks: a historical and tutorial review

PubMed Central

McClelland, James L.

2013-01-01

This article seeks to establish a rapprochement between explicitly Bayesian models of contextual effects in perception and neural network models of such effects, particularly the connectionist interactive activation (IA) model of perception. The article is in part an historical review and in part a tutorial, reviewing the probabilistic Bayesian approach to understanding perception and how it may be shaped by context, and also reviewing ideas about how such probabilistic computations may be carried out in neural networks, focusing on the role of context in interactive neural networks, in which both bottom-up and top-down signals affect the interpretation of sensory inputs. It is pointed out that connectionist units that use the logistic or softmax activation functions can exactly compute Bayesian posterior probabilities when the bias terms and connection weights affecting such units are set to the logarithms of appropriate probabilistic quantities. Bayesian concepts such the prior, likelihood, (joint and marginal) posterior, probability matching and maximizing, and calculating vs. sampling from the posterior are all reviewed and linked to neural network computations. Probabilistic and neural network models are explicitly linked to the concept of a probabilistic generative model that describes the relationship between the underlying target of perception (e.g., the word intended by a speaker or other source of sensory stimuli) and the sensory input that reaches the perceiver for use in inferring the underlying target. It is shown how a new version of the IA model called the multinomial interactive activation (MIA) model can sample correctly from the joint posterior of a proposed generative model for perception of letters in words, indicating that interactive processing is fully consistent with principled probabilistic computation. Ways in which these computations might be realized in real neural systems are also considered. PMID:23970868

Integrating probabilistic models of perception and interactive neural networks: a historical and tutorial review.

PubMed

McClelland, James L

2013-01-01

This article seeks to establish a rapprochement between explicitly Bayesian models of contextual effects in perception and neural network models of such effects, particularly the connectionist interactive activation (IA) model of perception. The article is in part an historical review and in part a tutorial, reviewing the probabilistic Bayesian approach to understanding perception and how it may be shaped by context, and also reviewing ideas about how such probabilistic computations may be carried out in neural networks, focusing on the role of context in interactive neural networks, in which both bottom-up and top-down signals affect the interpretation of sensory inputs. It is pointed out that connectionist units that use the logistic or softmax activation functions can exactly compute Bayesian posterior probabilities when the bias terms and connection weights affecting such units are set to the logarithms of appropriate probabilistic quantities. Bayesian concepts such the prior, likelihood, (joint and marginal) posterior, probability matching and maximizing, and calculating vs. sampling from the posterior are all reviewed and linked to neural network computations. Probabilistic and neural network models are explicitly linked to the concept of a probabilistic generative model that describes the relationship between the underlying target of perception (e.g., the word intended by a speaker or other source of sensory stimuli) and the sensory input that reaches the perceiver for use in inferring the underlying target. It is shown how a new version of the IA model called the multinomial interactive activation (MIA) model can sample correctly from the joint posterior of a proposed generative model for perception of letters in words, indicating that interactive processing is fully consistent with principled probabilistic computation. Ways in which these computations might be realized in real neural systems are also considered.

Dispersion compensation of fiber optic communication system with direct detection using artificial neural networks (ANNs)

NASA Astrophysics Data System (ADS)

Maghrabi, Mahmoud M. T.; Kumar, Shiva; Bakr, Mohamed H.

2018-02-01

This work introduces a powerful digital nonlinear feed-forward equalizer (NFFE), exploiting multilayer artificial neural network (ANN). It mitigates impairments of optical communication systems arising due to the nonlinearity introduced by direct photo-detection. In a direct detection system, the detection process is nonlinear due to the fact that the photo-current is proportional to the absolute square of the electric field intensity. The proposed equalizer provides the most efficient computational cost with high equalization performance. Its performance is comparable to the benchmark compensation performance achieved by maximum-likelihood sequence estimator. The equalizer trains an ANN to act as a nonlinear filter whose impulse response removes the intersymbol interference (ISI) distortions of the optical channel. Owing to the proposed extensive training of the equalizer, it achieves the ultimate performance limit of any feed-forward equalizer (FFE). The performance and efficiency of the equalizer is investigated by applying it to various practical short-reach fiber optic communication system scenarios. These scenarios are extracted from practical metro/media access networks and data center applications. The obtained results show that the ANN-NFFE compensates for the received BER degradation and significantly increases the tolerance to the chromatic dispersion distortion.

Embedded Streaming Deep Neural Networks Accelerator With Applications.

PubMed

Dundar, Aysegul; Jin, Jonghoon; Martini, Berin; Culurciello, Eugenio

2017-07-01

Deep convolutional neural networks (DCNNs) have become a very powerful tool in visual perception. DCNNs have applications in autonomous robots, security systems, mobile phones, and automobiles, where high throughput of the feedforward evaluation phase and power efficiency are important. Because of this increased usage, many field-programmable gate array (FPGA)-based accelerators have been proposed. In this paper, we present an optimized streaming method for DCNNs' hardware accelerator on an embedded platform. The streaming method acts as a compiler, transforming a high-level representation of DCNNs into operation codes to execute applications in a hardware accelerator. The proposed method utilizes maximum computational resources available based on a novel-scheduled routing topology that combines data reuse and data concatenation. It is tested with a hardware accelerator implemented on the Xilinx Kintex-7 XC7K325T FPGA. The system fully explores weight-level and node-level parallelizations of DCNNs and achieves a peak performance of 247 G-ops while consuming less than 4 W of power. We test our system with applications on object classification and object detection in real-world scenarios. Our results indicate high-performance efficiency, outperforming all other presented platforms while running these applications.

A four-dimensional virtual hand brain-machine interface using active dimension selection.

PubMed

Rouse, Adam G

2016-06-01

Brain-machine interfaces (BMI) traditionally rely on a fixed, linear transformation from neural signals to an output state-space. In this study, the assumption that a BMI must control a fixed, orthogonal basis set was challenged and a novel active dimension selection (ADS) decoder was explored. ADS utilizes a two stage decoder by using neural signals to both (i) select an active dimension being controlled and (ii) control the velocity along the selected dimension. ADS decoding was tested in a monkey using 16 single units from premotor and primary motor cortex to successfully control a virtual hand avatar to move to eight different postures. Following training with the ADS decoder to control 2, 3, and then 4 dimensions, each emulating a grasp shape of the hand, performance reached 93% correct with a bit rate of 2.4 bits s(-1) for eight targets. Selection of eight targets using ADS control was more efficient, as measured by bit rate, than either full four-dimensional control or computer assisted one-dimensional control. ADS decoding allows a user to quickly and efficiently select different hand postures. This novel decoding scheme represents a potential method to reduce the complexity of high-dimension BMI control of the hand.

