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).

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.

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.

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

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…

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.

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.

Application of artificial neural networks to composite ply micromechanics

NASA Technical Reports Server (NTRS)

Brown, D. A.; Murthy, P. L. N.; Berke, L.

1991-01-01

Artificial neural networks can provide improved computational efficiency relative to existing methods when an algorithmic description of functional relationships is either totally unavailable or is complex in nature. For complex calculations, significant reductions in elapsed computation time are possible. The primary goal is to demonstrate the applicability of artificial neural networks to composite material characterization. As a test case, a neural network was trained to accurately predict composite hygral, thermal, and mechanical properties when provided with basic information concerning the environment, constituent materials, and component ratios used in the creation of the composite. A brief introduction on neural networks is provided along with a description of the project itself.

Deep learning with coherent nanophotonic circuits

NASA Astrophysics Data System (ADS)

Shen, Yichen; Harris, Nicholas C.; Skirlo, Scott; Prabhu, Mihika; Baehr-Jones, Tom; Hochberg, Michael; Sun, Xin; Zhao, Shijie; Larochelle, Hugo; Englund, Dirk; Soljačić, Marin

2017-07-01

Artificial neural networks are computational network models inspired by signal processing in the brain. These models have dramatically improved performance for many machine-learning tasks, including speech and image recognition. However, today's computing hardware is inefficient at implementing neural networks, in large part because much of it was designed for von Neumann computing schemes. Significant effort has been made towards developing electronic architectures tuned to implement artificial neural networks that exhibit improved computational speed and accuracy. Here, we propose a new architecture for a fully optical neural network that, in principle, could offer an enhancement in computational speed and power efficiency over state-of-the-art electronics for conventional inference tasks. We experimentally demonstrate the essential part of the concept using a programmable nanophotonic processor featuring a cascaded array of 56 programmable Mach-Zehnder interferometers in a silicon photonic integrated circuit and show its utility for vowel recognition.

Electronic Neural Networks

NASA Technical Reports Server (NTRS)

Thakoor, Anil

1990-01-01

Viewgraphs on electronic neural networks for space station are presented. Topics covered include: electronic neural networks; electronic implementations; VLSI/thin film hybrid hardware for neurocomputing; computations with analog parallel processing; features of neuroprocessors; applications of neuroprocessors; neural network hardware for terrain trafficability determination; a dedicated processor for path planning; neural network system interface; neural network for robotic control; error backpropagation algorithm for learning; resource allocation matrix; global optimization neuroprocessor; and electrically programmable read only thin-film synaptic array.

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.

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).

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

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.

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.

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.

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 network approaches to capture temporal information

NASA Astrophysics Data System (ADS)

van Veelen, Martijn; Nijhuis, Jos; Spaanenburg, Ben

2000-05-01

The automated design and construction of neural networks receives growing attention of the neural networks community. Both the growing availability of computing power and development of mathematical and probabilistic theory have had severe impact on the design and modelling approaches of neural networks. This impact is most apparent in the use of neural networks to time series prediction. In this paper, we give our views on past, contemporary and future design and modelling approaches to neural forecasting.

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.

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

Advances in Artificial Neural Networks - Methodological Development and Application

USDA-ARS?s Scientific Manuscript database

Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...

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.

SPECIAL ISSUE ON OPTICAL PROCESSING OF INFORMATION: Optical neural networks based on holographic correlators

NASA Astrophysics Data System (ADS)

Sokolov, V. K.; Shubnikov, E. I.

1995-10-01

The three most important models of neural networks — a bidirectional associative memory, Hopfield networks, and adaptive resonance networks — are used as examples to show that a holographic correlator has its place in the neural computing paradigm.

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.

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.

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.

DANoC: An Efficient Algorithm and Hardware Codesign of Deep Neural Networks on Chip.

PubMed

Zhou, Xichuan; Li, Shengli; Tang, Fang; Hu, Shengdong; Lin, Zhi; Zhang, Lei

2017-07-18

Deep neural networks (NNs) are the state-of-the-art models for understanding the content of images and videos. However, implementing deep NNs in embedded systems is a challenging task, e.g., a typical deep belief network could exhaust gigabytes of memory and result in bandwidth and computational bottlenecks. To address this challenge, this paper presents an algorithm and hardware codesign for efficient deep neural computation. A hardware-oriented deep learning algorithm, named the deep adaptive network, is proposed to explore the sparsity of neural connections. By adaptively removing the majority of neural connections and robustly representing the reserved connections using binary integers, the proposed algorithm could save up to 99.9% memory utility and computational resources without undermining classification accuracy. An efficient sparse-mapping-memory-based hardware architecture is proposed to fully take advantage of the algorithmic optimization. Different from traditional Von Neumann architecture, the deep-adaptive network on chip (DANoC) brings communication and computation in close proximity to avoid power-hungry parameter transfers between on-board memory and on-chip computational units. Experiments over different image classification benchmarks show that the DANoC system achieves competitively high accuracy and efficiency comparing with the state-of-the-art approaches.

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.

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].

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification

NASA Astrophysics Data System (ADS)

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-12-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification.

PubMed

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-12-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification

PubMed Central

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-01-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value. PMID:27905520

Discrete-time neural network for fast solving large linear L1 estimation problems and its application to image restoration.

PubMed

Xia, Youshen; Sun, Changyin; Zheng, Wei Xing

2012-05-01

There is growing interest in solving linear L1 estimation problems for sparsity of the solution and robustness against non-Gaussian noise. This paper proposes a discrete-time neural network which can calculate large linear L1 estimation problems fast. The proposed neural network has a fixed computational step length and is proved to be globally convergent to an optimal solution. Then, the proposed neural network is efficiently applied to image restoration. Numerical results show that the proposed neural network is not only efficient in solving degenerate problems resulting from the nonunique solutions of the linear L1 estimation problems but also needs much less computational time than the related algorithms in solving both linear L1 estimation and image restoration problems.

An Expedient Study on Back-Propagation (BPN) Neural Networks for Modeling Automated Evaluation of the Answers and Progress of Deaf Students' That Possess Basic Knowledge of the English Language and Computer Skills

NASA Astrophysics Data System (ADS)

Vrettaros, John; Vouros, George; Drigas, Athanasios S.

This article studies the expediency of using neural networks technology and the development of back-propagation networks (BPN) models for modeling automated evaluation of the answers and progress of deaf students' that possess basic knowledge of the English language and computer skills, within a virtual e-learning environment. The performance of the developed neural models is evaluated with the correlation factor between the neural networks' response values and the real value data as well as the percentage measurement of the error between the neural networks' estimate values and the real value data during its training process and afterwards with unknown data that weren't used in the training process.

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...

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

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 .

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

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.

Geometric Bioinspired Networks for Recognition of 2-D and 3-D Low-Level Structures and Transformations.

PubMed

Bayro-Corrochano, Eduardo; Vazquez-Santacruz, Eduardo; Moya-Sanchez, Eduardo; Castillo-Munis, Efrain

2016-10-01

This paper presents the design of radial basis function geometric bioinspired networks and their applications. Until now, the design of neural networks has been inspired by the biological models of neural networks but mostly using vector calculus and linear algebra. However, these designs have never shown the role of geometric computing. The question is how biological neural networks handle complex geometric representations involving Lie group operations like rotations. Even though the actual artificial neural networks are biologically inspired, they are just models which cannot reproduce a plausible biological process. Until now researchers have not shown how, using these models, one can incorporate them into the processing of geometric computing. Here, for the first time in the artificial neural networks domain, we address this issue by designing a kind of geometric RBF using the geometric algebra framework. As a result, using our artificial networks, we show how geometric computing can be carried out by the artificial neural networks. Such geometric neural networks have a great potential in robot vision. This is the most important aspect of this contribution to propose artificial geometric neural networks for challenging tasks in perception and action. In our experimental analysis, we show the applicability of our geometric designs, and present interesting experiments using 2-D data of real images and 3-D screw axis data. In general, our models should be used to process different types of inputs, such as visual cues, touch (texture, elasticity, temperature), taste, and sound. One important task of a perception-action system is to fuse a variety of cues coming from the environment and relate them via a sensor-motor manifold with motor modules to carry out diverse reasoned actions.

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.

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.

Learning Universal Computations with Spikes

PubMed Central

Thalmeier, Dominik; Uhlmann, Marvin; Kappen, Hilbert J.; Memmesheimer, Raoul-Martin

2016-01-01

Providing the neurobiological basis of information processing in higher animals, spiking neural networks must be able to learn a variety of complicated computations, including the generation of appropriate, possibly delayed reactions to inputs and the self-sustained generation of complex activity patterns, e.g. for locomotion. Many such computations require previous building of intrinsic world models. Here we show how spiking neural networks may solve these different tasks. Firstly, we derive constraints under which classes of spiking neural networks lend themselves to substrates of powerful general purpose computing. The networks contain dendritic or synaptic nonlinearities and have a constrained connectivity. We then combine such networks with learning rules for outputs or recurrent connections. We show that this allows to learn even difficult benchmark tasks such as the self-sustained generation of desired low-dimensional chaotic dynamics or memory-dependent computations. Furthermore, we show how spiking networks can build models of external world systems and use the acquired knowledge to control them. PMID:27309381

Machine Learning and Quantum Mechanics

NASA Astrophysics Data System (ADS)

Chapline, George

The author has previously pointed out some similarities between selforganizing neural networks and quantum mechanics. These types of neural networks were originally conceived of as away of emulating the cognitive capabilities of the human brain. Recently extensions of these networks, collectively referred to as deep learning networks, have strengthened the connection between self-organizing neural networks and human cognitive capabilities. In this note we consider whether hardware quantum devices might be useful for emulating neural networks with human-like cognitive capabilities, or alternatively whether implementations of deep learning neural networks using conventional computers might lead to better algorithms for solving the many body Schrodinger equation.

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.

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.

Using Neural Net Technology To Enhance the Efficiency of a Computer Adaptive Testing Application.

ERIC Educational Resources Information Center

Van Nelson, C.; Henriksen, Larry W.

The potential for computer adaptive testing (CAT) has been well documented. In order to improve the efficiency of this process, it may be possible to utilize a neural network, or more specifically, a back propagation neural network. The paper asserts that in order to accomplish this end, it must be shown that grouping examinees by ability as…

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.

Electronic neural networks for global optimization

NASA Technical Reports Server (NTRS)

Thakoor, A. P.; Moopenn, A. W.; Eberhardt, S.

1990-01-01

An electronic neural network with feedback architecture, implemented in analog custom VLSI is described. Its application to problems of global optimization for dynamic assignment is discussed. The convergence properties of the neural network hardware are compared with computer simulation results. The neural network's ability to provide optimal or near optimal solutions within only a few neuron time constants, a speed enhancement of several orders of magnitude over conventional search methods, is demonstrated. The effect of noise on the circuit dynamics and the convergence behavior of the neural network hardware is also examined.

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.

Neural network applications in telecommunications

NASA Technical Reports Server (NTRS)

Alspector, Joshua

1994-01-01

Neural network capabilities include automatic and organized handling of complex information, quick adaptation to continuously changing environments, nonlinear modeling, and parallel implementation. This viewgraph presentation presents Bellcore work on applications, learning chip computational function, learning system block diagram, neural network equalization, broadband access control, calling-card fraud detection, software reliability prediction, and conclusions.

Neuromorphic Computing for Temporal Scientific Data Classification

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

Schuman, Catherine D.; Potok, Thomas E.; Young, Steven

In this work, we apply a spiking neural network model and an associated memristive neuromorphic implementation to an application in classifying temporal scientific data. We demonstrate that the spiking neural network model achieves comparable results to a previously reported convolutional neural network model, with significantly fewer neurons and synapses required.

Computational neural networks in chemistry: Model free mapping devices for predicting chemical reactivity from molecular structure

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

Elrod, D.W.

1992-01-01

Computational neural networks (CNNs) are a computational paradigm inspired by the brain's massively parallel network of highly interconnected neurons. The power of computational neural networks derives not so much from their ability to model the brain as from their ability to learn by example and to map highly complex, nonlinear functions, without the need to explicitly specify the functional relationship. Two central questions about CNNs were investigated in the context of predicting chemical reactions: (1) the mapping properties of neural networks and (2) the representation of chemical information for use in CNNs. Chemical reactivity is here considered an example ofmore » a complex, nonlinear function of molecular structure. CNN's were trained using modifications of the back propagation learning rule to map a three dimensional response surface similar to those typically observed in quantitative structure-activity and structure-property relationships. The computational neural network's mapping of the response surface was found to be robust to the effects of training sample size, noisy data and intercorrelated input variables. The investigation of chemical structure representation led to the development of a molecular structure-based connection-table representation suitable for neural network training. An extension of this work led to a BE-matrix structure representation that was found to be general for several classes of reactions. The CNN prediction of chemical reactivity and regiochemistry was investigated for electrophilic aromatic substitution reactions, Markovnikov addition to alkenes, Saytzeff elimination from haloalkanes, Diels-Alder cycloaddition, and retro Diels-Alder ring opening reactions using these connectivity-matrix derived representations. The reaction predictions made by the CNNs were more accurate than those of an expert system and were comparable to predictions made by chemists.« less

Some comparisons of complexity in dictionary-based and linear computational models.

PubMed

Gnecco, Giorgio; Kůrková, Věra; Sanguineti, Marcello

2011-03-01

Neural networks provide a more flexible approximation of functions than traditional linear regression. In the latter, one can only adjust the coefficients in linear combinations of fixed sets of functions, such as orthogonal polynomials or Hermite functions, while for neural networks, one may also adjust the parameters of the functions which are being combined. However, some useful properties of linear approximators (such as uniqueness, homogeneity, and continuity of best approximation operators) are not satisfied by neural networks. Moreover, optimization of parameters in neural networks becomes more difficult than in linear regression. Experimental results suggest that these drawbacks of neural networks are offset by substantially lower model complexity, allowing accuracy of approximation even in high-dimensional cases. We give some theoretical results comparing requirements on model complexity for two types of approximators, the traditional linear ones and so called variable-basis types, which include neural networks, radial, and kernel models. We compare upper bounds on worst-case errors in variable-basis approximation with lower bounds on such errors for any linear approximator. Using methods from nonlinear approximation and integral representations tailored to computational units, we describe some cases where neural networks outperform any linear approximator. Copyright © 2010 Elsevier Ltd. All rights reserved.

Container-code recognition system based on computer vision and deep neural networks

NASA Astrophysics Data System (ADS)

Liu, Yi; Li, Tianjian; Jiang, Li; Liang, Xiaoyao

2018-04-01

Automatic container-code recognition system becomes a crucial requirement for ship transportation industry in recent years. In this paper, an automatic container-code recognition system based on computer vision and deep neural networks is proposed. The system consists of two modules, detection module and recognition module. The detection module applies both algorithms based on computer vision and neural networks, and generates a better detection result through combination to avoid the drawbacks of the two methods. The combined detection results are also collected for online training of the neural networks. The recognition module exploits both character segmentation and end-to-end recognition, and outputs the recognition result which passes the verification. When the recognition module generates false recognition, the result will be corrected and collected for online training of the end-to-end recognition sub-module. By combining several algorithms, the system is able to deal with more situations, and the online training mechanism can improve the performance of the neural networks at runtime. The proposed system is able to achieve 93% of overall recognition accuracy.

Using Neural Networks to Improve the Performance of Radiative Transfer Modeling Used for Geometry Dependent LER Calculations

NASA Astrophysics Data System (ADS)

Fasnacht, Z.; Qin, W.; Haffner, D. P.; Loyola, D. G.; Joiner, J.; Krotkov, N. A.; Vasilkov, A. P.; Spurr, R. J. D.

2017-12-01

In order to estimate surface reflectance used in trace gas retrieval algorithms, radiative transfer models (RTM) such as the Vector Linearized Discrete Ordinate Radiative Transfer Model (VLIDORT) can be used to simulate the top of the atmosphere (TOA) radiances with advanced models of surface properties. With large volumes of satellite data, these model simulations can become computationally expensive. Look up table interpolation can improve the computational cost of the calculations, but the non-linear nature of the radiances requires a dense node structure if interpolation errors are to be minimized. In order to reduce our computational effort and improve the performance of look-up tables, neural networks can be trained to predict these radiances. We investigate the impact of using look-up table interpolation versus a neural network trained using the smart sampling technique, and show that neural networks can speed up calculations and reduce errors while using significantly less memory and RTM calls. In future work we will implement a neural network in operational processing to meet growing demands for reflectance modeling in support of high spatial resolution satellite missions.

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.

Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing.

PubMed

Kriegeskorte, Nikolaus

2015-11-24

Recent advances in neural network modeling have enabled major strides in computer vision and other artificial intelligence applications. Human-level visual recognition abilities are coming within reach of artificial systems. Artificial neural networks are inspired by the brain, and their computations could be implemented in biological neurons. Convolutional feedforward networks, which now dominate computer vision, take further inspiration from the architecture of the primate visual hierarchy. However, the current models are designed with engineering goals, not to model brain computations. Nevertheless, initial studies comparing internal representations between these models and primate brains find surprisingly similar representational spaces. With human-level performance no longer out of reach, we are entering an exciting new era, in which we will be able to build biologically faithful feedforward and recurrent computational models of how biological brains perform high-level feats of intelligence, including vision.

Bio-Inspired Computation: Clock-Free, Grid-Free, Scale-Free and Symbol Free

DTIC Science & Technology

2015-06-11

for Prediction Tasks in Spiking Neural Networks ." Artificial Neural Networks and Machine Learning–ICANN 2014. Springer, 2014. pp 635-642. Gibson, T...Henderson, JA and Wiles, J. "Predicting temporal sequences using an event-based spiking neural network incorporating learnable delays." IEEE...Adelaide (2014 Jan). Gibson, T and Wiles, J "Predicting temporal sequences using an event-based spiking neural network incorporating learnable delays" at

An Intelligent Ensemble Neural Network Model for Wind Speed Prediction in Renewable Energy Systems.

PubMed

Ranganayaki, V; Deepa, S N

2016-01-01

Various criteria are proposed to select the number of hidden neurons in artificial neural network (ANN) models and based on the criterion evolved an intelligent ensemble neural network model is proposed to predict wind speed in renewable energy applications. The intelligent ensemble neural model based wind speed forecasting is designed by averaging the forecasted values from multiple neural network models which includes multilayer perceptron (MLP), multilayer adaptive linear neuron (Madaline), back propagation neural network (BPN), and probabilistic neural network (PNN) so as to obtain better accuracy in wind speed prediction with minimum error. The random selection of hidden neurons numbers in artificial neural network results in overfitting or underfitting problem. This paper aims to avoid the occurrence of overfitting and underfitting problems. The selection of number of hidden neurons is done in this paper employing 102 criteria; these evolved criteria are verified by the computed various error values. The proposed criteria for fixing hidden neurons are validated employing the convergence theorem. The proposed intelligent ensemble neural model is applied for wind speed prediction application considering the real time wind data collected from the nearby locations. The obtained simulation results substantiate that the proposed ensemble model reduces the error value to minimum and enhances the accuracy. The computed results prove the effectiveness of the proposed ensemble neural network (ENN) model with respect to the considered error factors in comparison with that of the earlier models available in the literature.

An Intelligent Ensemble Neural Network Model for Wind Speed Prediction in Renewable Energy Systems

PubMed Central

Ranganayaki, V.; Deepa, S. N.

2016-01-01

Various criteria are proposed to select the number of hidden neurons in artificial neural network (ANN) models and based on the criterion evolved an intelligent ensemble neural network model is proposed to predict wind speed in renewable energy applications. The intelligent ensemble neural model based wind speed forecasting is designed by averaging the forecasted values from multiple neural network models which includes multilayer perceptron (MLP), multilayer adaptive linear neuron (Madaline), back propagation neural network (BPN), and probabilistic neural network (PNN) so as to obtain better accuracy in wind speed prediction with minimum error. The random selection of hidden neurons numbers in artificial neural network results in overfitting or underfitting problem. This paper aims to avoid the occurrence of overfitting and underfitting problems. The selection of number of hidden neurons is done in this paper employing 102 criteria; these evolved criteria are verified by the computed various error values. The proposed criteria for fixing hidden neurons are validated employing the convergence theorem. The proposed intelligent ensemble neural model is applied for wind speed prediction application considering the real time wind data collected from the nearby locations. The obtained simulation results substantiate that the proposed ensemble model reduces the error value to minimum and enhances the accuracy. The computed results prove the effectiveness of the proposed ensemble neural network (ENN) model with respect to the considered error factors in comparison with that of the earlier models available in the literature. PMID:27034973

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.

Neural networks and applications tutorial

NASA Astrophysics Data System (ADS)

Guyon, I.

1991-09-01

The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

The use of artificial neural networks in experimental data acquisition and aerodynamic design

NASA Technical Reports Server (NTRS)

Meade, Andrew J., Jr.

1991-01-01

It is proposed that an artificial neural network be used to construct an intelligent data acquisition system. The artificial neural networks (ANN) model has a potential for replacing traditional procedures as well as for use in computational fluid dynamics validation. Potential advantages of the ANN model are listed. As a proof of concept, the author modeled a NACA 0012 airfoil at specific conditions, using the neural network simulator NETS, developed by James Baffes of the NASA Johnson Space Center. The neural network predictions were compared to the actual data. It is concluded that artificial neural networks can provide an elegant and valuable class of mathematical tools for data analysis.

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.

A Study for the Feature Selection to Identify GIEMSA-Stained Human Chromosomes Based on Artificial Neural Network

DTIC Science & Technology

2001-10-25

neural network (ANN) has been adopted for the human chromosome classification. It is important to select optimum features for training neural network...Many studies for computer-based chromosome analysis have shown that it is possible to classify chromosomes into 24 subgroups. In addition, artificial

Evolving neural networks with genetic algorithms to study the string landscape

NASA Astrophysics Data System (ADS)

Ruehle, Fabian

2017-08-01

We study possible applications of artificial neural networks to examine the string landscape. Since the field of application is rather versatile, we propose to dynamically evolve these networks via genetic algorithms. This means that we start from basic building blocks and combine them such that the neural network performs best for the application we are interested in. We study three areas in which neural networks can be applied: to classify models according to a fixed set of (physically) appealing features, to find a concrete realization for a computation for which the precise algorithm is known in principle but very tedious to actually implement, and to predict or approximate the outcome of some involved mathematical computation which performs too inefficient to apply it, e.g. in model scans within the string landscape. We present simple examples that arise in string phenomenology for all three types of problems and discuss how they can be addressed by evolving neural networks from genetic algorithms.

A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network

NASA Astrophysics Data System (ADS)

Mahmoudi, Fariborz; Mirzashaeri, Mohsen; Shahamatnia, Ehsan; Faridnia, Saed

This paper introduces a novel design for handwritten letter recognition by employing a hybrid back-propagation neural network with an enhanced evolutionary algorithm. Feeding the neural network consists of a new approach which is invariant to translation, rotation, and scaling of input letters. Evolutionary algorithm is used for the global search of the search space and the back-propagation algorithm is used for the local search. The results have been computed by implementing this approach for recognizing 26 English capital letters in the handwritings of different people. The computational results show that the neural network reaches very satisfying results with relatively scarce input data and a promising performance improvement in convergence of the hybrid evolutionary back-propagation algorithms is exhibited.

Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics

PubMed Central

Burms, Jeroen; Caluwaerts, Ken; Dambre, Joni

2015-01-01

In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimize the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics. PMID:26347645

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.

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.

ChainMail based neural dynamics modeling of soft tissue deformation for surgical simulation.

PubMed

Zhang, Jinao; Zhong, Yongmin; Smith, Julian; Gu, Chengfan

2017-07-20

Realistic and real-time modeling and simulation of soft tissue deformation is a fundamental research issue in the field of surgical simulation. In this paper, a novel cellular neural network approach is presented for modeling and simulation of soft tissue deformation by combining neural dynamics of cellular neural network with ChainMail mechanism. The proposed method formulates the problem of elastic deformation into cellular neural network activities to avoid the complex computation of elasticity. The local position adjustments of ChainMail are incorporated into the cellular neural network as the local connectivity of cells, through which the dynamic behaviors of soft tissue deformation are transformed into the neural dynamics of cellular neural network. Experiments demonstrate that the proposed neural network approach is capable of modeling the soft tissues' nonlinear deformation and typical mechanical behaviors. The proposed method not only improves ChainMail's linear deformation with the nonlinear characteristics of neural dynamics but also enables the cellular neural network to follow the principle of continuum mechanics to simulate soft tissue deformation.

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.

A loop-based neural architecture for structured behavior encoding and decoding.

PubMed

Gisiger, Thomas; Boukadoum, Mounir

2018-02-01

We present a new type of artificial neural network that generalizes on anatomical and dynamical aspects of the mammal brain. Its main novelty lies in its topological structure which is built as an array of interacting elementary motifs shaped like loops. These loops come in various types and can implement functions such as gating, inhibitory or executive control, or encoding of task elements to name a few. Each loop features two sets of neurons and a control region, linked together by non-recurrent projections. The two neural sets do the bulk of the loop's computations while the control unit specifies the timing and the conditions under which the computations implemented by the loop are to be performed. By functionally linking many such loops together, a neural network is obtained that may perform complex cognitive computations. To demonstrate the potential offered by such a system, we present two neural network simulations. The first illustrates the structure and dynamics of a single loop implementing a simple gating mechanism. The second simulation shows how connecting four loops in series can produce neural activity patterns that are sufficient to pass a simplified delayed-response task. We also show that this network reproduces electrophysiological measurements gathered in various regions of the brain of monkeys performing similar tasks. We also demonstrate connections between this type of neural network and recurrent or long short-term memory network models, and suggest ways to generalize them for future artificial intelligence research. Copyright © 2017 Elsevier Ltd. All rights reserved.

Introduction to Concepts in Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Niebur, Dagmar

1995-01-01

This introduction to artificial neural networks summarizes some basic concepts of computational neuroscience and the resulting models of artificial neurons. The terminology of biological and artificial neurons, biological and machine learning and neural processing is introduced. The concepts of supervised and unsupervised learning are explained with examples from the power system area. Finally, a taxonomy of different types of neurons and different classes of artificial neural networks is presented.

Benchmark for Peak Detection Algorithms in Fiber Bragg Grating Interrogation and a New Neural Network for its Performance Improvement

PubMed Central

Negri, Lucas; Nied, Ademir; Kalinowski, Hypolito; Paterno, Aleksander

2011-01-01

This paper presents a benchmark for peak detection algorithms employed in fiber Bragg grating spectrometric interrogation systems. The accuracy, precision, and computational performance of currently used algorithms and those of a new proposed artificial neural network algorithm are compared. Centroid and gaussian fitting algorithms are shown to have the highest precision but produce systematic errors that depend on the FBG refractive index modulation profile. The proposed neural network displays relatively good precision with reduced systematic errors and improved computational performance when compared to other networks. Additionally, suitable algorithms may be chosen with the general guidelines presented. PMID:22163806

Data systems and computer science: Neural networks base R/T program overview

NASA Technical Reports Server (NTRS)

Gulati, Sandeep

1991-01-01

The research base, in the U.S. and abroad, for the development of neural network technology is discussed. The technical objectives are to develop and demonstrate adaptive, neural information processing concepts. The leveraging of external funding is also discussed.

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.

Multispectral image fusion using neural networks

NASA Technical Reports Server (NTRS)

Kagel, J. H.; Platt, C. A.; Donaven, T. W.; Samstad, E. A.

1990-01-01

A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard, a circuit card assembly, and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations, results, and a description of the prototype system are presented.

Using Neural Networks in the Mapping of Mixed Discrete/Continuous Design Spaces With Application to Structural Design

DTIC Science & Technology

1994-02-01

desired that the problem to which the design space mapping techniques were applied be easily analyzed, yet provide a design space with realistic complexity...consistent fully stressed solution. 3 DESIGN SPACE MAPPING In order to reduce the computational expense required to optimize design spaces, neural networks...employed in this study. Some of the issues involved in using neural networks to do design space mapping are how to configure the neural network, how much

An adaptive Hinfinity controller design for bank-to-turn missiles using ridge Gaussian neural networks.

PubMed

Lin, Chuan-Kai; Wang, Sheng-De

2004-11-01

A new autopilot design for bank-to-turn (BTT) missiles is presented. In the design of autopilot, a ridge Gaussian neural network with local learning capability and fewer tuning parameters than Gaussian neural networks is proposed to model the controlled nonlinear systems. We prove that the proposed ridge Gaussian neural network, which can be a universal approximator, equals the expansions of rotated and scaled Gaussian functions. Although ridge Gaussian neural networks can approximate the nonlinear and complex systems accurately, the small approximation errors may affect the tracking performance significantly. Therefore, by employing the Hinfinity control theory, it is easy to attenuate the effects of the approximation errors of the ridge Gaussian neural networks to a prescribed level. Computer simulation results confirm the effectiveness of the proposed ridge Gaussian neural networks-based autopilot with Hinfinity stabilization.

Combined Use of Tissue Morphology, Neural Network Analysis of Chromatin Texture and Clinical Variables to Predict Prostate Cancer Agressiveness from Biopsy Water

DTIC Science & Technology

2000-10-01

Purpose: To combine clinical, serum, pathologic and computer derived information into an artificial neural network to develop/validate a model to...Development of an artificial neural network (year 02). Prospective validation of this model (projected year 03). All models will be tested and

Combined Use of Tissue Morphology, Neural Network Analysis of Chromatin Texture & Clinical Variables to Predict Prostate Cancer Agressiveness from Biopsy Material

DTIC Science & Technology

1999-10-01

THE PURPOSE OF THIS REPORT IS TO COMBINE CLINICAL, SERUM, PATHOLOGICAL AND COMPUTER DERIVED INFORMATION INTO AN ARTIFICIAL NEURAL NETWORK TO DEVELOP...01). Development of a artificial neural network model (year 02). Prospective validation of this model (projected year 03). All models will be tested

Analog Processor To Solve Optimization Problems

NASA Technical Reports Server (NTRS)

Duong, Tuan A.; Eberhardt, Silvio P.; Thakoor, Anil P.

1993-01-01

Proposed analog processor solves "traveling-salesman" problem, considered paradigm of global-optimization problems involving routing or allocation of resources. Includes electronic neural network and auxiliary circuitry based partly on concepts described in "Neural-Network Processor Would Allocate Resources" (NPO-17781) and "Neural Network Solves 'Traveling-Salesman' Problem" (NPO-17807). Processor based on highly parallel computing solves problem in significantly less time.

Coherence resonance in bursting neural networks

NASA Astrophysics Data System (ADS)

Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J.

2015-10-01

Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal—a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.

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.

Application of Neural Network Optimized by Mind Evolutionary Computation in Building Energy Prediction

NASA Astrophysics Data System (ADS)

Song, Chen; Zhong-Cheng, Wu; Hong, Lv

2018-03-01

Building Energy forecasting plays an important role in energy management and plan. Using mind evolutionary algorithm to find the optimal network weights and threshold, to optimize the BP neural network, can overcome the problem of the BP neural network into a local minimum point. The optimized network is used for time series prediction, and the same month forecast, to get two predictive values. Then two kinds of predictive values are put into neural network, to get the final forecast value. The effectiveness of the method was verified by experiment with the energy value of three buildings in Hefei.

NETS

NASA Technical Reports Server (NTRS)

Baffes, Paul T.

1993-01-01

NETS development tool provides environment for simulation and development of neural networks - computer programs that "learn" from experience. Written in ANSI standard C, program allows user to generate C code for implementation of neural network.

A Direct Position-Determination Approach for Multiple Sources Based on Neural Network Computation.

PubMed

Chen, Xin; Wang, Ding; Yin, Jiexin; Wu, Ying

2018-06-13

The most widely used localization technology is the two-step method that localizes transmitters by measuring one or more specified positioning parameters. Direct position determination (DPD) is a promising technique that directly localizes transmitters from sensor outputs and can offer superior localization performance. However, existing DPD algorithms such as maximum likelihood (ML)-based and multiple signal classification (MUSIC)-based estimations are computationally expensive, making it difficult to satisfy real-time demands. To solve this problem, we propose the use of a modular neural network for multiple-source DPD. In this method, the area of interest is divided into multiple sub-areas. Multilayer perceptron (MLP) neural networks are employed to detect the presence of a source in a sub-area and filter sources in other sub-areas, and radial basis function (RBF) neural networks are utilized for position estimation. Simulation results show that a number of appropriately trained neural networks can be successfully used for DPD. The performance of the proposed MLP-MLP-RBF method is comparable to the performance of the conventional MUSIC-based DPD algorithm for various signal-to-noise ratios and signal power ratios. Furthermore, the MLP-MLP-RBF network is less computationally intensive than the classical DPD algorithm and is therefore an attractive choice for real-time applications.

Predicting Time-to-Relapse in Breast Cancer Using Neural Networks

DTIC Science & Technology

1997-12-01

CODE 17. SECURITY CLASSIFICATION OF REPORT Unclassified 118. SECURITY CLASSIFICATION OF THIS PAGE Unclassified 19. SECURITY CLASSIFICATION OF...Lowell WE, and Davis GL. A neural network that predicts psychiatric length of stay. MD Computing 10:87-92, 1993. Ebell MH. Artificial neural netowrks

A Dynamic Connectome Supports the Emergence of Stable Computational Function of Neural Circuits through Reward-Based Learning.

PubMed

Kappel, David; Legenstein, Robert; Habenschuss, Stefan; Hsieh, Michael; Maass, Wolfgang

2018-01-01

Synaptic connections between neurons in the brain are dynamic because of continuously ongoing spine dynamics, axonal sprouting, and other processes. In fact, it was recently shown that the spontaneous synapse-autonomous component of spine dynamics is at least as large as the component that depends on the history of pre- and postsynaptic neural activity. These data are inconsistent with common models for network plasticity and raise the following questions: how can neural circuits maintain a stable computational function in spite of these continuously ongoing processes, and what could be functional uses of these ongoing processes? Here, we present a rigorous theoretical framework for these seemingly stochastic spine dynamics and rewiring processes in the context of reward-based learning tasks. We show that spontaneous synapse-autonomous processes, in combination with reward signals such as dopamine, can explain the capability of networks of neurons in the brain to configure themselves for specific computational tasks, and to compensate automatically for later changes in the network or task. Furthermore, we show theoretically and through computer simulations that stable computational performance is compatible with continuously ongoing synapse-autonomous changes. After reaching good computational performance it causes primarily a slow drift of network architecture and dynamics in task-irrelevant dimensions, as observed for neural activity in motor cortex and other areas. On the more abstract level of reinforcement learning the resulting model gives rise to an understanding of reward-driven network plasticity as continuous sampling of network configurations.

A Dynamic Connectome Supports the Emergence of Stable Computational Function of Neural Circuits through Reward-Based Learning

PubMed Central

Habenschuss, Stefan; Hsieh, Michael

2018-01-01

Synaptic connections between neurons in the brain are dynamic because of continuously ongoing spine dynamics, axonal sprouting, and other processes. In fact, it was recently shown that the spontaneous synapse-autonomous component of spine dynamics is at least as large as the component that depends on the history of pre- and postsynaptic neural activity. These data are inconsistent with common models for network plasticity and raise the following questions: how can neural circuits maintain a stable computational function in spite of these continuously ongoing processes, and what could be functional uses of these ongoing processes? Here, we present a rigorous theoretical framework for these seemingly stochastic spine dynamics and rewiring processes in the context of reward-based learning tasks. We show that spontaneous synapse-autonomous processes, in combination with reward signals such as dopamine, can explain the capability of networks of neurons in the brain to configure themselves for specific computational tasks, and to compensate automatically for later changes in the network or task. Furthermore, we show theoretically and through computer simulations that stable computational performance is compatible with continuously ongoing synapse-autonomous changes. After reaching good computational performance it causes primarily a slow drift of network architecture and dynamics in task-irrelevant dimensions, as observed for neural activity in motor cortex and other areas. On the more abstract level of reinforcement learning the resulting model gives rise to an understanding of reward-driven network plasticity as continuous sampling of network configurations. PMID:29696150

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.

Six networks on a universal neuromorphic computing substrate.

PubMed

Pfeil, Thomas; Grübl, Andreas; Jeltsch, Sebastian; Müller, Eric; Müller, Paul; Petrovici, Mihai A; Schmuker, Michael; Brüderle, Daniel; Schemmel, Johannes; Meier, Karlheinz

2013-01-01

In this study, we present a highly configurable neuromorphic computing substrate and use it for emulating several types of neural networks. At the heart of this system lies a mixed-signal chip, with analog implementations of neurons and synapses and digital transmission of action potentials. Major advantages of this emulation device, which has been explicitly designed as a universal neural network emulator, are its inherent parallelism and high acceleration factor compared to conventional computers. Its configurability allows the realization of almost arbitrary network topologies and the use of widely varied neuronal and synaptic parameters. Fixed-pattern noise inherent to analog circuitry is reduced by calibration routines. An integrated development environment allows neuroscientists to operate the device without any prior knowledge of neuromorphic circuit design. As a showcase for the capabilities of the system, we describe the successful emulation of six different neural networks which cover a broad spectrum of both structure and functionality.

Six Networks on a Universal Neuromorphic Computing Substrate

PubMed Central

Pfeil, Thomas; Grübl, Andreas; Jeltsch, Sebastian; Müller, Eric; Müller, Paul; Petrovici, Mihai A.; Schmuker, Michael; Brüderle, Daniel; Schemmel, Johannes; Meier, Karlheinz

2013-01-01

In this study, we present a highly configurable neuromorphic computing substrate and use it for emulating several types of neural networks. At the heart of this system lies a mixed-signal chip, with analog implementations of neurons and synapses and digital transmission of action potentials. Major advantages of this emulation device, which has been explicitly designed as a universal neural network emulator, are its inherent parallelism and high acceleration factor compared to conventional computers. Its configurability allows the realization of almost arbitrary network topologies and the use of widely varied neuronal and synaptic parameters. Fixed-pattern noise inherent to analog circuitry is reduced by calibration routines. An integrated development environment allows neuroscientists to operate the device without any prior knowledge of neuromorphic circuit design. As a showcase for the capabilities of the system, we describe the successful emulation of six different neural networks which cover a broad spectrum of both structure and functionality. PMID:23423583

Development of programmable artificial neural networks

NASA Technical Reports Server (NTRS)

Meade, Andrew J.

1993-01-01

Conventionally programmed digital computers can process numbers with great speed and precision, but do not easily recognize patterns or imprecise or contradictory data. Instead of being programmed in the conventional sense, artificial neural networks are capable of self-learning through exposure to repeated examples. However, the training of an ANN can be a time consuming and unpredictable process. A general method is being developed to mate the adaptability of the ANN with the speed and precision of the digital computer. This method was successful in building feedforward networks that can approximate functions and their partial derivatives from examples in a single iteration. The general method also allows the formation of feedforward networks that can approximate the solution to nonlinear ordinary and partial differential equations to desired accuracy without the need of examples. It is believed that continued research will produce artificial neural networks that can be used with confidence in practical scientific computing and engineering applications.

