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.

Efficiently modeling neural networks on massively parallel computers

NASA Technical Reports Server (NTRS)

Farber, Robert M.

1993-01-01

Neural networks are a very useful tool for analyzing and modeling complex real world systems. Applying neural network simulations to real world problems generally involves large amounts of data and massive amounts of computation. To efficiently handle the computational requirements of large problems, we have implemented at Los Alamos a highly efficient neural network compiler for serial computers, vector computers, vector parallel computers, and fine grain SIMD computers such as the CM-2 connection machine. This paper describes the mapping used by the compiler to implement feed-forward backpropagation neural networks for a SIMD (Single Instruction Multiple Data) architecture parallel computer. Thinking Machines Corporation has benchmarked our code at 1.3 billion interconnects per second (approximately 3 gigaflops) on a 64,000 processor CM-2 connection machine (Singer 1990). This mapping is applicable to other SIMD computers and can be implemented on MIMD computers such as the CM-5 connection machine. Our mapping has virtually no communications overhead with the exception of the communications required for a global summation across the processors (which has a sub-linear runtime growth on the order of O(log(number of processors)). We can efficiently model very large neural networks which have many neurons and interconnects and our mapping can extend to arbitrarily large networks (within memory limitations) by merging the memory space of separate processors with fast adjacent processor interprocessor communications. This paper will consider the simulation of only feed forward neural network although this method is extendable to recurrent networks.

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.

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.

Sentence alignment using feed forward neural network.

PubMed

Fattah, Mohamed Abdel; Ren, Fuji; Kuroiwa, Shingo

2006-12-01

Parallel corpora have become an essential resource for work in multi lingual natural language processing. However, sentence aligned parallel corpora are more efficient than non-aligned parallel corpora for cross language information retrieval and machine translation applications. In this paper, we present a new approach to align sentences in bilingual parallel corpora based on feed forward neural network classifier. A feature parameter vector is extracted from the text pair under consideration. This vector contains text features such as length, punctuate score, and cognate score values. A set of manually prepared training data has been assigned to train the feed forward neural network. Another set of data was used for testing. Using this new approach, we could achieve an error reduction of 60% over length based approach when applied on English-Arabic parallel documents. Moreover this new approach is valid for any language pair and it is quite flexible approach since the feature parameter vector may contain more/less or different features than that we used in our system such as lexical match feature.

Automated target recognition and tracking using an optical pattern recognition neural network

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin

1991-01-01

The on-going development of an automatic target recognition and tracking system at the Jet Propulsion Laboratory is presented. This system is an optical pattern recognition neural network (OPRNN) that is an integration of an innovative optical parallel processor and a feature extraction based neural net training algorithm. The parallel optical processor provides high speed and vast parallelism as well as full shift invariance. The neural network algorithm enables simultaneous discrimination of multiple noisy targets in spite of their scales, rotations, perspectives, and various deformations. This fully developed OPRNN system can be effectively utilized for the automated spacecraft recognition and tracking that will lead to success in the Automated Rendezvous and Capture (AR&C) of the unmanned Cargo Transfer Vehicle (CTV). One of the most powerful optical parallel processors for automatic target recognition is the multichannel correlator. With the inherent advantages of parallel processing capability and shift invariance, multiple objects can be simultaneously recognized and tracked using this multichannel correlator. This target tracking capability can be greatly enhanced by utilizing a powerful feature extraction based neural network training algorithm such as the neocognitron. The OPRNN, currently under investigation at JPL, is constructed with an optical multichannel correlator where holographic filters have been prepared using the neocognitron training algorithm. The computation speed of the neocognitron-type OPRNN is up to 10(exp 14) analog connections/sec that enabling the OPRNN to outperform its state-of-the-art electronics counterpart by at least two orders of magnitude.

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.

Anatomically constrained neural network models for the categorization of facial expression

NASA Astrophysics Data System (ADS)

McMenamin, Brenton W.; Assadi, Amir H.

2004-12-01

The ability to recognize facial expression in humans is performed with the amygdala which uses parallel processing streams to identify the expressions quickly and accurately. Additionally, it is possible that a feedback mechanism may play a role in this process as well. Implementing a model with similar parallel structure and feedback mechanisms could be used to improve current facial recognition algorithms for which varied expressions are a source for error. An anatomically constrained artificial neural-network model was created that uses this parallel processing architecture and feedback to categorize facial expressions. The presence of a feedback mechanism was not found to significantly improve performance for models with parallel architecture. However the use of parallel processing streams significantly improved accuracy over a similar network that did not have parallel architecture. Further investigation is necessary to determine the benefits of using parallel streams and feedback mechanisms in more advanced object recognition tasks.

Anatomically constrained neural network models for the categorization of facial expression

NASA Astrophysics Data System (ADS)

McMenamin, Brenton W.; Assadi, Amir H.