Application of artificial neural networks to gaming

NASA Astrophysics Data System (ADS)

Baba, Norio; Kita, Tomio; Oda, Kazuhiro

1995-04-01

Recently, neural network technology has been applied to various actual problems. It has succeeded in producing a large number of intelligent systems. In this article, we suggest that it could be applied to the field of gaming. In particular, we suggest that the neural network model could be used to mimic players' characters. Several computer simulation results using a computer gaming system which is a modified version of the COMMONS GAME confirm our idea.

Investigation of a Neural Network Implementation of a TCP Packet Anomaly Detection System

DTIC Science & Technology

2004-05-01

reconnatre les nouvelles variantes d’attaque. Les réseaux de neurones artificiels (ANN) ont les capacités d’apprendre à partir de schémas et de...Computational Intelligence Techniques in Intrusion Detection Systems. In IASTED International Conference on Neural Networks and Computational Intelligence , pp...Neural Network Training: Overfitting May be Harder than Expected. In Proceedings of the Fourteenth National Conference on Artificial Intelligence , AAAI-97

Program Helps Simulate Neural Networks

NASA Technical Reports Server (NTRS)

Villarreal, James; Mcintire, Gary

1993-01-01

Neural Network Environment on Transputer System (NNETS) computer program provides users high degree of flexibility in creating and manipulating wide variety of neural-network topologies at processing speeds not found in conventional computing environments. Supports back-propagation and back-propagation-related algorithms. Back-propagation algorithm used is implementation of Rumelhart's generalized delta rule. NNETS developed on INMOS Transputer(R). Predefines back-propagation network, Jordan network, and reinforcement network to assist users in learning and defining own networks. Also enables users to configure other neural-network paradigms from NNETS basic architecture. Small portion of software written in OCCAM(R) language.

Computationally assisted screening and design of cell-interactive peptides by a cell-based assay using peptide arrays and a fuzzy neural network algorithm.

PubMed

Kaga, Chiaki; Okochi, Mina; Tomita, Yasuyuki; Kato, Ryuji; Honda, Hiroyuki

2008-03-01

We developed a method of effective peptide screening that combines experiments and computational analysis. The method is based on the concept that screening efficiency can be enhanced from even limited data by use of a model derived from computational analysis that serves as a guide to screening and combining the model with subsequent repeated experiments. Here we focus on cell-adhesion peptides as a model application of this peptide-screening strategy. Cell-adhesion peptides were screened by use of a cell-based assay of a peptide array. Starting with the screening data obtained from a limited, random 5-mer library (643 sequences), a rule regarding structural characteristics of cell-adhesion peptides was extracted by fuzzy neural network (FNN) analysis. According to this rule, peptides with unfavored residues in certain positions that led to inefficient binding were eliminated from the random sequences. In the restricted, second random library (273 sequences), the yield of cell-adhesion peptides having an adhesion rate more than 1.5-fold to that of the basal array support was significantly high (31%) compared with the unrestricted random library (20%). In the restricted third library (50 sequences), the yield of cell-adhesion peptides increased to 84%. We conclude that a repeated cycle of experiments screening limited numbers of peptides can be assisted by the rule-extracting feature of FNN.

Quantum neural networks: Current status and prospects for development

NASA Astrophysics Data System (ADS)

Altaisky, M. V.; Kaputkina, N. E.; Krylov, V. A.

2014-11-01

The idea of quantum artificial neural networks, first formulated in [34], unites the artificial neural network concept with the quantum computation paradigm. Quantum artificial neural networks were first systematically considered in the PhD thesis by T. Menneer (1998). Based on the works of Menneer and Narayanan [42, 43], Kouda, Matsui, and Nishimura [35, 36], Altaisky [2, 68], Zhou [67], and others, quantum-inspired learning algorithms for neural networks were developed, and are now used in various training programs and computer games [29, 30]. The first practically realizable scaled hardware-implemented model of the quantum artificial neural network is obtained by D-Wave Systems, Inc. [33]. It is a quantum Hopfield network implemented on the basis of superconducting quantum interference devices (SQUIDs). In this work we analyze possibilities and underlying principles of an alternative way to implement quantum neural networks on the basis of quantum dots. A possibility of using quantum neural network algorithms in automated control systems, associative memory devices, and in modeling biological and social networks is examined.

Polarity-specific high-level information propagation in neural networks.

PubMed

Lin, Yen-Nan; Chang, Po-Yen; Hsiao, Pao-Yueh; Lo, Chung-Chuan

2014-01-01

Analyzing the connectome of a nervous system provides valuable information about the functions of its subsystems. Although much has been learned about the architectures of neural networks in various organisms by applying analytical tools developed for general networks, two distinct and functionally important properties of neural networks are often overlooked. First, neural networks are endowed with polarity at the circuit level: Information enters a neural network at input neurons, propagates through interneurons, and leaves via output neurons. Second, many functions of nervous systems are implemented by signal propagation through high-level pathways involving multiple and often recurrent connections rather than by the shortest paths between nodes. In the present study, we analyzed two neural networks: the somatic nervous system of Caenorhabditis elegans (C. elegans) and the partial central complex network of Drosophila, in light of these properties. Specifically, we quantified high-level propagation in the vertical and horizontal directions: the former characterizes how signals propagate from specific input nodes to specific output nodes and the latter characterizes how a signal from a specific input node is shared by all output nodes. We found that the two neural networks are characterized by very efficient vertical and horizontal propagation. In comparison, classic small-world networks show a trade-off between vertical and horizontal propagation; increasing the rewiring probability improves the efficiency of horizontal propagation but worsens the efficiency of vertical propagation. Our result provides insights into how the complex functions of natural neural networks may arise from a design that allows them to efficiently transform and combine input signals.