Proceedings of the Second Joint Technology Workshop on Neural Networks and Fuzzy Logic, volume 2

NASA Technical Reports Server (NTRS)

Lea, Robert N. (Editor); Villarreal, James A. (Editor)

1991-01-01

Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by NASA and the University of Texas, Houston. Topics addressed included adaptive systems, learning algorithms, network architectures, vision, robotics, neurobiological connections, speech recognition and synthesis, fuzzy set theory and application, control and dynamics processing, space applications, fuzzy logic and neural network computers, approximate reasoning, and multiobject decision making.

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.

Neural Network Optimization of Ligament Stiffnesses for the Enhanced Predictive Ability of a Patient-Specific, Computational Foot/Ankle Model.

PubMed

Chande, Ruchi D; Wayne, Jennifer S

2017-09-01

Computational models of diarthrodial joints serve to inform the biomechanical function of these structures, and as such, must be supplied appropriate inputs for performance that is representative of actual joint function. Inputs for these models are sourced from both imaging modalities as well as literature. The latter is often the source of mechanical properties for soft tissues, like ligament stiffnesses; however, such data are not always available for all the soft tissues nor is it known for patient-specific work. In the current research, a method to improve the ligament stiffness definition for a computational foot/ankle model was sought with the greater goal of improving the predictive ability of the computational model. Specifically, the stiffness values were optimized using artificial neural networks (ANNs); both feedforward and radial basis function networks (RBFNs) were considered. Optimal networks of each type were determined and subsequently used to predict stiffnesses for the foot/ankle model. Ultimately, the predicted stiffnesses were considered reasonable and resulted in enhanced performance of the computational model, suggesting that artificial neural networks can be used to optimize stiffness inputs.

A case for spiking neural network simulation based on configurable multiple-FPGA systems.

PubMed

Yang, Shufan; Wu, Qiang; Li, Renfa

2011-09-01

Recent neuropsychological research has begun to reveal that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of neuronal systems. Simulation of the spiking neural networks in software is unable to rapidly generate output spikes in large-scale of neural network. An alternative approach, hardware implementation of such system, provides the possibility to generate independent spikes precisely and simultaneously output spike waves in real time, under the premise that spiking neural network can take full advantage of hardware inherent parallelism. We introduce a configurable FPGA-oriented hardware platform for spiking neural network simulation in this work. We aim to use this platform to combine the speed of dedicated hardware with the programmability of software so that it might allow neuroscientists to put together sophisticated computation experiments of their own model. A feed-forward hierarchy network is developed as a case study to describe the operation of biological neural systems (such as orientation selectivity of visual cortex) and computational models of such systems. This model demonstrates how a feed-forward neural network constructs the circuitry required for orientation selectivity and provides platform for reaching a deeper understanding of the primate visual system. In the future, larger scale models based on this framework can be used to replicate the actual architecture in visual cortex, leading to more detailed predictions and insights into visual perception phenomenon.

Predictive Behavior of a Computational Foot/Ankle Model through Artificial Neural Networks.

PubMed

Chande, Ruchi D; Hargraves, Rosalyn Hobson; Ortiz-Robinson, Norma; Wayne, Jennifer S

2017-01-01

Computational models are useful tools to study the biomechanics of human joints. Their predictive performance is heavily dependent on bony anatomy and soft tissue properties. Imaging data provides anatomical requirements while approximate tissue properties are implemented from literature data, when available. We sought to improve the predictive capability of a computational foot/ankle model by optimizing its ligament stiffness inputs using feedforward and radial basis function neural networks. While the former demonstrated better performance than the latter per mean square error, both networks provided reasonable stiffness predictions for implementation into the computational model.

Computational properties of networks of synchronous groups of spiking neurons.

PubMed

Dayhoff, Judith E

2007-09-01

We demonstrate a model in which synchronously firing ensembles of neurons are networked to produce computational results. Each ensemble is a group of biological integrate-and-fire spiking neurons, with probabilistic interconnections between groups. An analogy is drawn in which each individual processing unit of an artificial neural network corresponds to a neuronal group in a biological model. The activation value of a unit in the artificial neural network corresponds to the fraction of active neurons, synchronously firing, in a biological neuronal group. Weights of the artificial neural network correspond to the product of the interconnection density between groups, the group size of the presynaptic group, and the postsynaptic potential heights in the synchronous group model. All three of these parameters can modulate connection strengths between neuronal groups in the synchronous group models. We give an example of nonlinear classification (XOR) and a function approximation example in which the capability of the artificial neural network can be captured by a neural network model with biological integrate-and-fire neurons configured as a network of synchronously firing ensembles of such neurons. We point out that the general function approximation capability proven for feedforward artificial neural networks appears to be approximated by networks of neuronal groups that fire in synchrony, where the groups comprise integrate-and-fire neurons. We discuss the advantages of this type of model for biological systems, its possible learning mechanisms, and the associated timing relationships.

Evaluation of a parallel implementation of the learning portion of the backward error propagation neural network: experiments in artifact identification.

PubMed Central

Sittig, D. F.; Orr, J. A.

1991-01-01

Various methods have been proposed in an attempt to solve problems in artifact and/or alarm identification including expert systems, statistical signal processing techniques, and artificial neural networks (ANN). ANNs consist of a large number of simple processing units connected by weighted links. To develop truly robust ANNs, investigators are required to train their networks on huge training data sets, requiring enormous computing power. We implemented a parallel version of the backward error propagation neural network training algorithm in the widely portable parallel programming language C-Linda. A maximum speedup of 4.06 was obtained with six processors. This speedup represents a reduction in total run-time from approximately 6.4 hours to 1.5 hours. We conclude that use of the master-worker model of parallel computation is an excellent method for obtaining speedups in the backward error propagation neural network training algorithm. PMID:1807607

A method of optimized neural network by L-M algorithm to transformer winding hot spot temperature forecasting

NASA Astrophysics Data System (ADS)

Wei, B. G.; Wu, X. Y.; Yao, Z. F.; Huang, H.

2017-11-01

Transformers are essential devices of the power system. The accurate computation of the highest temperature (HST) of a transformer’s windings is very significant, as for the HST is a fundamental parameter in controlling the load operation mode and influencing the life time of the insulation. Based on the analysis of the heat transfer processes and the thermal characteristics inside transformers, there is taken into consideration the influence of factors like the sunshine, external wind speed etc. on the oil-immersed transformers. Experimental data and the neural network are used for modeling and protesting of the HST, and furthermore, investigations are conducted on the optimization of the structure and algorithms of neutral network are conducted. Comparison is made between the measured values and calculated values by using the recommended algorithm of IEC60076 and by using the neural network algorithm proposed by the authors; comparison that shows that the value computed with the neural network algorithm approximates better the measured value than the value computed with the algorithm proposed by IEC60076.

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.

Low-dimensional recurrent neural network-based Kalman filter for speech enhancement.

PubMed

Xia, Youshen; Wang, Jun

2015-07-01

This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the proposed recurrent neural network and the speech signal is then recovered from Kalman filtering. The proposed recurrent neural network is globally asymptomatically stable to the noise-constrained estimate. Because the noise-constrained estimate has a robust performance against non-Gaussian noise, the proposed recurrent neural network-based speech enhancement algorithm can minimize the estimation error of Kalman filter parameters in non-Gaussian noise. Furthermore, having a low-dimensional model feature, the proposed neural network-based speech enhancement algorithm has a much faster speed than two existing recurrent neural networks-based speech enhancement algorithms. Simulation results show that the proposed recurrent neural network-based speech enhancement algorithm can produce a good performance with fast computation and noise reduction. Copyright © 2015 Elsevier Ltd. All rights reserved.

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.

Neural networks: Application to medical imaging

NASA Technical Reports Server (NTRS)

Clarke, Laurence P.

1994-01-01

The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.

On the sample complexity of learning for networks of spiking neurons with nonlinear synaptic interactions.

PubMed

Schmitt, Michael

2004-09-01

We study networks of spiking neurons that use the timing of pulses to encode information. Nonlinear interactions model the spatial groupings of synapses on the neural dendrites and describe the computations performed at local branches. Within a theoretical framework of learning we analyze the question of how many training examples these networks must receive to be able to generalize well. Bounds for this sample complexity of learning can be obtained in terms of a combinatorial parameter known as the pseudodimension. This dimension characterizes the computational richness of a neural network and is given in terms of the number of network parameters. Two types of feedforward architectures are considered: constant-depth networks and networks of unconstrained depth. We derive asymptotically tight bounds for each of these network types. Constant depth networks are shown to have an almost linear pseudodimension, whereas the pseudodimension of general networks is quadratic. Networks of spiking neurons that use temporal coding are becoming increasingly more important in practical tasks such as computer vision, speech recognition, and motor control. The question of how well these networks generalize from a given set of training examples is a central issue for their successful application as adaptive systems. The results show that, although coding and computation in these networks is quite different and in many cases more powerful, their generalization capabilities are at least as good as those of traditional neural network models.

Review On Applications Of Neural Network To Computer Vision

NASA Astrophysics Data System (ADS)

Li, Wei; Nasrabadi, Nasser M.

1989-03-01

Neural network models have many potential applications to computer vision due to their parallel structures, learnability, implicit representation of domain knowledge, fault tolerance, and ability of handling statistical data. This paper demonstrates the basic principles, typical models and their applications in this field. Variety of neural models, such as associative memory, multilayer back-propagation perceptron, self-stabilized adaptive resonance network, hierarchical structured neocognitron, high order correlator, network with gating control and other models, can be applied to visual signal recognition, reinforcement, recall, stereo vision, motion, object tracking and other vision processes. Most of the algorithms have been simulated on com-puters. Some have been implemented with special hardware. Some systems use features, such as edges and profiles, of images as the data form for input. Other systems use raw data as input signals to the networks. We will present some novel ideas contained in these approaches and provide a comparison of these methods. Some unsolved problems are mentioned, such as extracting the intrinsic properties of the input information, integrating those low level functions to a high-level cognitive system, achieving invariances and other problems. Perspectives of applications of some human vision models and neural network models are analyzed.

Vectorized algorithms for spiking neural network simulation.

PubMed

Brette, Romain; Goodman, Dan F M

2011-06-01

High-level languages (Matlab, Python) are popular in neuroscience because they are flexible and accelerate development. However, for simulating spiking neural networks, the cost of interpretation is a bottleneck. We describe a set of algorithms to simulate large spiking neural networks efficiently with high-level languages using vector-based operations. These algorithms constitute the core of Brian, a spiking neural network simulator written in the Python language. Vectorized simulation makes it possible to combine the flexibility of high-level languages with the computational efficiency usually associated with compiled languages.

A novel joint-processing adaptive nonlinear equalizer using a modular recurrent neural network for chaotic communication systems.

PubMed

Zhao, Haiquan; Zeng, Xiangping; Zhang, Jiashu; Liu, Yangguang; Wang, Xiaomin; Li, Tianrui

2011-01-01

To eliminate nonlinear channel distortion in chaotic communication systems, a novel joint-processing adaptive nonlinear equalizer based on a pipelined recurrent neural network (JPRNN) is proposed, using a modified real-time recurrent learning (RTRL) algorithm. Furthermore, an adaptive amplitude RTRL algorithm is adopted to overcome the deteriorating effect introduced by the nesting process. Computer simulations illustrate that the proposed equalizer outperforms the pipelined recurrent neural network (PRNN) and recurrent neural network (RNN) equalizers. Copyright © 2010 Elsevier Ltd. All rights reserved.

FPGA platform for prototyping and evaluation of neural network automotive applications

NASA Technical Reports Server (NTRS)

Aranki, N.; Tawel, R.

2002-01-01

In this paper we present an FPGA based reconfigurable computing platform for prototyping and evaluation of advanced neural network based applications for control and diagnostics in an automotive sub-systems.

Using Artificial Neural Networks in Educational Research: Some Comparisons with Linear Statistical Models.

ERIC Educational Resources Information Center

Everson, Howard T.; And Others

This paper explores the feasibility of neural computing methods such as artificial neural networks (ANNs) and abductory induction mechanisms (AIM) for use in educational measurement. ANNs and AIMS methods are contrasted with more traditional statistical techniques, such as multiple regression and discriminant function analyses, for making…

Neural Network Machine Learning and Dimension Reduction for Data Visualization

NASA Technical Reports Server (NTRS)

Liles, Charles A.

2014-01-01

Neural network machine learning in computer science is a continuously developing field of study. Although neural network models have been developed which can accurately predict a numeric value or nominal classification, a general purpose method for constructing neural network architecture has yet to be developed. Computer scientists are often forced to rely on a trial-and-error process of developing and improving accurate neural network models. In many cases, models are constructed from a large number of input parameters. Understanding which input parameters have the greatest impact on the prediction of the model is often difficult to surmise, especially when the number of input variables is very high. This challenge is often labeled the "curse of dimensionality" in scientific fields. However, techniques exist for reducing the dimensionality of problems to just two dimensions. Once a problem's dimensions have been mapped to two dimensions, it can be easily plotted and understood by humans. The ability to visualize a multi-dimensional dataset can provide a means of identifying which input variables have the highest effect on determining a nominal or numeric output. Identifying these variables can provide a better means of training neural network models; models can be more easily and quickly trained using only input variables which appear to affect the outcome variable. The purpose of this project is to explore varying means of training neural networks and to utilize dimensional reduction for visualizing and understanding complex datasets.

Neural-Network-Development Program

NASA Technical Reports Server (NTRS)

Phillips, Todd A.

1993-01-01

NETS, software tool for development and evaluation of neural networks, provides simulation of neural-network algorithms plus computing environment for development of such algorithms. Uses back-propagation learning method for all of networks it creates. Enables user to customize patterns of connections between layers of network. Also provides features for saving, during learning process, values of weights, providing more-precise control over learning process. Written in ANSI standard C language. Machine-independent version (MSC-21588) includes only code for command-line-interface version of NETS 3.0.

ARACHNE: A neural-neuroglial network builder with remotely controlled parallel computing

PubMed Central

Rusakov, Dmitri A.; Savtchenko, Leonid P.

2017-01-01

Creating and running realistic models of neural networks has hitherto been a task for computing professionals rather than experimental neuroscientists. This is mainly because such networks usually engage substantial computational resources, the handling of which requires specific programing skills. Here we put forward a newly developed simulation environment ARACHNE: it enables an investigator to build and explore cellular networks of arbitrary biophysical and architectural complexity using the logic of NEURON and a simple interface on a local computer or a mobile device. The interface can control, through the internet, an optimized computational kernel installed on a remote computer cluster. ARACHNE can combine neuronal (wired) and astroglial (extracellular volume-transmission driven) network types and adopt realistic cell models from the NEURON library. The program and documentation (current version) are available at GitHub repository https://github.com/LeonidSavtchenko/Arachne under the MIT License (MIT). PMID:28362877

A biologically inspired neural network for dynamic programming.

PubMed

Francelin Romero, R A; Kacpryzk, J; Gomide, F

2001-12-01

An artificial neural network with a two-layer feedback topology and generalized recurrent neurons, for solving nonlinear discrete dynamic optimization problems, is developed. A direct method to assign the weights of neural networks is presented. The method is based on Bellmann's Optimality Principle and on the interchange of information which occurs during the synaptic chemical processing among neurons. The neural network based algorithm is an advantageous approach for dynamic programming due to the inherent parallelism of the neural networks; further it reduces the severity of computational problems that can occur in methods like conventional methods. Some illustrative application examples are presented to show how this approach works out including the shortest path and fuzzy decision making problems.

Neural nets on the MPP

NASA Technical Reports Server (NTRS)

Hastings, Harold M.; Waner, Stefan

1987-01-01

The Massively Parallel Processor (MPP) is an ideal machine for computer experiments with simulated neural nets as well as more general cellular automata. Experiments using the MPP with a formal model neural network are described. The results on problem mapping and computational efficiency apply equally well to the neural nets of Hopfield, Hinton et al., and Geman and Geman.

Classification of Magneto-Optic Images using Neural Networks

NASA Technical Reports Server (NTRS)

Nath, Shridhar; Wincheski, Buzz; Fulton, Jim; Namkung, Min

1994-01-01

A real time imaging system with a neural network classifier has been incorporated on a Macintosh computer in conjunction with an MOI system. This system images rivets on aircraft aluminium structures using eddy currents and magnetic imaging. Moment invariant functions from the image of a rivet is used to train a multilayer perceptron neural network to classify the rivets as good or bad (rivets with cracks).

Calculation of Crystallographic Texture of BCC Steels During Cold Rolling

NASA Astrophysics Data System (ADS)

Das, Arpan

2017-05-01

BCC alloys commonly tend to develop strong fibre textures and often represent as isointensity diagrams in φ 1 sections or by fibre diagrams. Alpha fibre in bcc steels is generally characterised by <110> crystallographic axis parallel to the rolling direction. The objective of present research is to correlate carbon content, carbide dispersion, rolling reduction, Euler angles (ϕ) (when φ 1 = 0° and φ 2 = 45° along alpha fibre) and the resulting alpha fibre texture orientation intensity. In the present research, Bayesian neural computation has been employed to correlate these and compare with the existing feed-forward neural network model comprehensively. Excellent match to the measured texture data within the bounding box of texture training data set has been already predicted through the feed-forward neural network model by other researchers. Feed-forward neural network prediction outside the bounds of training texture data showed deviations from the expected values. Currently, Bayesian computation has been similarly applied to confirm that the predictions are reasonable in the context of basic metallurgical principles, and matched better outside the bounds of training texture data set than the reported feed-forward neural network. Bayesian computation puts error bars on predicted values and allows significance of each individual parameters to be estimated. Additionally, it is also possible by Bayesian computation to estimate the isolated influence of particular variable such as carbon concentration, which exactly cannot in practice be varied independently. This shows the ability of the Bayesian neural network to examine the new phenomenon in situations where the data cannot be accessed through experiments.

High-Lift Optimization Design Using Neural Networks on a Multi-Element Airfoil

NASA Technical Reports Server (NTRS)

Greenman, Roxana M.; Roth, Karlin R.; Smith, Charles A. (Technical Monitor)

1998-01-01

The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle at which it occurs. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag, and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural networks were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 83% compared with traditional gradient-based optimization procedures for multiple optimization runs.

Neural Dynamics as Sampling: A Model for Stochastic Computation in Recurrent Networks of Spiking Neurons

PubMed Central

Buesing, Lars; Bill, Johannes; Nessler, Bernhard; Maass, Wolfgang

2011-01-01

The organization of computations in networks of spiking neurons in the brain is still largely unknown, in particular in view of the inherently stochastic features of their firing activity and the experimentally observed trial-to-trial variability of neural systems in the brain. In principle there exists a powerful computational framework for stochastic computations, probabilistic inference by sampling, which can explain a large number of macroscopic experimental data in neuroscience and cognitive science. But it has turned out to be surprisingly difficult to create a link between these abstract models for stochastic computations and more detailed models of the dynamics of networks of spiking neurons. Here we create such a link and show that under some conditions the stochastic firing activity of networks of spiking neurons can be interpreted as probabilistic inference via Markov chain Monte Carlo (MCMC) sampling. Since common methods for MCMC sampling in distributed systems, such as Gibbs sampling, are inconsistent with the dynamics of spiking neurons, we introduce a different approach based on non-reversible Markov chains that is able to reflect inherent temporal processes of spiking neuronal activity through a suitable choice of random variables. We propose a neural network model and show by a rigorous theoretical analysis that its neural activity implements MCMC sampling of a given distribution, both for the case of discrete and continuous time. This provides a step towards closing the gap between abstract functional models of cortical computation and more detailed models of networks of spiking neurons. PMID:22096452

Dynamical synapses enhance neural information processing: gracefulness, accuracy, and mobility.

PubMed

Fung, C C Alan; Wong, K Y Michael; Wang, He; Wu, Si

2012-05-01

Experimental data have revealed that neuronal connection efficacy exhibits two forms of short-term plasticity: short-term depression (STD) and short-term facilitation (STF). They have time constants residing between fast neural signaling and rapid learning and may serve as substrates for neural systems manipulating temporal information on relevant timescales. This study investigates the impact of STD and STF on the dynamics of continuous attractor neural networks and their potential roles in neural information processing. We find that STD endows the network with slow-decaying plateau behaviors: the network that is initially being stimulated to an active state decays to a silent state very slowly on the timescale of STD rather than on that of neuralsignaling. This provides a mechanism for neural systems to hold sensory memory easily and shut off persistent activities gracefully. With STF, we find that the network can hold a memory trace of external inputs in the facilitated neuronal interactions, which provides a way to stabilize the network response to noisy inputs, leading to improved accuracy in population decoding. Furthermore, we find that STD increases the mobility of the network states. The increased mobility enhances the tracking performance of the network in response to time-varying stimuli, leading to anticipative neural responses. In general, we find that STD and STP tend to have opposite effects on network dynamics and complementary computational advantages, suggesting that the brain may employ a strategy of weighting them differentially depending on the computational purpose.

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.

Streaming parallel GPU acceleration of large-scale filter-based spiking neural networks.

PubMed

Slażyński, Leszek; Bohte, Sander

2012-01-01

The arrival of graphics processing (GPU) cards suitable for massively parallel computing promises affordable large-scale neural network simulation previously only available at supercomputing facilities. While the raw numbers suggest that GPUs may outperform CPUs by at least an order of magnitude, the challenge is to develop fine-grained parallel algorithms to fully exploit the particulars of GPUs. Computation in a neural network is inherently parallel and thus a natural match for GPU architectures: given inputs, the internal state for each neuron can be updated in parallel. We show that for filter-based spiking neurons, like the Spike Response Model, the additive nature of membrane potential dynamics enables additional update parallelism. This also reduces the accumulation of numerical errors when using single precision computation, the native precision of GPUs. We further show that optimizing simulation algorithms and data structures to the GPU's architecture has a large pay-off: for example, matching iterative neural updating to the memory architecture of the GPU speeds up this simulation step by a factor of three to five. With such optimizations, we can simulate in better-than-realtime plausible spiking neural networks of up to 50 000 neurons, processing over 35 million spiking events per second.

Vibrational Analysis of Engine Components Using Neural-Net Processing and Electronic Holography

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Fite, E. Brian; Mehmed, Oral; Thorp, Scott A.

1997-01-01

The use of computational-model trained artificial neural networks to acquire damage specific information from electronic holograms is discussed. A neural network is trained to transform two time-average holograms into a pattern related to the bending-induced-strain distribution of the vibrating component. The bending distribution is very sensitive to component damage unlike the characteristic fringe pattern or the displacement amplitude distribution. The neural network processor is fast for real-time visualization of damage. The two-hologram limit makes the processor more robust to speckle pattern decorrelation. Undamaged and cracked cantilever plates serve as effective objects for testing the combination of electronic holography and neural-net processing. The requirements are discussed for using finite-element-model trained neural networks for field inspections of engine components. The paper specifically discusses neural-network fringe pattern analysis in the presence of the laser speckle effect and the performances of two limiting cases of the neural-net architecture.

Vibrational Analysis of Engine Components Using Neural-Net Processing and Electronic Holography

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Fite, E. Brian; Mehmed, Oral; Thorp, Scott A.

1998-01-01

The use of computational-model trained artificial neural networks to acquire damage specific information from electronic holograms is discussed. A neural network is trained to transform two time-average holograms into a pattern related to the bending-induced-strain distribution of the vibrating component. The bending distribution is very sensitive to component damage unlike the characteristic fringe pattern or the displacement amplitude distribution. The neural network processor is fast for real-time visualization of damage. The two-hologram limit makes the processor more robust to speckle pattern decorrelation. Undamaged and cracked cantilever plates serve as effective objects for testing the combination of electronic holography and neural-net processing. The requirements are discussed for using finite-element-model trained neural networks for field inspections of engine components. The paper specifically discusses neural-network fringe pattern analysis in the presence of the laser speckle effect and the performances of two limiting cases of the neural-net architecture.

The Study of Learners' Preference for Visual Complexity on Small Screens of Mobile Computers Using Neural Networks

ERIC Educational Resources Information Center

Wang, Lan-Ting; Lee, Kun-Chou

2014-01-01

The vision plays an important role in educational technologies because it can produce and communicate quite important functions in teaching and learning. In this paper, learners' preference for the visual complexity on small screens of mobile computers is studied by neural networks. The visual complexity in this study is divided into five…

CLIPS on the NeXT computer

NASA Technical Reports Server (NTRS)

Charnock, Elizabeth; Eng, Norman

1990-01-01

This paper discusses the integration of CLIPS into a hybrid expert system neural network AI tool for the NeXT computer. The main discussion is devoted to the joining of these two AI paradigms in a mutually beneficial relationship. We conclude that expert systems and neural networks should not be considered as competing AI implementation methods, but rather as complimentary components of a whole.

Neural networks for vertical microcode compaction

NASA Astrophysics Data System (ADS)

Chu, Pong P.

1992-09-01

Neural networks provide an alternative way to solve complex optimization problems. Instead of performing a program of instructions sequentially as in a traditional computer, neural network model explores many competing hypotheses simultaneously using its massively parallel net. The paper shows how to use the neural network approach to perform vertical micro-code compaction for a micro-programmed control unit. The compaction procedure includes two basic steps. The first step determines the compatibility classes and the second step selects a minimal subset to cover the control signals. Since the selection process is an NP- complete problem, to find an optimal solution is impractical. In this study, we employ a customized neural network to obtain the minimal subset. We first formalize this problem, and then define an `energy function' and map it to a two-layer fully connected neural network. The modified network has two types of neurons and can always obtain a valid solution.

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.

Vector Symbolic Spiking Neural Network Model of Hippocampal Subarea CA1 Novelty Detection Functionality.

PubMed

Agerskov, Claus

2016-04-01

A neural network model is presented of novelty detection in the CA1 subdomain of the hippocampal formation from the perspective of information flow. This computational model is restricted on several levels by both anatomical information about hippocampal circuitry and behavioral data from studies done in rats. Several studies report that the CA1 area broadcasts a generalized novelty signal in response to changes in the environment. Using the neural engineering framework developed by Eliasmith et al., a spiking neural network architecture is created that is able to compare high-dimensional vectors, symbolizing semantic information, according to the semantic pointer hypothesis. This model then computes the similarity between the vectors, as both direct inputs and a recalled memory from a long-term memory network by performing the dot-product operation in a novelty neural network architecture. The developed CA1 model agrees with available neuroanatomical data, as well as the presented behavioral data, and so it is a biologically realistic model of novelty detection in the hippocampus, which can provide a feasible explanation for experimentally observed dynamics.

Development of a computational model on the neural activity patterns of a visual working memory in a hierarchical feedforward Network

NASA Astrophysics Data System (ADS)

An, Soyoung; Choi, Woochul; Paik, Se-Bum

2015-11-01

Understanding the mechanism of information processing in the human brain remains a unique challenge because the nonlinear interactions between the neurons in the network are extremely complex and because controlling every relevant parameter during an experiment is difficult. Therefore, a simulation using simplified computational models may be an effective approach. In the present study, we developed a general model of neural networks that can simulate nonlinear activity patterns in the hierarchical structure of a neural network system. To test our model, we first examined whether our simulation could match the previously-observed nonlinear features of neural activity patterns. Next, we performed a psychophysics experiment for a simple visual working memory task to evaluate whether the model could predict the performance of human subjects. Our studies show that the model is capable of reproducing the relationship between memory load and performance and may contribute, in part, to our understanding of how the structure of neural circuits can determine the nonlinear neural activity patterns in the human brain.

Thermalnet: a Deep Convolutional Network for Synthetic Thermal Image Generation

NASA Astrophysics Data System (ADS)

Kniaz, V. V.; Gorbatsevich, V. S.; Mizginov, V. A.

2017-05-01

Deep convolutional neural networks have dramatically changed the landscape of the modern computer vision. Nowadays methods based on deep neural networks show the best performance among image recognition and object detection algorithms. While polishing of network architectures received a lot of scholar attention, from the practical point of view the preparation of a large image dataset for a successful training of a neural network became one of major challenges. This challenge is particularly profound for image recognition in wavelengths lying outside the visible spectrum. For example no infrared or radar image datasets large enough for successful training of a deep neural network are available to date in public domain. Recent advances of deep neural networks prove that they are also capable to do arbitrary image transformations such as super-resolution image generation, grayscale image colorisation and imitation of style of a given artist. Thus a natural question arise: how could be deep neural networks used for augmentation of existing large image datasets? This paper is focused on the development of the Thermalnet deep convolutional neural network for augmentation of existing large visible image datasets with synthetic thermal images. The Thermalnet network architecture is inspired by colorisation deep neural networks.

Pencil-and-Paper Neural Networks: An Undergraduate Laboratory Exercise in Computational Neuroscience

PubMed Central

Crisp, Kevin M.; Sutter, Ellen N.; Westerberg, Jacob A.

2015-01-01

Although it has been more than 70 years since McCulloch and Pitts published their seminal work on artificial neural networks, such models remain primarily in the domain of computer science departments in undergraduate education. This is unfortunate, as simple network models offer undergraduate students a much-needed bridge between cellular neurobiology and processes governing thought and behavior. Here, we present a very simple laboratory exercise in which students constructed, trained and tested artificial neural networks by hand on paper. They explored a variety of concepts, including pattern recognition, pattern completion, noise elimination and stimulus ambiguity. Learning gains were evident in changes in the use of language when writing about information processing in the brain. PMID:26557791

Correlation Filter Synthesis Using Neural Networks.

DTIC Science & Technology

1993-12-01

trained neural networks may be understood as "smart" data interpolators, the stored filter and the filter synthesis approaches have much in common: in...the former new filters are found by searching a data bank consisting of the filters themselves; in the latter filters are formed from a distributed... data bank that contains neural network interaction strengths or weights. 1.2 Key Results and Outputs Excellent computer simulation results were

Multi-Frame Convolutional Neural Networks for Object Detection in Temporal Data

DTIC Science & Technology

2017-03-01

maximum 200 words) Given the problem of detecting objects in video , existing neural-network solutions rely on a post-processing step to combine...information across frames and strengthen conclusions. This technique has been successful for videos with simple, dominant objects but it cannot detect objects...Computer Science iii THIS PAGE INTENTIONALLY LEFT BLANK iv ABSTRACT Given the problem of detecting objects in video , existing neural-network solutions rely

The graph neural network model.

PubMed

Scarselli, Franco; Gori, Marco; Tsoi, Ah Chung; Hagenbuchner, Markus; Monfardini, Gabriele

2009-01-01

Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) is an element of IR(m) that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.

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.

Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks

ERIC Educational Resources Information Center

Ray, Loye Lynn

2014-01-01

The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…

Numerical solution of differential equations by artificial neural networks

NASA Technical Reports Server (NTRS)

Meade, Andrew J., Jr.

1995-01-01

Conventionally programmed digital computers can process numbers with great speed and precision, but do not easily recognize patterns or imprecise or contradictory data. Instead of being programmed in the conventional sense, artificial neural networks (ANN's) are capable of self-learning through exposure to repeated examples. However, the training of an ANN can be a time consuming and unpredictable process. A general method is being developed by the author to mate the adaptability of the ANN with the speed and precision of the digital computer. This method has been successful in building feedforward networks that can approximate functions and their partial derivatives from examples in a single iteration. The general method also allows the formation of feedforward networks that can approximate the solution to nonlinear ordinary and partial differential equations to desired accuracy without the need of examples. It is believed that continued research will produce artificial neural networks that can be used with confidence in practical scientific computing and engineering applications.

Linear and nonlinear ARMA model parameter estimation using an artificial neural network

NASA Technical Reports Server (NTRS)

Chon, K. H.; Cohen, R. J.

1997-01-01

This paper addresses parametric system identification of linear and nonlinear dynamic systems by analysis of the input and output signals. Specifically, we investigate the relationship between estimation of the system using a feedforward neural network model and estimation of the system by use of linear and nonlinear autoregressive moving-average (ARMA) models. By utilizing a neural network model incorporating a polynomial activation function, we show the equivalence of the artificial neural network to the linear and nonlinear ARMA models. We compare the parameterization of the estimated system using the neural network and ARMA approaches by utilizing data generated by means of computer simulations. Specifically, we show that the parameters of a simulated ARMA system can be obtained from the neural network analysis of the simulated data or by conventional least squares ARMA analysis. The feasibility of applying neural networks with polynomial activation functions to the analysis of experimental data is explored by application to measurements of heart rate (HR) and instantaneous lung volume (ILV) fluctuations.

Fast Recall for Complex-Valued Hopfield Neural Networks with Projection Rules.

PubMed

Kobayashi, Masaki

2017-01-01

Many models of neural networks have been extended to complex-valued neural networks. A complex-valued Hopfield neural network (CHNN) is a complex-valued version of a Hopfield neural network. Complex-valued neurons can represent multistates, and CHNNs are available for the storage of multilevel data, such as gray-scale images. The CHNNs are often trapped into the local minima, and their noise tolerance is low. Lee improved the noise tolerance of the CHNNs by detecting and exiting the local minima. In the present work, we propose a new recall algorithm that eliminates the local minima. We show that our proposed recall algorithm not only accelerated the recall but also improved the noise tolerance through computer simulations.

Deep learning and the electronic structure problem

NASA Astrophysics Data System (ADS)

Mills, Kyle; Spanner, Michael; Tamblyn, Isaac

In the past decade, the fields of artificial intelligence and computer vision have progressed remarkably. Supported by the enthusiasm of large tech companies, as well as significant hardware advances and the utilization of graphical processing units to accelerate computations, deep neural networks (DNN) are gaining momentum as a robust choice for many diverse machine learning applications. We have demonstrated the ability of a DNN to solve a quantum mechanical eigenvalue equation directly, without the need to compute a wavefunction, and without knowledge of the underlying physics. We have trained a convolutional neural network to predict the total energy of an electron in a confining, 2-dimensional electrostatic potential. We numerically solved the one-electron Schrödinger equation for millions of electrostatic potentials, and used this as training data for our neural network. Four classes of potentials were assessed: the canonical cases of the harmonic oscillator and infinite well, and two types of randomly generated potentials for which no analytic solution is known. We compare the performance of the neural network and consider how these results could lead to future advances in electronic structure theory.

DCS-Neural-Network Program for Aircraft Control and Testing

NASA Technical Reports Server (NTRS)

Jorgensen, Charles C.

2006-01-01

A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.

Proceedings of the Second Joint Technology Workshop on Neural Networks and Fuzzy Logic, volume 1

NASA Technical Reports Server (NTRS)

Lea, Robert N. (Editor); Villarreal, James (Editor)

1991-01-01

Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by NASA and the University of Houston, Clear Lake. The workshop was held April 11 to 13 at the Johnson Space Flight Center. Technical topics addressed included adaptive systems, learning algorithms, network architectures, vision, robotics, neurobiological connections, speech recognition and synthesis, fuzzy set theory and application, control and dynamics processing, space applications, fuzzy logic and neural network computers, approximate reasoning, and multiobject decision making.

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.

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

Hamadneh, Nawaf; Sathasivam, Saratha; Choon, Ong Hong

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 (T{sub p}: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 amore » 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.« less

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.

Stability and synchronization analysis of inertial memristive neural networks with time delays.

PubMed

Rakkiyappan, R; Premalatha, S; Chandrasekar, A; Cao, Jinde

2016-10-01

This paper is concerned with the problem of stability and pinning synchronization of a class of inertial memristive neural networks with time delay. In contrast to general inertial neural networks, inertial memristive neural networks is applied to exhibit the synchronization and stability behaviors due to the physical properties of memristors and the differential inclusion theory. By choosing an appropriate variable transmission, the original system can be transformed into first order differential equations. Then, several sufficient conditions for the stability of inertial memristive neural networks by using matrix measure and Halanay inequality are derived. These obtained criteria are capable of reducing computational burden in the theoretical part. In addition, the evaluation is done on pinning synchronization for an array of linearly coupled inertial memristive neural networks, to derive the condition using matrix measure strategy. Finally, the two numerical simulations are presented to show the effectiveness of acquired theoretical results.

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.

Neural-Network Object-Recognition Program

NASA Technical Reports Server (NTRS)

Spirkovska, L.; Reid, M. B.

1993-01-01

HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.

Computational Models of Neuron-Astrocyte Interactions Lead to Improved Efficacy in the Performance of Neural Networks

PubMed Central

Alvarellos-González, Alberto; Pazos, Alejandro; Porto-Pazos, Ana B.

2012-01-01

The importance of astrocytes, one part of the glial system, for information processing in the brain has recently been demonstrated. Regarding information processing in multilayer connectionist systems, it has been shown that systems which include artificial neurons and astrocytes (Artificial Neuron-Glia Networks) have well-known advantages over identical systems including only artificial neurons. Since the actual impact of astrocytes in neural network function is unknown, we have investigated, using computational models, different astrocyte-neuron interactions for information processing; different neuron-glia algorithms have been implemented for training and validation of multilayer Artificial Neuron-Glia Networks oriented toward classification problem resolution. The results of the tests performed suggest that all the algorithms modelling astrocyte-induced synaptic potentiation improved artificial neural network performance, but their efficacy depended on the complexity of the problem. PMID:22649480

Computational models of neuron-astrocyte interactions lead to improved efficacy in the performance of neural networks.

PubMed

Alvarellos-González, Alberto; Pazos, Alejandro; Porto-Pazos, Ana B

2012-01-01

The importance of astrocytes, one part of the glial system, for information processing in the brain has recently been demonstrated. Regarding information processing in multilayer connectionist systems, it has been shown that systems which include artificial neurons and astrocytes (Artificial Neuron-Glia Networks) have well-known advantages over identical systems including only artificial neurons. Since the actual impact of astrocytes in neural network function is unknown, we have investigated, using computational models, different astrocyte-neuron interactions for information processing; different neuron-glia algorithms have been implemented for training and validation of multilayer Artificial Neuron-Glia Networks oriented toward classification problem resolution. The results of the tests performed suggest that all the algorithms modelling astrocyte-induced synaptic potentiation improved artificial neural network performance, but their efficacy depended on the complexity of the problem.

Comparison of artificial intelligence classifiers for SIP attack data

NASA Astrophysics Data System (ADS)

Safarik, Jakub; Slachta, Jiri

2016-05-01

Honeypot application is a source of valuable data about attacks on the network. We run several SIP honeypots in various computer networks, which are separated geographically and logically. Each honeypot runs on public IP address and uses standard SIP PBX ports. All information gathered via honeypot is periodically sent to the centralized server. This server classifies all attack data by neural network algorithm. The paper describes optimizations of a neural network classifier, which lower the classification error. The article contains the comparison of two neural network algorithm used for the classification of validation data. The first is the original implementation of the neural network described in recent work; the second neural network uses further optimizations like input normalization or cross-entropy cost function. We also use other implementations of neural networks and machine learning classification algorithms. The comparison test their capabilities on validation data to find the optimal classifier. The article result shows promise for further development of an accurate SIP attack classification engine.

Parallel consensual neural networks.

PubMed

Benediktsson, J A; Sveinsson, J R; Ersoy, O K; Swain, P H

1997-01-01

A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks. The output responses from the stage networks are then weighted and combined to make a consensual decision. In this paper, optimization methods are used in order to weight the outputs from the stage networks. Two approaches are proposed to compute the data transforms for the PCNN, one for binary data and another for analog data. The analog approach uses wavelet packets. The experimental results obtained with the proposed approach show that the PCNN outperforms both a conjugate-gradient backpropagation neural network and conventional statistical methods in terms of overall classification accuracy of test data.

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.

Texture and art with deep neural networks.

PubMed

Gatys, Leon A; Ecker, Alexander S; Bethge, Matthias

2017-10-01

Although the study of biological vision and computer vision attempt to understand powerful visual information processing from different angles, they have a long history of informing each other. Recent advances in texture synthesis that were motivated by visual neuroscience have led to a substantial advance in image synthesis and manipulation in computer vision using convolutional neural networks (CNNs). Here, we review these recent advances and discuss how they can in turn inspire new research in visual perception and computational neuroscience. Copyright © 2017. Published by Elsevier Ltd.

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

Pruning artificial neural networks using neural complexity measures.

PubMed

Jorgensen, Thomas D; Haynes, Barry P; Norlund, Charlotte C F

2008-10-01

This paper describes a new method for pruning artificial neural networks, using a measure of the neural complexity of the neural network. This measure is used to determine the connections that should be pruned. The measure computes the information-theoretic complexity of a neural network, which is similar to, yet different from previous research on pruning. The method proposed here shows how overly large and complex networks can be reduced in size, whilst retaining learnt behaviour and fitness. The technique proposed here helps to discover a network topology that matches the complexity of the problem it is meant to solve. This novel pruning technique is tested in a robot control domain, simulating a racecar. It is shown, that the proposed pruning method is a significant improvement over the most commonly used pruning method Magnitude Based Pruning. Furthermore, some of the pruned networks prove to be faster learners than the benchmark network that they originate from. This means that this pruning method can also help to unleash hidden potential in a network, because the learning time decreases substantially for a pruned a network, due to the reduction of dimensionality of the network.

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.

Comparison of Computational-Model and Experimental-Example Trained Neural Networks for Processing Speckled Fringe Patterns

NASA Technical Reports Server (NTRS)

Decker, A. J.; Fite, E. B.; Thorp, S. A.; Mehmed, O.

1998-01-01

The responses of artificial neural networks to experimental and model-generated inputs are compared for detection of damage in twisted fan blades using electronic holography. The training-set inputs, for this work, are experimentally generated characteristic patterns of the vibrating blades. The outputs are damage-flag indicators or second derivatives of the sensitivity-vector-projected displacement vectors from a finite element model. Artificial neural networks have been trained in the past with computational-model-generated training sets. This approach avoids the difficult inverse calculations traditionally used to compare interference fringes with the models. But the high modeling standards are hard to achieve, even with fan-blade finite-element models.

Comparison of Computational, Model and Experimental, Example Trained Neural Networks for Processing Speckled Fringe Patterns

NASA Technical Reports Server (NTRS)

Decker, A. J.; Fite, E. B.; Thorp, S. A.; Mehmed, O.

1998-01-01

The responses of artificial neural networks to experimental and model-generated inputs are compared for detection of damage in twisted fan blades using electronic holography. The training-set inputs, for this work, are experimentally generated characteristic patterns of the vibrating blades. The outputs are damage-flag indicators or second derivatives of the sensitivity-vector-projected displacement vectors from a finite element model. Artificial neural networks have been trained in the past with computational-model- generated training sets. This approach avoids the difficult inverse calculations traditionally used to compare interference fringes with the models. But the high modeling standards are hard to achieve, even with fan-blade finite-element models.

Application of artificial neural networks with backpropagation technique in the financial data

NASA Astrophysics Data System (ADS)

Jaiswal, Jitendra Kumar; Das, Raja

2017-11-01

The propensity of applying neural networks has been proliferated in multiple disciplines for research activities since the past recent decades because of its powerful control with regulatory parameters for pattern recognition and classification. It is also being widely applied for forecasting in the numerous divisions. Since financial data have been readily available due to the involvement of computers and computing systems in the stock market premises throughout the world, researchers have also developed numerous techniques and algorithms to analyze the data from this sector. In this paper we have applied neural network with backpropagation technique to find the data pattern from finance section and prediction for stock values as well.

Bio-inspired computational heuristics to study Lane-Emden systems arising in astrophysics model.

PubMed

Ahmad, Iftikhar; Raja, Muhammad Asif Zahoor; Bilal, Muhammad; Ashraf, Farooq

2016-01-01

This study reports novel hybrid computational methods for the solutions of nonlinear singular Lane-Emden type differential equation arising in astrophysics models by exploiting the strength of unsupervised neural network models and stochastic optimization techniques. In the scheme the neural network, sub-part of large field called soft computing, is exploited for modelling of the equation in an unsupervised manner. The proposed approximated solutions of higher order ordinary differential equation are calculated with the weights of neural networks trained with genetic algorithm, and pattern search hybrid with sequential quadratic programming for rapid local convergence. The results of proposed solvers for solving the nonlinear singular systems are in good agreements with the standard solutions. Accuracy and convergence the design schemes are demonstrated by the results of statistical performance measures based on the sufficient large number of independent runs.

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

Constructive autoassociative neural network for facial recognition.

PubMed

Fernandes, Bruno J T; Cavalcanti, George D C; Ren, Tsang I

2014-01-01

Autoassociative artificial neural networks have been used in many different computer vision applications. However, it is difficult to define the most suitable neural network architecture because this definition is based on previous knowledge and depends on the problem domain. To address this problem, we propose a constructive autoassociative neural network called CANet (Constructive Autoassociative Neural Network). CANet integrates the concepts of receptive fields and autoassociative memory in a dynamic architecture that changes the configuration of the receptive fields by adding new neurons in the hidden layer, while a pruning algorithm removes neurons from the output layer. Neurons in the CANet output layer present lateral inhibitory connections that improve the recognition rate. Experiments in face recognition and facial expression recognition show that the CANet outperforms other methods presented in the literature.

Artificial neural network prediction of aircraft aeroelastic behavior

NASA Astrophysics Data System (ADS)

Pesonen, Urpo Juhani

An Artificial Neural Network that predicts aeroelastic behavior of aircraft is presented. The neural net was designed to predict the shape of a flexible wing in static flight conditions using results from a structural analysis and an aerodynamic analysis performed with traditional computational tools. To generate reliable training and testing data for the network, an aeroelastic analysis code using these tools as components was designed and validated. To demonstrate the advantages and reliability of Artificial Neural Networks, a network was also designed and trained to predict airfoil maximum lift at low Reynolds numbers where wind tunnel data was used for the training. Finally, a neural net was designed and trained to predict the static aeroelastic behavior of a wing without the need to iterate between the structural and aerodynamic solvers.

Soft computing methods in design of superalloys

NASA Technical Reports Server (NTRS)

Cios, K. J.; Berke, L.; Vary, A.; Sharma, S.

1995-01-01

Soft computing techniques of neural networks and genetic algorithms are used in the design of superalloys. The cyclic oxidation attack parameter K(sub a), generated from tests at NASA Lewis Research Center, is modeled as a function of the superalloy chemistry and test temperature using a neural network. This model is then used in conjunction with a genetic algorithm to obtain an optimized superalloy composition resulting in low K(sub a) values.

Soft Computing Methods in Design of Superalloys

NASA Technical Reports Server (NTRS)

Cios, K. J.; Berke, L.; Vary, A.; Sharma, S.

1996-01-01

Soft computing techniques of neural networks and genetic algorithms are used in the design of superalloys. The cyclic oxidation attack parameter K(sub a), generated from tests at NASA Lewis Research Center, is modelled as a function of the superalloy chemistry and test temperature using a neural network. This model is then used in conjunction with a genetic algorithm to obtain an optimized superalloy composition resulting in low K(sub a) values.

Nonvolatile Ionic Two-Terminal Memory Device

NASA Technical Reports Server (NTRS)

Williams, Roger M.

1990-01-01

Conceptual solid-state memory device nonvolatile and erasable and has only two terminals. Proposed device based on two effects: thermal phase transition and reversible intercalation of ions. Transfer of sodium ions between source of ions and electrical switching element increases or decreases electrical conductance of element, turning switch "on" or "off". Used in digital computers and neural-network computers. In neural networks, many small, densely packed switches function as erasable, nonvolatile synaptic elements.

Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography

NASA Astrophysics Data System (ADS)

Lähivaara, Timo; Kärkkäinen, Leo; Huttunen, Janne M. J.; Hesthaven, Jan S.

2018-02-01

We study the feasibility of data based machine learning applied to ultrasound tomography to estimate water-saturated porous material parameters. In this work, the data to train the neural networks is simulated by solving wave propagation in coupled poroviscoelastic-viscoelastic-acoustic media. As the forward model, we consider a high-order discontinuous Galerkin method while deep convolutional neural networks are used to solve the parameter estimation problem. In the numerical experiment, we estimate the material porosity and tortuosity while the remaining parameters which are of less interest are successfully marginalized in the neural networks-based inversion. Computational examples confirms the feasibility and accuracy of this approach.

Salient regions detection using convolutional neural networks and color volume

NASA Astrophysics Data System (ADS)

Liu, Guang-Hai; Hou, Yingkun

2018-03-01

Convolutional neural network is an important technique in machine learning, pattern recognition and image processing. In order to reduce the computational burden and extend the classical LeNet-5 model to the field of saliency detection, we propose a simple and novel computing model based on LeNet-5 network. In the proposed model, hue, saturation and intensity are utilized to extract depth cues, and then we integrate depth cues and color volume to saliency detection following the basic structure of the feature integration theory. Experimental results show that the proposed computing model outperforms some existing state-of-the-art methods on MSRA1000 and ECSSD datasets.

Development of the disable software reporting system on the basis of the neural network

NASA Astrophysics Data System (ADS)

Gavrylenko, S.; Babenko, O.; Ignatova, E.

2018-04-01

The PE structure of malicious and secure software is analyzed, features are highlighted, binary sign vectors are obtained and used as inputs for training the neural network. A software model for detecting malware based on the ART-1 neural network was developed, optimal similarity coefficients were found, and testing was performed. The obtained research results showed the possibility of using the developed system of identifying malicious software in computer systems protection systems

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.

An alternative approach for neural network evolution with a genetic algorithm: crossover by combinatorial optimization.

PubMed

García-Pedrajas, Nicolás; Ortiz-Boyer, Domingo; Hervás-Martínez, César

2006-05-01

In this work we present a new approach to crossover operator in the genetic evolution of neural networks. The most widely used evolutionary computation paradigm for neural network evolution is evolutionary programming. This paradigm is usually preferred due to the problems caused by the application of crossover to neural network evolution. However, crossover is the most innovative operator within the field of evolutionary computation. One of the most notorious problems with the application of crossover to neural networks is known as the permutation problem. This problem occurs due to the fact that the same network can be represented in a genetic coding by many different codifications. Our approach modifies the standard crossover operator taking into account the special features of the individuals to be mated. We present a new model for mating individuals that considers the structure of the hidden layer and redefines the crossover operator. As each hidden node represents a non-linear projection of the input variables, we approach the crossover as a problem on combinatorial optimization. We can formulate the problem as the extraction of a subset of near-optimal projections to create the hidden layer of the new network. This new approach is compared to a classical crossover in 25 real-world problems with an excellent performance. Moreover, the networks obtained are much smaller than those obtained with classical crossover operator.

How Captain Amerika uses neural networks to fight crime

NASA Technical Reports Server (NTRS)

Rogers, Steven K.; Kabrisky, Matthew; Ruck, Dennis W.; Oxley, Mark E.

1994-01-01

Artificial neural network models can make amazing computations. These models are explained along with their application in problems associated with fighting crime. Specific problems addressed are identification of people using face recognition, speaker identification, and fingerprint and handwriting analysis (biometric authentication).

Optoelectronic Integrated Circuits For Neural Networks

NASA Technical Reports Server (NTRS)

Psaltis, D.; Katz, J.; Kim, Jae-Hoon; Lin, S. H.; Nouhi, A.

1990-01-01

Many threshold devices placed on single substrate. Integrated circuits containing optoelectronic threshold elements developed for use as planar arrays of artificial neurons in research on neural-network computers. Mounted with volume holograms recorded in photorefractive crystals serving as dense arrays of variable interconnections between neurons.

Optimization behavior of brainstem respiratory neurons. A cerebral neural network model.

PubMed

Poon, C S

1991-01-01

A recent model of respiratory control suggested that the steady-state respiratory responses to CO2 and exercise may be governed by an optimal control law in the brainstem respiratory neurons. It was not certain, however, whether such complex optimization behavior could be accomplished by a realistic biological neural network. To test this hypothesis, we developed a hybrid computer-neural model in which the dynamics of the lung, brain and other tissue compartments were simulated on a digital computer. Mimicking the "controller" was a human subject who pedalled on a bicycle with varying speed (analog of ventilatory output) with a view to minimize an analog signal of the total cost of breathing (chemical and mechanical) which was computed interactively and displayed on an oscilloscope. In this manner, the visuomotor cortex served as a proxy (homolog) of the brainstem respiratory neurons in the model. Results in 4 subjects showed a linear steady-state ventilatory CO2 response to arterial PCO2 during simulated CO2 inhalation and a nearly isocapnic steady-state response during simulated exercise. Thus, neural optimization is a plausible mechanism for respiratory control during exercise and can be achieved by a neural network with cognitive computational ability without the need for an exercise stimulus.

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.

Computational exploration of neuron and neural network models in neurobiology.

PubMed

Prinz, Astrid A

2007-01-01

The electrical activity of individual neurons and neuronal networks is shaped by the complex interplay of a large number of non-linear processes, including the voltage-dependent gating of ion channels and the activation of synaptic receptors. These complex dynamics make it difficult to understand how individual neuron or network parameters-such as the number of ion channels of a given type in a neuron's membrane or the strength of a particular synapse-influence neural system function. Systematic exploration of cellular or network model parameter spaces by computational brute force can overcome this difficulty and generate comprehensive data sets that contain information about neuron or network behavior for many different combinations of parameters. Searching such data sets for parameter combinations that produce functional neuron or network output provides insights into how narrowly different neural system parameters have to be tuned to produce a desired behavior. This chapter describes the construction and analysis of databases of neuron or neuronal network models and describes some of the advantages and downsides of such exploration methods.

Neuromorphic neural interfaces: from neurophysiological inspiration to biohybrid coupling with nervous systems

NASA Astrophysics Data System (ADS)

Broccard, Frédéric D.; Joshi, Siddharth; Wang, Jun; Cauwenberghs, Gert

2017-08-01

Objective. Computation in nervous systems operates with different computational primitives, and on different hardware, than traditional digital computation and is thus subjected to different constraints from its digital counterpart regarding the use of physical resources such as time, space and energy. In an effort to better understand neural computation on a physical medium with similar spatiotemporal and energetic constraints, the field of neuromorphic engineering aims to design and implement electronic systems that emulate in very large-scale integration (VLSI) hardware the organization and functions of neural systems at multiple levels of biological organization, from individual neurons up to large circuits and networks. Mixed analog/digital neuromorphic VLSI systems are compact, consume little power and operate in real time independently of the size and complexity of the model. Approach. This article highlights the current efforts to interface neuromorphic systems with neural systems at multiple levels of biological organization, from the synaptic to the system level, and discusses the prospects for future biohybrid systems with neuromorphic circuits of greater complexity. Main results. Single silicon neurons have been interfaced successfully with invertebrate and vertebrate neural networks. This approach allowed the investigation of neural properties that are inaccessible with traditional techniques while providing a realistic biological context not achievable with traditional numerical modeling methods. At the network level, populations of neurons are envisioned to communicate bidirectionally with neuromorphic processors of hundreds or thousands of silicon neurons. Recent work on brain-machine interfaces suggests that this is feasible with current neuromorphic technology. Significance. Biohybrid interfaces between biological neurons and VLSI neuromorphic systems of varying complexity have started to emerge in the literature. Primarily intended as a computational tool for investigating fundamental questions related to neural dynamics, the sophistication of current neuromorphic systems now allows direct interfaces with large neuronal networks and circuits, resulting in potentially interesting clinical applications for neuroengineering systems, neuroprosthetics and neurorehabilitation.

Using an Extended Kalman Filter Learning Algorithm for Feed-Forward Neural Networks to Describe Tracer Correlations

NASA Technical Reports Server (NTRS)

Lary, David J.; Mussa, Yussuf

2004-01-01

In this study a new extended Kalman filter (EKF) learning algorithm for feed-forward neural networks (FFN) is used. With the EKF approach, the training of the FFN can be seen as state estimation for a non-linear stationary process. The EKF method gives excellent convergence performances provided that there is enough computer core memory and that the machine precision is high. Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). The neural network was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9997. The neural network Fortran code used is available for download.

Brain architecture: a design for natural computation.

PubMed

Kaiser, Marcus

2007-12-15

Fifty years ago, John von Neumann compared the architecture of the brain with that of the computers he invented and which are still in use today. In those days, the organization of computers was based on concepts of brain organization. Here, we give an update on current results on the global organization of neural systems. For neural systems, we outline how the spatial and topological architecture of neuronal and cortical networks facilitates robustness against failures, fast processing and balanced network activation. Finally, we discuss mechanisms of self-organization for such architectures. After all, the organization of the brain might again inspire computer architecture.

Predicate calculus for an architecture of multiple neural networks

NASA Astrophysics Data System (ADS)

Consoli, Robert H.

1990-08-01

Future projects with neural networks will require multiple individual network components. Current efforts along these lines are ad hoc. This paper relates the neural network to a classical device and derives a multi-part architecture from that model. Further it provides a Predicate Calculus variant for describing the location and nature of the trainings and suggests Resolution Refutation as a method for determining the performance of the system as well as the location of needed trainings for specific proofs. 2. THE NEURAL NETWORK AND A CLASSICAL DEVICE Recently investigators have been making reports about architectures of multiple neural networksL234. These efforts are appearing at an early stage in neural network investigations they are characterized by architectures suggested directly by the problem space. Touretzky and Hinton suggest an architecture for processing logical statements1 the design of this architecture arises from the syntax of a restricted class of logical expressions and exhibits syntactic limitations. In similar fashion a multiple neural netword arises out of a control problem2 from the sequence learning problem3 and from the domain of machine learning. 4 But a general theory of multiple neural devices is missing. More general attempts to relate single or multiple neural networks to classical computing devices are not common although an attempt is made to relate single neural devices to a Turing machines and Sun et a!. develop a multiple neural architecture that performs pattern classification.

Automated Induction Of Rule-Based Neural Networks

NASA Technical Reports Server (NTRS)

Smyth, Padhraic J.; Goodman, Rodney M.

1994-01-01

Prototype expert systems implemented in software and are functionally equivalent to neural networks set up automatically and placed into operation within minutes following information-theoretic approach to automated acquisition of knowledge from large example data bases. Approach based largely on use of ITRULE computer program.

Computing by robust transience: How the fronto-parietal network performs sequential category-based decisions

PubMed Central

Chaisangmongkon, Warasinee; Swaminathan, Sruthi K.; Freedman, David J.; Wang, Xiao-Jing

2017-01-01

Summary Decision making involves dynamic interplay between internal judgements and external perception, which has been investigated in delayed match-to-category (DMC) experiments. Our analysis of neural recordings shows that, during DMC tasks, LIP and PFC neurons demonstrate mixed, time-varying, and heterogeneous selectivity, but previous theoretical work has not established the link between these neural characteristics and population-level computations. We trained a recurrent network model to perform DMC tasks and found that the model can remarkably reproduce key features of neuronal selectivity at the single-neuron and population levels. Analysis of the trained networks elucidates that robust transient trajectories of the neural population are the key driver of sequential categorical decisions. The directions of trajectories are governed by network self-organized connectivity, defining a ‘neural landscape’, consisting of a task-tailored arrangement of slow states and dynamical tunnels. With this model, we can identify functionally-relevant circuit motifs and generalize the framework to solve other categorization tasks. PMID:28334612

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.

Artificial intelligence: Neural network model as the multidisciplinary team member in clinical decision support to avoid medical mistakes.

PubMed

Buzaev, Igor Vyacheslavovich; Plechev, Vladimir Vyacheslavovich; Nikolaeva, Irina Evgenievna; Galimova, Rezida Maratovna

2016-09-01

The continuous uninterrupted feedback system is the essential part of any well-organized system. We propose aLYNX concept that is a possibility to use an artificial intelligence algorithm or a neural network model in decision-making system so as to avoid possible mistakes and to remind the doctors to review tactics once more in selected cases. aLYNX system includes: registry with significant factors, decisions and results; machine learning process based on this registry data; the use of the machine learning results as the adviser. We show a possibility to build a computer adviser with a neural network model for making a choice between coronary aortic bypass surgery (CABG) and percutaneous coronary intervention (PCI) in order to achieve a higher 5-year survival rate in patients with angina based on the experience of 5107 patients. The neural network was trained by 4679 patients who achieved 5-year survival. Among them, 2390 patients underwent PCI and 2289 CABG. After training, the correlation coefficient ( r ) of the network was 0.74 for training, 0.67 for validation, 0.71 for test and 0.73 for total. Simulation of the neural network function has been performed after training in the two groups of patients with known 5-year outcome. The disagreement rate was significantly higher in the dead patient group than that in the survivor group between neural network model and heart team [16.8% (787/4679) vs. 20.3% (87/428), P  = 0.065)]. The study shows the possibility to build a computer adviser with a neural network model for making a choice between CABG and PCI in order to achieve a higher 5-year survival rate in patients with angina.

A Neural Network Aero Design System for Advanced Turbo-Engines

NASA Technical Reports Server (NTRS)

Sanz, Jose M.

1999-01-01

An inverse design method calculates the blade shape that produces a prescribed input pressure distribution. By controlling this input pressure distribution the aerodynamic design objectives can easily be met. Because of the intrinsic relationship between pressure distribution and airfoil physical properties, a Neural Network can be trained to choose the optimal pressure distribution that would meet a set of physical requirements. Neural network systems have been attempted in the context of direct design methods. From properties ascribed to a set of blades the neural network is trained to infer the properties of an 'interpolated' blade shape. The problem is that, especially in transonic regimes where we deal with intrinsically non linear and ill posed problems, small perturbations of the blade shape can produce very large variations of the flow parameters. It is very unlikely that, under these circumstances, a neural network will be able to find the proper solution. The unique situation in the present method is that the neural network can be trained to extract the required input pressure distribution from a database of pressure distributions while the inverse method will still compute the exact blade shape that corresponds to this 'interpolated' input pressure distribution. In other words, the interpolation process is transferred to a smoother problem, namely, finding what pressure distribution would produce the required flow conditions and, once this is done, the inverse method will compute the exact solution for this problem. The use of neural network is, in this context, highly related to the use of proper optimization techniques. The optimization is used essentially as an automation procedure to force the input pressure distributions to achieve the required aero and structural design parameters. A multilayered feed forward network with back-propagation is used to train the system for pattern association and classification.

Computer graphics testbed to simulate and test vision systems for space applications

NASA Technical Reports Server (NTRS)

Cheatham, John B.

1991-01-01

Artificial intelligence concepts are applied to robotics. Artificial neural networks, expert systems and laser imaging techniques for autonomous space robots are being studied. A computer graphics laser range finder simulator developed by Wu has been used by Weiland and Norwood to study use of artificial neural networks for path planning and obstacle avoidance. Interest is expressed in applications of CLIPS, NETS, and Fuzzy Control. These applications are applied to robot navigation.

FIRST Quantum-(1980)-Computing DISCOVERY in Siegel-Rosen-Feynman-...A.-I. Neural-Networks: Artificial(ANN)/Biological(BNN) and Siegel FIRST Semantic-Web and Siegel FIRST ``Page''-``Brin'' ``PageRank'' PRE-Google Search-Engines!!!

NASA Astrophysics Data System (ADS)

Rosen, Charles; Siegel, Edward Carl-Ludwig; Feynman, Richard; Wunderman, Irwin; Smith, Adolph; Marinov, Vesco; Goldman, Jacob; Brine, Sergey; Poge, Larry; Schmidt, Erich; Young, Frederic; Goates-Bulmer, William-Steven; Lewis-Tsurakov-Altshuler, Thomas-Valerie-Genot; Ibm/Exxon Collaboration; Google/Uw Collaboration; Microsoft/Amazon Collaboration; Oracle/Sun Collaboration; Ostp/Dod/Dia/Nsa/W.-F./Boa/Ubs/Ub Collaboration

2013-03-01

Belew[Finding Out About, Cambridge(2000)] and separately full-decade pre-Page/Brin/Google FIRST Siegel-Rosen(Machine-Intelligence/Atherton)-Feynman-Smith-Marinov(Guzik Enterprises/Exxon-Enterprises/A.-I./Santa Clara)-Wunderman(H.-P.) [IBM Conf. on Computers and Mathematics, Stanford(1986); APS Mtgs.(1980s): Palo Alto/Santa Clara/San Francisco/...(1980s) MRS Spring-Mtgs.(1980s): Palo Alto/San Jose/San Francisco/...(1980-1992) FIRST quantum-computing via Bose-Einstein quantum-statistics(BEQS) Bose-Einstein CONDENSATION (BEC) in artificial-intelligence(A-I) artificial neural-networks(A-N-N) and biological neural-networks(B-N-N) and Siegel[J. Noncrystalline-Solids 40, 453(1980); Symp. on Fractals..., MRS Fall-Mtg., Boston(1989)-5-papers; Symp. on Scaling..., (1990); Symp. on Transport in Geometric-Constraint (1990)

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.

Computer-assisted cervical cancer screening using neural networks.

PubMed

Mango, L J

1994-03-15

A practical and effective system for the computer-assisted screening of conventionally prepared cervical smears is presented and described. Recent developments in neural network technology have made computerized analysis of the complex cellular scenes found on Pap smears possible. The PAPNET Cytological Screening System uses neural networks to automatically analyze conventional smears by locating and recognizing potentially abnormal cells. It then displays images of these objects for review and final diagnosis by qualified cytologists. The results of the studies presented indicate that the PAPNET system could be a useful tool for both the screening and rescreening of cervical smears. In addition, the system has been shown to be sensitive to some types of abnormalities which have gone undetected during manual screening.

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.

Modified neural networks for rapid recovery of tokamak plasma parameters for real time control

NASA Astrophysics Data System (ADS)

Sengupta, A.; Ranjan, P.

2002-07-01

Two modified neural network techniques are used for the identification of the equilibrium plasma parameters of the Superconducting Steady State Tokamak I from external magnetic measurements. This is expected to ultimately assist in a real time plasma control. As different from the conventional network structure where a single network with the optimum number of processing elements calculates the outputs, a multinetwork system connected in parallel does the calculations here in one of the methods. This network is called the double neural network. The accuracy of the recovered parameters is clearly more than the conventional network. The other type of neural network used here is based on the statistical function parametrization combined with a neural network. The principal component transformation removes linear dependences from the measurements and a dimensional reduction process reduces the dimensionality of the input space. This reduced and transformed input set, rather than the entire set, is fed into the neural network input. This is known as the principal component transformation-based neural network. The accuracy of the recovered parameters in the latter type of modified network is found to be a further improvement over the accuracy of the double neural network. This result differs from that obtained in an earlier work where the double neural network showed better performance. The conventional network and the function parametrization methods have also been used for comparison. The conventional network has been used for an optimization of the set of magnetic diagnostics. The effective set of sensors, as assessed by this network, are compared with the principal component based network. Fault tolerance of the neural networks has been tested. The double neural network showed the maximum resistance to faults in the diagnostics, while the principal component based network performed poorly. Finally the processing times of the methods have been compared. The double network and the principal component network involve the minimum computation time, although the conventional network also performs well enough to be used in real time.

Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images.

PubMed

Li, Wei; Cao, Peng; Zhao, Dazhe; Wang, Junbo

2016-01-01

Computer aided detection (CAD) systems can assist radiologists by offering a second opinion on early diagnosis of lung cancer. Classification and feature representation play critical roles in false-positive reduction (FPR) in lung nodule CAD. We design a deep convolutional neural networks method for nodule classification, which has an advantage of autolearning representation and strong generalization ability. A specified network structure for nodule images is proposed to solve the recognition of three types of nodules, that is, solid, semisolid, and ground glass opacity (GGO). Deep convolutional neural networks are trained by 62,492 regions-of-interest (ROIs) samples including 40,772 nodules and 21,720 nonnodules from the Lung Image Database Consortium (LIDC) database. Experimental results demonstrate the effectiveness of the proposed method in terms of sensitivity and overall accuracy and that it consistently outperforms the competing methods.

Neurale Netwerken en Radarsystemen (Neural Networks and Radar Systems)

DTIC Science & Technology

1989-08-01

general issues in cognitive science", Parallel distributed processing, Vol 1: Foundations, Rumelhart et al. 1986 pp 110-146 THO rapport Pagina 151 36 D.E...34Neural networks (part 2)",Expert Focus, IEEE Expert, Spring 1988. 61 J.A. Anderson, " Cognitive and Psychological Computations with Neural Models", IEEE...Pagina 154 69 David H. Ackley, Geoffrey E. Hinton and Terrence J. Sejnowski, "A Learning Algorithm for Boltzmann machines", cognitive science 9, 147-169

Neural Network Prototyping Package Within IRAF

NASA Technical Reports Server (NTRS)

Bazell, David

1997-01-01

The purpose of this contract was to develop a neural network package within the IRAF environment to allow users to easily understand and use different neural network algorithms the analysis of astronomical data. The package was developed for use within IRAF to allow portability to different computing environments and to provide a familiar and easy to use interface with the routines. In addition to developing the software and supporting documentation, we planned to use the system for the analysis of several sample problems to prove its viability and usefulness.

Modular neural networks: a survey.

PubMed

Auda, G; Kamel, M

1999-04-01

Modular Neural Networks (MNNs) is a rapidly growing field in artificial Neural Networks (NNs) research. This paper surveys the different motivations for creating MNNs: biological, psychological, hardware, and computational. Then, the general stages of MNN design are outlined and surveyed as well, viz., task decomposition techniques, learning schemes and multi-module decision-making strategies. Advantages and disadvantages of the surveyed methods are pointed out, and an assessment with respect to practical potential is provided. Finally, some general recommendations for future designs are presented.

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.

Avalanche and edge-of-chaos criticality do not necessarily co-occur in neural networks.

PubMed

Kanders, Karlis; Lorimer, Tom; Stoop, Ruedi

2017-04-01

There are indications that for optimizing neural computation, neural networks may operate at criticality. Previous approaches have used distinct fingerprints of criticality, leaving open the question whether the different notions would necessarily reflect different aspects of one and the same instance of criticality, or whether they could potentially refer to distinct instances of criticality. In this work, we choose avalanche criticality and edge-of-chaos criticality and demonstrate for a recurrent spiking neural network that avalanche criticality does not necessarily entrain dynamical edge-of-chaos criticality. This suggests that the different fingerprints may pertain to distinct phenomena.

Avalanche and edge-of-chaos criticality do not necessarily co-occur in neural networks

NASA Astrophysics Data System (ADS)

Kanders, Karlis; Lorimer, Tom; Stoop, Ruedi

2017-04-01

There are indications that for optimizing neural computation, neural networks may operate at criticality. Previous approaches have used distinct fingerprints of criticality, leaving open the question whether the different notions would necessarily reflect different aspects of one and the same instance of criticality, or whether they could potentially refer to distinct instances of criticality. In this work, we choose avalanche criticality and edge-of-chaos criticality and demonstrate for a recurrent spiking neural network that avalanche criticality does not necessarily entrain dynamical edge-of-chaos criticality. This suggests that the different fingerprints may pertain to distinct phenomena.

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.

Tutorial: Neural networks and their potential application in nuclear power plants

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

Uhrig, R.E.

A neural network is a data processing system consisting of a number of simple, highly interconnected processing elements in an architecture inspired by the structure of the cerebral cortex portion of the brain. Hence, neural networks are often capable of doing things which humans or animals do well but which conventional computers often do poorly. Neural networks have emerged in the past few years as an area of unusual opportunity for research, development and application to a variety of real world problems. Indeed, neural networks exhibit characteristics and capabilities not provided by any other technology. Examples include reading Japanese Kanjimore » characters and human handwriting, reading a typewritten manuscript aloud, compensating for alignment errors in robots, interpreting very noise'' signals (e.g. electroencephalograms), modeling complex systems that cannot be modelled mathematically, and predicting whether proposed loans will be good or fail. This paper presents a brief tutorial on neural networks and describes research on the potential applications to nuclear power plants.« less

Neural networks: Alternatives to conventional techniques for automatic docking

NASA Technical Reports Server (NTRS)

Vinz, Bradley L.

1994-01-01

Automatic docking of orbiting spacecraft is a crucial operation involving the identification of vehicle orientation as well as complex approach dynamics. The chaser spacecraft must be able to recognize the target spacecraft within a scene and achieve accurate closing maneuvers. In a video-based system, a target scene must be captured and transformed into a pattern of pixels. Successful recognition lies in the interpretation of this pattern. Due to their powerful pattern recognition capabilities, artificial neural networks offer a potential role in interpretation and automatic docking processes. Neural networks can reduce the computational time required by existing image processing and control software. In addition, neural networks are capable of recognizing and adapting to changes in their dynamic environment, enabling enhanced performance, redundancy, and fault tolerance. Most neural networks are robust to failure, capable of continued operation with a slight degradation in performance after minor failures. This paper discusses the particular automatic docking tasks neural networks can perform as viable alternatives to conventional techniques.

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.

High variation subarctic topsoil pollutant concentration prediction using neural network residual kriging

NASA Astrophysics Data System (ADS)

Sergeev, A. P.; Tarasov, D. A.; Buevich, A. G.; Subbotina, I. E.; Shichkin, A. V.; Sergeeva, M. V.; Lvova, O. A.

2017-06-01

The work deals with the application of neural networks residual kriging (NNRK) to the spatial prediction of the abnormally distributed soil pollutant (Cr). It is known that combination of geostatistical interpolation approaches (kriging) and neural networks leads to significantly better prediction accuracy and productivity. Generalized regression neural networks and multilayer perceptrons are classes of neural networks widely used for the continuous function mapping. Each network has its own pros and cons; however both demonstrated fast training and good mapping possibilities. In the work, we examined and compared two combined techniques: generalized regression neural network residual kriging (GRNNRK) and multilayer perceptron residual kriging (MLPRK). The case study is based on the real data sets on surface contamination by chromium at a particular location of the subarctic Novy Urengoy, Russia, obtained during the previously conducted screening. The proposed models have been built, implemented and validated using ArcGIS and MATLAB environments. The networks structures have been chosen during a computer simulation based on the minimization of the RMSE. MLRPK showed the best predictive accuracy comparing to the geostatistical approach (kriging) and even to GRNNRK.

A Rotational Motion Perception Neural Network Based on Asymmetric Spatiotemporal Visual Information Processing.

PubMed

Hu, Bin; Yue, Shigang; Zhang, Zhuhong

All complex motion patterns can be decomposed into several elements, including translation, expansion/contraction, and rotational motion. In biological vision systems, scientists have found that specific types of visual neurons have specific preferences to each of the three motion elements. There are computational models on translation and expansion/contraction perceptions; however, little has been done in the past to create computational models for rotational motion perception. To fill this gap, we proposed a neural network that utilizes a specific spatiotemporal arrangement of asymmetric lateral inhibited direction selective neural networks (DSNNs) for rotational motion perception. The proposed neural network consists of two parts-presynaptic and postsynaptic parts. In the presynaptic part, there are a number of lateral inhibited DSNNs to extract directional visual cues. In the postsynaptic part, similar to the arrangement of the directional columns in the cerebral cortex, these direction selective neurons are arranged in a cyclic order to perceive rotational motion cues. In the postsynaptic network, the delayed excitation from each direction selective neuron is multiplied by the gathered excitation from this neuron and its unilateral counterparts depending on which rotation, clockwise (cw) or counter-cw (ccw), to perceive. Systematic experiments under various conditions and settings have been carried out and validated the robustness and reliability of the proposed neural network in detecting cw or ccw rotational motion. This research is a critical step further toward dynamic visual information processing.All complex motion patterns can be decomposed into several elements, including translation, expansion/contraction, and rotational motion. In biological vision systems, scientists have found that specific types of visual neurons have specific preferences to each of the three motion elements. There are computational models on translation and expansion/contraction perceptions; however, little has been done in the past to create computational models for rotational motion perception. To fill this gap, we proposed a neural network that utilizes a specific spatiotemporal arrangement of asymmetric lateral inhibited direction selective neural networks (DSNNs) for rotational motion perception. The proposed neural network consists of two parts-presynaptic and postsynaptic parts. In the presynaptic part, there are a number of lateral inhibited DSNNs to extract directional visual cues. In the postsynaptic part, similar to the arrangement of the directional columns in the cerebral cortex, these direction selective neurons are arranged in a cyclic order to perceive rotational motion cues. In the postsynaptic network, the delayed excitation from each direction selective neuron is multiplied by the gathered excitation from this neuron and its unilateral counterparts depending on which rotation, clockwise (cw) or counter-cw (ccw), to perceive. Systematic experiments under various conditions and settings have been carried out and validated the robustness and reliability of the proposed neural network in detecting cw or ccw rotational motion. This research is a critical step further toward dynamic visual information processing.

Fuzzy wavelet plus a quantum neural network as a design base for power system stability enhancement.

PubMed

Ganjefar, Soheil; Tofighi, Morteza; Karami, Hamidreza

2015-11-01

In this study, we introduce an indirect adaptive fuzzy wavelet neural controller (IAFWNC) as a power system stabilizer to damp inter-area modes of oscillations in a multi-machine power system. Quantum computing is an efficient method for improving the computational efficiency of neural networks, so we developed an identifier based on a quantum neural network (QNN) to train the IAFWNC in the proposed scheme. All of the controller parameters are tuned online based on the Lyapunov stability theory to guarantee the closed-loop stability. A two-machine, two-area power system equipped with a static synchronous series compensator as a series flexible ac transmission system was used to demonstrate the effectiveness of the proposed controller. The simulation and experimental results demonstrated that the proposed IAFWNC scheme can achieve favorable control performance. Copyright © 2015 Elsevier Ltd. All rights reserved.

eLoom and Flatland: specification, simulation and visualization engines for the study of arbitrary hierarchical neural architectures.

PubMed

Caudell, Thomas P; Xiao, Yunhai; Healy, Michael J

2003-01-01

eLoom is an open source graph simulation software tool, developed at the University of New Mexico (UNM), that enables users to specify and simulate neural network models. Its specification language and libraries enables users to construct and simulate arbitrary, potentially hierarchical network structures on serial and parallel processing systems. In addition, eLoom is integrated with UNM's Flatland, an open source virtual environments development tool to provide real-time visualizations of the network structure and activity. Visualization is a useful method for understanding both learning and computation in artificial neural networks. Through 3D animated pictorially representations of the state and flow of information in the network, a better understanding of network functionality is achieved. ART-1, LAPART-II, MLP, and SOM neural networks are presented to illustrate eLoom and Flatland's capabilities.

Implementing a Bayes Filter in a Neural Circuit: The Case of Unknown Stimulus Dynamics.