Polarity-specific high-level information propagation in neural networks

PubMed Central

Lin, Yen-Nan; Chang, Po-Yen; Hsiao, Pao-Yueh; Lo, Chung-Chuan

2014-01-01

Analyzing the connectome of a nervous system provides valuable information about the functions of its subsystems. Although much has been learned about the architectures of neural networks in various organisms by applying analytical tools developed for general networks, two distinct and functionally important properties of neural networks are often overlooked. First, neural networks are endowed with polarity at the circuit level: Information enters a neural network at input neurons, propagates through interneurons, and leaves via output neurons. Second, many functions of nervous systems are implemented by signal propagation through high-level pathways involving multiple and often recurrent connections rather than by the shortest paths between nodes. In the present study, we analyzed two neural networks: the somatic nervous system of Caenorhabditis elegans (C. elegans) and the partial central complex network of Drosophila, in light of these properties. Specifically, we quantified high-level propagation in the vertical and horizontal directions: the former characterizes how signals propagate from specific input nodes to specific output nodes and the latter characterizes how a signal from a specific input node is shared by all output nodes. We found that the two neural networks are characterized by very efficient vertical and horizontal propagation. In comparison, classic small-world networks show a trade-off between vertical and horizontal propagation; increasing the rewiring probability improves the efficiency of horizontal propagation but worsens the efficiency of vertical propagation. Our result provides insights into how the complex functions of natural neural networks may arise from a design that allows them to efficiently transform and combine input signals. PMID:24672472

Soft computing techniques toward modeling the water supplies of Cyprus.

PubMed

Iliadis, L; Maris, F; Tachos, S

2011-10-01

This research effort aims in the application of soft computing techniques toward water resources management. More specifically, the target is the development of reliable soft computing models capable of estimating the water supply for the case of "Germasogeia" mountainous watersheds in Cyprus. Initially, ε-Regression Support Vector Machines (ε-RSVM) and fuzzy weighted ε-RSVMR models have been developed that accept five input parameters. At the same time, reliable artificial neural networks have been developed to perform the same job. The 5-fold cross validation approach has been employed in order to eliminate bad local behaviors and to produce a more representative training data set. Thus, the fuzzy weighted Support Vector Regression (SVR) combined with the fuzzy partition has been employed in an effort to enhance the quality of the results. Several rational and reliable models have been produced that can enhance the efficiency of water policy designers. Copyright © 2011 Elsevier Ltd. All rights reserved.

Target Identification Using Harmonic Wavelet Based ISAR Imaging

NASA Astrophysics Data System (ADS)

Shreyamsha Kumar, B. K.; Prabhakar, B.; Suryanarayana, K.; Thilagavathi, V.; Rajagopal, R.

2006-12-01

A new approach has been proposed to reduce the computations involved in the ISAR imaging, which uses harmonic wavelet-(HW) based time-frequency representation (TFR). Since the HW-based TFR falls into a category of nonparametric time-frequency (T-F) analysis tool, it is computationally efficient compared to parametric T-F analysis tools such as adaptive joint time-frequency transform (AJTFT), adaptive wavelet transform (AWT), and evolutionary AWT (EAWT). Further, the performance of the proposed method of ISAR imaging is compared with the ISAR imaging by other nonparametric T-F analysis tools such as short-time Fourier transform (STFT) and Choi-Williams distribution (CWD). In the ISAR imaging, the use of HW-based TFR provides similar/better results with significant (92%) computational advantage compared to that obtained by CWD. The ISAR images thus obtained are identified using a neural network-based classification scheme with feature set invariant to translation, rotation, and scaling.

SiNC: Saliency-injected neural codes for representation and efficient retrieval of medical radiographs

PubMed Central

Sajjad, Muhammad; Mehmood, Irfan; Baik, Sung Wook

2017-01-01

Medical image collections contain a wealth of information which can assist radiologists and medical experts in diagnosis and disease detection for making well-informed decisions. However, this objective can only be realized if efficient access is provided to semantically relevant cases from the ever-growing medical image repositories. In this paper, we present an efficient method for representing medical images by incorporating visual saliency and deep features obtained from a fine-tuned convolutional neural network (CNN) pre-trained on natural images. Saliency detector is employed to automatically identify regions of interest like tumors, fractures, and calcified spots in images prior to feature extraction. Neuronal activation features termed as neural codes from different CNN layers are comprehensively studied to identify most appropriate features for representing radiographs. This study revealed that neural codes from the last fully connected layer of the fine-tuned CNN are found to be the most suitable for representing medical images. The neural codes extracted from the entire image and salient part of the image are fused to obtain the saliency-injected neural codes (SiNC) descriptor which is used for indexing and retrieval. Finally, locality sensitive hashing techniques are applied on the SiNC descriptor to acquire short binary codes for allowing efficient retrieval in large scale image collections. Comprehensive experimental evaluations on the radiology images dataset reveal that the proposed framework achieves high retrieval accuracy and efficiency for scalable image retrieval applications and compares favorably with existing approaches. PMID:28771497

The Brain as a Distributed Intelligent Processing System: An EEG Study

PubMed Central

da Rocha, Armando Freitas; Rocha, Fábio Theoto; Massad, Eduardo

2011-01-01

Background Various neuroimaging studies, both structural and functional, have provided support for the proposal that a distributed brain network is likely to be the neural basis of intelligence. The theory of Distributed Intelligent Processing Systems (DIPS), first developed in the field of Artificial Intelligence, was proposed to adequately model distributed neural intelligent processing. In addition, the neural efficiency hypothesis suggests that individuals with higher intelligence display more focused cortical activation during cognitive performance, resulting in lower total brain activation when compared with individuals who have lower intelligence. This may be understood as a property of the DIPS. Methodology and Principal Findings In our study, a new EEG brain mapping technique, based on the neural efficiency hypothesis and the notion of the brain as a Distributed Intelligence Processing System, was used to investigate the correlations between IQ evaluated with WAIS (Whechsler Adult Intelligence Scale) and WISC (Wechsler Intelligence Scale for Children), and the brain activity associated with visual and verbal processing, in order to test the validity of a distributed neural basis for intelligence. Conclusion The present results support these claims and the neural efficiency hypothesis. PMID:21423657

Signal recognition efficiencies of artificial neural-network pulse-shape discrimination in HPGe -decay searches

NASA Astrophysics Data System (ADS)

Caldwell, A.; Cossavella, F.; Majorovits, B.; Palioselitis, D.; Volynets, O.

2015-07-01

A pulse-shape discrimination method based on artificial neural networks was applied to pulses simulated for different background, signal and signal-like interactions inside a germanium detector. The simulated pulses were used to investigate variations of efficiencies as a function of used training set. It is verified that neural networks are well-suited to identify background pulses in true-coaxial high-purity germanium detectors. The systematic uncertainty on the signal recognition efficiency derived using signal-like evaluation samples from calibration measurements is estimated to be 5 %. This uncertainty is due to differences between signal and calibration samples.

Large-scale neural circuit mapping data analysis accelerated with the graphical processing unit (GPU).