PubMed

Sokoloski, Sacha

2017-09-01

In order to interact intelligently with objects in the world, animals must first transform neural population responses into estimates of the dynamic, unknown stimuli that caused them. The Bayesian solution to this problem is known as a Bayes filter, which applies Bayes' rule to combine population responses with the predictions of an internal model. The internal model of the Bayes filter is based on the true stimulus dynamics, and in this note, we present a method for training a theoretical neural circuit to approximately implement a Bayes filter when the stimulus dynamics are unknown. To do this we use the inferential properties of linear probabilistic population codes to compute Bayes' rule and train a neural network to compute approximate predictions by the method of maximum likelihood. In particular, we perform stochastic gradient descent on the negative log-likelihood of the neural network parameters with a novel approximation of the gradient. We demonstrate our methods on a finite-state, a linear, and a nonlinear filtering problem and show how the hidden layer of the neural network develops tuning curves consistent with findings in experimental neuroscience.

A Constructive Neural-Network Approach to Modeling Psychological Development

ERIC Educational Resources Information Center

Shultz, Thomas R.

2012-01-01

This article reviews a particular computational modeling approach to the study of psychological development--that of constructive neural networks. This approach is applied to a variety of developmental domains and issues, including Piagetian tasks, shift learning, language acquisition, number comparison, habituation of visual attention, concept…

Memristor-Based Analog Computation and Neural Network Classification with a Dot Product Engine.

PubMed

Hu, Miao; Graves, Catherine E; Li, Can; Li, Yunning; Ge, Ning; Montgomery, Eric; Davila, Noraica; Jiang, Hao; Williams, R Stanley; Yang, J Joshua; Xia, Qiangfei; Strachan, John Paul

2018-03-01

Using memristor crossbar arrays to accelerate computations is a promising approach to efficiently implement algorithms in deep neural networks. Early demonstrations, however, are limited to simulations or small-scale problems primarily due to materials and device challenges that limit the size of the memristor crossbar arrays that can be reliably programmed to stable and analog values, which is the focus of the current work. High-precision analog tuning and control of memristor cells across a 128 × 64 array is demonstrated, and the resulting vector matrix multiplication (VMM) computing precision is evaluated. Single-layer neural network inference is performed in these arrays, and the performance compared to a digital approach is assessed. Memristor computing system used here reaches a VMM accuracy equivalent of 6 bits, and an 89.9% recognition accuracy is achieved for the 10k MNIST handwritten digit test set. Forecasts show that with integrated (on chip) and scaled memristors, a computational efficiency greater than 100 trillion operations per second per Watt is possible. © 2018 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Neural networks with multiple general neuron models: a hybrid computational intelligence approach using Genetic Programming.

PubMed

Barton, Alan J; Valdés, Julio J; Orchard, Robert

2009-01-01

Classical neural networks are composed of neurons whose nature is determined by a certain function (the neuron model), usually pre-specified. In this paper, a type of neural network (NN-GP) is presented in which: (i) each neuron may have its own neuron model in the form of a general function, (ii) any layout (i.e network interconnection) is possible, and (iii) no bias nodes or weights are associated to the connections, neurons or layers. The general functions associated to a neuron are learned by searching a function space. They are not provided a priori, but are rather built as part of an Evolutionary Computation process based on Genetic Programming. The resulting network solutions are evaluated based on a fitness measure, which may, for example, be based on classification or regression errors. Two real-world examples are presented to illustrate the promising behaviour on classification problems via construction of a low-dimensional representation of a high-dimensional parameter space associated to the set of all network solutions.

The Effects of GABAergic Polarity Changes on Episodic Neural Network Activity in Developing Neural Systems.

PubMed

Blanco, Wilfredo; Bertram, Richard; Tabak, Joël

2017-01-01

Early in development, neural systems have primarily excitatory coupling, where even GABAergic synapses are excitatory. Many of these systems exhibit spontaneous episodes of activity that have been characterized through both experimental and computational studies. As development progress the neural system goes through many changes, including synaptic remodeling, intrinsic plasticity in the ion channel expression, and a transformation of GABAergic synapses from excitatory to inhibitory. What effect each of these, and other, changes have on the network behavior is hard to know from experimental studies since they all happen in parallel. One advantage of a computational approach is that one has the ability to study developmental changes in isolation. Here, we examine the effects of GABAergic synapse polarity change on the spontaneous activity of both a mean field and a neural network model that has both glutamatergic and GABAergic coupling, representative of a developing neural network. We find some intuitive behavioral changes as the GABAergic neurons go from excitatory to inhibitory, shared by both models, such as a decrease in the duration of episodes. We also find some paradoxical changes in the activity that are only present in the neural network model. In particular, we find that during early development the inter-episode durations become longer on average, while later in development they become shorter. In addressing this unexpected finding, we uncover a priming effect that is particularly important for a small subset of neurons, called the "intermediate neurons." We characterize these neurons and demonstrate why they are crucial to episode initiation, and why the paradoxical behavioral change result from priming of these neurons. The study illustrates how even arguably the simplest of developmental changes that occurs in neural systems can present non-intuitive behaviors. It also makes predictions about neural network behavioral changes that occur during development that may be observable even in actual neural systems where these changes are convoluted with changes in synaptic connectivity and intrinsic neural plasticity.

Determination of the geophysical model function of NSCAT and its corresponding variance by the use of neural networks

NASA Astrophysics Data System (ADS)

Mejia, C.; Badran, F.; Bentamy, A.; Crepon, M.; Thiria, S.; Tran, N.

1999-05-01

We have computed two geophysical model functions (one for the vertical and one for the horizontal polarization) for the NASA scatterometer (NSCAT) by using neural networks. These neural network geophysical model functions (NNGMFs) were estimated with NSCAT scatterometer σO measurements collocated with European Centre for Medium-Range Weather Forecasts analyzed wind vectors during the period January 15 to April 15, 1997. We performed a student t test showing that the NNGMFs estimate the NSCAT σO with a confidence level of 95%. Analysis of the results shows that the mean NSCAT signal depends on the incidence angle and the wind speed and presents the classical biharmonic modulation with respect to the wind azimuth. NSCAT σO increases with respect to the wind speed and presents a well-marked change at around 7 m s-1. The upwind-downwind amplitude is higher for the horizontal polarization signal than for vertical polarization, indicating that the use of horizontal polarization can give additional information for wind retrieval. Comparison of the σO computed by the NNGMFs against the NSCAT-measured σO show a quite low rms, except at low wind speeds. We also computed two specific neural networks for estimating the variance associated to these GMFs. The variances are analyzed with respect to geophysical parameters. This led us to compute the geophysical signal-to-noise ratio, i.e., Kp. The Kp values are quite high at low wind speed and decrease at high wind speed. At constant wind speed the highest Kp are at crosswind directions, showing that the crosswind values are the most difficult to estimate. These neural networks can be expressed as analytical functions, and FORTRAN subroutines can be provided.

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

Modeling fluctuations in default-mode brain network using a spiking neural network.

PubMed

Yamanishi, Teruya; Liu, Jian-Qin; Nishimura, Haruhiko

2012-08-01

Recently, numerous attempts have been made to understand the dynamic behavior of complex brain systems using neural network models. The fluctuations in blood-oxygen-level-dependent (BOLD) brain signals at less than 0.1 Hz have been observed by functional magnetic resonance imaging (fMRI) for subjects in a resting state. This phenomenon is referred to as a "default-mode brain network." In this study, we model the default-mode brain network by functionally connecting neural communities composed of spiking neurons in a complex network. Through computational simulations of the model, including transmission delays and complex connectivity, the network dynamics of the neural system and its behavior are discussed. The results show that the power spectrum of the modeled fluctuations in the neuron firing patterns is consistent with the default-mode brain network's BOLD signals when transmission delays, a characteristic property of the brain, have finite values in a given range.

On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks

PubMed Central

Tonelli, Paul; Mouret, Jean-Baptiste

2013-01-01

A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural networks are (1) the developmental process that links genes to nervous systems, which enables the evolution of large, regular neural networks, and (2) synaptic plasticity, which allows neural networks to change during their lifetime. So far, these two topics have been mainly studied separately. The present paper shows that they are actually deeply connected. Using a simple operant conditioning task and a classic evolutionary algorithm, we compare three ways to encode plastic neural networks: a direct encoding, a developmental encoding inspired by computational neuroscience models, and a developmental encoding inspired by morphogen gradients (similar to HyperNEAT). Our results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks. Complementary experiments reveal that this result is likely the consequence of the bias of developmental encodings towards regular structures: (1) in our experimental setup, encodings that tend to produce more regular networks yield networks with better general learning abilities; (2) whatever the encoding is, networks that are the more regular are statistically those that have the best learning abilities. PMID:24236099

Modular representation of layered neural networks.

PubMed

Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

2018-01-01

Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge from the inference provided by a layered neural network, since its internal representation has many nonlinear and complex parameters embedded in hierarchical layers. Therefore, it becomes important to establish a new methodology by which layered neural networks can be understood. In this paper, we propose a new method for extracting a global and simplified structure from a layered neural network. Based on network analysis, the proposed method detects communities or clusters of units with similar connection patterns. We show its effectiveness by applying it to three use cases. (1) Network decomposition: it can decompose a trained neural network into multiple small independent networks thus dividing the problem and reducing the computation time. (2) Training assessment: the appropriateness of a trained result with a given hyperparameter or randomly chosen initial parameters can be evaluated by using a modularity index. And (3) data analysis: in practical data it reveals the community structure in the input, hidden, and output layers, which serves as a clue for discovering knowledge from a trained neural network. Copyright © 2017 Elsevier Ltd. All rights reserved.

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.

Psychometric Measurement Models and Artificial Neural Networks

ERIC Educational Resources Information Center

Sese, Albert; Palmer, Alfonso L.; Montano, Juan J.

2004-01-01

The study of measurement models in psychometrics by means of dimensionality reduction techniques such as Principal Components Analysis (PCA) is a very common practice. In recent times, an upsurge of interest in the study of artificial neural networks apt to computing a principal component extraction has been observed. Despite this interest, the…

Proceedings of the Third International Workshop on Neural Networks and Fuzzy Logic, volume 2

NASA Technical Reports Server (NTRS)

Culbert, Christopher J. (Editor)

1993-01-01

Papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by the National Aeronautics and Space Administration and cosponsored by the University of Houston, Clear Lake, held 1-3 Jun. 1992 at the Lyndon B. Johnson Space Center in Houston, Texas are included. During the three days approximately 50 papers were presented. Technical topics addressed included adaptive systems; learning algorithms; network architectures; vision; robotics; neurobiological connections; speech recognition and synthesis; fuzzy set theory and application, control and dynamics processing; space applications; fuzzy logic and neural network computers; approximate reasoning; and multiobject decision making.

Face recognition: a convolutional neural-network approach.

PubMed

Lawrence, S; Giles, C L; Tsoi, A C; Back, A D

1997-01-01

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

Neural network for processing both spatial and temporal data with time based back-propagation

NASA Technical Reports Server (NTRS)

Villarreal, James A. (Inventor); Shelton, Robert O. (Inventor)

1993-01-01

Neural networks are computing systems modeled after the paradigm of the biological brain. For years, researchers using various forms of neural networks have attempted to model the brain's information processing and decision-making capabilities. Neural network algorithms have impressively demonstrated the capability of modeling spatial information. On the other hand, the application of parallel distributed models to the processing of temporal data has been severely restricted. The invention introduces a novel technique which adds the dimension of time to the well known back-propagation neural network algorithm. In the space-time neural network disclosed herein, the synaptic weights between two artificial neurons (processing elements) are replaced with an adaptable-adjustable filter. Instead of a single synaptic weight, the invention provides a plurality of weights representing not only association, but also temporal dependencies. In this case, the synaptic weights are the coefficients to the adaptable digital filters. Novelty is believed to lie in the disclosure of a processing element and a network of the processing elements which are capable of processing temporal as well as spacial data.

Reinforced Adversarial Neural Computer for de Novo Molecular Design.

PubMed

Putin, Evgeny; Asadulaev, Arip; Ivanenkov, Yan; Aladinskiy, Vladimir; Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alán; Zhavoronkov, Alex

2018-06-12

In silico modeling is a crucial milestone in modern drug design and development. Although computer-aided approaches in this field are well-studied, the application of deep learning methods in this research area is at the beginning. In this work, we present an original deep neural network (DNN) architecture named RANC (Reinforced Adversarial Neural Computer) for the de novo design of novel small-molecule organic structures based on the generative adversarial network (GAN) paradigm and reinforcement learning (RL). As a generator RANC uses a differentiable neural computer (DNC), a category of neural networks, with increased generation capabilities due to the addition of an explicit memory bank, which can mitigate common problems found in adversarial settings. The comparative results have shown that RANC trained on the SMILES string representation of the molecules outperforms its first DNN-based counterpart ORGANIC by several metrics relevant to drug discovery: the number of unique structures, passing medicinal chemistry filters (MCFs), Muegge criteria, and high QED scores. RANC is able to generate structures that match the distributions of the key chemical features/descriptors (e.g., MW, logP, TPSA) and lengths of the SMILES strings in the training data set. Therefore, RANC can be reasonably regarded as a promising starting point to develop novel molecules with activity against different biological targets or pathways. In addition, this approach allows scientists to save time and covers a broad chemical space populated with novel and diverse compounds.

An introduction to neural networks surgery, a field of neuromodulation which is based on advances in neural networks science and digitised brain imaging.

PubMed

Sakas, D E; Panourias, I G; Simpson, B A

2007-01-01

Operative Neuromodulation is the field of altering electrically or chemically the signal transmission in the nervous system by implanted devices in order to excite, inhibit or tune the activities of neurons or neural networks and produce therapeutic effects. The present article reviews relevant literature on procedures or devices applied either in contact with the cerebral cortex or cranial nerves or in deep sites inside the brain in order to treat various refractory neurological conditions such as: a) chronic pain (facial, somatic, deafferentation, phantom limb), b) movement disorders (Parkinson's disease, dystonia, Tourette syndrome), c) epilepsy, d) psychiatric disease, e) hearing deficits, and f) visual loss. These data indicate that in operative neuromodulation, a new field emerges that is based on neural networks research and on advances in digitised stereometric brain imaging which allow precise localisation of cerebral neural networks and their relay stations; this field can be described as Neural networks surgery because it aims to act extrinsically or intrinsically on neural networks and to alter therapeutically the neural signal transmission with the use of implantable electrical or electronic devices. The authors also review neurotechnology literature relevant to neuroengineering, nanotechnologies, brain computer interfaces, hybrid cultured probes, neuromimetics, neuroinformatics, neurocomputation, and computational neuromodulation; the latter field is dedicated to the study of the biophysical and mathematical characteristics of electrochemical neuromodulation. The article also brings forward particularly interesting lines of research such as the carbon nanofibers electrode arrays for simultaneous electrochemical recording and stimulation, closed-loop systems for responsive neuromodulation, and the intracortical electrodes for restoring hearing or vision. The present review of cerebral neuromodulatory procedures highlights the transition from the conventional neurosurgery of resective or ablative techniques to a highly selective "surgery of networks". The dynamics of the convergence of the above biomedical and technological fields with biological restorative approaches have important implications for patients with severe neurological disorders.

Applying Gradient Descent in Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Cui, Nan

2018-04-01

With the development of the integrated circuit and computer science, people become caring more about solving practical issues via information technologies. Along with that, a new subject called Artificial Intelligent (AI) comes up. One popular research interest of AI is about recognition algorithm. In this paper, one of the most common algorithms, Convolutional Neural Networks (CNNs) will be introduced, for image recognition. Understanding its theory and structure is of great significance for every scholar who is interested in this field. Convolution Neural Network is an artificial neural network which combines the mathematical method of convolution and neural network. The hieratical structure of CNN provides it reliable computer speed and reasonable error rate. The most significant characteristics of CNNs are feature extraction, weight sharing and dimension reduction. Meanwhile, combining with the Back Propagation (BP) mechanism and the Gradient Descent (GD) method, CNNs has the ability to self-study and in-depth learning. Basically, BP provides an opportunity for backwardfeedback for enhancing reliability and GD is used for self-training process. This paper mainly discusses the CNN and the related BP and GD algorithms, including the basic structure and function of CNN, details of each layer, the principles and features of BP and GD, and some examples in practice with a summary in the end.

Engineering Applications of Neural Computing: A State-of-the-Art Survey

DTIC Science & Technology

1991-05-01

results of the neural networks and compare with doctor’s knowledge. In veterinary medicine, a system for diag- nosis of mastitis in dairy cows is...construction of a hybrid system for diagnosing mastitis in COWS . Perhaps the most noteworthy application is the neural network-based explosive...diagnosis of mastitis in a limited set of experimental data showed excellent accuracy. In engineering facility management, monitoring and diagnostics are

Pattern recognition neural-net by spatial mapping of biology visual field

NASA Astrophysics Data System (ADS)

Lin, Xin; Mori, Masahiko

2000-05-01

The method of spatial mapping in biology vision field is applied to artificial neural networks for pattern recognition. By the coordinate transform that is called the complex-logarithm mapping and Fourier transform, the input images are transformed into scale- rotation- and shift- invariant patterns, and then fed into a multilayer neural network for learning and recognition. The results of computer simulation and an optical experimental system are described.

A New Stochastic Technique for Painlevé Equation-I Using Neural Network Optimized with Swarm Intelligence

PubMed Central

Raja, Muhammad Asif Zahoor; Khan, Junaid Ali; Ahmad, Siraj-ul-Islam; Qureshi, Ijaz Mansoor

2012-01-01

A methodology for solution of Painlevé equation-I is presented using computational intelligence technique based on neural networks and particle swarm optimization hybridized with active set algorithm. The mathematical model of the equation is developed with the help of linear combination of feed-forward artificial neural networks that define the unsupervised error of the model. This error is minimized subject to the availability of appropriate weights of the networks. The learning of the weights is carried out using particle swarm optimization algorithm used as a tool for viable global search method, hybridized with active set algorithm for rapid local convergence. The accuracy, convergence rate, and computational complexity of the scheme are analyzed based on large number of independents runs and their comprehensive statistical analysis. The comparative studies of the results obtained are made with MATHEMATICA solutions, as well as, with variational iteration method and homotopy perturbation method. PMID:22919371

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

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.

Neural networks with local receptive fields and superlinear VC dimension.

PubMed

Schmitt, Michael

2002-04-01

Local receptive field neurons comprise such well-known and widely used unit types as radial basis function (RBF) neurons and neurons with center-surround receptive field. We study the Vapnik-Chervonenkis (VC) dimension of feedforward neural networks with one hidden layer of these units. For several variants of local receptive field neurons, we show that the VC dimension of these networks is superlinear. In particular, we establish the bound Omega(W log k) for any reasonably sized network with W parameters and k hidden nodes. This bound is shown to hold for discrete center-surround receptive field neurons, which are physiologically relevant models of cells in the mammalian visual system, for neurons computing a difference of gaussians, which are popular in computational vision, and for standard RBF neurons, a major alternative to sigmoidal neurons in artificial neural networks. The result for RBF neural networks is of particular interest since it answers a question that has been open for several years. The results also give rise to lower bounds for networks with fixed input dimension. Regarding constants, all bounds are larger than those known thus far for similar architectures with sigmoidal neurons. The superlinear lower bounds contrast with linear upper bounds for single local receptive field neurons also derived here.

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.

Superconducting Optoelectronic Circuits for Neuromorphic Computing

NASA Astrophysics Data System (ADS)

Shainline, Jeffrey M.; Buckley, Sonia M.; Mirin, Richard P.; Nam, Sae Woo

2017-03-01

Neural networks have proven effective for solving many difficult computational problems, yet implementing complex neural networks in software is computationally expensive. To explore the limits of information processing, it is necessary to implement new hardware platforms with large numbers of neurons, each with a large number of connections to other neurons. Here we propose a hybrid semiconductor-superconductor hardware platform for the implementation of neural networks and large-scale neuromorphic computing. The platform combines semiconducting few-photon light-emitting diodes with superconducting-nanowire single-photon detectors to behave as spiking neurons. These processing units are connected via a network of optical waveguides, and variable weights of connection can be implemented using several approaches. The use of light as a signaling mechanism overcomes fanout and parasitic constraints on electrical signals while simultaneously introducing physical degrees of freedom which can be employed for computation. The use of supercurrents achieves the low power density (1 mW /cm2 at 20-MHz firing rate) necessary to scale to systems with enormous entropy. Estimates comparing the proposed hardware platform to a human brain show that with the same number of neurons (1 011) and 700 independent connections per neuron, the hardware presented here may achieve an order of magnitude improvement in synaptic events per second per watt.

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.

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.

Practical approximation method for firing-rate models of coupled neural networks with correlated inputs

NASA Astrophysics Data System (ADS)

Barreiro, Andrea K.; Ly, Cheng

2017-08-01

Rapid experimental advances now enable simultaneous electrophysiological recording of neural activity at single-cell resolution across large regions of the nervous system. Models of this neural network activity will necessarily increase in size and complexity, thus increasing the computational cost of simulating them and the challenge of analyzing them. Here we present a method to approximate the activity and firing statistics of a general firing rate network model (of the Wilson-Cowan type) subject to noisy correlated background inputs. The method requires solving a system of transcendental equations and is fast compared to Monte Carlo simulations of coupled stochastic differential equations. We implement the method with several examples of coupled neural networks and show that the results are quantitatively accurate even with moderate coupling strengths and an appreciable amount of heterogeneity in many parameters. This work should be useful for investigating how various neural attributes qualitatively affect the spiking statistics of coupled neural networks.

HRLSim: a high performance spiking neural network simulator for GPGPU clusters.

PubMed

Minkovich, Kirill; Thibeault, Corey M; O'Brien, Michael John; Nogin, Aleksey; Cho, Youngkwan; Srinivasa, Narayan

2014-02-01

Modeling of large-scale spiking neural models is an important tool in the quest to understand brain function and subsequently create real-world applications. This paper describes a spiking neural network simulator environment called HRL Spiking Simulator (HRLSim). This simulator is suitable for implementation on a cluster of general purpose graphical processing units (GPGPUs). Novel aspects of HRLSim are described and an analysis of its performance is provided for various configurations of the cluster. With the advent of inexpensive GPGPU cards and compute power, HRLSim offers an affordable and scalable tool for design, real-time simulation, and analysis of large-scale spiking neural networks.

A System for Video Surveillance and Monitoring CMU VSAM Final Report

DTIC Science & Technology

1999-11-30

motion-based skeletonization, neural network , spatio-temporal salience Patterns inside image chips, spurious motion rejection, model -based... network of sensors with respect to the model coordinate system, computation of 3D geolocation estimates, and graphical display of object hypotheses...rithms have been developed. The first uses view dependent visual properties to train a neural network classifier to recognize four classes: single

F77NNS - A FORTRAN-77 NEURAL NETWORK SIMULATOR

NASA Technical Reports Server (NTRS)

Mitchell, P. H.

1994-01-01

F77NNS (A FORTRAN-77 Neural Network Simulator) simulates the popular back error propagation neural network. F77NNS is an ANSI-77 FORTRAN program designed to take advantage of vectorization when run on machines having this capability, but it will run on any computer with an ANSI-77 FORTRAN Compiler. Artificial neural networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to biological nerve cells. Problems which involve pattern matching or system modeling readily fit the class of problems which F77NNS is designed to solve. The program's formulation trains a neural network using Rumelhart's back-propagation algorithm. Typically the nodes of a network are grouped together into clumps called layers. A network will generally have an input layer through which the various environmental stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. The back-propagation training algorithm can require massive computational resources to implement a large network such as a network capable of learning text-to-phoneme pronunciation rules as in the famous Sehnowski experiment. The Sehnowski neural network learns to pronounce 1000 common English words. The standard input data defines the specific inputs that control the type of run to be made, and input files define the NN in terms of the layers and nodes, as well as the input/output (I/O) pairs. The program has a restart capability so that a neural network can be solved in stages suitable to the user's resources and desires. F77NNS allows the user to customize the patterns of connections between layers of a network. The size of the neural network to be solved is limited only by the amount of random access memory (RAM) available to the user. The program has a memory requirement of about 900K. The standard distribution medium for this package is a .25 inch streaming magnetic tape cartridge in UNIX tar format. It is also available on a 3.5 inch diskette in UNIX tar format. F77NNS was developed in 1989.

Neurocomputing

NASA Technical Reports Server (NTRS)

Hecht-Nielsen, Robert

1990-01-01

The present work is intended to give technologists, research scientists, and mathematicians a graduate-level overview of the field of neurocomputing. After exploring the relationship of this field to general neuroscience, attention is given to neural network building blocks, the self-adaptation equations of learning laws, the data-transformation structures of associative networks, and the multilayer data-transformation structures of mapping networks. Also treated are the neurocomputing frontiers of spatiotemporal, stochastic, and hierarchical networks, 'neurosoftware', the creation of neural network-based computers, and neurocomputing applications in sensor processing, control, and data analysis.

A modular architecture for transparent computation in recurrent neural networks.

PubMed

Carmantini, Giovanni S; Beim Graben, Peter; Desroches, Mathieu; Rodrigues, Serafim

2017-01-01

Computation is classically studied in terms of automata, formal languages and algorithms; yet, the relation between neural dynamics and symbolic representations and operations is still unclear in traditional eliminative connectionism. Therefore, we suggest a unique perspective on this central issue, to which we would like to refer as transparent connectionism, by proposing accounts of how symbolic computation can be implemented in neural substrates. In this study we first introduce a new model of dynamics on a symbolic space, the versatile shift, showing that it supports the real-time simulation of a range of automata. We then show that the Gödelization of versatile shifts defines nonlinear dynamical automata, dynamical systems evolving on a vectorial space. Finally, we present a mapping between nonlinear dynamical automata and recurrent artificial neural networks. The mapping defines an architecture characterized by its granular modularity, where data, symbolic operations and their control are not only distinguishable in activation space, but also spatially localizable in the network itself, while maintaining a distributed encoding of symbolic representations. The resulting networks simulate automata in real-time and are programmed directly, in the absence of network training. To discuss the unique characteristics of the architecture and their consequences, we present two examples: (i) the design of a Central Pattern Generator from a finite-state locomotive controller, and (ii) the creation of a network simulating a system of interactive automata that supports the parsing of garden-path sentences as investigated in psycholinguistics experiments. Copyright © 2016 Elsevier Ltd. All rights reserved.

Asymptotic stability of delay-difference system of hopfield neural networks via matrix inequalities and application.

PubMed

Ratchagit, Kreangkri

2007-10-01

In this paper, we derive a sufficient condition for asymptotic stability of the zero solution of delay-difference system of Hopfield neural networks in terms of certain matrix inequalities by using a discrete version of the Lyapunov second method. The result is applied to obtain new asymptotic stability condition for some class of delay-difference system such as delay-difference system of Hopfield neural networks with multiple delays in terms of certain matrix inequalities. Our results can be well suited for computational purposes.

Neural network controller development for a magnetically suspended flywheel energy storage system

NASA Technical Reports Server (NTRS)

Fittro, Roger L.; Pang, Da-Chen; Anand, Davinder K.

1994-01-01

A neural network controller has been developed to accommodate disturbances and nonlinearities and improve the robustness of a magnetically suspended flywheel energy storage system. The controller is trained using the back propagation-through-time technique incorporated with a time-averaging scheme. The resulting nonlinear neural network controller improves system performance by adapting flywheel stiffness and damping based on operating speed. In addition, a hybrid multi-layered neural network controller is developed off-line which is capable of improving system performance even further. All of the research presented in this paper was implemented via a magnetic bearing computer simulation. However, careful attention was paid to developing a practical methodology which will make future application to the actual bearing system fairly straightforward.

Concurrent heterogeneous neural model simulation on real-time neuromimetic hardware.

PubMed

Rast, Alexander; Galluppi, Francesco; Davies, Sergio; Plana, Luis; Patterson, Cameron; Sharp, Thomas; Lester, David; Furber, Steve

2011-11-01

Dedicated hardware is becoming increasingly essential to simulate emerging very-large-scale neural models. Equally, however, it needs to be able to support multiple models of the neural dynamics, possibly operating simultaneously within the same system. This may be necessary either to simulate large models with heterogeneous neural types, or to simplify simulation and analysis of detailed, complex models in a large simulation by isolating the new model to a small subpopulation of a larger overall network. The SpiNNaker neuromimetic chip is a dedicated neural processor able to support such heterogeneous simulations. Implementing these models on-chip uses an integrated library-based tool chain incorporating the emerging PyNN interface that allows a modeller to input a high-level description and use an automated process to generate an on-chip simulation. Simulations using both LIF and Izhikevich models demonstrate the ability of the SpiNNaker system to generate and simulate heterogeneous networks on-chip, while illustrating, through the network-scale effects of wavefront synchronisation and burst gating, methods that can provide effective behavioural abstractions for large-scale hardware modelling. SpiNNaker's asynchronous virtual architecture permits greater scope for model exploration, with scalable levels of functional and temporal abstraction, than conventional (or neuromorphic) computing platforms. The complete system illustrates a potential path to understanding the neural model of computation, by building (and breaking) neural models at various scales, connecting the blocks, then comparing them against the biology: computational cognitive neuroscience. Copyright © 2011 Elsevier Ltd. All rights reserved.

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.

Application of a neural network for reflectance spectrum classification

NASA Astrophysics Data System (ADS)

Yang, Gefei; Gartley, Michael

2017-05-01

Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

Network traffic anomaly prediction using Artificial Neural Network

NASA Astrophysics Data System (ADS)

Ciptaningtyas, Hening Titi; Fatichah, Chastine; Sabila, Altea

2017-03-01

As the excessive increase of internet usage, the malicious software (malware) has also increase significantly. Malware is software developed by hacker for illegal purpose(s), such as stealing data and identity, causing computer damage, or denying service to other user[1]. Malware which attack computer or server often triggers network traffic anomaly phenomena. Based on Sophos's report[2], Indonesia is the riskiest country of malware attack and it also has high network traffic anomaly. This research uses Artificial Neural Network (ANN) to predict network traffic anomaly based on malware attack in Indonesia which is recorded by Id-SIRTII/CC (Indonesia Security Incident Response Team on Internet Infrastructure/Coordination Center). The case study is the highest malware attack (SQL injection) which has happened in three consecutive years: 2012, 2013, and 2014[4]. The data series is preprocessed first, then the network traffic anomaly is predicted using Artificial Neural Network and using two weight update algorithms: Gradient Descent and Momentum. Error of prediction is calculated using Mean Squared Error (MSE) [7]. The experimental result shows that MSE for SQL Injection is 0.03856. So, this approach can be used to predict network traffic anomaly.

Evaluation of Physiologically-Based Artificial Neural Network Models to Detect Operator Workload in Remotely Piloted Aircraft Operations

DTIC Science & Technology

2016-07-13

to a computer via Bluetooth . Respiration is captured as a breathing waveform signal using a capacitive pressure sensor, sampled at 18 Hz. The...dropouts in the Bluetooth signal and artifacts caused by body movement. Workload models. Four artificial neural network models were created using

Forecasting PM10 in metropolitan areas: Efficacy of neural networks.

PubMed

Fernando, H J S; Mammarella, M C; Grandoni, G; Fedele, P; Di Marco, R; Dimitrova, R; Hyde, P

2012-04-01

Deterministic photochemical air quality models are commonly used for regulatory management and planning of urban airsheds. These models are complex, computer intensive, and hence are prohibitively expensive for routine air quality predictions. Stochastic methods are becoming increasingly popular as an alternative, which relegate decision making to artificial intelligence based on Neural Networks that are made of artificial neurons or 'nodes' capable of 'learning through training' via historic data. A Neural Network was used to predict particulate matter concentration at a regulatory monitoring site in Phoenix, Arizona; its development, efficacy as a predictive tool and performance vis-à-vis a commonly used regulatory photochemical model are described in this paper. It is concluded that Neural Networks are much easier, quicker and economical to implement without compromising the accuracy of predictions. Neural Networks can be used to develop rapid air quality warning systems based on a network of automated monitoring stations. Copyright © 2011 Elsevier Ltd. All rights reserved.

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.

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

PubMed

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

2017-11-01

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Computer-aided diagnostic system for diffuse liver diseases with ultrasonography by neural networks

NASA Astrophysics Data System (ADS)

Ogawa, K.; Fukushima, M.; Kubota, K.; Hisa, N.

1998-12-01

The aim of the study is to establish a computer-aided diagnostic system for diffuse liver diseases such as chronic active hepatitis (CAH) and liver cirrhosis (LC). The authors introduced an artificial neural network in the classification of these diseases. In this system the neural network was trained by feature parameters extracted from B-mode ultrasonic images of normal liver (NL), CAH and LC. For input data the authors used six parameters calculated by a region of interest (ROI) and a parameter calculated by five ROIs in each image. They were variance of pixel values, coefficient of variation, annular Fourier power spectrum, longitudinal Fourier power spectrum which were calculated for the ROI, and variation of the means of the five ROIs. In addition, the authors used two more parameters calculated from a co-occurrence matrix of pixel values in the ROI. The results showed that the neural network classifier was 83.8% in sensitivity for LC, 90.0% in sensitivity for CAH and 93.6% in specificity, and the system was considered to be helpful for clinical and educational use.

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.

Neural model of gene regulatory network: a survey on supportive meta-heuristics.

PubMed

Biswas, Surama; Acharyya, Sriyankar

2016-06-01

Gene regulatory network (GRN) is produced as a result of regulatory interactions between different genes through their coded proteins in cellular context. Having immense importance in disease detection and drug finding, GRN has been modelled through various mathematical and computational schemes and reported in survey articles. Neural and neuro-fuzzy models have been the focus of attraction in bioinformatics. Predominant use of meta-heuristic algorithms in training neural models has proved its excellence. Considering these facts, this paper is organized to survey neural modelling schemes of GRN and the efficacy of meta-heuristic algorithms towards parameter learning (i.e. weighting connections) within the model. This survey paper renders two different structure-related approaches to infer GRN which are global structure approach and substructure approach. It also describes two neural modelling schemes, such as artificial neural network/recurrent neural network based modelling and neuro-fuzzy modelling. The meta-heuristic algorithms applied so far to learn the structure and parameters of neutrally modelled GRN have been reviewed here.

A solution to neural field equations by a recurrent neural network method

NASA Astrophysics Data System (ADS)

Alharbi, Abir

2012-09-01

Neural field equations (NFE) are used to model the activity of neurons in the brain, it is introduced from a single neuron 'integrate-and-fire model' starting point. The neural continuum is spatially discretized for numerical studies, and the governing equations are modeled as a system of ordinary differential equations. In this article the recurrent neural network approach is used to solve this system of ODEs. This consists of a technique developed by combining the standard numerical method of finite-differences with the Hopfield neural network. The architecture of the net, energy function, updating equations, and algorithms are developed for the NFE model. A Hopfield Neural Network is then designed to minimize the energy function modeling the NFE. Results obtained from the Hopfield-finite-differences net show excellent performance in terms of accuracy and speed. The parallelism nature of the Hopfield approaches may make them easier to implement on fast parallel computers and give them the speed advantage over the traditional methods.

Neuronify: An Educational Simulator for Neural Circuits.

PubMed

Dragly, Svenn-Arne; Hobbi Mobarhan, Milad; Våvang Solbrå, Andreas; Tennøe, Simen; Hafreager, Anders; Malthe-Sørenssen, Anders; Fyhn, Marianne; Hafting, Torkel; Einevoll, Gaute T

2017-01-01

Educational software (apps) can improve science education by providing an interactive way of learning about complicated topics that are hard to explain with text and static illustrations. However, few educational apps are available for simulation of neural networks. Here, we describe an educational app, Neuronify, allowing the user to easily create and explore neural networks in a plug-and-play simulation environment. The user can pick network elements with adjustable parameters from a menu, i.e., synaptically connected neurons modelled as integrate-and-fire neurons and various stimulators (current sources, spike generators, visual, and touch) and recording devices (voltmeter, spike detector, and loudspeaker). We aim to provide a low entry point to simulation-based neuroscience by allowing students with no programming experience to create and simulate neural networks. To facilitate the use of Neuronify in teaching, a set of premade common network motifs is provided, performing functions such as input summation, gain control by inhibition, and detection of direction of stimulus movement. Neuronify is developed in C++ and QML using the cross-platform application framework Qt and runs on smart phones (Android, iOS) and tablet computers as well personal computers (Windows, Mac, Linux).

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.

Neuronify: An Educational Simulator for Neural Circuits

PubMed Central

Hafreager, Anders; Malthe-Sørenssen, Anders; Fyhn, Marianne

2017-01-01

Abstract Educational software (apps) can improve science education by providing an interactive way of learning about complicated topics that are hard to explain with text and static illustrations. However, few educational apps are available for simulation of neural networks. Here, we describe an educational app, Neuronify, allowing the user to easily create and explore neural networks in a plug-and-play simulation environment. The user can pick network elements with adjustable parameters from a menu, i.e., synaptically connected neurons modelled as integrate-and-fire neurons and various stimulators (current sources, spike generators, visual, and touch) and recording devices (voltmeter, spike detector, and loudspeaker). We aim to provide a low entry point to simulation-based neuroscience by allowing students with no programming experience to create and simulate neural networks. To facilitate the use of Neuronify in teaching, a set of premade common network motifs is provided, performing functions such as input summation, gain control by inhibition, and detection of direction of stimulus movement. Neuronify is developed in C++ and QML using the cross-platform application framework Qt and runs on smart phones (Android, iOS) and tablet computers as well personal computers (Windows, Mac, Linux). PMID:28321440

Application of artificial neural networks to the design optimization of aerospace structural components

NASA Technical Reports Server (NTRS)

Berke, Laszlo; Patnaik, Surya N.; Murthy, Pappu L. N.

1993-01-01

The application of artificial neural networks to capture structural design expertise is demonstrated. The principal advantage of a trained neural network is that it requires trivial computational effort to produce an acceptable new design. For the class of problems addressed, the development of a conventional expert system would be extremely difficult. In the present effort, a structural optimization code with multiple nonlinear programming algorithms and an artificial neural network code NETS were used. A set of optimum designs for a ring and two aircraft wings for static and dynamic constraints were generated by using the optimization codes. The optimum design data were processed to obtain input and output pairs, which were used to develop a trained artificial neural network with the code NETS. Optimum designs for new design conditions were predicted by using the trained network. Neural net prediction of optimum designs was found to be satisfactory for most of the output design parameters. However, results from the present study indicate that caution must be exercised to ensure that all design variables are within selected error bounds.

Optimum Design of Aerospace Structural Components Using Neural Networks

NASA Technical Reports Server (NTRS)

Berke, L.; Patnaik, S. N.; Murthy, P. L. N.

1993-01-01

The application of artificial neural networks to capture structural design expertise is demonstrated. The principal advantage of a trained neural network is that it requires a trivial computational effort to produce an acceptable new design. For the class of problems addressed, the development of a conventional expert system would be extremely difficult. In the present effort, a structural optimization code with multiple nonlinear programming algorithms and an artificial neural network code NETS were used. A set of optimum designs for a ring and two aircraft wings for static and dynamic constraints were generated using the optimization codes. The optimum design data were processed to obtain input and output pairs, which were used to develop a trained artificial neural network using the code NETS. Optimum designs for new design conditions were predicted using the trained network. Neural net prediction of optimum designs was found to be satisfactory for the majority of the output design parameters. However, results from the present study indicate that caution must be exercised to ensure that all design variables are within selected error bounds.