PubMed

Shi, Yulin; Veidenbaum, Alexander V; Nicolau, Alex; Xu, Xiangmin

2015-01-15

Modern neuroscience research demands computing power. Neural circuit mapping studies such as those using laser scanning photostimulation (LSPS) produce large amounts of data and require intensive computation for post hoc processing and analysis. Here we report on the design and implementation of a cost-effective desktop computer system for accelerated experimental data processing with recent GPU computing technology. A new version of Matlab software with GPU enabled functions is used to develop programs that run on Nvidia GPUs to harness their parallel computing power. We evaluated both the central processing unit (CPU) and GPU-enabled computational performance of our system in benchmark testing and practical applications. The experimental results show that the GPU-CPU co-processing of simulated data and actual LSPS experimental data clearly outperformed the multi-core CPU with up to a 22× speedup, depending on computational tasks. Further, we present a comparison of numerical accuracy between GPU and CPU computation to verify the precision of GPU computation. In addition, we show how GPUs can be effectively adapted to improve the performance of commercial image processing software such as Adobe Photoshop. To our best knowledge, this is the first demonstration of GPU application in neural circuit mapping and electrophysiology-based data processing. Together, GPU enabled computation enhances our ability to process large-scale data sets derived from neural circuit mapping studies, allowing for increased processing speeds while retaining data precision. Copyright © 2014 Elsevier B.V. All rights reserved.

Large scale neural circuit mapping data analysis accelerated with the graphical processing unit (GPU)

PubMed Central

Shi, Yulin; Veidenbaum, Alexander V.; Nicolau, Alex; Xu, Xiangmin

2014-01-01

Background Modern neuroscience research demands computing power. Neural circuit mapping studies such as those using laser scanning photostimulation (LSPS) produce large amounts of data and require intensive computation for post-hoc processing and analysis. New Method Here we report on the design and implementation of a cost-effective desktop computer system for accelerated experimental data processing with recent GPU computing technology. A new version of Matlab software with GPU enabled functions is used to develop programs that run on Nvidia GPUs to harness their parallel computing power. Results We evaluated both the central processing unit (CPU) and GPU-enabled computational performance of our system in benchmark testing and practical applications. The experimental results show that the GPU-CPU co-processing of simulated data and actual LSPS experimental data clearly outperformed the multi-core CPU with up to a 22x speedup, depending on computational tasks. Further, we present a comparison of numerical accuracy between GPU and CPU computation to verify the precision of GPU computation. In addition, we show how GPUs can be effectively adapted to improve the performance of commercial image processing software such as Adobe Photoshop. Comparison with Existing Method(s) To our best knowledge, this is the first demonstration of GPU application in neural circuit mapping and electrophysiology-based data processing. Conclusions Together, GPU enabled computation enhances our ability to process large-scale data sets derived from neural circuit mapping studies, allowing for increased processing speeds while retaining data precision. PMID:25277633

Distributed computing methodology for training neural networks in an image-guided diagnostic application.

PubMed

Plagianakos, V P; Magoulas, G D; Vrahatis, M N

2006-03-01

Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

Inference in the brain: Statistics flowing in redundant population codes

PubMed Central

Pitkow, Xaq; Angelaki, Dora E

2017-01-01

It is widely believed that the brain performs approximate probabilistic inference to estimate causal variables in the world from ambiguous sensory data. To understand these computations, we need to analyze how information is represented and transformed by the actions of nonlinear recurrent neural networks. We propose that these probabilistic computations function by a message-passing algorithm operating at the level of redundant neural populations. To explain this framework, we review its underlying concepts, including graphical models, sufficient statistics, and message-passing, and then describe how these concepts could be implemented by recurrently connected probabilistic population codes. The relevant information flow in these networks will be most interpretable at the population level, particularly for redundant neural codes. We therefore outline a general approach to identify the essential features of a neural message-passing algorithm. Finally, we argue that to reveal the most important aspects of these neural computations, we must study large-scale activity patterns during moderately complex, naturalistic behaviors. PMID:28595050

Computing single step operators of logic programming in radial basis function neural networks

NASA Astrophysics Data System (ADS)

Hamadneh, Nawaf; Sathasivam, Saratha; Choon, Ong Hong

2014-07-01

Logic programming is the process that leads from an original formulation of a computing problem to executable programs. A normal logic program consists of a finite set of clauses. A valuation I of logic programming is a mapping from ground atoms to false or true. The single step operator of any logic programming is defined as a function (Tp:I→I). Logic programming is well-suited to building the artificial intelligence systems. In this study, we established a new technique to compute the single step operators of logic programming in the radial basis function neural networks. To do that, we proposed a new technique to generate the training data sets of single step operators. The training data sets are used to build the neural networks. We used the recurrent radial basis function neural networks to get to the steady state (the fixed point of the operators). To improve the performance of the neural networks, we used the particle swarm optimization algorithm to train the networks.

SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks.

PubMed

Zenke, Friedemann; Ganguli, Surya

2018-06-01

A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in silico. Here we revisit the problem of supervised learning in temporally coding multilayer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three-factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric, and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike time patterns.

Neural networks as a control methodology

NASA Technical Reports Server (NTRS)

Mccullough, Claire L.

1990-01-01

While conventional computers must be programmed in a logical fashion by a person who thoroughly understands the task to be performed, the motivation behind neural networks is to develop machines which can train themselves to perform tasks, using available information about desired system behavior and learning from experience. There are three goals of this fellowship program: (1) to evaluate various neural net methods and generate computer software to implement those deemed most promising on a personal computer equipped with Matlab; (2) to evaluate methods currently in the professional literature for system control using neural nets to choose those most applicable to control of flexible structures; and (3) to apply the control strategies chosen in (2) to a computer simulation of a test article, the Control Structures Interaction Suitcase Demonstrator, which is a portable system consisting of a small flexible beam driven by a torque motor and mounted on springs tuned to the first flexible mode of the beam. Results of each are discussed.

Medical image analysis with artificial neural networks.

PubMed

Jiang, J; Trundle, P; Ren, J

2010-12-01

Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing, with the aims of increasing awareness of how neural networks can be applied to these areas and to provide a foundation for further research and practical development. Representative techniques and algorithms are explained in detail to provide inspiring examples illustrating: (i) how a known neural network with fixed structure and training procedure could be applied to resolve a medical imaging problem; (ii) how medical images could be analysed, processed, and characterised by neural networks; and (iii) how neural networks could be expanded further to resolve problems relevant to medical imaging. In the concluding section, a highlight of comparisons among many neural network applications is included to provide a global view on computational intelligence with neural networks in medical imaging. Copyright © 2010 Elsevier Ltd. All rights reserved.