Computational Models and Emergent Properties of Respiratory Neural Networks

PubMed Central

Lindsey, Bruce G.; Rybak, Ilya A.; Smith, Jeffrey C.

2012-01-01

Computational models of the neural control system for breathing in mammals provide a theoretical and computational framework bringing together experimental data obtained from different animal preparations under various experimental conditions. Many of these models were developed in parallel and iteratively with experimental studies and provided predictions guiding new experiments. This data-driven modeling approach has advanced our understanding of respiratory network architecture and neural mechanisms underlying generation of the respiratory rhythm and pattern, including their functional reorganization under different physiological conditions. Models reviewed here vary in neurobiological details and computational complexity and span multiple spatiotemporal scales of respiratory control mechanisms. Recent models describe interacting populations of respiratory neurons spatially distributed within the Bötzinger and pre-Bötzinger complexes and rostral ventrolateral medulla that contain core circuits of the respiratory central pattern generator (CPG). Network interactions within these circuits along with intrinsic rhythmogenic properties of neurons form a hierarchy of multiple rhythm generation mechanisms. The functional expression of these mechanisms is controlled by input drives from other brainstem components, including the retrotrapezoid nucleus and pons, which regulate the dynamic behavior of the core circuitry. The emerging view is that the brainstem respiratory network has rhythmogenic capabilities at multiple levels of circuit organization. This allows flexible, state-dependent expression of different neural pattern-generation mechanisms under various physiological conditions, enabling a wide repertoire of respiratory behaviors. Some models consider control of the respiratory CPG by pulmonary feedback and network reconfiguration during defensive behaviors such as cough. Future directions in modeling of the respiratory CPG are considered. PMID:23687564

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 Networks

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

Smith, Patrick I.

2003-09-23

Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neuralmore » networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing information [2]. Each one of these cells acts as a simple processor. When individual cells interact with one another, the complex abilities of the brain are made possible. In neural networks, the input or data are processed by a propagation function that adds up the values of all the incoming data. The ending value is then compared with a threshold or specific value. The resulting value must exceed the activation function value in order to become output. The activation function is a mathematical function that a neuron uses to produce an output referring to its input value. [8] Figure 1 depicts this process. Neural networks usually have three components an input, a hidden, and an output. These layers create the end result of the neural network. A real world example is a child associating the word dog with a picture. The child says dog and simultaneously looks a picture of a dog. The input is the spoken word ''dog'', the hidden is the brain processing, and the output will be the category of the word dog based on the picture. This illustration describes how a neural network functions.« less

Critical branching neural networks.

PubMed

Kello, Christopher T

2013-01-01

It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical branching and, in doing so, simulates observed scaling laws as pervasive to neural and behavioral activity. These scaling laws are related to neural and cognitive functions, in that critical branching is shown to yield spiking activity with maximal memory and encoding capacities when analyzed using reservoir computing techniques. The model is also shown to account for findings of pervasive 1/f scaling in speech and cued response behaviors that are difficult to explain by isolable causes. Issues and questions raised by the model and its results are discussed from the perspectives of physics, neuroscience, computer and information sciences, and psychological and cognitive sciences.

Complex Networks in Psychological Models

NASA Astrophysics Data System (ADS)

Wedemann, R. S.; Carvalho, L. S. A. V. D.; Donangelo, R.

We develop schematic, self-organizing, neural-network models to describe mechanisms associated with mental processes, by a neurocomputational substrate. These models are examples of real world complex networks with interesting general topological structures. Considering dopaminergic signal-to-noise neuronal modulation in the central nervous system, we propose neural network models to explain development of cortical map structure and dynamics of memory access, and unify different mental processes into a single neurocomputational substrate. Based on our neural network models, neurotic behavior may be understood as an associative memory process in the brain, and the linguistic, symbolic associative process involved in psychoanalytic working-through can be mapped onto a corresponding process of reconfiguration of the neural network. The models are illustrated through computer simulations, where we varied dopaminergic modulation and observed the self-organizing emergent patterns at the resulting semantic map, interpreting them as different manifestations of mental functioning, from psychotic through to normal and neurotic behavior, and creativity.

Towards cortex sized artificial neural systems.

PubMed

Johansson, Christopher; Lansner, Anders

2007-01-01

We propose, implement, and discuss an abstract model of the mammalian neocortex. This model is instantiated with a sparse recurrently connected neural network that has spiking leaky integrator units and continuous Hebbian learning. First we study the structure, modularization, and size of neocortex, and then we describe a generic computational model of the cortical circuitry. A characterizing feature of the model is that it is based on the modularization of neocortex into hypercolumns and minicolumns. Both a floating- and fixed-point arithmetic implementation of the model are presented along with simulation results. We conclude that an implementation on a cluster computer is not communication but computation bounded. A mouse and rat cortex sized version of our model executes in 44% and 23% of real-time respectively. Further, an instance of the model with 1.6 x 10(6) units and 2 x 10(11) connections performed noise reduction and pattern completion. These implementations represent the current frontier of large-scale abstract neural network simulations in terms of network size and running speed.

Modeling and Computing of Stock Index Forecasting Based on Neural Network and Markov Chain

PubMed Central

Dai, Yonghui; Han, Dongmei; Dai, Weihui

2014-01-01

The stock index reflects the fluctuation of the stock market. For a long time, there have been a lot of researches on the forecast of stock index. However, the traditional method is limited to achieving an ideal precision in the dynamic market due to the influences of many factors such as the economic situation, policy changes, and emergency events. Therefore, the approach based on adaptive modeling and conditional probability transfer causes the new attention of researchers. This paper presents a new forecast method by the combination of improved back-propagation (BP) neural network and Markov chain, as well as its modeling and computing technology. This method includes initial forecasting by improved BP neural network, division of Markov state region, computing of the state transition probability matrix, and the prediction adjustment. Results of the empirical study show that this method can achieve high accuracy in the stock index prediction, and it could provide a good reference for the investment in stock market. PMID:24782659

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.

Proceedings of the Third International Workshop on Neural Networks and Fuzzy Logic, volume 1

NASA Technical Reports Server (NTRS)

Culbert, Christopher J. (Editor)

1993-01-01

Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by the National Aeronautics and Space Administration and cosponsored by the University of Houston, Clear Lake. The workshop was held June 1-3, 1992 at the Lyndon B. Johnson Space Center in Houston, Texas. During the three days approximately 50 papers were presented. Technical topics addressed included adaptive systems; learning algorithms; network architectures; vision; robotics; neurobiological connections; speech recognition and synthesis; fuzzy set theory and application, control, and dynamics processing; space applications; fuzzy logic and neural network computers; approximate reasoning; and multiobject decision making.

Two-Dimensional High-Lift Aerodynamic Optimization Using Neural Networks

NASA Technical Reports Server (NTRS)

Greenman, Roxana M.

1998-01-01

The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle at which it occurs. The 'pressure difference rule,' which states that the maximum lift condition corresponds to a certain pressure difference between the peak suction pressure and the pressure at the trailing edge of the element, was applied and verified with experimental observations for this configuration. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural nets were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 44% compared with traditional gradient-based optimization procedures for multiple optimization runs.

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.

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.

A web-based system for neural network based classification in temporomandibular joint osteoarthritis.

PubMed

de Dumast, Priscille; Mirabel, Clément; Cevidanes, Lucia; Ruellas, Antonio; Yatabe, Marilia; Ioshida, Marcos; Ribera, Nina Tubau; Michoud, Loic; Gomes, Liliane; Huang, Chao; Zhu, Hongtu; Muniz, Luciana; Shoukri, Brandon; Paniagua, Beatriz; Styner, Martin; Pieper, Steve; Budin, Francois; Vimort, Jean-Baptiste; Pascal, Laura; Prieto, Juan Carlos

2018-07-01

The purpose of this study is to describe the methodological innovations of a web-based system for storage, integration and computation of biomedical data, using a training imaging dataset to remotely compute a deep neural network classifier of temporomandibular joint osteoarthritis (TMJOA). This study imaging dataset consisted of three-dimensional (3D) surface meshes of mandibular condyles constructed from cone beam computed tomography (CBCT) scans. The training dataset consisted of 259 condyles, 105 from control subjects and 154 from patients with diagnosis of TMJ OA. For the image analysis classification, 34 right and left condyles from 17 patients (39.9 ± 11.7 years), who experienced signs and symptoms of the disease for less than 5 years, were included as the testing dataset. For the integrative statistical model of clinical, biological and imaging markers, the sample consisted of the same 17 test OA subjects and 17 age and sex matched control subjects (39.4 ± 15.4 years), who did not show any sign or symptom of OA. For these 34 subjects, a standardized clinical questionnaire, blood and saliva samples were also collected. The technological methodologies in this study include a deep neural network classifier of 3D condylar morphology (ShapeVariationAnalyzer, SVA), and a flexible web-based system for data storage, computation and integration (DSCI) of high dimensional imaging, clinical, and biological data. The DSCI system trained and tested the neural network, indicating 5 stages of structural degenerative changes in condylar morphology in the TMJ with 91% close agreement between the clinician consensus and the SVA classifier. The DSCI remotely ran with a novel application of a statistical analysis, the Multivariate Functional Shape Data Analysis, that computed high dimensional correlations between shape 3D coordinates, clinical pain levels and levels of biological markers, and then graphically displayed the computation results. The findings of this study demonstrate a comprehensive phenotypic characterization of TMJ health and disease at clinical, imaging and biological levels, using novel flexible and versatile open-source tools for a web-based system that provides advanced shape statistical analysis and a neural network based classification of temporomandibular joint osteoarthritis. Published by Elsevier Ltd.

Spatiotemporal discrimination in neural networks with short-term synaptic plasticity

NASA Astrophysics Data System (ADS)

Shlaer, Benjamin; Miller, Paul

2015-03-01

Cells in recurrently connected neural networks exhibit bistability, which allows for stimulus information to persist in a circuit even after stimulus offset, i.e. short-term memory. However, such a system does not have enough hysteresis to encode temporal information about the stimuli. The biophysically described phenomenon of synaptic depression decreases synaptic transmission strengths due to increased presynaptic activity. This short-term reduction in synaptic strengths can destabilize attractor states in excitatory recurrent neural networks, causing the network to move along stimulus dependent dynamical trajectories. Such a network can successfully separate amplitudes and durations of stimuli from the number of successive stimuli. Stimulus number, duration and intensity encoding in randomly connected attractor networks with synaptic depression. Front. Comput. Neurosci. 7:59., and so provides a strong candidate network for the encoding of spatiotemporal information. Here we explicitly demonstrate the capability of a recurrent neural network with short-term synaptic depression to discriminate between the temporal sequences in which spatial stimuli are presented.

Neural-like growing networks

NASA Astrophysics Data System (ADS)

Yashchenko, Vitaliy A.

2000-03-01

On the basis of the analysis of scientific ideas reflecting the law in the structure and functioning the biological structures of a brain, and analysis and synthesis of knowledge, developed by various directions in Computer Science, also there were developed the bases of the theory of a new class neural-like growing networks, not having the analogue in world practice. In a base of neural-like growing networks the synthesis of knowledge developed by classical theories - semantic and neural of networks is. The first of them enable to form sense, as objects and connections between them in accordance with construction of the network. With thus each sense gets a separate a component of a network as top, connected to other tops. In common it quite corresponds to structure reflected in a brain, where each obvious concept is presented by certain structure and has designating symbol. Secondly, this network gets increased semantic clearness at the expense owing to formation not only connections between neural by elements, but also themselves of elements as such, i.e. here has a place not simply construction of a network by accommodation sense structures in environment neural of elements, and purely creation of most this environment, as of an equivalent of environment of memory. Thus neural-like growing networks are represented by the convenient apparatus for modeling of mechanisms of teleological thinking, as a fulfillment of certain psychophysiological of functions.

Electronic neuroprocessors

NASA Technical Reports Server (NTRS)

Thakoor, Anil

1991-01-01

The JPL Center for Space Microelectronics Technology (CSMT) is actively pursuing research in the neural network theory, algorithms, and electronics as well as optoelectronic neural net hardware implementations, to explore the strengths and application potential for a variety of NASA, DoD, as well as commercial application problems, where conventional computing techniques are extremely time-consuming, cumbersome, or simply non-existent. An overview of the JPL electronic neural network hardware development activities and some of the striking applications of the JPL electronic neuroprocessors are presented.

Optimization with artificial neural network systems - A mapping principle and a comparison to gradient based methods

NASA Technical Reports Server (NTRS)

Leong, Harrison Monfook

1988-01-01

General formulae for mapping optimization problems into systems of ordinary differential equations associated with artificial neural networks are presented. A comparison is made to optimization using gradient-search methods. The performance measure is the settling time from an initial state to a target state. A simple analytical example illustrates a situation where dynamical systems representing artificial neural network methods would settle faster than those representing gradient-search. Settling time was investigated for a more complicated optimization problem using computer simulations. The problem was a simplified version of a problem in medical imaging: determining loci of cerebral activity from electromagnetic measurements at the scalp. The simulations showed that gradient based systems typically settled 50 to 100 times faster than systems based on current neural network optimization methods.

Neural network-based system for pattern recognition through a fiber optic bundle

NASA Astrophysics Data System (ADS)

Gamo-Aranda, Javier; Rodriguez-Horche, Paloma; Merchan-Palacios, Miguel; Rosales-Herrera, Pablo; Rodriguez, M.

2001-04-01

A neural network based system to identify images transmitted through a Coherent Fiber-optic Bundle (CFB) is presented. Patterns are generated in a computer, displayed on a Spatial Light Modulator, imaged onto the input face of the CFB, and recovered optically by a CCD sensor array for further processing. Input and output optical subsystems were designed and used to that end. The recognition step of the transmitted patterns is made by a powerful, widely-used, neural network simulator running on the control PC. A complete PC-based interface was developed to control the different tasks involved in the system. An optical analysis of the system capabilities was carried out prior to performing the recognition step. Several neural network topologies were tested, and the corresponding numerical results are also presented and discussed.

Gradient calculations for dynamic recurrent neural networks: a survey.

PubMed

Pearlmutter, B A

1995-01-01

Surveys learning algorithms for recurrent neural networks with hidden units and puts the various techniques into a common framework. The authors discuss fixed point learning algorithms, namely recurrent backpropagation and deterministic Boltzmann machines, and nonfixed point algorithms, namely backpropagation through time, Elman's history cutoff, and Jordan's output feedback architecture. Forward propagation, an on-line technique that uses adjoint equations, and variations thereof, are also discussed. In many cases, the unified presentation leads to generalizations of various sorts. The author discusses advantages and disadvantages of temporally continuous neural networks in contrast to clocked ones continues with some "tricks of the trade" for training, using, and simulating continuous time and recurrent neural networks. The author presents some simulations, and at the end, addresses issues of computational complexity and learning speed.

Neural network approach for the calculation of potential coefficients in quantum mechanics

NASA Astrophysics Data System (ADS)

Ossandón, Sebastián; Reyes, Camilo; Cumsille, Patricio; Reyes, Carlos M.

2017-05-01

A numerical method based on artificial neural networks is used to solve the inverse Schrödinger equation for a multi-parameter class of potentials. First, the finite element method was used to solve repeatedly the direct problem for different parametrizations of the chosen potential function. Then, using the attainable eigenvalues as a training set of the direct radial basis neural network a map of new eigenvalues was obtained. This relationship was later inverted and refined by training an inverse radial basis neural network, allowing the calculation of the unknown parameters and therefore estimating the potential function. Three numerical examples are presented in order to prove the effectiveness of the method. The results show that the method proposed has the advantage to use less computational resources without a significant accuracy loss.

Synchronization in a noise-driven developing neural network

NASA Astrophysics Data System (ADS)

Lin, I.-H.; Wu, R.-K.; Chen, C.-M.

2011-11-01

We use computer simulations to investigate the structural and dynamical properties of a developing neural network whose activity is driven by noise. Structurally, the constructed neural networks in our simulations exhibit the small-world properties that have been observed in several neural networks. The dynamical change of neuronal membrane potential is described by the Hodgkin-Huxley model, and two types of learning rules, including spike-timing-dependent plasticity (STDP) and inverse STDP, are considered to restructure the synaptic strength between neurons. Clustered synchronized firing (SF) of the network is observed when the network connectivity (number of connections/maximal connections) is about 0.75, in which the firing rate of neurons is only half of the network frequency. At the connectivity of 0.86, all neurons fire synchronously at the network frequency. The network SF frequency increases logarithmically with the culturing time of a growing network and decreases exponentially with the delay time in signal transmission. These conclusions are consistent with experimental observations. The phase diagrams of SF in a developing network are investigated for both learning rules.

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.

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

Rebooting Computers as Learning Machines

DOE PAGES

DeBenedictis, Erik P.

2016-06-13

Artificial neural networks could become the technological driver that replaces Moore's law, boosting computers' utlity through a process akin to automatic programming--although physics and computer architecture would are also a factor.

Rebooting Computers as Learning Machines

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

DeBenedictis, Erik P.

Artificial neural networks could become the technological driver that replaces Moore's law, boosting computers' utlity through a process akin to automatic programming--although physics and computer architecture would are also a factor.

Simple techniques for improving deep neural network outcomes on commodity hardware

NASA Astrophysics Data System (ADS)

Colina, Nicholas Christopher A.; Perez, Carlos E.; Paraan, Francis N. C.

2017-08-01

We benchmark improvements in the performance of deep neural networks (DNN) on the MNIST data test upon imple-menting two simple modifications to the algorithm that have little overhead computational cost. First is GPU parallelization on a commodity graphics card, and second is initializing the DNN with random orthogonal weight matrices prior to optimization. Eigenspectra analysis of the weight matrices reveal that the initially orthogonal matrices remain nearly orthogonal after training. The probability distributions from which these orthogonal matrices are drawn are also shown to significantly affect the performance of these deep neural networks.

Application of a neural network to simulate analysis in an optimization process

NASA Technical Reports Server (NTRS)

Rogers, James L.; Lamarsh, William J., II

1992-01-01

A new experimental software package called NETS/PROSSS aimed at reducing the computing time required to solve a complex design problem is described. The software combines a neural network for simulating the analysis program with an optimization program. The neural network is applied to approximate results of a finite element analysis program to quickly obtain a near-optimal solution. Results of the NETS/PROSSS optimization process can also be used as an initial design in a normal optimization process and make it possible to converge to an optimum solution with significantly fewer iterations.

Simulating and Synthesizing Substructures Using Neural Network and Genetic Algorithms

NASA Technical Reports Server (NTRS)

Liu, Youhua; Kapania, Rakesh K.; VanLandingham, Hugh F.

1997-01-01

The feasibility of simulating and synthesizing substructures by computational neural network models is illustrated by investigating a statically indeterminate beam, using both a 1-D and a 2-D plane stress modelling. The beam can be decomposed into two cantilevers with free-end loads. By training neural networks to simulate the cantilever responses to different loads, the original beam problem can be solved as a match-up between two subsystems under compatible interface conditions. The genetic algorithms are successfully used to solve the match-up problem. Simulated results are found in good agreement with the analytical or FEM solutions.

Automated detection of videotaped neonatal seizures of epileptic origin.

PubMed

Karayiannis, Nicolaos B; Xiong, Yaohua; Tao, Guozhi; Frost, James D; Wise, Merrill S; Hrachovy, Richard A; Mizrahi, Eli M

2006-06-01

This study aimed at the development of a seizure-detection system by training neural networks with quantitative motion information extracted from short video segments of neonatal seizures of the myoclonic and focal clonic types and random infant movements. The motion of the infants' body parts was quantified by temporal motion-strength signals extracted from video segments by motion-segmentation methods based on optical flow computation. The area of each frame occupied by the infants' moving body parts was segmented by clustering the motion parameters obtained by fitting an affine model to the pixel velocities. The motion of the infants' body parts also was quantified by temporal motion-trajectory signals extracted from video recordings by robust motion trackers based on block-motion models. These motion trackers were developed to adjust autonomously to illumination and contrast changes that may occur during the video-frame sequence. Video segments were represented by quantitative features obtained by analyzing motion-strength and motion-trajectory signals in both the time and frequency domains. Seizure recognition was performed by conventional feed-forward neural networks, quantum neural networks, and cosine radial basis function neural networks, which were trained to detect neonatal seizures of the myoclonic and focal clonic types and to distinguish them from random infant movements. The computational tools and procedures developed for automated seizure detection were evaluated on a set of 240 video segments of 54 patients exhibiting myoclonic seizures (80 segments), focal clonic seizures (80 segments), and random infant movements (80 segments). Regardless of the decision scheme used for interpreting the responses of the trained neural networks, all the neural network models exhibited sensitivity and specificity>90%. For one of the decision schemes proposed for interpreting the responses of the trained neural networks, the majority of the trained neural-network models exhibited sensitivity>90% and specificity>95%. In particular, cosine radial basis function neural networks achieved the performance targets of this phase of the project (i.e., sensitivity>95% and specificity>95%). The best among the motion segmentation and tracking methods developed in this study produced quantitative features that constitute a reliable basis for detecting neonatal seizures. The performance targets of this phase of the project were achieved by combining the quantitative features obtained by analyzing motion-strength signals with those produced by analyzing motion-trajectory signals. The computational procedures and tools developed in this study to perform off-line analysis of short video segments will be used in the next phase of this project, which involves the integration of these procedures and tools into a system that can process and analyze long video recordings of infants monitored for seizures in real time.

Optical computing and neural networks; Proceedings of the Meeting, National Chiao Tung Univ., Hsinchu, Taiwan, Dec. 16, 17, 1992

NASA Technical Reports Server (NTRS)

Hsu, Ken-Yuh (Editor); Liu, Hua-Kuang (Editor)

1992-01-01

The present conference discusses optical neural networks, photorefractive nonlinear optics, optical pattern recognition, digital and analog processors, and holography and its applications. Attention is given to bifurcating optical information processing, neural structures in digital halftoning, an exemplar-based optical neural net classifier for color pattern recognition, volume storage in photorefractive disks, and microlaser-based compact optical neuroprocessors. Also treated are the optical implementation of a feature-enhanced optical interpattern-associative neural network model and its optical implementation, an optical pattern binary dual-rail logic gate module, a theoretical analysis for holographic associative memories, joint transform correlators, image addition and subtraction via the Talbot effect, and optical wavelet-matched filters. (No individual items are abstracted in this volume)

Optical computing and neural networks; Proceedings of the Meeting, National Chiao Tung Univ., Hsinchu, Taiwan, Dec. 16, 17, 1992

NASA Astrophysics Data System (ADS)

Hsu, Ken-Yuh; Liu, Hua-Kuang

The present conference discusses optical neural networks, photorefractive nonlinear optics, optical pattern recognition, digital and analog processors, and holography and its applications. Attention is given to bifurcating optical information processing, neural structures in digital halftoning, an exemplar-based optical neural net classifier for color pattern recognition, volume storage in photorefractive disks, and microlaser-based compact optical neuroprocessors. Also treated are the optical implementation of a feature-enhanced optical interpattern-associative neural network model and its optical implementation, an optical pattern binary dual-rail logic gate module, a theoretical analysis for holographic associative memories, joint transform correlators, image addition and subtraction via the Talbot effect, and optical wavelet-matched filters. (No individual items are abstracted in this volume)

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-designed pulse sequences for robust control of singlet-triplet qubits

NASA Astrophysics Data System (ADS)

Yang, Xu-Chen; Yung, Man-Hong; Wang, Xin

2018-04-01

Composite pulses are essential for universal manipulation of singlet-triplet spin qubits. In the absence of noise, they are required to perform arbitrary single-qubit operations due to the special control constraint of a singlet-triplet qubit, while in a noisy environment, more complicated sequences have been developed to dynamically correct the error. Tailoring these sequences typically requires numerically solving a set of nonlinear equations. Here we demonstrate that these pulse sequences can be generated by a well-trained, double-layer neural network. For sequences designed for the noise-free case, the trained neural network is capable of producing almost exactly the same pulses known in the literature. For more complicated noise-correcting sequences, the neural network produces pulses with slightly different line shapes, but the robustness against noises remains comparable. These results indicate that the neural network can be a judicious and powerful alternative to existing techniques in developing pulse sequences for universal fault-tolerant quantum computation.

Local synchronization of chaotic neural networks with sampled-data and saturating actuators.

PubMed

Wu, Zheng-Guang; Shi, Peng; Su, Hongye; Chu, Jian

2014-12-01

This paper investigates the problem of local synchronization of chaotic neural networks with sampled-data and actuator saturation. A new time-dependent Lyapunov functional is proposed for the synchronization error systems. The advantage of the constructed Lyapunov functional lies in the fact that it is positive definite at sampling times but not necessarily between sampling times, and makes full use of the available information about the actual sampling pattern. A local stability condition of the synchronization error systems is derived, based on which a sampled-data controller with respect to the actuator saturation is designed to ensure that the master neural networks and slave neural networks are locally asymptotically synchronous. Two optimization problems are provided to compute the desired sampled-data controller with the aim of enlarging the set of admissible initial conditions or the admissible sampling upper bound ensuring the local synchronization of the considered chaotic neural networks. A numerical example is used to demonstrate the effectiveness of the proposed design technique.

Multistability of memristive Cohen-Grossberg neural networks with non-monotonic piecewise linear activation functions and time-varying delays.

PubMed

Nie, Xiaobing; Zheng, Wei Xing; Cao, Jinde

2015-11-01

The problem of coexistence and dynamical behaviors of multiple equilibrium points is addressed for a class of memristive Cohen-Grossberg neural networks with non-monotonic piecewise linear activation functions and time-varying delays. By virtue of the fixed point theorem, nonsmooth analysis theory and other analytical tools, some sufficient conditions are established to guarantee that such n-dimensional memristive Cohen-Grossberg neural networks can have 5(n) equilibrium points, among which 3(n) equilibrium points are locally exponentially stable. It is shown that greater storage capacity can be achieved by neural networks with the non-monotonic activation functions introduced herein than the ones with Mexican-hat-type activation function. In addition, unlike most existing multistability results of neural networks with monotonic activation functions, those obtained 3(n) locally stable equilibrium points are located both in saturated regions and unsaturated regions. The theoretical findings are verified by an illustrative example with computer simulations. Copyright © 2015 Elsevier Ltd. All rights reserved.

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.

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

Planning chemical syntheses with deep neural networks and symbolic AI

NASA Astrophysics Data System (ADS)

Segler, Marwin H. S.; Preuss, Mike; Waller, Mark P.

2018-03-01

To plan the syntheses of small organic molecules, chemists use retrosynthesis, a problem-solving technique in which target molecules are recursively transformed into increasingly simpler precursors. Computer-aided retrosynthesis would be a valuable tool but at present it is slow and provides results of unsatisfactory quality. Here we use Monte Carlo tree search and symbolic artificial intelligence (AI) to discover retrosynthetic routes. We combined Monte Carlo tree search with an expansion policy network that guides the search, and a filter network to pre-select the most promising retrosynthetic steps. These deep neural networks were trained on essentially all reactions ever published in organic chemistry. Our system solves for almost twice as many molecules, thirty times faster than the traditional computer-aided search method, which is based on extracted rules and hand-designed heuristics. In a double-blind AB test, chemists on average considered our computer-generated routes to be equivalent to reported literature routes.

Automatic Seismic-Event Classification with Convolutional Neural Networks.

NASA Astrophysics Data System (ADS)

Bueno Rodriguez, A.; Titos Luzón, M.; Garcia Martinez, L.; Benitez, C.; Ibáñez, J. M.

2017-12-01

Active volcanoes exhibit a wide range of seismic signals, providing vast amounts of unlabelled volcano-seismic data that can be analyzed through the lens of artificial intelligence. However, obtaining high-quality labelled data is time-consuming and expensive. Deep neural networks can process data in their raw form, compute high-level features and provide a better representation of the input data distribution. These systems can be deployed to classify seismic data at scale, enhance current early-warning systems and build extensive seismic catalogs. In this research, we aim to classify spectrograms from seven different seismic events registered at "Volcán de Fuego" (Colima, Mexico), during four eruptive periods. Our approach is based on convolutional neural networks (CNNs), a sub-type of deep neural networks that can exploit grid structure from the data. Volcano-seismic signals can be mapped into a grid-like structure using the spectrogram: a representation of the temporal evolution in terms of time and frequency. Spectrograms were computed from the data using Hamming windows with 4 seconds length, 2.5 seconds overlapping and 128 points FFT resolution. Results are compared to deep neural networks, random forest and SVMs. Experiments show that CNNs can exploit temporal and frequency information, attaining a classification accuracy of 93%, similar to deep networks 91% but outperforming SVM and random forest. These results empirically show that CNNs are powerful models to classify a wide range of volcano-seismic signals, and achieve good generalization. Furthermore, volcano-seismic spectrograms contains useful discriminative information for the CNN, as higher layers of the network combine high-level features computed for each frequency band, helping to detect simultaneous events in time. Being at the intersection of deep learning and geophysics, this research enables future studies of how CNNs can be used in volcano monitoring to accurately determine the detection and location of seismic events.

Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation

NASA Astrophysics Data System (ADS)

Gaonkar, Bilwaj; Hovda, David; Martin, Neil; Macyszyn, Luke

2016-03-01

Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate this approach,using a publicly available head and neck CT dataset. We also show that a deep neural network of similar depth, if trained directly using backpropagation, cannot acheive the tasks achieved using our layer wise training paradigm.

Neural dynamic programming and its application to control systems

NASA Astrophysics Data System (ADS)

Seong, Chang-Yun

There are few general practical feedback control methods for nonlinear MIMO (multi-input-multi-output) systems, although such methods exist for their linear counterparts. Neural Dynamic Programming (NDP) is proposed as a practical design method of optimal feedback controllers for nonlinear MIMO systems. NDP is an offspring of both neural networks and optimal control theory. In optimal control theory, the optimal solution to any nonlinear MIMO control problem may be obtained from the Hamilton-Jacobi-Bellman equation (HJB) or the Euler-Lagrange equations (EL). The two sets of equations provide the same solution in different forms: EL leads to a sequence of optimal control vectors, called Feedforward Optimal Control (FOC); HJB yields a nonlinear optimal feedback controller, called Dynamic Programming (DP). DP produces an optimal solution that can reject disturbances and uncertainties as a result of feedback. Unfortunately, computation and storage requirements associated with DP solutions can be problematic, especially for high-order nonlinear systems. This dissertation presents an approximate technique for solving the DP problem based on neural network techniques that provides many of the performance benefits (e.g., optimality and feedback) of DP and benefits from the numerical properties of neural networks. We formulate neural networks to approximate optimal feedback solutions whose existence DP justifies. We show the conditions under which NDP closely approximates the optimal solution. Finally, we introduce the learning operator characterizing the learning process of the neural network in searching the optimal solution. The analysis of the learning operator provides not only a fundamental understanding of the learning process in neural networks but also useful guidelines for selecting the number of weights of the neural network. As a result, NDP finds---with a reasonable amount of computation and storage---the optimal feedback solutions to nonlinear MIMO control problems that would be very difficult to solve with DP. NDP was demonstrated on several applications such as the lateral autopilot logic for a Boeing 747, the minimum fuel control of a double-integrator plant with bounded control, the backward steering of a two-trailer truck, and the set-point control of a two-link robot arm.

Computer interpretation of thallium SPECT studies based on neural network analysis

NASA Astrophysics Data System (ADS)

Wang, David C.; Karvelis, K. C.

1991-06-01

A class of artificial intelligence (Al) programs known as neural networks are well suited to pattern recognition. A neural network is trained rather than programmed to recognize patterns. This differs from "expert system" Al programs in that it is not following an extensive set of rules determined by the programmer, but rather bases its decision on a gestalt interpretation of the image. The "bullseye" images from cardiac stress thallium tests performed on 50 male patients, as well as several simulated images were used to train the network. The network was able to accurately classify all patients in the training set. The network was then tested against 50 unknown patients and was able to correctly categorize 77% of the areas of ischemia and 92% of the areas of infarction. While not yet matching the ability of a trained physician, the neural network shows great promise in this area and has potential application in other areas of medical imaging.

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks

PubMed Central

Miconi, Thomas

2017-01-01

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior. DOI: http://dx.doi.org/10.7554/eLife.20899.001 PMID:28230528

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks.

PubMed

Miconi, Thomas

2017-02-23

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior.

Reward-based training of recurrent neural networks for cognitive and value-based tasks

PubMed Central

Song, H Francis; Yang, Guangyu R; Wang, Xiao-Jing

2017-01-01

Trained neural network models, which exhibit features of neural activity recorded from behaving animals, may provide insights into the circuit mechanisms of cognitive functions through systematic analysis of network activity and connectivity. However, in contrast to the graded error signals commonly used to train networks through supervised learning, animals learn from reward feedback on definite actions through reinforcement learning. Reward maximization is particularly relevant when optimal behavior depends on an animal’s internal judgment of confidence or subjective preferences. Here, we implement reward-based training of recurrent neural networks in which a value network guides learning by using the activity of the decision network to predict future reward. We show that such models capture behavioral and electrophysiological findings from well-known experimental paradigms. Our work provides a unified framework for investigating diverse cognitive and value-based computations, and predicts a role for value representation that is essential for learning, but not executing, a task. DOI: http://dx.doi.org/10.7554/eLife.21492.001 PMID:28084991

Using soft computing techniques to predict corrected air permeability using Thomeer parameters, air porosity and grain density

NASA Astrophysics Data System (ADS)

Nooruddin, Hasan A.; Anifowose, Fatai; Abdulraheem, Abdulazeez

2014-03-01

Soft computing techniques are recently becoming very popular in the oil industry. A number of computational intelligence-based predictive methods have been widely applied in the industry with high prediction capabilities. Some of the popular methods include feed-forward neural networks, radial basis function network, generalized regression neural network, functional networks, support vector regression and adaptive network fuzzy inference system. A comparative study among most popular soft computing techniques is presented using a large dataset published in literature describing multimodal pore systems in the Arab D formation. The inputs to the models are air porosity, grain density, and Thomeer parameters obtained using mercury injection capillary pressure profiles. Corrected air permeability is the target variable. Applying developed permeability models in recent reservoir characterization workflow ensures consistency between micro and macro scale information represented mainly by Thomeer parameters and absolute permeability. The dataset was divided into two parts with 80% of data used for training and 20% for testing. The target permeability variable was transformed to the logarithmic scale as a pre-processing step and to show better correlations with the input variables. Statistical and graphical analysis of the results including permeability cross-plots and detailed error measures were created. In general, the comparative study showed very close results among the developed models. The feed-forward neural network permeability model showed the lowest average relative error, average absolute relative error, standard deviations of error and root means squares making it the best model for such problems. Adaptive network fuzzy inference system also showed very good results.

Adaptiveness in monotone pseudo-Boolean optimization and stochastic neural computation.

PubMed

Grossi, Giuliano

2009-08-01

Hopfield neural network (HNN) is a nonlinear computational model successfully applied in finding near-optimal solutions of several difficult combinatorial problems. In many cases, the network energy function is obtained through a learning procedure so that its minima are states falling into a proper subspace (feasible region) of the search space. However, because of the network nonlinearity, a number of undesirable local energy minima emerge from the learning procedure, significantly effecting the network performance. In the neural model analyzed here, we combine both a penalty and a stochastic process in order to enhance the performance of a binary HNN. The penalty strategy allows us to gradually lead the search towards states representing feasible solutions, so avoiding oscillatory behaviors or asymptotically instable convergence. Presence of stochastic dynamics potentially prevents the network to fall into shallow local minima of the energy function, i.e., quite far from global optimum. Hence, for a given fixed network topology, the desired final distribution on the states can be reached by carefully modulating such process. The model uses pseudo-Boolean functions both to express problem constraints and cost function; a combination of these two functions is then interpreted as energy of the neural network. A wide variety of NP-hard problems fall in the class of problems that can be solved by the model at hand, particularly those having a monotonic quadratic pseudo-Boolean function as constraint function. That is, functions easily derived by closed algebraic expressions representing the constraint structure and easy (polynomial time) to maximize. We show the asymptotic convergence properties of this model characterizing its state space distribution at thermal equilibrium in terms of Markov chain and give evidence of its ability to find high quality solutions on benchmarks and randomly generated instances of two specific problems taken from the computational graph theory.

Introduction to a system for implementing neural net connections on SIMD architectures

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1988-01-01

Neural networks have attracted much interest recently, and using parallel architectures to simulate neural networks is a natural and necessary application. The SIMD model of parallel computation is chosen, because systems of this type can be built with large numbers of processing elements. However, such systems are not naturally suited to generalized communication. A method is proposed that allows an implementation of neural network connections on massively parallel SIMD architectures. The key to this system is an algorithm permitting the formation of arbitrary connections between the neurons. A feature is the ability to add new connections quickly. It also has error recovery ability and is robust over a variety of network topologies. Simulations of the general connection system, and its implementation on the Connection Machine, indicate that the time and space requirements are proportional to the product of the average number of connections per neuron and the diameter of the interconnection network.

Introduction to a system for implementing neural net connections on SIMD architectures

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1988-01-01

Neural networks have attracted much interest recently, and using parallel architectures to simulate neural networks is a natural and necessary application. The SIMD model of parallel computation is chosen, because systems of this type can be built with large numbers of processing elements. However, such systems are not naturally suited to generalized elements. A method is proposed that allows an implementation of neural network connections on massively parallel SIMD architectures. The key to this system is an algorithm permitting the formation of arbitrary connections between the neurons. A feature is the ability to add new connections quickly. It also has error recovery ability and is robust over a variety of network topologies. Simulations of the general connection system, and its implementation on the Connection Machine, indicate that the time and space requirements are proportional to the product of the average number of connections per neuron and the diameter of the interconnection network.

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.

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.

Chaos in a neural network circuit

NASA Astrophysics Data System (ADS)

Kepler, Thomas B.; Datt, Sumeet; Meyer, Robert B.; Abott, L. F.

1990-12-01

We have constructed a neural network circuit of four clipped, high-grain, integrating operational amplifiers coupled to each other through an array of digitally programmable resistor ladders (MDACs). In addition to fixed-point and cyclic behavior, the circuit exhibits chaotic behavior with complex strange attractors which are approached through period doubling, intermittent attractor expansion and/or quasiperiodic pathways. Couplings between the nonlinear circuit elements are controlled by a computer which can automatically search through the space of couplings for interesting phenomena. We report some initial statistical results relating the behavior of the network to properties of its coupling matrix. Through these results and further research the circuit should help resolve fundamental issues concerning chaos in neural networks.

Achieving supercomputer performance for neural net simulation with an array of digital signal processors

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

Muller, U.A.; Baumle, B.; Kohler, P.

1992-10-01

Music, a DSP-based system with a parallel distributed-memory architecture, provides enormous computing power yet retains the flexibility of a general-purpose computer. Reaching a peak performance of 2.7 Gflops at a significantly lower cost, power consumption, and space requirement than conventional supercomputers, Music is well suited to computationally intensive applications such as neural network simulation. 12 refs., 9 figs., 2 tabs.

Reduction of the dimension of neural network models in problems of pattern recognition and forecasting

NASA Astrophysics Data System (ADS)

Nasertdinova, A. D.; Bochkarev, V. V.

2017-11-01

Deep neural networks with a large number of parameters are a powerful tool for solving problems of pattern recognition, prediction and classification. Nevertheless, overfitting remains a serious problem in the use of such networks. A method of solving the problem of overfitting is proposed in this article. This method is based on reducing the number of independent parameters of a neural network model using the principal component analysis, and can be implemented using existing libraries of neural computing. The algorithm was tested on the problem of recognition of handwritten symbols from the MNIST database, as well as on the task of predicting time series (rows of the average monthly number of sunspots and series of the Lorentz system were used). It is shown that the application of the principal component analysis enables reducing the number of parameters of the neural network model when the results are good. The average error rate for the recognition of handwritten figures from the MNIST database was 1.12% (which is comparable to the results obtained using the "Deep training" methods), while the number of parameters of the neural network can be reduced to 130 times.

Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification

NASA Technical Reports Server (NTRS)

Hepner, George F.; Logan, Thomas; Ritter, Niles; Bryant, Nevin

1990-01-01

Recent research has shown an artificial neural network (ANN) to be capable of pattern recognition and the classification of image data. This paper examines the potential for the application of neural network computing to satellite image processing. A second objective is to provide a preliminary comparison and ANN classification. An artificial neural network can be trained to do land-cover classification of satellite imagery using selected sites representative of each class in a manner similar to conventional supervised classification. One of the major problems associated with recognition and classifications of pattern from remotely sensed data is the time and cost of developing a set of training sites. This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set. When using a minimal training set, the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure. This research is the foundation for developing application parameters for further prototyping of software and hardware implementations for artificial neural networks in satellite image and geographic information processing.

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.

Deep Learning: A Primer for Radiologists.

PubMed

Chartrand, Gabriel; Cheng, Phillip M; Vorontsov, Eugene; Drozdzal, Michal; Turcotte, Simon; Pal, Christopher J; Kadoury, Samuel; Tang, An

2017-01-01

Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. Deep learning methods produce a mapping from raw inputs to desired outputs (eg, image classes). Unlike traditional machine learning methods, which require hand-engineered feature extraction from inputs, deep learning methods learn these features directly from data. With the advent of large datasets and increased computing power, these methods can produce models with exceptional performance. These models are multilayer artificial neural networks, loosely inspired by biologic neural systems. Weighted connections between nodes (neurons) in the network are iteratively adjusted based on example pairs of inputs and target outputs by back-propagating a corrective error signal through the network. For computer vision tasks, convolutional neural networks (CNNs) have proven to be effective. Recently, several clinical applications of CNNs have been proposed and studied in radiology for classification, detection, and segmentation tasks. This article reviews the key concepts of deep learning for clinical radiologists, discusses technical requirements, describes emerging applications in clinical radiology, and outlines limitations and future directions in this field. Radiologists should become familiar with the principles and potential applications of deep learning in medical imaging. © RSNA, 2017.

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.

Quicklook Constituent Abundance and Stretch Parameter Retrieval for the Juno Microwave Radiometer using Neural Networks

NASA Astrophysics Data System (ADS)

Bellotti, A.; Steffes, P. G.

2016-12-01

The Juno Microwave Radiometer (MWR) has six channels ranging from 1.36-50 cm and the ability to peer deep into the Jovian atmosphere. An Artifical Neural Network algorithm has been developed to rapidly perform inversion for the deep abundance of ammonia, the deep abundance of water vapor, and atmospheric "stretch" (a parameter that reflects the deviation from a wet adiabate in the higher atmosphere). This algorithm is "trained" by using simulated emissions at the six wavelengths computed using the Juno atmospheric microwave radiative transfer (JAMRT) model presented by Oyafuso et al. (This meeting). By exploiting the emission measurements conducted at six wavelengths and at various incident angles, the neural network can provide preliminary results to a useful precison in a computational method hundreds of times faster than conventional methods. This can quickly provide important insights into the variability and structure of the Jovian atmosphere.

Baseline estimation in flame's spectra by using neural networks and robust statistics

NASA Astrophysics Data System (ADS)

Garces, Hugo; Arias, Luis; Rojas, Alejandro

2014-09-01

This work presents a baseline estimation method in flame spectra based on artificial intelligence structure as a neural network, combining robust statistics with multivariate analysis to automatically discriminate measured wavelengths belonging to continuous feature for model adaptation, surpassing restriction of measuring target baseline for training. The main contributions of this paper are: to analyze a flame spectra database computing Jolliffe statistics from Principal Components Analysis detecting wavelengths not correlated with most of the measured data corresponding to baseline; to systematically determine the optimal number of neurons in hidden layers based on Akaike's Final Prediction Error; to estimate baseline in full wavelength range sampling measured spectra; and to train an artificial intelligence structure as a Neural Network which allows to generalize the relation between measured and baseline spectra. The main application of our research is to compute total radiation with baseline information, allowing to diagnose combustion process state for optimization in early stages.

An Artificial Neural Network Evaluation of Tuberculosis Using Genetic and Physiological Patient Data

NASA Astrophysics Data System (ADS)

Griffin, William O.; Hanna, Josh; Razorilova, Svetlana; Kitaev, Mikhael; Alisherov, Avtandiil; Darsey, Jerry A.; Tarasenko, Olga

2010-04-01

When doctors see more cases of patients with tell-tale symptoms of a disease, it is hoped that they will be able to recognize an infection administer treatment appropriately, thereby speeding up recovery for sick patients. We hope that our studies can aid in the detection of tuberculosis by using a computer model called an artificial neural network. Our model looks at patients with and without tuberculosis (TB). The data that the neural network examined came from the following: patient' age, gender, place, of birth, blood type, Rhesus (Rh) factor, and genes of the human Leukocyte Antigens (HLA) system (9q34.1) present in the Major Histocompatibility Complex. With availability in genetic data and good research, we hope to give them an advantage in the detection of tuberculosis. We try to mimic the doctor's experience with a computer test, which will learn from patient data the factors that contribute to TB.

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

Fuzzy logic and neural networks in artificial intelligence and pattern recognition

NASA Astrophysics Data System (ADS)

Sanchez, Elie

1991-10-01

With the use of fuzzy logic techniques, neural computing can be integrated in symbolic reasoning to solve complex real world problems. In fact, artificial neural networks, expert systems, and fuzzy logic systems, in the context of approximate reasoning, share common features and techniques. A model of Fuzzy Connectionist Expert System is introduced, in which an artificial neural network is designed to construct the knowledge base of an expert system from, training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the synaptic connections in an AND-OR structure: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through min-max fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feedforward network is described and first illustrated in a biomedical application (medical diagnosis assistance from inflammatory-syndromes/proteins profiles). Then, it is shown how this methodology can be utilized for handwritten pattern recognition (characters play the role of diagnoses): in a fuzzy neuron describing a number for example, the linguistic weights represent fuzzy sets on cross-detecting lines and the numerical weights reflect the importance (or weakness) of connections between cross-detecting lines and characters.

Artificial neural network modeling of dissolved oxygen in reservoir.

PubMed

Chen, Wei-Bo; Liu, Wen-Cheng

2014-02-01

The water quality of reservoirs is one of the key factors in the operation and water quality management of reservoirs. Dissolved oxygen (DO) in water column is essential for microorganisms and a significant indicator of the state of aquatic ecosystems. In this study, two artificial neural network (ANN) models including back propagation neural network (BPNN) and adaptive neural-based fuzzy inference system (ANFIS) approaches and multilinear regression (MLR) model were developed to estimate the DO concentration in the Feitsui Reservoir of northern Taiwan. The input variables of the neural network are determined as water temperature, pH, conductivity, turbidity, suspended solids, total hardness, total alkalinity, and ammonium nitrogen. The performance of the ANN models and MLR model was assessed through the mean absolute error, root mean square error, and correlation coefficient computed from the measured and model-simulated DO values. The results reveal that ANN estimation performances were superior to those of MLR. Comparing to the BPNN and ANFIS models through the performance criteria, the ANFIS model is better than the BPNN model for predicting the DO values. Study results show that the neural network particularly using ANFIS model is able to predict the DO concentrations with reasonable accuracy, suggesting that the neural network is a valuable tool for reservoir management in Taiwan.

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.

Optical determination of material abundances by using neural networks for the derivation of spectral filters

NASA Astrophysics Data System (ADS)

Krippner, Wolfgang; Wagner, Felix; Bauer, Sebastian; Puente León, Fernando

2017-06-01

Using appropriately designed spectral filters allows to optically determine material abundances. While an infinite number of possibilities exist for determining spectral filters, we take advantage of using neural networks to derive spectral filters leading to precise estimations. To overcome some drawbacks that regularly influence the determination of material abundances using hyperspectral data, we incorporate the spectral variability of the raw materials into the training of the considered neural networks. As a main result, we successfully classify quantized material abundances optically. Thus, the main part of the high computational load, which belongs to the use of neural networks, is avoided. In addition, the derived material abundances become invariant against spatially varying illumination intensity as a remarkable benefit in comparison with spectral filters based on the Moore-Penrose pseudoinverse, for instance.

IR wireless cluster synapses of HYDRA very large neural networks

NASA Astrophysics Data System (ADS)

Jannson, Tomasz; Forrester, Thomas

2008-04-01

RF/IR wireless (virtual) synapses are critical components of HYDRA (Hyper-Distributed Robotic Autonomy) neural networks, already discussed in two earlier papers. The HYDRA network has the potential to be very large, up to 10 11-neurons and 10 18-synapses, based on already established technologies (cellular RF telephony and IR-wireless LANs). It is organized into almost fully connected IR-wireless clusters. The HYDRA neurons and synapses are very flexible, simple, and low-cost. They can be modified into a broad variety of biologically-inspired brain-like computing capabilities. In this third paper, we focus on neural hardware in general, and on IR-wireless synapses in particular. Such synapses, based on LED/LD-connections, dominate the HYDRA neural cluster.

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.

FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting.

PubMed

Alomar, Miquel L; Canals, Vincent; Perez-Mora, Nicolas; Martínez-Moll, Víctor; Rosselló, Josep L

2016-01-01

Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting.

FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting

PubMed Central

Alomar, Miquel L.; Canals, Vincent; Perez-Mora, Nicolas; Martínez-Moll, Víctor; Rosselló, Josep L.

2016-01-01

Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting. PMID:26880876

Exact computation of the maximum-entropy potential of spiking neural-network models.

PubMed

Cofré, R; Cessac, B

2014-05-01

Understanding how stimuli and synaptic connectivity influence the statistics of spike patterns in neural networks is a central question in computational neuroscience. The maximum-entropy approach has been successfully used to characterize the statistical response of simultaneously recorded spiking neurons responding to stimuli. However, in spite of good performance in terms of prediction, the fitting parameters do not explain the underlying mechanistic causes of the observed correlations. On the other hand, mathematical models of spiking neurons (neuromimetic models) provide a probabilistic mapping between the stimulus, network architecture, and spike patterns in terms of conditional probabilities. In this paper we build an exact analytical mapping between neuromimetic and maximum-entropy models.

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

Unified-theory-of-reinforcement neural networks do not simulate the blocking effect.

PubMed

Calvin, Nicholas T; J McDowell, J

2015-11-01

For the last 20 years the unified theory of reinforcement (Donahoe et al., 1993) has been used to develop computer simulations to evaluate its plausibility as an account for behavior. The unified theory of reinforcement states that operant and respondent learning occurs via the same neural mechanisms. As part of a larger project to evaluate the operant behavior predicted by the theory, this project was the first replication of neural network models based on the unified theory of reinforcement. In the process of replicating these neural network models it became apparent that a previously published finding, namely, that the networks simulate the blocking phenomenon (Donahoe et al., 1993), was a misinterpretation of the data. We show that the apparent blocking produced by these networks is an artifact of the inability of these networks to generate the same conditioned response to multiple stimuli. The piecemeal approach to evaluate the unified theory of reinforcement via simulation is critiqued and alternatives are discussed. Copyright © 2015 Elsevier B.V. All rights reserved.

SYNAPTIC DEPRESSION IN DEEP NEURAL NETWORKS FOR SPEECH PROCESSING.

PubMed

Zhang, Wenhao; Li, Hanyu; Yang, Minda; Mesgarani, Nima

2016-03-01

A characteristic property of biological neurons is their ability to dynamically change the synaptic efficacy in response to variable input conditions. This mechanism, known as synaptic depression, significantly contributes to the formation of normalized representation of speech features. Synaptic depression also contributes to the robust performance of biological systems. In this paper, we describe how synaptic depression can be modeled and incorporated into deep neural network architectures to improve their generalization ability. We observed that when synaptic depression is added to the hidden layers of a neural network, it reduces the effect of changing background activity in the node activations. In addition, we show that when synaptic depression is included in a deep neural network trained for phoneme classification, the performance of the network improves under noisy conditions not included in the training phase. Our results suggest that more complete neuron models may further reduce the gap between the biological performance and artificial computing, resulting in networks that better generalize to novel signal conditions.

The 2nd Symposium on the Frontiers of Massively Parallel Computations

NASA Technical Reports Server (NTRS)

Mills, Ronnie (Editor)

1988-01-01

Programming languages, computer graphics, neural networks, massively parallel computers, SIMD architecture, algorithms, digital terrain models, sort computation, simulation of charged particle transport on the massively parallel processor and image processing are among the topics discussed.

Assessing the effect of quantitative and qualitative predictors on gastric cancer individuals survival using hierarchical artificial neural network models.

PubMed

Amiri, Zohreh; Mohammad, Kazem; Mahmoudi, Mahmood; Parsaeian, Mahbubeh; Zeraati, Hojjat

2013-01-01

There are numerous unanswered questions in the application of artificial neural network models for analysis of survival data. In most studies, independent variables have been studied as qualitative dichotomous variables, and results of using discrete and continuous quantitative, ordinal, or multinomial categorical predictive variables in these models are not well understood in comparison to conventional models. This study was designed and conducted to examine the application of these models in order to determine the survival of gastric cancer patients, in comparison to the Cox proportional hazards model. We studied the postoperative survival of 330 gastric cancer patients who suffered surgery at a surgical unit of the Iran Cancer Institute over a five-year period. Covariates of age, gender, history of substance abuse, cancer site, type of pathology, presence of metastasis, stage, and number of complementary treatments were entered in the models, and survival probabilities were calculated at 6, 12, 18, 24, 36, 48, and 60 months using the Cox proportional hazards and neural network models. We estimated coefficients of the Cox model and the weights in the neural network (with 3, 5, and 7 nodes in the hidden layer) in the training group, and used them to derive predictions in the study group. Predictions with these two methods were compared with those of the Kaplan-Meier product limit estimator as the gold standard. Comparisons were performed with the Friedman and Kruskal-Wallis tests. Survival probabilities at different times were determined using the Cox proportional hazards and a neural network with three nodes in the hidden layer; the ratios of standard errors with these two methods to the Kaplan-Meier method were 1.1593 and 1.0071, respectively, revealed a significant difference between Cox and Kaplan-Meier (P < 0.05) and no significant difference between Cox and the neural network, and the neural network and the standard (Kaplan-Meier), as well as better accuracy for the neural network (with 3 nodes in the hidden layer). Probabilities of survival were calculated using three neural network models with 3, 5, and 7 nodes in the hidden layer, and it has been observed that none of the predictions was significantly different from results with the Kaplan-Meier method and they appeared more comparable towards the last months (fifth year). However, we observed better accuracy using the neural network with 5 nodes in the hidden layer. Using the Cox proportional hazards and a neural network with 3 nodes in the hidden layer, we found enhanced accuracy with the neural network model. Neural networks can provide more accurate predictions for survival probabilities compared to the Cox proportional hazards mode, especially now that advances in computer sciences have eliminated limitations associated with complex computations. It is not recommended in order to adding too many hidden layer nodes because sample size related effects can reduce the accuracy. We recommend increasing the number of nodes to a point that increased accuracy continues (decrease in mean standard error), however increasing nodes should cease when a change in this trend is observed.

Mastering the game of Go with deep neural networks and tree search.

PubMed

Silver, David; Huang, Aja; Maddison, Chris J; Guez, Arthur; Sifre, Laurent; van den Driessche, George; Schrittwieser, Julian; Antonoglou, Ioannis; Panneershelvam, Veda; Lanctot, Marc; Dieleman, Sander; Grewe, Dominik; Nham, John; Kalchbrenner, Nal; Sutskever, Ilya; Lillicrap, Timothy; Leach, Madeleine; Kavukcuoglu, Koray; Graepel, Thore; Hassabis, Demis

2016-01-28

The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses 'value networks' to evaluate board positions and 'policy networks' to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.

Application of artificial neural networks to identify equilibration in computer simulations

NASA Astrophysics Data System (ADS)

Leibowitz, Mitchell H.; Miller, Evan D.; Henry, Michael M.; Jankowski, Eric

2017-11-01

Determining which microstates generated by a thermodynamic simulation are representative of the ensemble for which sampling is desired is a ubiquitous, underspecified problem. Artificial neural networks are one type of machine learning algorithm that can provide a reproducible way to apply pattern recognition heuristics to underspecified problems. Here we use the open-source TensorFlow machine learning library and apply it to the problem of identifying which hypothetical observation sequences from a computer simulation are “equilibrated” and which are not. We generate training populations and test populations of observation sequences with embedded linear and exponential correlations. We train a two-neuron artificial network to distinguish the correlated and uncorrelated sequences. We find that this simple network is good enough for > 98% accuracy in identifying exponentially-decaying energy trajectories from molecular simulations.

Evolutionary image simplification for lung nodule classification with convolutional neural networks.

PubMed

Lückehe, Daniel; von Voigt, Gabriele

2018-05-29

Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.

Multisite two-photon imaging of neurons on multielectrode arrays

NASA Astrophysics Data System (ADS)

Potter, Steve M.; Lukina, Natalia; Longmuir, Kenneth J.; Wu, Yan

2001-04-01

We wish to understand how neural systems store, recall, and process information. We are using cultured networks of cortical neurons grown on microelectrode arrays as a model system for studying the emergent properties of ensembles of living neurons. We have developed a 2-way communication interface between the cultured network and a computer- generated animal, the Neurally Controlled Animat. Neural activity is used to control the behavior of the Animat, and 2- photon time-lapse imaging is carried out in order to observe the morphological changes that might underlie changes in neural processing. The 2-photon microscope is ideal for repeated imaging over hours or days, with submicron resolution and little photodamage. We have designed a computer-controlled microscope stage that allows imaging several locations in sequence, in order to collect more image data. For the latest progress, see: http://www.caltech.edu/~pinelab/PotterGroup.htm.

Characterization of physiological networks in sleep apnea patients using artificial neural networks for Granger causality computation

NASA Astrophysics Data System (ADS)

Cárdenas, Jhon; Orjuela-Cañón, Alvaro D.; Cerquera, Alexander; Ravelo, Antonio

2017-11-01

Different studies have used Transfer Entropy (TE) and Granger Causality (GC) computation to quantify interconnection between physiological systems. These methods have disadvantages in parametrization and availability in analytic formulas to evaluate the significance of the results. Other inconvenience is related with the assumptions in the distribution of the models generated from the data. In this document, the authors present a way to measure the causality that connect the Central Nervous System (CNS) and the Cardiac System (CS) in people diagnosed with obstructive sleep apnea syndrome (OSA) before and during treatment with continuous positive air pressure (CPAP). For this purpose, artificial neural networks were used to obtain models for GC computation, based on time series of normalized powers calculated from electrocardiography (EKG) and electroencephalography (EEG) signals recorded in polysomnography (PSG) studies.

A Computationally Inexpensive Optimal Guidance via Radial-Basis-Function Neural Network for Autonomous Soft Landing on Asteroids

PubMed Central

Zhang, Peng; Liu, Keping; Zhao, Bo; Li, Yuanchun

2015-01-01

Optimal guidance is essential for the soft landing task. However, due to its high computational complexities, it is hardly applied to the autonomous guidance. In this paper, a computationally inexpensive optimal guidance algorithm based on the radial basis function neural network (RBFNN) is proposed. The optimization problem of the trajectory for soft landing on asteroids is formulated and transformed into a two-point boundary value problem (TPBVP). Combining the database of initial states with the relative initial co-states, an RBFNN is trained offline. The optimal trajectory of the soft landing is determined rapidly by applying the trained network in the online guidance. The Monte Carlo simulations of soft landing on the Eros433 are performed to demonstrate the effectiveness of the proposed guidance algorithm. PMID:26367382

Preconditioning electromyographic data for an upper extremity model using neural networks

NASA Technical Reports Server (NTRS)

Roberson, D. J.; Fernjallah, M.; Barr, R. E.; Gonzalez, R. V.

1994-01-01

A back propagation neural network has been employed to precondition the electromyographic signal (EMG) that drives a computational model of the human upper extremity. This model is used to determine the complex relationship between EMG and muscle activation, and generates an optimal muscle activation scheme that simulates the actual activation. While the experimental and model predicted results of the ballistic muscle movement are very similar, the activation function between the start and the finish is not. This neural network preconditions the signal in an attempt to more closely model the actual activation function over the entire course of the muscle movement.

Artificial neural networks in biology and chemistry: the evolution of a new analytical tool.

PubMed

Cartwright, Hugh M

2008-01-01

Once regarded as an eccentric and unpromising algorithm for the analysis of scientific data, the neural network has been developed in the last decade into a powerful computational tool. Its use now spans all areas of science, from the physical sciences and engineering to the life sciences and allied subjects. Applications range from the assessment of epidemiological data or the deconvolution of spectra to highly practical applications, such as the electronic nose. This introductory chapter considers briefly the growth in the use of neural networks and provides some general background in preparation for the more detailed chapters that follow.

Spatial light modulators and applications III; Proceedings of the Meeting, San Diego, CA, Aug. 7, 8, 1989

NASA Astrophysics Data System (ADS)

Efron, Uzi

Recent advances in the technology and applications of spatial light modulators (SLMs) are discussed in review essays by leading experts. Topics addressed include materials for SLMs, SLM devices and device technology, applications to optical data processing, and applications to artificial neural networks. Particular attention is given to nonlinear optical polymers, liquid crystals, magnetooptic SLMs, multiple-quantum-well SLMs, deformable-mirror SLMs, three-dimensional optical memories, applications of photorefractive devices to optical computing, photonic neurocomputers and learning machines, holographic associative memories, SLMs as parallel memories for optoelectronic neural networks, and coherent-optics implementations of neural-network models.

Spatial light modulators and applications III; Proceedings of the Meeting, San Diego, CA, Aug. 7, 8, 1989

NASA Technical Reports Server (NTRS)

Efron, Uzi (Editor)

1990-01-01

Recent advances in the technology and applications of spatial light modulators (SLMs) are discussed in review essays by leading experts. Topics addressed include materials for SLMs, SLM devices and device technology, applications to optical data processing, and applications to artificial neural networks. Particular attention is given to nonlinear optical polymers, liquid crystals, magnetooptic SLMs, multiple-quantum-well SLMs, deformable-mirror SLMs, three-dimensional optical memories, applications of photorefractive devices to optical computing, photonic neurocomputers and learning machines, holographic associative memories, SLMs as parallel memories for optoelectronic neural networks, and coherent-optics implementations of neural-network models.

Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework

PubMed Central

Wang, Xiao-Jing

2016-01-01

The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs) that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, “trained” networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale’s principle), which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural activity patterns and behavior that can be modeled, and suggest a unified setting in which diverse cognitive computations and mechanisms can be studied. PMID:26928718

Water Level Prediction of Lake Cascade Mahakam Using Adaptive Neural Network Backpropagation (ANNBP)

NASA Astrophysics Data System (ADS)

Mislan; Gaffar, A. F. O.; Haviluddin; Puspitasari, N.

2018-04-01

A natural hazard information and flood events are indispensable as a form of prevention and improvement. One of the causes is flooding in the areas around the lake. Therefore, forecasting the surface of Lake water level to anticipate flooding is required. The purpose of this paper is implemented computational intelligence method namely Adaptive Neural Network Backpropagation (ANNBP) to forecasting the Lake Cascade Mahakam. Based on experiment, performance of ANNBP indicated that Lake water level prediction have been accurate by using mean square error (MSE) and mean absolute percentage error (MAPE). In other words, computational intelligence method can produce good accuracy. A hybrid and optimization of computational intelligence are focus in the future work.

Conic section function neural network circuitry for offline signature recognition.

PubMed

Erkmen, Burcu; Kahraman, Nihan; Vural, Revna A; Yildirim, Tulay

2010-04-01

In this brief, conic section function neural network (CSFNN) circuitry was designed for offline signature recognition. CSFNN is a unified framework for multilayer perceptron (MLP) and radial basis function (RBF) networks to make simultaneous use of advantages of both. The CSFNN circuitry architecture was developed using a mixed mode circuit implementation. The designed circuit system is problem independent. Hence, the general purpose neural network circuit system could be applied to various pattern recognition problems with different network sizes on condition with the maximum network size of 16-16-8. In this brief, CSFNN circuitry system has been applied to two different signature recognition problems. CSFNN circuitry was trained with chip-in-the-loop learning technique in order to compensate typical analog process variations. CSFNN hardware achieved highly comparable computational performances with CSFNN software for nonlinear signature recognition problems.

An Asynchronous Recurrent Network of Cellular Automaton-Based Neurons and Its Reproduction of Spiking Neural Network Activities.

PubMed

Matsubara, Takashi; Torikai, Hiroyuki

2016-04-01

Modeling and implementation approaches for the reproduction of input-output relationships in biological nervous tissues contribute to the development of engineering and clinical applications. However, because of high nonlinearity, the traditional modeling and implementation approaches encounter difficulties in terms of generalization ability (i.e., performance when reproducing an unknown data set) and computational resources (i.e., computation time and circuit elements). To overcome these difficulties, asynchronous cellular automaton-based neuron (ACAN) models, which are described as special kinds of cellular automata that can be implemented as small asynchronous sequential logic circuits have been proposed. This paper presents a novel type of such ACAN and a theoretical analysis of its excitability. This paper also presents a novel network of such neurons, which can mimic input-output relationships of biological and nonlinear ordinary differential equation model neural networks. Numerical analyses confirm that the presented network has a higher generalization ability than other major modeling and implementation approaches. In addition, Field-Programmable Gate Array-implementations confirm that the presented network requires lower computational resources.

Intelligence Applied to Air Vehicles

NASA Technical Reports Server (NTRS)

Rosen, Robert; Gross, Anthony R.; Fletcher, L. Skip; Zornetzer, Steven (Technical Monitor)

2000-01-01

The exponential growth in information technology has provided the potential for air vehicle capabilities that were previously unavailable to mission and vehicle designers. The increasing capabilities of computer hardware and software, including new developments such as neural networks, provide a new balance of work between humans and machines. This paper will describe several NASA projects, and review results and conclusions from ground and flight investigations where vehicle intelligence was developed and applied to aeronautical and space systems. In the first example, flight results from a neural network flight control demonstration will be reviewed. Using, a highly-modified F-15 aircraft, a NASA/Dryden experimental flight test program has demonstrated how the neural network software can correctly identify and respond to changes in aircraft stability and control characteristics. Using its on-line learning capability, the neural net software would identify that something in the vehicle has changed, then reconfigure the flight control computer system to adapt to those changes. The results of the Remote Agent software project will be presented. This capability will reduce the cost of future spacecraft operations as computers become "thinking" partners along with humans. In addition, the paper will describe the objectives and plans for the autonomous airplane program and the autonomous rotorcraft project. Technologies will also be developed.

Mittag-Leffler stability of fractional-order neural networks in the presence of generalized piecewise constant arguments.

PubMed

Wu, Ailong; Liu, Ling; Huang, Tingwen; Zeng, Zhigang

2017-01-01

Neurodynamic system is an emerging research field. To understand the essential motivational representations of neural activity, neurodynamics is an important question in cognitive system research. This paper is to investigate Mittag-Leffler stability of a class of fractional-order neural networks in the presence of generalized piecewise constant arguments. To identify neural types of computational principles in mathematical and computational analysis, the existence and uniqueness of the solution of neurodynamic system is the first prerequisite. We prove that the existence and uniqueness of the solution of the network holds when some conditions are satisfied. In addition, self-active neurodynamic system demands stable internal dynamical states (equilibria). The main emphasis will be then on several sufficient conditions to guarantee a unique equilibrium point. Furthermore, to provide deeper explanations of neurodynamic process, Mittag-Leffler stability is studied in detail. The established results are based on the theories of fractional differential equation and differential equation with generalized piecewise constant arguments. The derived criteria improve and extend the existing related results. Copyright © 2016 Elsevier Ltd. All rights reserved.

A neuromorphic network for generic multivariate data classification

PubMed Central

Schmuker, Michael; Pfeil, Thomas; Nawrot, Martin Paul

2014-01-01

Computational neuroscience has uncovered a number of computational principles used by nervous systems. At the same time, neuromorphic hardware has matured to a state where fast silicon implementations of complex neural networks have become feasible. En route to future technical applications of neuromorphic computing the current challenge lies in the identification and implementation of functional brain algorithms. Taking inspiration from the olfactory system of insects, we constructed a spiking neural network for the classification of multivariate data, a common problem in signal and data analysis. In this model, real-valued multivariate data are converted into spike trains using “virtual receptors” (VRs). Their output is processed by lateral inhibition and drives a winner-take-all circuit that supports supervised learning. VRs are conveniently implemented in software, whereas the lateral inhibition and classification stages run on accelerated neuromorphic hardware. When trained and tested on real-world datasets, we find that the classification performance is on par with a naïve Bayes classifier. An analysis of the network dynamics shows that stable decisions in output neuron populations are reached within less than 100 ms of biological time, matching the time-to-decision reported for the insect nervous system. Through leveraging a population code, the network tolerates the variability of neuronal transfer functions and trial-to-trial variation that is inevitably present on the hardware system. Our work provides a proof of principle for the successful implementation of a functional spiking neural network on a configurable neuromorphic hardware system that can readily be applied to real-world computing problems. PMID:24469794

Neural attractor network for application in visual field data classification.

PubMed

Fink, Wolfgang

2004-07-07

The purpose was to introduce a novel method for computer-based classification of visual field data derived from perimetric examination, that may act as a 'counsellor', providing an independent 'second opinion' to the diagnosing physician. The classification system consists of a Hopfield-type neural attractor network that obtains its input data from perimetric examination results. An iterative relaxation process determines the states of the neurons dynamically. Therefore, even 'noisy' perimetric output, e.g., early stages of a disease, may eventually be classified correctly according to the predefined idealized visual field defect (scotoma) patterns, stored as attractors of the network, that are found with diseases of the eye, optic nerve and the central nervous system. Preliminary tests of the classification system on real visual field data derived from perimetric examinations have shown a classification success of over 80%. Some of the main advantages of the Hopfield-attractor-network-based approach over feed-forward type neural networks are: (1) network architecture is defined by the classification problem; (2) no training is required to determine the neural coupling strengths; (3) assignment of an auto-diagnosis confidence level is possible by means of an overlap parameter and the Hamming distance. In conclusion, the novel method for computer-based classification of visual field data, presented here, furnishes a valuable first overview and an independent 'second opinion' in judging perimetric examination results, pointing towards a final diagnosis by a physician. It should not be considered a substitute for the diagnosing physician. Thanks to the worldwide accessibility of the Internet, the classification system offers a promising perspective towards modern computer-assisted diagnosis in both medicine and tele-medicine, for example and in particular, with respect to non-ophthalmic clinics or in communities where perimetric expertise is not readily available.

Genetic learning in rule-based and neural systems

NASA Technical Reports Server (NTRS)

Smith, Robert E.

1993-01-01

The design of neural networks and fuzzy systems can involve complex, nonlinear, and ill-conditioned optimization problems. Often, traditional optimization schemes are inadequate or inapplicable for such tasks. Genetic Algorithms (GA's) are a class of optimization procedures whose mechanics are based on those of natural genetics. Mathematical arguments show how GAs bring substantial computational leverage to search problems, without requiring the mathematical characteristics often necessary for traditional optimization schemes (e.g., modality, continuity, availability of derivative information, etc.). GA's have proven effective in a variety of search tasks that arise in neural networks and fuzzy systems. This presentation begins by introducing the mechanism and theoretical underpinnings of GA's. GA's are then related to a class of rule-based machine learning systems called learning classifier systems (LCS's). An LCS implements a low-level production-system that uses a GA as its primary rule discovery mechanism. This presentation illustrates how, despite its rule-based framework, an LCS can be thought of as a competitive neural network. Neural network simulator code for an LCS is presented. In this context, the GA is doing more than optimizing and objective function. It is searching for an ecology of hidden nodes with limited connectivity. The GA attempts to evolve this ecology such that effective neural network performance results. The GA is particularly well adapted to this task, given its naturally-inspired basis. The LCS/neural network analogy extends itself to other, more traditional neural networks. Conclusions to the presentation discuss the implications of using GA's in ecological search problems that arise in neural and fuzzy systems.

A Feasibility Study for Perioperative Ventricular Tachycardia Prognosis and Detection and Noise Detection Using a Neural Network and Predictive Linear Operators

NASA Technical Reports Server (NTRS)

Moebes, T. A.

1994-01-01

To locate the accessory pathway(s) in preexicitation syndromes, epicardial and endocardial ventricular mapping is performed during anterograde ventricular activation via accessory pathway(s) from data originally received in signal form. As the number of channels increases, it is pertinent that more automated detection of coherent/incoherent signals is achieved as well as the prediction and prognosis of ventricular tachywardia (VT). Today's computers and computer program algorithms are not good in simple perceptual tasks such as recognizing a pattern or identifying a sound. This discrepancy, among other things, has been a major motivating factor in developing brain-based, massively parallel computing architectures. Neural net paradigms have proven to be effective at pattern recognition tasks. In signal processing, the picking of coherent/incoherent signals represents a pattern recognition task for computer systems. The picking of signals representing the onset ot VT also represents such a computer task. We attacked this problem by defining four signal attributes for each potential first maximal arrival peak and one signal attribute over the entire signal as input to a back propagation neural network. One attribute was the predicted amplitude value after the maximum amplitude over a data window. Then, by using a set of known (user selected) coherent/incoherent signals, and signals representing the onset of VT, we trained the back propagation network to recognize coherent/incoherent signals, and signals indicating the onset of VT. Since our output scheme involves a true or false decision, and since the output unit computes values between 0 and 1, we used a Fuzzy Arithmetic approach to classify data as coherent/incoherent signals. Furthermore, a Mean-Square Error Analysis was used to determine system stability. The neural net based picking coherent/incoherent signal system achieved high accuracy on picking coherent/incoherent signals on different patients. The system also achieved a high accuracy of picking signals which represent the onset of VT, that is, VT immediately followed these signals. A special binary representation of the input and output data allowed the neural network to train very rapidly as compared to another standard decimal or normalized representations of the data.

Performance evaluation of coherent Ising machines against classical neural networks

NASA Astrophysics Data System (ADS)

Haribara, Yoshitaka; Ishikawa, Hitoshi; Utsunomiya, Shoko; Aihara, Kazuyuki; Yamamoto, Yoshihisa

2017-12-01

The coherent Ising machine is expected to find a near-optimal solution in various combinatorial optimization problems, which has been experimentally confirmed with optical parametric oscillators and a field programmable gate array circuit. The similar mathematical models were proposed three decades ago by Hopfield et al in the context of classical neural networks. In this article, we compare the computational performance of both models.

Coherent Ising machines—optical neural networks operating at the quantum limit

NASA Astrophysics Data System (ADS)

Yamamoto, Yoshihisa; Aihara, Kazuyuki; Leleu, Timothee; Kawarabayashi, Ken-ichi; Kako, Satoshi; Fejer, Martin; Inoue, Kyo; Takesue, Hiroki

2017-12-01

In this article, we will introduce the basic concept and the quantum feature of a novel computing system, coherent Ising machines, and describe their theoretical and experimental performance. We start with the discussion how to construct such physical devices as the quantum analog of classical neuron and synapse, and end with the performance comparison against various classical neural networks implemented in CPU and supercomputers.

Nonvolatile Array Of Synapses For Neural Network

NASA Technical Reports Server (NTRS)

Tawel, Raoul

1993-01-01

Elements of array programmed with help of ultraviolet light. A 32 x 32 very-large-scale integrated-circuit array of electronic synapses serves as building-block chip for analog neural-network computer. Synaptic weights stored in nonvolatile manner. Makes information content of array invulnerable to loss of power, and, by eliminating need for circuitry to refresh volatile synaptic memory, makes architecture simpler and more compact.

Demonstration of Self-Training Autonomous Neural Networks in Space Vehicle Docking Simulations

NASA Technical Reports Server (NTRS)

Patrick, M. Clinton; Thaler, Stephen L.; Stevenson-Chavis, Katherine

2006-01-01

Neural Networks have been under examination for decades in many areas of research, with varying degrees of success and acceptance. Key goals of computer learning, rapid problem solution, and automatic adaptation have been elusive at best. This paper summarizes efforts at NASA's Marshall Space Flight Center harnessing such technology to autonomous space vehicle docking for the purpose of evaluating applicability to future missions.

Neural network technologies

NASA Technical Reports Server (NTRS)

Villarreal, James A.

1991-01-01

A whole new arena of computer technologies is now beginning to form. Still in its infancy, neural network technology is a biologically inspired methodology which draws on nature's own cognitive processes. The Software Technology Branch has provided a software tool, Neural Execution and Training System (NETS), to industry, government, and academia to facilitate and expedite the use of this technology. NETS is written in the C programming language and can be executed on a variety of machines. Once a network has been debugged, NETS can produce a C source code which implements the network. This code can then be incorporated into other software systems. Described here are various software projects currently under development with NETS and the anticipated future enhancements to NETS and the technology.

Stimulus Sensitivity of a Spiking Neural Network Model

NASA Astrophysics Data System (ADS)

Chevallier, Julien

2018-02-01

Some recent papers relate the criticality of complex systems to their maximal capacity of information processing. In the present paper, we consider high dimensional point processes, known as age-dependent Hawkes processes, which have been used to model spiking neural networks. Using mean-field approximation, the response of the network to a stimulus is computed and we provide a notion of stimulus sensitivity. It appears that the maximal sensitivity is achieved in the sub-critical regime, yet almost critical for a range of biologically relevant parameters.

Neural network system for purposeful behavior based on foveal visual preprocessor

NASA Astrophysics Data System (ADS)

Golovan, Alexander V.; Shevtsova, Natalia A.; Klepatch, Arkadi A.

1996-10-01

Biologically plausible model of the system with an adaptive behavior in a priori environment and resistant to impairment has been developed. The system consists of input, learning, and output subsystems. The first subsystems classifies input patterns presented as n-dimensional vectors in accordance with some associative rule. The second one being a neural network determines adaptive responses of the system to input patterns. Arranged neural groups coding possible input patterns and appropriate output responses are formed during learning by means of negative reinforcement. Output subsystem maps a neural network activity into the system behavior in the environment. The system developed has been studied by computer simulation imitating a collision-free motion of a mobile robot. After some learning period the system 'moves' along a road without collisions. It is shown that in spite of impairment of some neural network elements the system functions reliably after relearning. Foveal visual preprocessor model developed earlier has been tested to form a kind of visual input to the system.