Cost-Benefit Analysis of Computer Resources for Machine Learning

USGS Publications Warehouse

Champion, Richard A.

2007-01-01

Machine learning describes pattern-recognition algorithms - in this case, probabilistic neural networks (PNNs). These can be computationally intensive, in part because of the nonlinear optimizer, a numerical process that calibrates the PNN by minimizing a sum of squared errors. This report suggests efficiencies that are expressed as cost and benefit. The cost is computer time needed to calibrate the PNN, and the benefit is goodness-of-fit, how well the PNN learns the pattern in the data. There may be a point of diminishing returns where a further expenditure of computer resources does not produce additional benefits. Sampling is suggested as a cost-reduction strategy. One consideration is how many points to select for calibration and another is the geometric distribution of the points. The data points may be nonuniformly distributed across space, so that sampling at some locations provides additional benefit while sampling at other locations does not. A stratified sampling strategy can be designed to select more points in regions where they reduce the calibration error and fewer points in regions where they do not. Goodness-of-fit tests ensure that the sampling does not introduce bias. This approach is illustrated by statistical experiments for computing correlations between measures of roadless area and population density for the San Francisco Bay Area. The alternative to training efficiencies is to rely on high-performance computer systems. These may require specialized programming and algorithms that are optimized for parallel performance.

Real-time simulation of a spiking neural network model of the basal ganglia circuitry using general purpose computing on graphics processing units.

PubMed

Igarashi, Jun; Shouno, Osamu; Fukai, Tomoki; Tsujino, Hiroshi

2011-11-01

Real-time simulation of a biologically realistic spiking neural network is necessary for evaluation of its capacity to interact with real environments. However, the real-time simulation of such a neural network is difficult due to its high computational costs that arise from two factors: (1) vast network size and (2) the complicated dynamics of biologically realistic neurons. In order to address these problems, mainly the latter, we chose to use general purpose computing on graphics processing units (GPGPUs) for simulation of such a neural network, taking advantage of the powerful computational capability of a graphics processing unit (GPU). As a target for real-time simulation, we used a model of the basal ganglia that has been developed according to electrophysiological and anatomical knowledge. The model consists of heterogeneous populations of 370 spiking model neurons, including computationally heavy conductance-based models, connected by 11,002 synapses. Simulation of the model has not yet been performed in real-time using a general computing server. By parallelization of the model on the NVIDIA Geforce GTX 280 GPU in data-parallel and task-parallel fashion, faster-than-real-time simulation was robustly realized with only one-third of the GPU's total computational resources. Furthermore, we used the GPU's full computational resources to perform faster-than-real-time simulation of three instances of the basal ganglia model; these instances consisted of 1100 neurons and 33,006 synapses and were synchronized at each calculation step. Finally, we developed software for simultaneous visualization of faster-than-real-time simulation output. These results suggest the potential power of GPGPU techniques in real-time simulation of realistic neural networks. Copyright © 2011 Elsevier Ltd. All rights reserved.

Influence of neural adaptation on dynamics and equilibrium state of neural activities in a ring neural network

NASA Astrophysics Data System (ADS)

Takiyama, Ken

2017-12-01

How neural adaptation affects neural information processing (i.e. the dynamics and equilibrium state of neural activities) is a central question in computational neuroscience. In my previous works, I analytically clarified the dynamics and equilibrium state of neural activities in a ring-type neural network model that is widely used to model the visual cortex, motor cortex, and several other brain regions. The neural dynamics and the equilibrium state in the neural network model corresponded to a Bayesian computation and statistically optimal multiple information integration, respectively, under a biologically inspired condition. These results were revealed in an analytically tractable manner; however, adaptation effects were not considered. Here, I analytically reveal how the dynamics and equilibrium state of neural activities in a ring neural network are influenced by spike-frequency adaptation (SFA). SFA is an adaptation that causes gradual inhibition of neural activity when a sustained stimulus is applied, and the strength of this inhibition depends on neural activities. I reveal that SFA plays three roles: (1) SFA amplifies the influence of external input in neural dynamics; (2) SFA allows the history of the external input to affect neural dynamics; and (3) the equilibrium state corresponds to the statistically optimal multiple information integration independent of the existence of SFA. In addition, the equilibrium state in a ring neural network model corresponds to the statistically optimal integration of multiple information sources under biologically inspired conditions, independent of the existence of SFA.

Beyond Reason: Emotion

NASA Astrophysics Data System (ADS)

Suárez Araujo, Carmen Paz; Barahona da Fonseca, Isabel; Barahona da Fonseca, José; Simões da Fonseca, J.

2004-08-01

A theoretical approach that aims to the identification of information processing that may be responsible for emotional dimensions of subjective experience is studied as an initial step in the construction of a neural net model of affective dimensions of psychological experiences. In this paper it is suggested that a way of orientated recombination of attributes can be present not only in the perceptive processing but also in cognitive ones. We will present an analysis of the most important emotion theories, we show their neural organization and we propose the neural computation approach as an appropriate framework for generating knowledge about the neural base of emotional experience. Finally, in this study we present a scheme corresponding to framework to design a computational neural multi-system for Emotion (CONEMSE).

Neural constraints on learning.

PubMed

Sadtler, Patrick T; Quick, Kristin M; Golub, Matthew D; Chase, Steven M; Ryu, Stephen I; Tyler-Kabara, Elizabeth C; Yu, Byron M; Batista, Aaron P

2014-08-28

Learning, whether motor, sensory or cognitive, requires networks of neurons to generate new activity patterns. As some behaviours are easier to learn than others, we asked if some neural activity patterns are easier to generate than others. Here we investigate whether an existing network constrains the patterns that a subset of its neurons is capable of exhibiting, and if so, what principles define this constraint. We employed a closed-loop intracortical brain-computer interface learning paradigm in which Rhesus macaques (Macaca mulatta) controlled a computer cursor by modulating neural activity patterns in the primary motor cortex. Using the brain-computer interface paradigm, we could specify and alter how neural activity mapped to cursor velocity. At the start of each session, we observed the characteristic activity patterns of the recorded neural population. The activity of a neural population can be represented in a high-dimensional space (termed the neural space), wherein each dimension corresponds to the activity of one neuron. These characteristic activity patterns comprise a low-dimensional subspace (termed the intrinsic manifold) within the neural space. The intrinsic manifold presumably reflects constraints imposed by the underlying neural circuitry. Here we show that the animals could readily learn to proficiently control the cursor using neural activity patterns that were within the intrinsic manifold. However, animals were less able to learn to proficiently control the cursor using activity patterns that were outside of the intrinsic manifold. These results suggest that the existing structure of a network can shape learning. On a timescale of hours, it seems to be difficult to learn to generate neural activity patterns that are not consistent with the existing network structure. These findings offer a network-level explanation for the observation that we are more readily able to learn new skills when they are related to the skills that we already possess.