Adaptive Optimization of Aircraft Engine Performance Using Neural Networks

NASA Technical Reports Server (NTRS)

Simon, Donald L.; Long, Theresa W.

1995-01-01

Preliminary results are presented on the development of an adaptive neural network based control algorithm to enhance aircraft engine performance. This work builds upon a previous National Aeronautics and Space Administration (NASA) effort known as Performance Seeking Control (PSC). PSC is an adaptive control algorithm which contains a model of the aircraft's propulsion system which is updated on-line to match the operation of the aircraft's actual propulsion system. Information from the on-line model is used to adapt the control system during flight to allow optimal operation of the aircraft's propulsion system (inlet, engine, and nozzle) to improve aircraft engine performance without compromising reliability or operability. Performance Seeking Control has been shown to yield reductions in fuel flow, increases in thrust, and reductions in engine fan turbine inlet temperature. The neural network based adaptive control, like PSC, will contain a model of the propulsion system which will be used to calculate optimal control commands on-line. Hopes are that it will be able to provide some additional benefits above and beyond those of PSC. The PSC algorithm is computationally intensive, it is valid only at near steady-state flight conditions, and it has no way to adapt or learn on-line. These issues are being addressed in the development of the optimal neural controller. Specialized neural network processing hardware is being developed to run the software, the algorithm will be valid at steady-state and transient conditions, and will take advantage of the on-line learning capability of neural networks. Future plans include testing the neural network software and hardware prototype against an aircraft engine simulation. In this paper, the proposed neural network software and hardware is described and preliminary neural network training results are presented.

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.

Prediction of forced expiratory volume in pulmonary function test using radial basis neural networks and k-means clustering.

PubMed

Manoharan, Sujatha C; Ramakrishnan, Swaminathan

2009-10-01

In this work, prediction of forced expiratory volume in pulmonary function test, carried out using spirometry and neural networks is presented. The pulmonary function data were recorded from volunteers using commercial available flow volume spirometer in standard acquisition protocol. The Radial Basis Function neural networks were used to predict forced expiratory volume in 1 s (FEV1) from the recorded flow volume curves. The optimal centres of the hidden layer of radial basis function were determined by k-means clustering algorithm. The performance of the neural network model was evaluated by computing their prediction error statistics of average value, standard deviation, root mean square and their correlation with the true data for normal, restrictive and obstructive cases. Results show that the adopted neural networks are capable of predicting FEV1 in both normal and abnormal cases. Prediction accuracy was more in obstructive abnormality when compared to restrictive cases. It appears that this method of assessment is useful in diagnosing the pulmonary abnormalities with incomplete data and data with poor recording.

Linking structure and activity in nonlinear spiking networks

PubMed Central

Josić, Krešimir; Shea-Brown, Eric

2017-01-01

Recent experimental advances are producing an avalanche of data on both neural connectivity and neural activity. To take full advantage of these two emerging datasets we need a framework that links them, revealing how collective neural activity arises from the structure of neural connectivity and intrinsic neural dynamics. This problem of structure-driven activity has drawn major interest in computational neuroscience. Existing methods for relating activity and architecture in spiking networks rely on linearizing activity around a central operating point and thus fail to capture the nonlinear responses of individual neurons that are the hallmark of neural information processing. Here, we overcome this limitation and present a new relationship between connectivity and activity in networks of nonlinear spiking neurons by developing a diagrammatic fluctuation expansion based on statistical field theory. We explicitly show how recurrent network structure produces pairwise and higher-order correlated activity, and how nonlinearities impact the networks’ spiking activity. Our findings open new avenues to investigating how single-neuron nonlinearities—including those of different cell types—combine with connectivity to shape population activity and function. PMID:28644840

Development of a neural network for early detection of renal osteodystrophy

NASA Astrophysics Data System (ADS)

Cheng, Shirley N.; Chan, Heang-Ping; Adler, Ronald; Niklason, Loren T.; Chang, Chair-Li

1991-07-01

Bone erosion presenting as subperiosteal resorption on the phalanges of the hand is an early manifestation of hyperparathyroidism associated with chronic renal failure. At present, the diagnosis is made by trained radiologists through visual inspection of hand radiographs. In this study, a neural network is being developed to assess the feasibility of computer-aided detection of these changes. A two-pass approach is adopted. The digitized image is first compressed by a Laplacian pyramid compact code. The first neural network locates the region of interest using vertical projections along the phalanges and then the horizontal projections across the phalanges. A second neural network is used to classify texture variations of trabecular patterns in the region using a concurrence matrix as the input to a two-dimensional sensor layer to detect the degree of associated osteopenia. Preliminary results demonstrate the feasibility of this approach.

New exponential synchronization criteria for time-varying delayed neural networks with discontinuous activations.

PubMed

Cai, Zuowei; Huang, Lihong; Zhang, Lingling

2015-05-01

This paper investigates the problem of exponential synchronization of time-varying delayed neural networks with discontinuous neuron activations. Under the extended Filippov differential inclusion framework, by designing discontinuous state-feedback controller and using some analytic techniques, new testable algebraic criteria are obtained to realize two different kinds of global exponential synchronization of the drive-response system. Moreover, we give the estimated rate of exponential synchronization which depends on the delays and system parameters. The obtained results extend some previous works on synchronization of delayed neural networks not only with continuous activations but also with discontinuous activations. Finally, numerical examples are provided to show the correctness of our analysis via computer simulations. Our method and theoretical results have a leading significance in the design of synchronized neural network circuits involving discontinuous factors and time-varying delays. Copyright © 2015 Elsevier Ltd. All rights reserved.

Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement.

PubMed

Yue, Shigang; Rind, F Claire

2006-05-01

The lobula giant movement detector (LGMD) is an identified neuron in the locust brain that responds most strongly to the images of an approaching object such as a predator. Its computational model can cope with unpredictable environments without using specific object recognition algorithms. In this paper, an LGMD-based neural network is proposed with a new feature enhancement mechanism to enhance the expanded edges of colliding objects via grouped excitation for collision detection with complex backgrounds. The isolated excitation caused by background detail will be filtered out by the new mechanism. Offline tests demonstrated the advantages of the presented LGMD-based neural network in complex backgrounds. Real time robotics experiments using the LGMD-based neural network as the only sensory system showed that the system worked reliably in a wide range of conditions; in particular, the robot was able to navigate in arenas with structured surrounds and complex backgrounds.

Artificial neural networks in evaluation and optimization of modified release solid dosage forms.

PubMed

Ibrić, Svetlana; Djuriš, Jelena; Parojčić, Jelena; Djurić, Zorica

2012-10-18

Implementation of the Quality by Design (QbD) approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE) as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM) is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN) in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms.

Artificial Neural Networks in Evaluation and Optimization of Modified Release Solid Dosage Forms

PubMed Central

Ibrić, Svetlana; Djuriš, Jelena; Parojčić, Jelena; Djurić, Zorica

2012-01-01

Implementation of the Quality by Design (QbD) approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE) as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM) is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN) in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms. PMID:24300369

RM-SORN: a reward-modulated self-organizing recurrent neural network.

PubMed

Aswolinskiy, Witali; Pipa, Gordon

2015-01-01

Neural plasticity plays an important role in learning and memory. Reward-modulation of plasticity offers an explanation for the ability of the brain to adapt its neural activity to achieve a rewarded goal. Here, we define a neural network model that learns through the interaction of Intrinsic Plasticity (IP) and reward-modulated Spike-Timing-Dependent Plasticity (STDP). IP enables the network to explore possible output sequences and STDP, modulated by reward, reinforces the creation of the rewarded output sequences. The model is tested on tasks for prediction, recall, non-linear computation, pattern recognition, and sequence generation. It achieves performance comparable to networks trained with supervised learning, while using simple, biologically motivated plasticity rules, and rewarding strategies. The results confirm the importance of investigating the interaction of several plasticity rules in the context of reward-modulated learning and whether reward-modulated self-organization can explain the amazing capabilities of the brain.

Neuromorphic photonic networks using silicon photonic weight banks.

PubMed

Tait, Alexander N; de Lima, Thomas Ferreira; Zhou, Ellen; Wu, Allie X; Nahmias, Mitchell A; Shastri, Bhavin J; Prucnal, Paul R

2017-08-07

Photonic systems for high-performance information processing have attracted renewed interest. Neuromorphic silicon photonics has the potential to integrate processing functions that vastly exceed the capabilities of electronics. We report first observations of a recurrent silicon photonic neural network, in which connections are configured by microring weight banks. A mathematical isomorphism between the silicon photonic circuit and a continuous neural network model is demonstrated through dynamical bifurcation analysis. Exploiting this isomorphism, a simulated 24-node silicon photonic neural network is programmed using "neural compiler" to solve a differential system emulation task. A 294-fold acceleration against a conventional benchmark is predicted. We also propose and derive power consumption analysis for modulator-class neurons that, as opposed to laser-class neurons, are compatible with silicon photonic platforms. At increased scale, Neuromorphic silicon photonics could access new regimes of ultrafast information processing for radio, control, and scientific computing.

Impaired Tuning of Neural Ensembles and the Pathophysiology of Schizophrenia: A Translational and Computational Neuroscience Perspective.

PubMed

Krystal, John H; Anticevic, Alan; Yang, Genevieve J; Dragoi, George; Driesen, Naomi R; Wang, Xiao-Jing; Murray, John D

2017-05-15

The functional optimization of neural ensembles is central to human higher cognitive functions. When the functions through which neural activity is tuned fail to develop or break down, symptoms and cognitive impairments arise. This review considers ways in which disturbances in the balance of excitation and inhibition might develop and be expressed in cortical networks in association with schizophrenia. This presentation is framed within a developmental perspective that begins with disturbances in glutamate synaptic development in utero. It considers developmental correlates and consequences, including compensatory mechanisms that increase intrinsic excitability or reduce inhibitory tone. It also considers the possibility that these homeostatic increases in excitability have potential negative functional and structural consequences. These negative functional consequences of disinhibition may include reduced working memory-related cortical activity associated with the downslope of the "inverted-U" input-output curve, impaired spatial tuning of neural activity and impaired sparse coding of information, and deficits in the temporal tuning of neural activity and its implication for neural codes. The review concludes by considering the functional significance of noisy activity for neural network function. The presentation draws on computational neuroscience and pharmacologic and genetic studies in animals and humans, particularly those involving N-methyl-D-aspartate glutamate receptor antagonists, to illustrate principles of network regulation that give rise to features of neural dysfunction associated with schizophrenia. While this presentation focuses on schizophrenia, the general principles outlined in the review may have broad implications for considering disturbances in the regulation of neural ensembles in psychiatric disorders. Published by Elsevier Inc.

The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction.

PubMed

Casey, M

1996-08-15

Recurrent neural networks (RNNs) can learn to perform finite state computations. It is shown that an RNN performing a finite state computation must organize its state space to mimic the states in the minimal deterministic finite state machine that can perform that computation, and a precise description of the attractor structure of such systems is given. This knowledge effectively predicts activation space dynamics, which allows one to understand RNN computation dynamics in spite of complexity in activation dynamics. This theory provides a theoretical framework for understanding finite state machine (FSM) extraction techniques and can be used to improve training methods for RNNs performing FSM computations. This provides an example of a successful approach to understanding a general class of complex systems that has not been explicitly designed, e.g., systems that have evolved or learned their internal structure.

The prediction in computer color matching of dentistry based on GA+BP neural network.

PubMed

Li, Haisheng; Lai, Long; Chen, Li; Lu, Cheng; Cai, Qiang

2015-01-01

Although the use of computer color matching can reduce the influence of subjective factors by technicians, matching the color of a natural tooth with a ceramic restoration is still one of the most challenging topics in esthetic prosthodontics. Back propagation neural network (BPNN) has already been introduced into the computer color matching in dentistry, but it has disadvantages such as unstable and low accuracy. In our study, we adopt genetic algorithm (GA) to optimize the initial weights and threshold values in BPNN for improving the matching precision. To our knowledge, we firstly combine the BPNN with GA in computer color matching in dentistry. Extensive experiments demonstrate that the proposed method improves the precision and prediction robustness of the color matching in restorative dentistry.

Multisensory visual servoing by a neural network.

PubMed

Wei, G Q; Hirzinger, G

1999-01-01

Conventional computer vision methods for determining a robot's end-effector motion based on sensory data needs sensor calibration (e.g., camera calibration) and sensor-to-hand calibration (e.g., hand-eye calibration). This involves many computations and even some difficulties, especially when different kinds of sensors are involved. In this correspondence, we present a neural network approach to the motion determination problem without any calibration. Two kinds of sensory data, namely, camera images and laser range data, are used as the input to a multilayer feedforward network to associate the direct transformation from the sensory data to the required motions. This provides a practical sensor fusion method. Using a recursive motion strategy and in terms of a network correction, we relax the requirement for the exactness of the learned transformation. Another important feature of our work is that the goal position can be changed without having to do network retraining. Experimental results show the effectiveness of our method.

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.

Recognition of partially occluded threat objects using the annealed Hopefield network

NASA Technical Reports Server (NTRS)

Kim, Jung H.; Yoon, Sung H.; Park, Eui H.; Ntuen, Celestine A.

1992-01-01

Recognition of partially occluded objects has been an important issue to airport security because occlusion causes significant problems in identifying and locating objects during baggage inspection. The neural network approach is suitable for the problems in the sense that the inherent parallelism of neural networks pursues many hypotheses in parallel resulting in high computation rates. Moreover, they provide a greater degree of robustness or fault tolerance than conventional computers. The annealed Hopfield network which is derived from the mean field annealing (MFA) has been developed to find global solutions of a nonlinear system. In the study, it has been proven that the system temperature of MFA is equivalent to the gain of the sigmoid function of a Hopfield network. In our early work, we developed the hybrid Hopfield network (HHN) for fast and reliable matching. However, HHN doesn't guarantee global solutions and yields false matching under heavily occluded conditions because HHN is dependent on initial states by its nature. In this paper, we present the annealed Hopfield network (AHN) for occluded object matching problems. In AHN, the mean field theory is applied to the hybird Hopfield network in order to improve computational complexity of the annealed Hopfield network and provide reliable matching under heavily occluded conditions. AHN is slower than HHN. However, AHN provides near global solutions without initial restrictions and provides less false matching than HHN. In conclusion, a new algorithm based upon a neural network approach was developed to demonstrate the feasibility of the automated inspection of threat objects from x-ray images. The robustness of the algorithm is proved by identifying occluded target objects with large tolerance of their features.

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.

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.

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

Feasibility of Using Neural Network Models to Accelerate the Testing of Mechanical Systems

NASA Technical Reports Server (NTRS)

Fusaro, Robert L.

1998-01-01

Verification testing is an important aspect of the design process for mechanical mechanisms, and full-scale, full-length life testing is typically used to qualify any new component for use in space. However, as the required life specification is increased, full-length life tests become more costly and lengthen the development time. At the NASA Lewis Research Center, we theorized that neural network systems may be able to model the operation of a mechanical device. If so, the resulting neural network models could simulate long-term mechanical testing with data from a short-term test. This combination of computer modeling and short-term mechanical testing could then be used to verify the reliability of mechanical systems, thereby eliminating the costs associated with long-term testing. Neural network models could also enable designers to predict the performance of mechanisms at the conceptual design stage by entering the critical parameters as input and running the model to predict performance. The purpose of this study was to assess the potential of using neural networks to predict the performance and life of mechanical systems. To do this, we generated a neural network system to model wear obtained from three accelerated testing devices: 1) A pin-on-disk tribometer; 2) A line-contact rub-shoe tribometer; 3) A four-ball tribometer.

Empirical modeling for intelligent, real-time manufacture control

NASA Technical Reports Server (NTRS)

Xu, Xiaoshu

1994-01-01

Artificial neural systems (ANS), also known as neural networks, are an attempt to develop computer systems that emulate the neural reasoning behavior of biological neural systems (e.g. the human brain). As such, they are loosely based on biological neural networks. The ANS consists of a series of nodes (neurons) and weighted connections (axons) that, when presented with a specific input pattern, can associate specific output patterns. It is essentially a highly complex, nonlinear, mathematical relationship or transform. These constructs have two significant properties that have proven useful to the authors in signal processing and process modeling: noise tolerance and complex pattern recognition. Specifically, the authors have developed a new network learning algorithm that has resulted in the successful application of ANS's to high speed signal processing and to developing models of highly complex processes. Two of the applications, the Weld Bead Geometry Control System and the Welding Penetration Monitoring System, are discussed in the body of this paper.

Efficacy of an artificial neural network-based approach to endoscopic ultrasound elastography in diagnosis of focal pancreatic masses.

PubMed

Săftoiu, Adrian; Vilmann, Peter; Gorunescu, Florin; Janssen, Jan; Hocke, Michael; Larsen, Michael; Iglesias-Garcia, Julio; Arcidiacono, Paolo; Will, Uwe; Giovannini, Marc; Dietrich, Cristoph F; Havre, Roald; Gheorghe, Cristian; McKay, Colin; Gheonea, Dan Ionuţ; Ciurea, Tudorel

2012-01-01

By using strain assessment, real-time endoscopic ultrasound (EUS) elastography provides additional information about a lesion's characteristics in the pancreas. We assessed the accuracy of real-time EUS elastography in focal pancreatic lesions using computer-aided diagnosis by artificial neural network analysis. We performed a prospective, blinded, multicentric study at of 258 patients (774 recordings from EUS elastography) who were diagnosed with chronic pancreatitis (n = 47) or pancreatic adenocarcinoma (n = 211) from 13 tertiary academic medical centers in Europe (the European EUS Elastography Multicentric Study Group). We used postprocessing software analysis to compute individual frames of elastography movies recorded by retrieving hue histogram data from a dynamic sequence of EUS elastography into a numeric matrix. The data then were analyzed in an extended neural network analysis, to automatically differentiate benign from malignant patterns. The neural computing approach had 91.14% training accuracy (95% confidence interval [CI], 89.87%-92.42%) and 84.27% testing accuracy (95% CI, 83.09%-85.44%). These results were obtained using the 10-fold cross-validation technique. The statistical analysis of the classification process showed a sensitivity of 87.59%, a specificity of 82.94%, a positive predictive value of 96.25%, and a negative predictive value of 57.22%. Moreover, the corresponding area under the receiver operating characteristic curve was 0.94 (95% CI, 0.91%-0.97%), which was significantly higher than the values obtained by simple mean hue histogram analysis, for which the area under the receiver operating characteristic was 0.85. Use of the artificial intelligence methodology via artificial neural networks supports the medical decision process, providing fast and accurate diagnoses. Copyright © 2012 AGA Institute. Published by Elsevier Inc. All rights reserved.

Identifying Jets Using Artifical Neural Networks

NASA Astrophysics Data System (ADS)

Rosand, Benjamin; Caines, Helen; Checa, Sofia

2017-09-01

We investigate particle jet interactions with the Quark Gluon Plasma (QGP) using artificial neural networks modeled on those used in computer image recognition. We create jet images by binning jet particles into pixels and preprocessing every image. We analyzed the jets with a Multi-layered maxout network and a convolutional network. We demonstrate each network's effectiveness in differentiating simulated quenched jets from unquenched jets, and we investigate the method that the network uses to discriminate among different quenched jet simulations. Finally, we develop a greater understanding of the physics behind quenched jets by investigating what the network learnt as well as its effectiveness in differentiating samples. Yale College Freshman Summer Research Fellowship in the Sciences and Engineering.

A solution for two-dimensional mazes with use of chaotic dynamics in a recurrent neural network model.

PubMed

Suemitsu, Yoshikazu; Nara, Shigetoshi

2004-09-01

Chaotic dynamics introduced into a neural network model is applied to solving two-dimensional mazes, which are ill-posed problems. A moving object moves from the position at t to t + 1 by simply defined motion function calculated from firing patterns of the neural network model at each time step t. We have embedded several prototype attractors that correspond to the simple motion of the object orienting toward several directions in two-dimensional space in our neural network model. Introducing chaotic dynamics into the network gives outputs sampled from intermediate state points between embedded attractors in a state space, and these dynamics enable the object to move in various directions. System parameter switching between a chaotic and an attractor regime in the state space of the neural network enables the object to move to a set target in a two-dimensional maze. Results of computer simulations show that the success rate for this method over 300 trials is higher than that of random walk. To investigate why the proposed method gives better performance, we calculate and discuss statistical data with respect to dynamical structure.

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.

Goal-Directed Decision Making with Spiking Neurons.

PubMed

Friedrich, Johannes; Lengyel, Máté

2016-02-03

Behavioral and neuroscientific data on reward-based decision making point to a fundamental distinction between habitual and goal-directed action selection. The formation of habits, which requires simple updating of cached values, has been studied in great detail, and the reward prediction error theory of dopamine function has enjoyed prominent success in accounting for its neural bases. In contrast, the neural circuit mechanisms of goal-directed decision making, requiring extended iterative computations to estimate values online, are still unknown. Here we present a spiking neural network that provably solves the difficult online value estimation problem underlying goal-directed decision making in a near-optimal way and reproduces behavioral as well as neurophysiological experimental data on tasks ranging from simple binary choice to sequential decision making. Our model uses local plasticity rules to learn the synaptic weights of a simple neural network to achieve optimal performance and solves one-step decision-making tasks, commonly considered in neuroeconomics, as well as more challenging sequential decision-making tasks within 1 s. These decision times, and their parametric dependence on task parameters, as well as the final choice probabilities match behavioral data, whereas the evolution of neural activities in the network closely mimics neural responses recorded in frontal cortices during the execution of such tasks. Our theory provides a principled framework to understand the neural underpinning of goal-directed decision making and makes novel predictions for sequential decision-making tasks with multiple rewards. Goal-directed actions requiring prospective planning pervade decision making, but their circuit-level mechanisms remain elusive. We show how a model circuit of biologically realistic spiking neurons can solve this computationally challenging problem in a novel way. The synaptic weights of our network can be learned using local plasticity rules such that its dynamics devise a near-optimal plan of action. By systematically comparing our model results to experimental data, we show that it reproduces behavioral decision times and choice probabilities as well as neural responses in a rich set of tasks. Our results thus offer the first biologically realistic account for complex goal-directed decision making at a computational, algorithmic, and implementational level. Copyright © 2016 the authors 0270-6474/16/361529-18$15.00/0.

Goal-Directed Decision Making with Spiking Neurons

PubMed Central

Lengyel, Máté

2016-01-01

Behavioral and neuroscientific data on reward-based decision making point to a fundamental distinction between habitual and goal-directed action selection. The formation of habits, which requires simple updating of cached values, has been studied in great detail, and the reward prediction error theory of dopamine function has enjoyed prominent success in accounting for its neural bases. In contrast, the neural circuit mechanisms of goal-directed decision making, requiring extended iterative computations to estimate values online, are still unknown. Here we present a spiking neural network that provably solves the difficult online value estimation problem underlying goal-directed decision making in a near-optimal way and reproduces behavioral as well as neurophysiological experimental data on tasks ranging from simple binary choice to sequential decision making. Our model uses local plasticity rules to learn the synaptic weights of a simple neural network to achieve optimal performance and solves one-step decision-making tasks, commonly considered in neuroeconomics, as well as more challenging sequential decision-making tasks within 1 s. These decision times, and their parametric dependence on task parameters, as well as the final choice probabilities match behavioral data, whereas the evolution of neural activities in the network closely mimics neural responses recorded in frontal cortices during the execution of such tasks. Our theory provides a principled framework to understand the neural underpinning of goal-directed decision making and makes novel predictions for sequential decision-making tasks with multiple rewards. SIGNIFICANCE STATEMENT Goal-directed actions requiring prospective planning pervade decision making, but their circuit-level mechanisms remain elusive. We show how a model circuit of biologically realistic spiking neurons can solve this computationally challenging problem in a novel way. The synaptic weights of our network can be learned using local plasticity rules such that its dynamics devise a near-optimal plan of action. By systematically comparing our model results to experimental data, we show that it reproduces behavioral decision times and choice probabilities as well as neural responses in a rich set of tasks. Our results thus offer the first biologically realistic account for complex goal-directed decision making at a computational, algorithmic, and implementational level. PMID:26843636

Artificial astrocytes improve neural network performance.

PubMed

Porto-Pazos, Ana B; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso

2011-04-19

Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.

Artificial Astrocytes Improve Neural Network Performance

PubMed Central

Porto-Pazos, Ana B.; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso

2011-01-01

Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function. PMID:21526157

Lateral Information Processing by Spiking Neurons: A Theoretical Model of the Neural Correlate of Consciousness

PubMed Central

Ebner, Marc; Hameroff, Stuart

2011-01-01

Cognitive brain functions, for example, sensory perception, motor control and learning, are understood as computation by axonal-dendritic chemical synapses in networks of integrate-and-fire neurons. Cognitive brain functions may occur either consciously or nonconsciously (on “autopilot”). Conscious cognition is marked by gamma synchrony EEG, mediated largely by dendritic-dendritic gap junctions, sideways connections in input/integration layers. Gap-junction-connected neurons define a sub-network within a larger neural network. A theoretical model (the “conscious pilot”) suggests that as gap junctions open and close, a gamma-synchronized subnetwork, or zone moves through the brain as an executive agent, converting nonconscious “auto-pilot” cognition to consciousness, and enhancing computation by coherent processing and collective integration. In this study we implemented sideways “gap junctions” in a single-layer artificial neural network to perform figure/ground separation. The set of neurons connected through gap junctions form a reconfigurable resistive grid or sub-network zone. In the model, outgoing spikes are temporally integrated and spatially averaged using the fixed resistive grid set up by neurons of similar function which are connected through gap-junctions. This spatial average, essentially a feedback signal from the neuron's output, determines whether particular gap junctions between neurons will open or close. Neurons connected through open gap junctions synchronize their output spikes. We have tested our gap-junction-defined sub-network in a one-layer neural network on artificial retinal inputs using real-world images. Our system is able to perform figure/ground separation where the laterally connected sub-network of neurons represents a perceived object. Even though we only show results for visual stimuli, our approach should generalize to other modalities. The system demonstrates a moving sub-network zone of synchrony, within which the contents of perception are represented and contained. This mobile zone can be viewed as a model of the neural correlate of consciousness in the brain. PMID:22046178

Lateral information processing by spiking neurons: a theoretical model of the neural correlate of consciousness.

PubMed

Ebner, Marc; Hameroff, Stuart

2011-01-01

Cognitive brain functions, for example, sensory perception, motor control and learning, are understood as computation by axonal-dendritic chemical synapses in networks of integrate-and-fire neurons. Cognitive brain functions may occur either consciously or nonconsciously (on "autopilot"). Conscious cognition is marked by gamma synchrony EEG, mediated largely by dendritic-dendritic gap junctions, sideways connections in input/integration layers. Gap-junction-connected neurons define a sub-network within a larger neural network. A theoretical model (the "conscious pilot") suggests that as gap junctions open and close, a gamma-synchronized subnetwork, or zone moves through the brain as an executive agent, converting nonconscious "auto-pilot" cognition to consciousness, and enhancing computation by coherent processing and collective integration. In this study we implemented sideways "gap junctions" in a single-layer artificial neural network to perform figure/ground separation. The set of neurons connected through gap junctions form a reconfigurable resistive grid or sub-network zone. In the model, outgoing spikes are temporally integrated and spatially averaged using the fixed resistive grid set up by neurons of similar function which are connected through gap-junctions. This spatial average, essentially a feedback signal from the neuron's output, determines whether particular gap junctions between neurons will open or close. Neurons connected through open gap junctions synchronize their output spikes. We have tested our gap-junction-defined sub-network in a one-layer neural network on artificial retinal inputs using real-world images. Our system is able to perform figure/ground separation where the laterally connected sub-network of neurons represents a perceived object. Even though we only show results for visual stimuli, our approach should generalize to other modalities. The system demonstrates a moving sub-network zone of synchrony, within which the contents of perception are represented and contained. This mobile zone can be viewed as a model of the neural correlate of consciousness in the brain.

Evolvable rough-block-based neural network and its biomedical application to hypoglycemia detection system.

PubMed

San, Phyo Phyo; Ling, Sai Ho; Nuryani; Nguyen, Hung

2014-08-01

This paper focuses on the hybridization technology using rough sets concepts and neural computing for decision and classification purposes. Based on the rough set properties, the lower region and boundary region are defined to partition the input signal to a consistent (predictable) part and an inconsistent (random) part. In this way, the neural network is designed to deal only with the boundary region, which mainly consists of an inconsistent part of applied input signal causing inaccurate modeling of the data set. Owing to different characteristics of neural network (NN) applications, the same structure of conventional NN might not give the optimal solution. Based on the knowledge of application in this paper, a block-based neural network (BBNN) is selected as a suitable classifier due to its ability to evolve internal structures and adaptability in dynamic environments. This architecture will systematically incorporate the characteristics of application to the structure of hybrid rough-block-based neural network (R-BBNN). A global training algorithm, hybrid particle swarm optimization with wavelet mutation is introduced for parameter optimization of proposed R-BBNN. The performance of the proposed R-BBNN algorithm was evaluated by an application to the field of medical diagnosis using real hypoglycemia episodes in patients with Type 1 diabetes mellitus. The performance of the proposed hybrid system has been compared with some of the existing neural networks. The comparison results indicated that the proposed method has improved classification performance and results in early convergence of the network.

A design philosophy for multi-layer neural networks with applications to robot control

NASA Technical Reports Server (NTRS)

Vadiee, Nader; Jamshidi, MO

1989-01-01

A system is proposed which receives input information from many sensors that may have diverse scaling, dimension, and data representations. The proposed system tolerates sensory information with faults. The proposed self-adaptive processing technique has great promise in integrating the techniques of artificial intelligence and neural networks in an attempt to build a more intelligent computing environment. The proposed architecture can provide a detailed decision tree based on the input information, information stored in a long-term memory, and the adapted rule-based knowledge. A mathematical model for analysis will be obtained to validate the cited hypotheses. An extensive software program will be developed to simulate a typical example of pattern recognition problem. It is shown that the proposed model displays attention, expectation, spatio-temporal, and predictory behavior which are specific to the human brain. The anticipated results of this research project are: (1) creation of a new dynamic neural network structure, and (2) applications to and comparison with conventional multi-layer neural network structures. The anticipated benefits from this research are vast. The model can be used in a neuro-computer architecture as a building block which can perform complicated, nonlinear, time-varying mapping from a multitude of input excitory classes to an output or decision environment. It can be used for coordinating different sensory inputs and past experience of a dynamic system and actuating signals. The commercial applications of this project can be the creation of a special-purpose neuro-computer hardware which can be used in spatio-temporal pattern recognitions in such areas as air defense systems, e.g., target tracking, and recognition. Potential robotics-related applications are trajectory planning, inverse dynamics computations, hierarchical control, task-oriented control, and collision avoidance.

An adaptive drug delivery design using neural networks for effective treatment of infectious diseases: a simulation study.

PubMed

Padhi, Radhakant; Bhardhwaj, Jayender R

2009-06-01

An adaptive drug delivery design is presented in this paper using neural networks for effective treatment of infectious diseases. The generic mathematical model used describes the coupled evolution of concentration of pathogens, plasma cells, antibodies and a numerical value that indicates the relative characteristic of a damaged organ due to the disease under the influence of external drugs. From a system theoretic point of view, the external drugs can be interpreted as control inputs, which can be designed based on control theoretic concepts. In this study, assuming a set of nominal parameters in the mathematical model, first a nonlinear controller (drug administration) is designed based on the principle of dynamic inversion. This nominal drug administration plan was found to be effective in curing "nominal model patients" (patients whose immunological dynamics conform to the mathematical model used for the control design exactly. However, it was found to be ineffective in curing "realistic model patients" (patients whose immunological dynamics may have off-nominal parameter values and possibly unwanted inputs) in general. Hence, to make the drug delivery dosage design more effective for realistic model patients, a model-following adaptive control design is carried out next by taking the help of neural networks, that are trained online. Simulation studies indicate that the adaptive controller proposed in this paper holds promise in killing the invading pathogens and healing the damaged organ even in the presence of parameter uncertainties and continued pathogen attack. Note that the computational requirements for computing the control are very minimal and all associated computations (including the training of neural networks) can be carried out online. However it assumes that the required diagnosis process can be carried out at a sufficient faster rate so that all the states are available for control computation.

Neurocomputation by Reaction Diffusion

NASA Astrophysics Data System (ADS)

Liang, Ping

1995-08-01

This Letter demonstrates the possible role nonsynaptic diffusion neurotransmission may play in neurocomputation using an artificial neural network model. A reaction-diffusion neural network model with field-based information-processing mechanisms is proposed. The advantages of nonsynaptic field neurotransmission from a computational viewpoint demonstrated in this Letter include long-range inhibition using only local interaction, nonhardwired and changeable (target specific) long-range communication pathways, and multiple simultaneous spatiotemporal organization processes in the same medium.

Connectomic constraints on computation in feedforward networks of spiking neurons.

PubMed

Ramaswamy, Venkatakrishnan; Banerjee, Arunava

2014-10-01

Several efforts are currently underway to decipher the connectome or parts thereof in a variety of organisms. Ascertaining the detailed physiological properties of all the neurons in these connectomes, however, is out of the scope of such projects. It is therefore unclear to what extent knowledge of the connectome alone will advance a mechanistic understanding of computation occurring in these neural circuits, especially when the high-level function of the said circuit is unknown. We consider, here, the question of how the wiring diagram of neurons imposes constraints on what neural circuits can compute, when we cannot assume detailed information on the physiological response properties of the neurons. We call such constraints-that arise by virtue of the connectome-connectomic constraints on computation. For feedforward networks equipped with neurons that obey a deterministic spiking neuron model which satisfies a small number of properties, we ask if just by knowing the architecture of a network, we can rule out computations that it could be doing, no matter what response properties each of its neurons may have. We show results of this form, for certain classes of network architectures. On the other hand, we also prove that with the limited set of properties assumed for our model neurons, there are fundamental limits to the constraints imposed by network structure. Thus, our theory suggests that while connectomic constraints might restrict the computational ability of certain classes of network architectures, we may require more elaborate information on the properties of neurons in the network, before we can discern such results for other classes of networks.

What the success of brain imaging implies about the neural code.

PubMed

Guest, Olivia; Love, Bradley C

2017-01-19

The success of fMRI places constraints on the nature of the neural code. The fact that researchers can infer similarities between neural representations, despite fMRI's limitations, implies that certain neural coding schemes are more likely than others. For fMRI to succeed given its low temporal and spatial resolution, the neural code must be smooth at the voxel and functional level such that similar stimuli engender similar internal representations. Through proof and simulation, we determine which coding schemes are plausible given both fMRI's successes and its limitations in measuring neural activity. Deep neural network approaches, which have been forwarded as computational accounts of the ventral stream, are consistent with the success of fMRI, though functional smoothness breaks down in the later network layers. These results have implications for the nature of the neural code and ventral stream, as well as what can be successfully investigated with fMRI.

High-performance reconfigurable hardware architecture for restricted Boltzmann machines.

PubMed

Ly, Daniel Le; Chow, Paul

2010-11-01

Despite the popularity and success of neural networks in research, the number of resulting commercial or industrial applications has been limited. A primary cause for this lack of adoption is that neural networks are usually implemented as software running on general-purpose processors. Hence, a hardware implementation that can exploit the inherent parallelism in neural networks is desired. This paper investigates how the restricted Boltzmann machine (RBM), which is a popular type of neural network, can be mapped to a high-performance hardware architecture on field-programmable gate array (FPGA) platforms. The proposed modular framework is designed to reduce the time complexity of the computations through heavily customized hardware engines. A method to partition large RBMs into smaller congruent components is also presented, allowing the distribution of one RBM across multiple FPGA resources. The framework is tested on a platform of four Xilinx Virtex II-Pro XC2VP70 FPGAs running at 100 MHz through a variety of different configurations. The maximum performance was obtained by instantiating an RBM of 256 × 256 nodes distributed across four FPGAs, which resulted in a computational speed of 3.13 billion connection-updates-per-second and a speedup of 145-fold over an optimized C program running on a 2.8-GHz Intel processor.

The next generation of neural network chips

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

Beiu, V.

There have been many national and international neural networks research initiatives: USA (DARPA, NIBS), Canada (IRIS), Japan (HFSP) and Europe (BRAIN, GALA TEA, NERVES, ELENE NERVES 2) -- just to mention a few. Recent developments in the field of neural networks, cognitive science, bioengineering and electrical engineering have made it possible to understand more about the functioning of large ensembles of identical processing elements. There are more research papers than ever proposing solutions and hardware implementations are by no means an exception. Two fields (computing and neuroscience) are interacting in ways nobody could imagine just several years ago, and --more » with the advent of new technologies -- researchers are focusing on trying to copy the Brain. Such an exciting confluence may quite shortly lead to revolutionary new computers and it is the aim of this invited session to bring to light some of the challenging research aspects dealing with the hardware realizability of future intelligent chips. Present-day (conventional) technology is (still) mostly digital and, thus, occupies wider areas and consumes much more power than the solutions envisaged. The innovative algorithmic and architectural ideals should represent important breakthroughs, paving the way towards making neural network chips available to the industry at competitive prices, in relatively small packages and consuming a fraction of the power required by equivalent digital solutions.« less

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.

The neural circuits for arithmetic principles.

PubMed

Liu, Jie; Zhang, Han; Chen, Chuansheng; Chen, Hui; Cui, Jiaxin; Zhou, Xinlin

2017-02-15

Arithmetic principles are the regularities underlying arithmetic computation. Little is known about how the brain supports the processing of arithmetic principles. The current fMRI study examined neural activation and functional connectivity during the processing of verbalized arithmetic principles, as compared to numerical computation and general language processing. As expected, arithmetic principles elicited stronger activation in bilateral horizontal intraparietal sulcus and right supramarginal gyrus than did language processing, and stronger activation in left middle temporal lobe and left orbital part of inferior frontal gyrus than did computation. In contrast, computation elicited greater activation in bilateral horizontal intraparietal sulcus (extending to posterior superior parietal lobule) than did either arithmetic principles or language processing. Functional connectivity analysis with the psychophysiological interaction approach (PPI) showed that left temporal-parietal (MTG-HIPS) connectivity was stronger during the processing of arithmetic principle and language than during computation, whereas parietal-occipital connectivities were stronger during computation than during the processing of arithmetic principles and language. Additionally, the left fronto-parietal (orbital IFG-HIPS) connectivity was stronger during the processing of arithmetic principles than during computation. The results suggest that verbalized arithmetic principles engage a neural network that overlaps but is distinct from the networks for computation and language processing. Copyright © 2016 Elsevier Inc. All rights reserved.

Privacy-preserving backpropagation neural network learning.

PubMed

Chen, Tingting; Zhong, Sheng

2009-10-01

With the development of distributed computing environment , many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms. In this paper, we focus on preserving the privacy in an important learning model, multilayer neural networks. We present a privacy-preserving two-party distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other. We provide complete correctness and security analysis of our algorithms. The effectiveness of our algorithms is verified by experiments on various real world data sets.

A neural network strategy for end-point optimization of batch processes.

PubMed

Krothapally, M; Palanki, S

1999-01-01

The traditional way of operating batch processes has been to utilize an open-loop "golden recipe". However, there can be substantial batch to batch variation in process conditions and this open-loop strategy can lead to non-optimal operation. In this paper, a new approach is presented for end-point optimization of batch processes by utilizing neural networks. This strategy involves the training of two neural networks; one to predict switching times and the other to predict the input profile in the singular region. This approach alleviates the computational problems associated with the classical Pontryagin's approach and the nonlinear programming approach. The efficacy of this scheme is illustrated via simulation of a fed-batch fermentation.

Slow Computing Simulation of Bio-plausible Control

DTIC Science & Technology

2012-03-01

information networks, neuromorphic chips would become necessary. Small unstable flying platforms currently require RTK, GPS, or Vicon closed-circuit...Visual, and IR Sensing FPGA ASIC Neuromorphic Chip Simulation Quad Rotor Robotic Insect Uniform Independent Network Single Modality Neural Network... neuromorphic Processing across parallel computational elements =0.54 N u m b e r o f c o m p u ta tio n s - No info 14 integrated circuit

Information processing in echo state networks at the edge of chaos.

PubMed

Boedecker, Joschka; Obst, Oliver; Lizier, Joseph T; Mayer, N Michael; Asada, Minoru

2012-09-01

We investigate information processing in randomly connected recurrent neural networks. It has been shown previously that the computational capabilities of these networks are maximized when the recurrent layer is close to the border between a stable and an unstable dynamics regime, the so called edge of chaos. The reasons, however, for this maximized performance are not completely understood. We adopt an information-theoretical framework and are for the first time able to quantify the computational capabilities between elements of these networks directly as they undergo the phase transition to chaos. Specifically, we present evidence that both information transfer and storage in the recurrent layer are maximized close to this phase transition, providing an explanation for why guiding the recurrent layer toward the edge of chaos is computationally useful. As a consequence, our study suggests self-organized ways of improving performance in recurrent neural networks, driven by input data. Moreover, the networks we study share important features with biological systems such as feedback connections and online computation on input streams. A key example is the cerebral cortex, which was shown to also operate close to the edge of chaos. Consequently, the behavior of model systems as studied here is likely to shed light on reasons why biological systems are tuned into this specific regime.

Improved Classification of Lung Cancer Using Radial Basis Function Neural Network with Affine Transforms of Voss Representation.

PubMed

Adetiba, Emmanuel; Olugbara, Oludayo O

2015-01-01

Lung cancer is one of the diseases responsible for a large number of cancer related death cases worldwide. The recommended standard for screening and early detection of lung cancer is the low dose computed tomography. However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for screening and early detection of lung cancer. We present computational methods that can be implemented in a functional multi-genomic system for classification, screening and early detection of lung cancer victims. Samples of top ten biomarker genes previously reported to have the highest frequency of lung cancer mutations and sequences of normal biomarker genes were respectively collected from the COSMIC and NCBI databases to validate the computational methods. Experiments were performed based on the combinations of Z-curve and tetrahedron affine transforms, Histogram of Oriented Gradient (HOG), Multilayer perceptron and Gaussian Radial Basis Function (RBF) neural networks to obtain an appropriate combination of computational methods to achieve improved classification of lung cancer biomarker genes. Results show that a combination of affine transforms of Voss representation, HOG genomic features and Gaussian RBF neural network perceptibly improves classification accuracy, specificity and sensitivity of lung cancer biomarker genes as well as achieving low mean square error.

Deep Learning and Developmental Learning: Emergence of Fine-to-Coarse Conceptual Categories at Layers of Deep Belief Network.

PubMed

Sadeghi, Zahra

2016-09-01

In this paper, I investigate conceptual categories derived from developmental processing in a deep neural network. The similarity matrices of deep representation at each layer of neural network are computed and compared with their raw representation. While the clusters generated by raw representation stand at the basic level of abstraction, conceptual categories obtained from deep representation shows a bottom-up transition procedure. Results demonstrate a developmental course of learning from specific to general level of abstraction through learned layers of representations in a deep belief network. © The Author(s) 2016.

Space shuttle main engine fault detection using neural networks

NASA Technical Reports Server (NTRS)

Bishop, Thomas; Greenwood, Dan; Shew, Kenneth; Stevenson, Fareed

1991-01-01

A method for on-line Space Shuttle Main Engine (SSME) anomaly detection and fault typing using a feedback neural network is described. The method involves the computation of features representing time-variance of SSME sensor parameters, using historical test case data. The network is trained, using backpropagation, to recognize a set of fault cases. The network is then able to diagnose new fault cases correctly. An essential element of the training technique is the inclusion of randomly generated data along with the real data, in order to span the entire input space of potential non-nominal data.

Cellular computational platform and neurally inspired elements thereof

DOEpatents

Okandan, Murat

2016-11-22

A cellular computational platform is disclosed that includes a multiplicity of functionally identical, repeating computational hardware units that are interconnected electrically and optically. Each computational hardware unit includes a reprogrammable local memory and has interconnections to other such units that have reconfigurable weights. Each computational hardware unit is configured to transmit signals into the network for broadcast in a protocol-less manner to other such units in the network, and to respond to protocol-less broadcast messages that it receives from the network. Each computational hardware unit is further configured to reprogram the local memory in response to incoming electrical and/or optical signals.

A neutron spectrum unfolding code based on generalized regression artificial neural networks.

PubMed

Del Rosario Martinez-Blanco, Ma; Ornelas-Vargas, Gerardo; Castañeda-Miranda, Celina Lizeth; Solís-Sánchez, Luis Octavio; Castañeda-Miranada, Rodrigo; Vega-Carrillo, Héctor René; Celaya-Padilla, Jose M; Garza-Veloz, Idalia; Martínez-Fierro, Margarita; Ortiz-Rodríguez, José Manuel

2016-11-01

The most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. Novel methods based on Artificial Neural Networks have been widely investigated. In prior works, back propagation neural networks (BPNN) have been used to solve the neutron spectrometry problem, however, some drawbacks still exist using this kind of neural nets, i.e. the optimum selection of the network topology and the long training time. Compared to BPNN, it's usually much faster to train a generalized regression neural network (GRNN). That's mainly because spread constant is the only parameter used in GRNN. Another feature is that the network will converge to a global minimum, provided that the optimal values of spread has been determined and that the dataset adequately represents the problem space. In addition, GRNN are often more accurate than BPNN in the prediction. These characteristics make GRNNs to be of great interest in the neutron spectrometry domain. This work presents a computational tool based on GRNN capable to solve the neutron spectrometry problem. This computational code, automates the pre-processing, training and testing stages using a k-fold cross validation of 3 folds, the statistical analysis and the post-processing of the information, using 7 Bonner spheres rate counts as only entrance data. The code was designed for a Bonner Spheres System based on a 6 LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. Copyright © 2016 Elsevier Ltd. All rights reserved.

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.

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.

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.

AN ARTIFICIAL NEURAL NETWORK EVALUATION OF TUBERCULOSIS USING GENETIC AND PHYSIOLOGICAL PATIENT DATA

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

Griffin, William O.; Darsey, Jerry A.; Hanna, Josh

When doctors see more cases of patients with tell-tale symptoms of a disease, it is hoped that they will be able to recognize an infection administer treatment appropriately, thereby speeding up recovery for sick patients. We hope that our studies can aid in the detection of tuberculosis by using a computer model called an artificial neural network. Our model looks at patients with and without tuberculosis (TB). The data that the neural network examined came from the following: patient' age, gender, place, of birth, blood type, Rhesus (Rh) factor, and genes of the human Leukocyte Antigens (HLA) system (9q34.1) presentmore » in the Major Histocompatibility Complex. With availability in genetic data and good research, we hope to give them an advantage in the detection of tuberculosis. We try to mimic the doctor's experience with a computer test, which will learn from patient data the factors that contribute to TB.« less

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.

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.

Nonlinearly Activated Neural Network for Solving Time-Varying Complex Sylvester Equation.

PubMed

Li, Shuai; Li, Yangming

2013-10-28

The Sylvester equation is often encountered in mathematics and control theory. For the general time-invariant Sylvester equation problem, which is defined in the domain of complex numbers, the Bartels-Stewart algorithm and its extensions are effective and widely used with an O(n³) time complexity. When applied to solving the time-varying Sylvester equation, the computation burden increases intensively with the decrease of sampling period and cannot satisfy continuous realtime calculation requirements. For the special case of the general Sylvester equation problem defined in the domain of real numbers, gradient-based recurrent neural networks are able to solve the time-varying Sylvester equation in real time, but there always exists an estimation error while a recently proposed recurrent neural network by Zhang et al [this type of neural network is called Zhang neural network (ZNN)] converges to the solution ideally. The advancements in complex-valued neural networks cast light to extend the existing real-valued ZNN for solving the time-varying real-valued Sylvester equation to its counterpart in the domain of complex numbers. In this paper, a complex-valued ZNN for solving the complex-valued Sylvester equation problem is investigated and the global convergence of the neural network is proven with the proposed nonlinear complex-valued activation functions. Moreover, a special type of activation function with a core function, called sign-bi-power function, is proven to enable the ZNN to converge in finite time, which further enhances its advantage in online processing. In this case, the upper bound of the convergence time is also derived analytically. Simulations are performed to evaluate and compare the performance of the neural network with different parameters and activation functions. Both theoretical analysis and numerical simulations validate the effectiveness of the proposed method.

An overview on development of neural network technology

NASA Technical Reports Server (NTRS)

Lin, Chun-Shin

1993-01-01

The study has been to obtain a bird's-eye view of the current neural network technology and the neural network research activities in NASA. The purpose was two fold. One was to provide a reference document for NASA researchers who want to apply neural network techniques to solve their problems. Another one was to report out survey results regarding NASA research activities and provide a view on what NASA is doing, what potential difficulty exists and what NASA can/should do. In a ten week study period, we interviewed ten neural network researchers in the Langley Research Center and sent out 36 survey forms to researchers at the Johnson Space Center, Lewis Research Center, Ames Research Center and Jet Propulsion Laboratory. We also sent out 60 similar forms to educators and corporation researchers to collect general opinions regarding this field. Twenty-eight survey forms, 11 from NASA researchers and 17 from outside, were returned. Survey results were reported in our final report. In the final report, we first provided an overview on the neural network technology. We reviewed ten neural network structures, discussed the applications in five major areas, and compared the analog, digital and hybrid electronic implementation of neural networks. In the second part, we summarized known NASA neural network research studies and reported the results of the questionnaire survey. Survey results show that most studies are still in the development and feasibility study stage. We compared the techniques, application areas, researchers' opinions on this technology, and many aspects between NASA and non-NASA groups. We also summarized their opinions on difficulties encountered. Applications are considered the top research priority by most researchers. Hardware development and learning algorithm improvement are the next. The lack of financial and management support is among the difficulties in research study. All researchers agree that the use of neural networks could result in cost saving. Fault tolerance has been claimed as one important feature of neural computing. However, the survey indicates that very few studies address this issue. Fault tolerance is important in space mission and aircraft control. We believe that it is worthy for NASA to devote more efforts into the utilization of this feature.

A Markovian event-based framework for stochastic spiking neural networks.

PubMed

Touboul, Jonathan D; Faugeras, Olivier D

2011-11-01

In spiking neural networks, the information is conveyed by the spike times, that depend on the intrinsic dynamics of each neuron, the input they receive and on the connections between neurons. In this article we study the Markovian nature of the sequence of spike times in stochastic neural networks, and in particular the ability to deduce from a spike train the next spike time, and therefore produce a description of the network activity only based on the spike times regardless of the membrane potential process. To study this question in a rigorous manner, we introduce and study an event-based description of networks of noisy integrate-and-fire neurons, i.e. that is based on the computation of the spike times. We show that the firing times of the neurons in the networks constitute a Markov chain, whose transition probability is related to the probability distribution of the interspike interval of the neurons in the network. In the cases where the Markovian model can be developed, the transition probability is explicitly derived in such classical cases of neural networks as the linear integrate-and-fire neuron models with excitatory and inhibitory interactions, for different types of synapses, possibly featuring noisy synaptic integration, transmission delays and absolute and relative refractory period. This covers most of the cases that have been investigated in the event-based description of spiking deterministic neural networks.

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.

Memristive Mixed-Signal Neuromorphic Systems: Energy-Efficient Learning at the Circuit-Level

DOE PAGES

Chakma, Gangotree; Adnan, Md Musabbir; Wyer, Austin R.; ...

2017-11-23

Neuromorphic computing is non-von Neumann computer architecture for the post Moore’s law era of computing. Since a main focus of the post Moore’s law era is energy-efficient computing with fewer resources and less area, neuromorphic computing contributes effectively in this research. Here in this paper, we present a memristive neuromorphic system for improved power and area efficiency. Our particular mixed-signal approach implements neural networks with spiking events in a synchronous way. Moreover, the use of nano-scale memristive devices saves both area and power in the system. We also provide device-level considerations that make the system more energy-efficient. The proposed systemmore » additionally includes synchronous digital long term plasticity, an online learning methodology that helps the system train the neural networks during the operation phase and improves the efficiency in learning considering the power consumption and area overhead.« less

Memristive Mixed-Signal Neuromorphic Systems: Energy-Efficient Learning at the Circuit-Level

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

Chakma, Gangotree; Adnan, Md Musabbir; Wyer, Austin R.

Neuromorphic computing is non-von Neumann computer architecture for the post Moore’s law era of computing. Since a main focus of the post Moore’s law era is energy-efficient computing with fewer resources and less area, neuromorphic computing contributes effectively in this research. Here in this paper, we present a memristive neuromorphic system for improved power and area efficiency. Our particular mixed-signal approach implements neural networks with spiking events in a synchronous way. Moreover, the use of nano-scale memristive devices saves both area and power in the system. We also provide device-level considerations that make the system more energy-efficient. The proposed systemmore » additionally includes synchronous digital long term plasticity, an online learning methodology that helps the system train the neural networks during the operation phase and improves the efficiency in learning considering the power consumption and area overhead.« less

Artificial neural networks as quantum associative memory

NASA Astrophysics Data System (ADS)

Hamilton, Kathleen; Schrock, Jonathan; Imam, Neena; Humble, Travis

We present results related to the recall accuracy and capacity of Hopfield networks implemented on commercially available quantum annealers. The use of Hopfield networks and artificial neural networks as content-addressable memories offer robust storage and retrieval of classical information, however, implementation of these models using currently available quantum annealers faces several challenges: the limits of precision when setting synaptic weights, the effects of spurious spin-glass states and minor embedding of densely connected graphs into fixed-connectivity hardware. We consider neural networks which are less than fully-connected, and also consider neural networks which contain multiple sparsely connected clusters. We discuss the effect of weak edge dilution on the accuracy of memory recall, and discuss how the multiple clique structure affects the storage capacity. Our work focuses on storage of patterns which can be embedded into physical hardware containing n < 1000 qubits. This work was supported by the United States Department of Defense and used resources of the Computational Research and Development Programs as Oak Ridge National Laboratory under Contract No. DE-AC0500OR22725 with the U. S. Department of Energy.

Complex Rotation Quantum Dynamic Neural Networks (CRQDNN) using Complex Quantum Neuron (CQN): Applications to time series prediction.

PubMed

Cui, Yiqian; Shi, Junyou; Wang, Zili

2015-11-01

Quantum Neural Networks (QNN) models have attracted great attention since it innovates a new neural computing manner based on quantum entanglement. However, the existing QNN models are mainly based on the real quantum operations, and the potential of quantum entanglement is not fully exploited. In this paper, we proposes a novel quantum neuron model called Complex Quantum Neuron (CQN) that realizes a deep quantum entanglement. Also, a novel hybrid networks model Complex Rotation Quantum Dynamic Neural Networks (CRQDNN) is proposed based on Complex Quantum Neuron (CQN). CRQDNN is a three layer model with both CQN and classical neurons. An infinite impulse response (IIR) filter is embedded in the Networks model to enable the memory function to process time series inputs. The Levenberg-Marquardt (LM) algorithm is used for fast parameter learning. The networks model is developed to conduct time series predictions. Two application studies are done in this paper, including the chaotic time series prediction and electronic remaining useful life (RUL) prediction. Copyright © 2015 Elsevier Ltd. All rights reserved.

Cascading a systolic array and a feedforward neural network for navigation and obstacle avoidance using potential fields

NASA Technical Reports Server (NTRS)

Plumer, Edward S.

1991-01-01

A technique is developed for vehicle navigation and control in the presence of obstacles. A potential function was devised that peaks at the surface of obstacles and has its minimum at the proper vehicle destination. This function is computed using a systolic array and is guaranteed not to have local minima. A feedfoward neural network is then used to control the steering of the vehicle using local potential field information. In this case, the vehicle is a trailer truck backing up. Previous work has demonstrated the capability of a neural network to control steering of such a trailer truck backing to a loading platform, but without obstacles. Now, the neural network was able to learn to navigate a trailer truck around obstacles while backing toward its destination. The network is trained in an obstacle free space to follow the negative gradient of the field, after which the network is able to control and navigate the truck to its target destination in a space of obstacles which may be stationary or movable.

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.

Evolution, learning, and cognition

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

Lee, Y.C.

1988-01-01

The book comprises more than fifteen articles in the areas of neural networks and connectionist systems, classifier systems, adaptive network systems, genetic algorithm, cellular automata, artificial immune systems, evolutionary genetics, cognitive science, optical computing, combinatorial optimization, and cybernetics.

Holographic neural networks versus conventional neural networks: a comparative evaluation for the classification of landmine targets in ground-penetrating radar images

NASA Astrophysics Data System (ADS)

Mudigonda, Naga R.; Kacelenga, Ray; Edwards, Mark

2004-09-01

This paper evaluates the performance of a holographic neural network in comparison with a conventional feedforward backpropagation neural network for the classification of landmine targets in ground penetrating radar images. The data used in the study was acquired from four different test sites using the landmine detection system developed by General Dynamics Canada Ltd., in collaboration with the Defense Research and Development Canada, Suffield. A set of seven features extracted for each detected alarm is used as stimulus inputs for the networks. The recall responses of the networks are then evaluated against the ground truth to declare true or false detections. The area computed under the receiver operating characteristic curve is used for comparative purposes. With a large dataset comprising of data from multiple sites, both the holographic and conventional networks showed comparable trends in recall accuracies with area values of 0.88 and 0.87, respectively. By using independent validation datasets, the holographic network"s generalization performance was observed to be better (mean area = 0.86) as compared to the conventional network (mean area = 0.82). Despite the widely publicized theoretical advantages of the holographic technology, use of more than the required number of cortical memory elements resulted in an over-fitting phenomenon of the holographic network.

An evolutionary algorithm that constructs recurrent neural networks.

PubMed

Angeline, P J; Saunders, G M; Pollack, J B

1994-01-01

Standard methods for simultaneously inducing the structure and weights of recurrent neural networks limit every task to an assumed class of architectures. Such a simplification is necessary since the interactions between network structure and function are not well understood. Evolutionary computations, which include genetic algorithms and evolutionary programming, are population-based search methods that have shown promise in many similarly complex tasks. This paper argues that genetic algorithms are inappropriate for network acquisition and describes an evolutionary program, called GNARL, that simultaneously acquires both the structure and weights for recurrent networks. GNARL's empirical acquisition method allows for the emergence of complex behaviors and topologies that are potentially excluded by the artificial architectural constraints imposed in standard network induction methods.

Neural Network Prediction of Failure of Damaged Composite Pressure Vessels from Strain Field Data Acquired by a Computer Vision Method

NASA Technical Reports Server (NTRS)

Russell, Samuel S.; Lansing, Matthew D.

1997-01-01

This effort used a new and novel method of acquiring strains called Sub-pixel Digital Video Image Correlation (SDVIC) on impact damaged Kevlar/epoxy filament wound pressure vessels during a proof test. To predict the burst pressure, the hoop strain field distribution around the impact location from three vessels was used to train a neural network. The network was then tested on additional pressure vessels. Several variations on the network were tried. The best results were obtained using a single hidden layer. SDVIC is a fill-field non-contact computer vision technique which provides in-plane deformation and strain data over a load differential. This method was used to determine hoop and axial displacements, hoop and axial linear strains, the in-plane shear strains and rotations in the regions surrounding impact sites in filament wound pressure vessels (FWPV) during proof loading by internal pressurization. The relationship between these deformation measurement values and the remaining life of the pressure vessels, however, requires a complex theoretical model or numerical simulation. Both of these techniques are time consuming and complicated. Previous results using neural network methods had been successful in predicting the burst pressure for graphite/epoxy pressure vessels based upon acoustic emission (AE) measurements in similar tests. The neural network associates the character of the AE amplitude distribution, which depends upon the extent of impact damage, with the burst pressure. Similarly, higher amounts of impact damage are theorized to cause a higher amount of strain concentration in the damage effected zone at a given pressure and result in lower burst pressures. This relationship suggests that a neural network might be able to find an empirical relationship between the SDVIC strain field data and the burst pressure, analogous to the AE method, with greater speed and simplicity than theoretical or finite element modeling. The process of testing SDVIC neural network analysis and some encouraging preliminary results are presented in this paper. Details are given concerning the processing of SDVIC output data such that it may be used as back propagation neural network (BPNN) input data. The software written to perform this processing and the BPNN algorithm are also discussed. It will be shown that, with limited training, test results indicate an average error in burst pressure prediction of approximately six percent,

Data systems and computer science programs: Overview

NASA Technical Reports Server (NTRS)

Smith, Paul H.; Hunter, Paul

1991-01-01

An external review of the Integrated Technology Plan for the Civil Space Program is presented. The topics are presented in viewgraph form and include the following: onboard memory and storage technology; advanced flight computers; special purpose flight processors; onboard networking and testbeds; information archive, access, and retrieval; visualization; neural networks; software engineering; and flight control and operations.

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

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

Ortiz-Rodriguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetrymore » with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in neural net approach it is possible to reduce the rate counts used to unfold the neutron spectrum. To evaluate these codes a computer tool called Neutron Spectrometry and dosimetry computer tool was designed. The results obtained with this package are showed. The codes here mentioned are freely available upon request to the authors.« less

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

NASA Astrophysics Data System (ADS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-07-01

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetry with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in neural net approach it is possible to reduce the rate counts used to unfold the neutron spectrum. To evaluate these codes a computer tool called Neutron Spectrometry and dosimetry computer tool was designed. The results obtained with this package are showed. The codes here mentioned are freely available upon request to the authors.

A Physics-driven Neural Networks-based Simulation System (PhyNNeSS) for multimodal interactive virtual environments involving nonlinear deformable objects

PubMed Central

De, Suvranu; Deo, Dhannanjay; Sankaranarayanan, Ganesh; Arikatla, Venkata S.

2012-01-01

Background While an update rate of 30 Hz is considered adequate for real time graphics, a much higher update rate of about 1 kHz is necessary for haptics. Physics-based modeling of deformable objects, especially when large nonlinear deformations and complex nonlinear material properties are involved, at these very high rates is one of the most challenging tasks in the development of real time simulation systems. While some specialized solutions exist, there is no general solution for arbitrary nonlinearities. Methods In this work we present PhyNNeSS - a Physics-driven Neural Networks-based Simulation System - to address this long-standing technical challenge. The first step is an off-line pre-computation step in which a database is generated by applying carefully prescribed displacements to each node of the finite element models of the deformable objects. In the next step, the data is condensed into a set of coefficients describing neurons of a Radial Basis Function network (RBFN). During real-time computation, these neural networks are used to reconstruct the deformation fields as well as the interaction forces. Results We present realistic simulation examples from interactive surgical simulation with real time force feedback. As an example, we have developed a deformable human stomach model and a Penrose-drain model used in the Fundamentals of Laparoscopic Surgery (FLS) training tool box. Conclusions A unique computational modeling system has been developed that is capable of simulating the response of nonlinear deformable objects in real time. The method distinguishes itself from previous efforts in that a systematic physics-based pre-computational step allows training of neural networks which may be used in real time simulations. We show, through careful error analysis, that the scheme is scalable, with the accuracy being controlled by the number of neurons used in the simulation. PhyNNeSS has been integrated into SoFMIS (Software Framework for Multimodal Interactive Simulation) for general use. PMID:22629108

Convolutional neural networks and face recognition task

NASA Astrophysics Data System (ADS)

Sochenkova, A.; Sochenkov, I.; Makovetskii, A.; Vokhmintsev, A.; Melnikov, A.

2017-09-01

Computer vision tasks are remaining very important for the last couple of years. One of the most complicated problems in computer vision is face recognition that could be used in security systems to provide safety and to identify person among the others. There is a variety of different approaches to solve this task, but there is still no universal solution that would give adequate results in some cases. Current paper presents following approach. Firstly, we extract an area containing face, then we use Canny edge detector. On the next stage we use convolutional neural networks (CNN) to finally solve face recognition and person identification task.

Adaptive Fuzzy Systems in Computational Intelligence

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1996-01-01

In recent years, the interest in computational intelligence techniques, which currently includes neural networks, fuzzy systems, and evolutionary programming, has grown significantly and a number of their applications have been developed in the government and industry. In future, an essential element in these systems will be fuzzy systems that can learn from experience by using neural network in refining their performances. The GARIC architecture, introduced earlier, is an example of a fuzzy reinforcement learning system which has been applied in several control domains such as cart-pole balancing, simulation of to Space Shuttle orbital operations, and tether control. A number of examples from GARIC's applications in these domains will be demonstrated.

Raingauge-Based Rainfall Nowcasting with Artificial Neural Network

NASA Astrophysics Data System (ADS)

Liong, Shie-Yui; He, Shan

2010-05-01

Rainfall forecasting and nowcasting are of great importance, for instance, in real-time flood early warning systems. Long term rainfall forecasting demands global climate, land, and sea data, thus, large computing power and storage capacity are required. Rainfall nowcasting's computing requirement, on the other hand, is much less. Rainfall nowcasting may use data captured by radar and/or weather stations. This paper presents the application of Artificial Neural Network (ANN) on rainfall nowcasting using data observed at weather and/or rainfall stations. The study focuses on the North-East monsoon period (December, January and February) in Singapore. Rainfall and weather data from ten stations, between 2000 and 2006, were selected and divided into three groups for training, over-fitting test and validation of the ANN. Several neural network architectures were tried in the study. Two architectures, Backpropagation ANN and Group Method of Data Handling ANN, yielded better rainfall nowcasting, up to two hours, than the other architectures. The obtained rainfall nowcasts were then used by a catchment model to forecast catchment runoff. The results of runoff forecast are encouraging and promising.With ANN's high computational speed, the proposed approach may be deliverable for creating the real-time flood early warning system.

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.

Real-time identification of indoor pollutant source positions based on neural network locator of contaminant sources and optimized sensor networks.

PubMed

Vukovic, Vladimir; Tabares-Velasco, Paulo Cesar; Srebric, Jelena

2010-09-01

A growing interest in security and occupant exposure to contaminants revealed a need for fast and reliable identification of contaminant sources during incidental situations. To determine potential contaminant source positions in outdoor environments, current state-of-the-art modeling methods use computational fluid dynamic simulations on parallel processors. In indoor environments, current tools match accidental contaminant distributions with cases from precomputed databases of possible concentration distributions. These methods require intensive computations in pre- and postprocessing. On the other hand, neural networks emerged as a tool for rapid concentration forecasting of outdoor environmental contaminants such as nitrogen oxides or sulfur dioxide. All of these modeling methods depend on the type of sensors used for real-time measurements of contaminant concentrations. A review of the existing sensor technologies revealed that no perfect sensor exists, but intensity of work in this area provides promising results in the near future. The main goal of the presented research study was to extend neural network modeling from the outdoor to the indoor identification of source positions, making this technology applicable to building indoor environments. The developed neural network Locator of Contaminant Sources was also used to optimize number and allocation of contaminant concentration sensors for real-time prediction of indoor contaminant source positions. Such prediction should take place within seconds after receiving real-time contaminant concentration sensor data. For the purpose of neural network training, a multizone program provided distributions of contaminant concentrations for known source positions throughout a test building. Trained networks had an output indicating contaminant source positions based on measured concentrations in different building zones. A validation case based on a real building layout and experimental data demonstrated the ability of this method to identify contaminant source positions. Future research intentions are focused on integration with real sensor networks and model improvements for much more complicated contamination scenarios.

A single network adaptive critic (SNAC) architecture for optimal control synthesis for a class of nonlinear systems.

PubMed

Padhi, Radhakant; Unnikrishnan, Nishant; Wang, Xiaohua; Balakrishnan, S N

2006-12-01

Even though dynamic programming offers an optimal control solution in a state feedback form, the method is overwhelmed by computational and storage requirements. Approximate dynamic programming implemented with an Adaptive Critic (AC) neural network structure has evolved as a powerful alternative technique that obviates the need for excessive computations and storage requirements in solving optimal control problems. In this paper, an improvement to the AC architecture, called the "Single Network Adaptive Critic (SNAC)" is presented. This approach is applicable to a wide class of nonlinear systems where the optimal control (stationary) equation can be explicitly expressed in terms of the state and costate variables. The selection of this terminology is guided by the fact that it eliminates the use of one neural network (namely the action network) that is part of a typical dual network AC setup. As a consequence, the SNAC architecture offers three potential advantages: a simpler architecture, lesser computational load and elimination of the approximation error associated with the eliminated network. In order to demonstrate these benefits and the control synthesis technique using SNAC, two problems have been solved with the AC and SNAC approaches and their computational performances are compared. One of these problems is a real-life Micro-Electro-Mechanical-system (MEMS) problem, which demonstrates that the SNAC technique is applicable to complex engineering systems.

Prediction of 5-year overall survival in cervical cancer patients treated with radical hysterectomy using computational intelligence methods.

PubMed

Obrzut, Bogdan; Kusy, Maciej; Semczuk, Andrzej; Obrzut, Marzanna; Kluska, Jacek

2017-12-12

Computational intelligence methods, including non-linear classification algorithms, can be used in medical research and practice as a decision making tool. This study aimed to evaluate the usefulness of artificial intelligence models for 5-year overall survival prediction in patients with cervical cancer treated by radical hysterectomy. The data set was collected from 102 patients with cervical cancer FIGO stage IA2-IIB, that underwent primary surgical treatment. Twenty-three demographic, tumor-related parameters and selected perioperative data of each patient were collected. The simulations involved six computational intelligence methods: the probabilistic neural network (PNN), multilayer perceptron network, gene expression programming classifier, support vector machines algorithm, radial basis function neural network and k-Means algorithm. The prediction ability of the models was determined based on the accuracy, sensitivity, specificity, as well as the area under the receiver operating characteristic curve. The results of the computational intelligence methods were compared with the results of linear regression analysis as a reference model. The best results were obtained by the PNN model. This neural network provided very high prediction ability with an accuracy of 0.892 and sensitivity of 0.975. The area under the receiver operating characteristics curve of PNN was also high, 0.818. The outcomes obtained by other classifiers were markedly worse. The PNN model is an effective tool for predicting 5-year overall survival in cervical cancer patients treated with radical hysterectomy.

Unique Applications for Artificial Neural Networks. Phase 1

DTIC Science & Technology

1991-08-08

significance. For the VRP, a problem that has received considerable attention in the literature, the new NGO-VRP methodology generates better solutions...represent the stop assignments of each route. The effect of the genetic recombinations is to make simple local exchanges to the relative positions of the...technique for representing a computer-based associative memory [Arbib, 1987]. In our routing system, the basic job of the neural network system is to accept

Improved result on stability analysis of discrete stochastic neural networks with time delay

NASA Astrophysics Data System (ADS)

Wu, Zhengguang; Su, Hongye; Chu, Jian; Zhou, Wuneng

2009-04-01

This Letter investigates the problem of exponential stability for discrete stochastic time-delay neural networks. By defining a novel Lyapunov functional, an improved delay-dependent exponential stability criterion is established in terms of linear matrix inequality (LMI) approach. Meanwhile, the computational complexity of the newly established stability condition is reduced because less variables are involved. Numerical example is given to illustrate the effectiveness and the benefits of the proposed method.

Imaging techniques in digital forensic investigation: a study using neural networks

NASA Astrophysics Data System (ADS)

Williams, Godfried

2006-09-01

Imaging techniques have been applied to a number of applications, such as translation and classification problems in medicine and defence. This paper examines the application of imaging techniques in digital forensics investigation using neural networks. A review of applications of digital image processing is presented, whiles a Pedagogical analysis of computer forensics is also highlighted. A data set describing selected images in different forms are used in the simulation and experimentation.

Boosting Contextual Information for Deep Neural Network Based Voice Activity Detection

DTIC Science & Technology

2015-02-01

multi-resolution stacking (MRS), which is a stack of ensemble classifiers. Each classifier in a building block inputs the concatenation of the predictions ...a base classifier in MRS, named boosted deep neural network (bDNN). bDNN first generates multiple base predictions from different contexts of a single...frame by only one DNN and then aggregates the base predictions for a better prediction of the frame, and it is different from computationally

Neural associative memories for the integration of language, vision and action in an autonomous agent.

PubMed

Markert, H; Kaufmann, U; Kara Kayikci, Z; Palm, G

2009-03-01

Language understanding is a long-standing problem in computer science. However, the human brain is capable of processing complex languages with seemingly no difficulties. This paper shows a model for language understanding using biologically plausible neural networks composed of associative memories. The model is able to deal with ambiguities on the single word and grammatical level. The language system is embedded into a robot in order to demonstrate the correct semantical understanding of the input sentences by letting the robot perform corresponding actions. For that purpose, a simple neural action planning system has been combined with neural networks for visual object recognition and visual attention control mechanisms.

Neuromorphic Computing for Very Large Test and Evaluation Data Analysis

DTIC Science & Technology

2014-05-01

analysis and utilization of newly available hardware- based artificial neural network chips. These two aspects of the program are complementary. The...neuromorphic architectures research focused on long term disruptive technologies with high risk but revolutionary potential. The hardware- based neural...today. Overall, hardware- based neural processing research allows us to study the fundamental system and architectural issues relevant for employing

HONTIOR - HIGHER-ORDER NEURAL NETWORK FOR TRANSFORMATION INVARIANT OBJECT RECOGNITION

NASA Technical Reports Server (NTRS)

Spirkovska, L.

1994-01-01

Neural networks have been applied in numerous fields, including transformation invariant object recognition, wherein an object is recognized despite changes in the object's position in the input field, size, or rotation. One of the more successful neural network methods used in invariant object recognition is the higher-order neural network (HONN) method. With a HONN, known relationships are exploited and the desired invariances are built directly into the architecture of the network, eliminating the need for the network to learn invariance to transformations. This results in a significant reduction in the training time required, since the network needs to be trained on only one view of each object, not on numerous transformed views. Moreover, one hundred percent accuracy is guaranteed for images characterized by the built-in distortions, providing noise is not introduced through pixelation. The program HONTIOR implements a third-order neural network having invariance to translation, scale, and in-plane rotation built directly into the architecture, Thus, for 2-D transformation invariance, the network needs only to be trained on just one view of each object. HONTIOR can also be used for 3-D transformation invariant object recognition by training the network only on a set of out-of-plane rotated views. Historically, the major drawback of HONNs has been that the size of the input field was limited to the memory required for the large number of interconnections in a fully connected network. HONTIOR solves this problem by coarse coding the input images (coding an image as a set of overlapping but offset coarser images). Using this scheme, large input fields (4096 x 4096 pixels) can easily be represented using very little virtual memory (30Mb). The HONTIOR distribution consists of three main programs. The first program contains the training and testing routines for a third-order neural network. The second program contains the same training and testing procedures as the first, but it also contains a number of functions to display and edit training and test images. Finally, the third program is an auxiliary program which calculates the included angles for a given input field size. HONTIOR is written in C language, and was originally developed for Sun3 and Sun4 series computers. Both graphic and command line versions of the program are provided. The command line version has been successfully compiled and executed both on computers running the UNIX operating system and on DEC VAX series computer running VMS. The graphic version requires the SunTools windowing environment, and therefore runs only on Sun series computers. The executable for the graphics version of HONTIOR requires 1Mb of RAM. The standard distribution medium for HONTIOR is a .25 inch streaming magnetic tape cartridge in UNIX tar format. It is also available on a 3.5 inch diskette in UNIX tar format. The package includes sample input and output data. HONTIOR was developed in 1991. Sun, Sun3 and Sun4 are trademarks of Sun Microsystems, Inc. UNIX is a registered trademark of AT&T Bell Laboratories. DEC, VAX, and VMS are trademarks of Digital Equipment Corporation.

A spiking neural network model of model-free reinforcement learning with high-dimensional sensory input and perceptual ambiguity.

PubMed

Nakano, Takashi; Otsuka, Makoto; Yoshimoto, Junichiro; Doya, Kenji

2015-01-01

A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach.

A Spiking Neural Network Model of Model-Free Reinforcement Learning with High-Dimensional Sensory Input and Perceptual Ambiguity

PubMed Central

Nakano, Takashi; Otsuka, Makoto; Yoshimoto, Junichiro; Doya, Kenji

2015-01-01

A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach. PMID:25734662

Dynamic decomposition of spatiotemporal neural signals

PubMed Central

2017-01-01

Neural signals are characterized by rich temporal and spatiotemporal dynamics that reflect the organization of cortical networks. Theoretical research has shown how neural networks can operate at different dynamic ranges that correspond to specific types of information processing. Here we present a data analysis framework that uses a linearized model of these dynamic states in order to decompose the measured neural signal into a series of components that capture both rhythmic and non-rhythmic neural activity. The method is based on stochastic differential equations and Gaussian process regression. Through computer simulations and analysis of magnetoencephalographic data, we demonstrate the efficacy of the method in identifying meaningful modulations of oscillatory signals corrupted by structured temporal and spatiotemporal noise. These results suggest that the method is particularly suitable for the analysis and interpretation of complex temporal and spatiotemporal neural signals. PMID:28558039

A neural network approach for the blind deconvolution of turbulent flows

NASA Astrophysics Data System (ADS)

Maulik, R.; San, O.

2017-11-01

We present a single-layer feedforward artificial neural network architecture trained through a supervised learning approach for the deconvolution of flow variables from their coarse grained computations such as those encountered in large eddy simulations. We stress that the deconvolution procedure proposed in this investigation is blind, i.e. the deconvolved field is computed without any pre-existing information about the filtering procedure or kernel. This may be conceptually contrasted to the celebrated approximate deconvolution approaches where a filter shape is predefined for an iterative deconvolution process. We demonstrate that the proposed blind deconvolution network performs exceptionally well in the a-priori testing of both two-dimensional Kraichnan and three-dimensional Kolmogorov turbulence and shows promise in forming the backbone of a physics-augmented data-driven closure for the Navier-Stokes equations.

Implementation of logic functions and computations by chemical kinetics

NASA Astrophysics Data System (ADS)

Hjelmfelt, A.; Ross, J.

We review our work on the computational functions of the kinetics of chemical networks. We examine spatially homogeneous networks which are based on prototypical reactions occurring in living cells and show the construction of logic gates and sequential and parallel networks. This work motivates the study of an important biochemical pathway, glycolysis, and we demonstrate that the switch that controls the flux in the direction of glycolysis or gluconeogenesis may be described as a fuzzy AND operator. We also study a spatially inhomogeneous network which shares features of theoretical and biological neural networks.

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