Spatial-Temporal Reasoning Applications of Computational Intelligence in the Game of Go and Computer Networks

DTIC Science & Technology

2012-01-01

dimensionality, Tesauro used a backpropagation- based , three-layer neural network and implemented the outcome from a self-play game as the reinforcement signal...a school of fish, flock of birds, and colony of ants. Our literature review reveals that no one has used PSO to train the neural network ...trained with a variant of PSO called cellular PSO (CPSO). CSRN is a supervised learning neural network (SLNN). The proposed algorithm for the

Hybrid computing using a neural network with dynamic external memory.

PubMed

Graves, Alex; Wayne, Greg; Reynolds, Malcolm; Harley, Tim; Danihelka, Ivo; Grabska-Barwińska, Agnieszka; Colmenarejo, Sergio Gómez; Grefenstette, Edward; Ramalho, Tiago; Agapiou, John; Badia, Adrià Puigdomènech; Hermann, Karl Moritz; Zwols, Yori; Ostrovski, Georg; Cain, Adam; King, Helen; Summerfield, Christopher; Blunsom, Phil; Kavukcuoglu, Koray; Hassabis, Demis

2016-10-27

Artificial neural networks are remarkably adept at sensory processing, sequence learning and reinforcement learning, but are limited in their ability to represent variables and data structures and to store data over long timescales, owing to the lack of an external memory. Here we introduce a machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer. Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from data. When trained with supervised learning, we demonstrate that a DNC can successfully answer synthetic questions designed to emulate reasoning and inference problems in natural language. We show that it can learn tasks such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs such as transport networks and family trees. When trained with reinforcement learning, a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols. Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read-write memory.

Open angle glaucoma effects on preattentive visual search efficiency for flicker, motion displacement and orientation pop-out tasks.

PubMed

Loughman, James; Davison, Peter; Flitcroft, Ian

2007-11-01

Preattentive visual search (PAVS) describes rapid and efficient retinal and neural processing capable of immediate target detection in the visual field. Damage to the nerve fibre layer or visual pathway might reduce the efficiency with which the visual system performs such analysis. The purpose of this study was to test the hypothesis that patients with glaucoma are impaired on parallel search tasks, and that this would serve to distinguish glaucoma in early cases. Three groups of observers (glaucoma patients, suspect and normal individuals) were examined, using computer-generated flicker, orientation, and vertical motion displacement targets to assess PAVS efficiency. The task required rapid and accurate localisation of a singularity embedded in a field of 119 homogeneous distractors on either the left or right-hand side of a computer monitor. All subjects also completed a choice reaction time (CRT) task. Independent sample T tests revealed PAVS efficiency to be significantly impaired in the glaucoma group compared with both normal and suspect individuals. Performance was impaired in all types of glaucoma tested. Analysis between normal and suspect individuals revealed a significant difference only for motion displacement response times. Similar analysis using a PAVS/CRT index confirmed the glaucoma findings but also showed statistically significant differences between suspect and normal individuals across all target types. A test of PAVS efficiency appears capable of differentiating early glaucoma from both normal and suspect cases. Analysis incorporating a PAVS/CRT index enhances the diagnostic capacity to differentiate normal from suspect cases.

Progressively expanded neural network for automatic material identification in hyperspectral imagery

NASA Astrophysics Data System (ADS)

Paheding, Sidike

The science of hyperspectral remote sensing focuses on the exploitation of the spectral signatures of various materials to enhance capabilities including object detection, recognition, and material characterization. Hyperspectral imagery (HSI) has been extensively used for object detection and identification applications since it provides plenty of spectral information to uniquely identify materials by their reflectance spectra. HSI-based object detection algorithms can be generally classified into stochastic and deterministic approaches. Deterministic approaches are comparatively simple to apply since it is usually based on direct spectral similarity such as spectral angles or spectral correlation. In contrast, stochastic algorithms require statistical modeling and estimation for target class and non-target class. Over the decades, many single class object detection methods have been proposed in the literature, however, deterministic multiclass object detection in HSI has not been explored. In this work, we propose a deterministic multiclass object detection scheme, named class-associative spectral fringe-adjusted joint transform correlation. Human brain is capable of simultaneously processing high volumes of multi-modal data received every second of the day. In contrast, a machine sees input data simply as random binary numbers. Although machines are computationally efficient, they are inferior when comes to data abstraction and interpretation. Thus, mimicking the learning strength of human brain has been current trend in artificial intelligence. In this work, we present a biological inspired neural network, named progressively expanded neural network (PEN Net), based on nonlinear transformation of input neurons to a feature space for better pattern differentiation. In PEN Net, discrete fixed excitations are disassembled and scattered in the feature space as a nonlinear line. Each disassembled element on the line corresponds to a pattern with similar features. Unlike the conventional neural network where hidden neurons need to be iteratively adjusted to achieve better accuracy, our proposed PEN Net does not require hidden neurons tuning which achieves better computational efficiency, and it has also shown superior performance in HSI classification tasks compared to the state-of-the-arts. Spectral-spatial features based HSI classification framework has shown stronger strength compared to spectral-only based methods. In our lastly proposed technique, PEN Net is incorporated with multiscale spatial features (i.e., multiscale complete local binary pattern) to perform a spectral-spatial classification of HSI. Several experiments demonstrate excellent performance of our proposed technique compared to the more recent developed approaches.

Brain Signal Variability Differentially Affects Cognitive Flexibility and Cognitive Stability.

PubMed

Armbruster-Genç, Diana J N; Ueltzhöffer, Kai; Fiebach, Christian J

2016-04-06

Recent research yielded the intriguing conclusion that, in healthy adults, higher levels of variability in neuronal processes are beneficial for cognitive functioning. Beneficial effects of variability in neuronal processing can also be inferred from neurocomputational theories of working memory, albeit this holds only for tasks requiring cognitive flexibility. However, cognitive stability, i.e., the ability to maintain a task goal in the face of irrelevant distractors, should suffer under high levels of brain signal variability. To directly test this prediction, we studied both behavioral and brain signal variability during cognitive flexibility (i.e., task switching) and cognitive stability (i.e., distractor inhibition) in a sample of healthy human subjects and developed an efficient and easy-to-implement analysis approach to assess BOLD-signal variability in event-related fMRI task paradigms. Results show a general positive effect of neural variability on task performance as assessed by accuracy measures. However, higher levels of BOLD-signal variability in the left inferior frontal junction area result in reduced error rate costs during task switching and thus facilitate cognitive flexibility. In contrast, variability in the same area has a detrimental effect on cognitive stability, as shown in a negative effect of variability on response time costs during distractor inhibition. This pattern was mirrored at the behavioral level, with higher behavioral variability predicting better task switching but worse distractor inhibition performance. Our data extend previous results on brain signal variability by showing a differential effect of brain signal variability that depends on task context, in line with predictions from computational theories. Recent neuroscientific research showed that the human brain signal is intrinsically variable and suggested that this variability improves performance. Computational models of prefrontal neural networks predict differential effects of variability for different behavioral situations requiring either cognitive flexibility or stability. However, this hypothesis has so far not been put to an empirical test. In this study, we assessed cognitive flexibility and cognitive stability, and, besides a generally positive effect of neural variability on accuracy measures, we show that neural variability in a prefrontal brain area at the inferior frontal junction is differentially associated with performance: higher levels of variability are beneficial for the effectiveness of task switching (cognitive flexibility) but detrimental for the efficiency of distractor inhibition (cognitive stability). Copyright © 2016 the authors 0270-6474/16/363978-10$15.00/0.

A Neural Network Architecture For Rapid Model Indexing In Computer Vision Systems

NASA Astrophysics Data System (ADS)

Pawlicki, Ted

1988-03-01

Models of objects stored in memory have been shown to be useful for guiding the processing of computer vision systems. A major consideration in such systems, however, is how stored models are initially accessed and indexed by the system. As the number of stored models increases, the time required to search memory for the correct model becomes high. Parallel distributed, connectionist, neural networks' have been shown to have appealing content addressable memory properties. This paper discusses an architecture for efficient storage and reference of model memories stored as stable patterns of activity in a parallel, distributed, connectionist, neural network. The emergent properties of content addressability and resistance to noise are exploited to perform indexing of the appropriate object centered model from image centered primitives. The system consists of three network modules each of which represent information relative to a different frame of reference. The model memory network is a large state space vector where fields in the vector correspond to ordered component objects and relative, object based spatial relationships between the component objects. The component assertion network represents evidence about the existence of object primitives in the input image. It establishes local frames of reference for object primitives relative to the image based frame of reference. The spatial relationship constraint network is an intermediate representation which enables the association between the object based and the image based frames of reference. This intermediate level represents information about possible object orderings and establishes relative spatial relationships from the image based information in the component assertion network below. It is also constrained by the lawful object orderings in the model memory network above. The system design is consistent with current psychological theories of recognition by component. It also seems to support Marr's notions of hierarchical indexing. (i.e. the specificity, adjunct, and parent indices) It supports the notion that multiple canonical views of an object may have to be stored in memory to enable its efficient identification. The use of variable fields in the state space vectors appears to keep the number of required nodes in the network down to a tractable number while imposing a semantic value on different areas of the state space. This semantic imposition supports an interface between the analogical aspects of neural networks and the propositional paradigms of symbolic processing.

Accuracy and Calibration of Computational Approaches for Inpatient Mortality Predictive Modeling.

PubMed

Nakas, Christos T; Schütz, Narayan; Werners, Marcus; Leichtle, Alexander B

2016-01-01

Electronic Health Record (EHR) data can be a key resource for decision-making support in clinical practice in the "big data" era. The complete database from early 2012 to late 2015 involving hospital admissions to Inselspital Bern, the largest Swiss University Hospital, was used in this study, involving over 100,000 admissions. Age, sex, and initial laboratory test results were the features/variables of interest for each admission, the outcome being inpatient mortality. Computational decision support systems were utilized for the calculation of the risk of inpatient mortality. We assessed the recently proposed Acute Laboratory Risk of Mortality Score (ALaRMS) model, and further built generalized linear models, generalized estimating equations, artificial neural networks, and decision tree systems for the predictive modeling of the risk of inpatient mortality. The Area Under the ROC Curve (AUC) for ALaRMS marginally corresponded to the anticipated accuracy (AUC = 0.858). Penalized logistic regression methodology provided a better result (AUC = 0.872). Decision tree and neural network-based methodology provided even higher predictive performance (up to AUC = 0.912 and 0.906, respectively). Additionally, decision tree-based methods can efficiently handle Electronic Health Record (EHR) data that have a significant amount of missing records (in up to >50% of the studied features) eliminating the need for imputation in order to have complete data. In conclusion, we show that statistical learning methodology can provide superior predictive performance in comparison to existing methods and can also be production ready. Statistical modeling procedures provided unbiased, well-calibrated models that can be efficient decision support tools for predicting inpatient mortality and assigning preventive measures.

The role of fluid intelligence and learning in analogical reasoning: How to become neurally efficient?

PubMed

Dix, Annika; Wartenburger, Isabell; van der Meer, Elke

2016-10-01

This study on analogical reasoning evaluates the impact of fluid intelligence on adaptive changes in neural efficiency over the course of an experiment and specifies the underlying cognitive processes. Grade 10 students (N=80) solved unfamiliar geometric analogy tasks of varying difficulty. Neural efficiency was measured by the event-related desynchronization (ERD) in the alpha band, an indicator of cortical activity. Neural efficiency was defined as a low amount of cortical activity accompanying high performance during problem-solving. Students solved the tasks faster and more accurately the higher their FI was. Moreover, while high FI led to greater cortical activity in the first half of the experiment, high FI was associated with a neurally more efficient processing (i.e., better performance but same amount of cortical activity) in the second half of the experiment. Performance in difficult tasks improved over the course of the experiment for all students while neural efficiency increased for students with higher but decreased for students with lower fluid intelligence. Based on analyses of the alpha sub-bands, we argue that high fluid intelligence was associated with a stronger investment of attentional resource in the integration of information and the encoding of relations in this unfamiliar task in the first half of the experiment (lower-2 alpha band). Students with lower fluid intelligence seem to adapt their applied strategies over the course of the experiment (i.e., focusing on task-relevant information; lower-1 alpha band). Thus, the initially lower cortical activity and its increase in students with lower fluid intelligence might reflect the overcoming of mental overload that was present in the first half of the experiment. Copyright © 2016 Elsevier Inc. All rights reserved.

Neural decoding of collective wisdom with multi-brain computing.

PubMed

Eckstein, Miguel P; Das, Koel; Pham, Binh T; Peterson, Matthew F; Abbey, Craig K; Sy, Jocelyn L; Giesbrecht, Barry

2012-01-02

Group decisions and even aggregation of multiple opinions lead to greater decision accuracy, a phenomenon known as collective wisdom. Little is known about the neural basis of collective wisdom and whether its benefits arise in late decision stages or in early sensory coding. Here, we use electroencephalography and multi-brain computing with twenty humans making perceptual decisions to show that combining neural activity across brains increases decision accuracy paralleling the improvements shown by aggregating the observers' opinions. Although the largest gains result from an optimal linear combination of neural decision variables across brains, a simpler neural majority decision rule, ubiquitous in human behavior, results in substantial benefits. In contrast, an extreme neural response rule, akin to a group following the most extreme opinion, results in the least improvement with group size. Analyses controlling for number of electrodes and time-points while increasing number of brains demonstrate unique benefits arising from integrating neural activity across different brains. The benefits of multi-brain integration are present in neural activity as early as 200 ms after stimulus presentation in lateral occipital sites and no additional benefits arise in decision related neural activity. Sensory-related neural activity can predict collective choices reached by aggregating individual opinions, voting results, and decision confidence as accurately as neural activity related to decision components. Estimation of the potential for the collective to execute fast decisions by combining information across numerous brains, a strategy prevalent in many animals, shows large time-savings. Together, the findings suggest that for perceptual decisions the neural activity supporting collective wisdom and decisions arises in early sensory stages and that many properties of collective cognition are explainable by the neural coding of information across multiple brains. Finally, our methods highlight the potential of multi-brain computing as a technique to rapidly and in parallel gather increased information about the environment as well as to access collective perceptual/cognitive choices and mental states. Copyright © 2011 Elsevier Inc. All rights reserved.

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce.

PubMed

Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan

2016-01-01

A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.

Object-processing neural efficiency differentiates object from spatial visualizers.

PubMed

Motes, Michael A; Malach, Rafael; Kozhevnikov, Maria

2008-11-19

The visual system processes object properties and spatial properties in distinct subsystems, and we hypothesized that this distinction might extend to individual differences in visual processing. We conducted a functional MRI study investigating the neural underpinnings of individual differences in object versus spatial visual processing. Nine participants of high object-processing ability ('object' visualizers) and eight participants of high spatial-processing ability ('spatial' visualizers) were scanned, while they performed an object-processing task. Object visualizers showed lower bilateral neural activity in lateral occipital complex and lower right-lateralized neural activity in dorsolateral prefrontal cortex. The data indicate that high object-processing ability is associated with more efficient use of visual-object resources, resulting in less neural activity in the object-processing pathway.

Neuromechanic: a computational platform for simulation and analysis of the neural control of movement

PubMed Central

Bunderson, Nathan E.; Bingham, Jeffrey T.; Sohn, M. Hongchul; Ting, Lena H.; Burkholder, Thomas J.

2015-01-01

Neuromusculoskeletal models solve the basic problem of determining how the body moves under the influence of external and internal forces. Existing biomechanical modeling programs often emphasize dynamics with the goal of finding a feed-forward neural program to replicate experimental data or of estimating force contributions or individual muscles. The computation of rigid-body dynamics, muscle forces, and activation of the muscles are often performed separately. We have developed an intrinsically forward computational platform (Neuromechanic, www.neuromechanic.com) that explicitly represents the interdependencies among rigid body dynamics, frictional contact, muscle mechanics, and neural control modules. This formulation has significant advantages for optimization and forward simulation, particularly with application to neural controllers with feedback or regulatory features. Explicit inclusion of all state dependencies allows calculation of system derivatives with respect to kinematic states as well as muscle and neural control states, thus affording a wealth of analytical tools, including linearization, stability analyses and calculation of initial conditions for forward simulations. In this review, we describe our algorithm for generating state equations and explain how they may be used in integration, linearization and stability analysis tools to provide structural insights into the neural control of movement. PMID:23027632

Biological neural networks as model systems for designing future parallel processing computers

NASA Technical Reports Server (NTRS)

Ross, Muriel D.

1991-01-01

One of the more interesting debates of the present day centers on whether human intelligence can be simulated by computer. The author works under the premise that neurons individually are not smart at all. Rather, they are physical units which are impinged upon continuously by other matter that influences the direction of voltage shifts across the units membranes. It is only the action of a great many neurons, billions in the case of the human nervous system, that intelligent behavior emerges. What is required to understand even the simplest neural system is painstaking analysis, bit by bit, of the architecture and the physiological functioning of its various parts. The biological neural network studied, the vestibular utricular and saccular maculas of the inner ear, are among the most simple of the mammalian neural networks to understand and model. While there is still a long way to go to understand even this most simple neural network in sufficient detail for extrapolation to computers and robots, a start was made. Moreover, the insights obtained and the technologies developed help advance the understanding of the more complex neural networks that underlie human intelligence.

Neuromechanic: a computational platform for simulation and analysis of the neural control of movement.

PubMed

Bunderson, Nathan E; Bingham, Jeffrey T; Sohn, M Hongchul; Ting, Lena H; Burkholder, Thomas J

2012-10-01

Neuromusculoskeletal models solve the basic problem of determining how the body moves under the influence of external and internal forces. Existing biomechanical modeling programs often emphasize dynamics with the goal of finding a feed-forward neural program to replicate experimental data or of estimating force contributions or individual muscles. The computation of rigid-body dynamics, muscle forces, and activation of the muscles are often performed separately. We have developed an intrinsically forward computational platform (Neuromechanic, www.neuromechanic.com) that explicitly represents the interdependencies among rigid body dynamics, frictional contact, muscle mechanics, and neural control modules. This formulation has significant advantages for optimization and forward simulation, particularly with application to neural controllers with feedback or regulatory features. Explicit inclusion of all state dependencies allows calculation of system derivatives with respect to kinematic states and muscle and neural control states, thus affording a wealth of analytical tools, including linearization, stability analyses and calculation of initial conditions for forward simulations. In this review, we describe our algorithm for generating state equations and explain how they may be used in integration, linearization, and stability analysis tools to provide structural insights into the neural control of movement. Copyright © 2012 John Wiley & Sons, Ltd.