2005-01-01

The ability to recognize facial expression in humans is performed with the amygdala which uses parallel processing streams to identify the expressions quickly and accurately. Additionally, it is possible that a feedback mechanism may play a role in this process as well. Implementing a model with similar parallel structure and feedback mechanisms could be used to improve current facial recognition algorithms for which varied expressions are a source for error. An anatomically constrained artificial neural-network model was created that uses this parallel processing architecture and feedback to categorize facial expressions. The presence of a feedback mechanism was not found to significantly improve performance for models with parallel architecture. However the use of parallel processing streams significantly improved accuracy over a similar network that did not have parallel architecture. Further investigation is necessary to determine the benefits of using parallel streams and feedback mechanisms in more advanced object recognition tasks.

Optical-Correlator Neural Network Based On Neocognitron

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Stoner, William W.

1994-01-01

Multichannel optical correlator implements shift-invariant, high-discrimination pattern-recognizing neural network based on paradigm of neocognitron. Selected as basic building block of this neural network because invariance under shifts is inherent advantage of Fourier optics included in optical correlators in general. Neocognitron is conceptual electronic neural-network model for recognition of visual patterns. Multilayer processing achieved by iteratively feeding back output of feature correlator to input spatial light modulator and updating Fourier filters. Neural network trained by use of characteristic features extracted from target images. Multichannel implementation enables parallel processing of large number of selected features.

Parallel protein secondary structure prediction based on neural networks.

PubMed

Zhong, Wei; Altun, Gulsah; Tian, Xinmin; Harrison, Robert; Tai, Phang C; Pan, Yi

2004-01-01

Protein secondary structure prediction has a fundamental influence on today's bioinformatics research. In this work, binary and tertiary classifiers of protein secondary structure prediction are implemented on Denoeux belief neural network (DBNN) architecture. Hydrophobicity matrix, orthogonal matrix, BLOSUM62 and PSSM (position specific scoring matrix) are experimented separately as the encoding schemes for DBNN. The experimental results contribute to the design of new encoding schemes. New binary classifier for Helix versus not Helix ( approximately H) for DBNN produces prediction accuracy of 87% when PSSM is used for the input profile. The performance of DBNN binary classifier is comparable to other best prediction methods. The good test results for binary classifiers open a new approach for protein structure prediction with neural networks. Due to the time consuming task of training the neural networks, Pthread and OpenMP are employed to parallelize DBNN in the hyperthreading enabled Intel architecture. Speedup for 16 Pthreads is 4.9 and speedup for 16 OpenMP threads is 4 in the 4 processors shared memory architecture. Both speedup performance of OpenMP and Pthread is superior to that of other research. With the new parallel training algorithm, thousands of amino acids can be processed in reasonable amount of time. Our research also shows that hyperthreading technology for Intel architecture is efficient for parallel biological algorithms.

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.

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.

An Artificial Neural Networks Method for Solving Partial Differential Equations

NASA Astrophysics Data System (ADS)

Alharbi, Abir

2010-09-01

While there already exists many analytical and numerical techniques for solving PDEs, this paper introduces an approach using artificial neural networks. The approach consists of a technique developed by combining the standard numerical method, finite-difference, with the Hopfield neural network. The method is denoted Hopfield-finite-difference (HFD). The architecture of the nets, energy function, updating equations, and algorithms are developed for the method. The HFD method has been used successfully to approximate the solution of classical PDEs, such as the Wave, Heat, Poisson and the Diffusion equations, and on a system of PDEs. The software Matlab is used to obtain the results in both tabular and graphical form. The results are similar in terms of accuracy to those obtained by standard numerical methods. In terms of speed, the parallel nature of the Hopfield nets methods makes them easier to implement on fast parallel computers while some numerical methods need extra effort for parallelization.

Glove-talk II - a neural-network interface which maps gestures to parallel formant speech synthesizer controls.

PubMed

Fels, S S; Hinton, G E

1997-01-01

Glove-Talk II is a system which translates hand gestures to speech through an adaptive interface. Hand gestures are mapped continuously to ten control parameters of a parallel formant speech synthesizer. The mapping allows the hand to act as an artificial vocal tract that produces speech in real time. This gives an unlimited vocabulary in addition to direct control of fundamental frequency and volume. Currently, the best version of Glove-Talk II uses several input devices, a parallel formant speech synthesizer, and three neural networks. The gesture-to-speech task is divided into vowel and consonant production by using a gating network to weight the outputs of a vowel and a consonant neural network. The gating network and the consonant network are trained with examples from the user. The vowel network implements a fixed user-defined relationship between hand position and vowel sound and does not require any training examples from the user. Volume, fundamental frequency, and stop consonants are produced with a fixed mapping from the input devices. With Glove-Talk II, the subject can speak slowly but with far more natural sounding pitch variations than a text-to-speech synthesizer.

Neural network based speech synthesizer: A preliminary report

NASA Technical Reports Server (NTRS)

Villarreal, James A.; Mcintire, Gary

1987-01-01

A neural net based speech synthesis project is discussed. The novelty is that the reproduced speech was extracted from actual voice recordings. In essence, the neural network learns the timing, pitch fluctuations, connectivity between individual sounds, and speaking habits unique to that individual person. The parallel distributed processing network used for this project is the generalized backward propagation network which has been modified to also learn sequences of actions or states given in a particular plan.

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.

Design of neural networks for classification of remotely sensed imagery

NASA Technical Reports Server (NTRS)

Chettri, Samir R.; Cromp, Robert F.; Birmingham, Mark

1992-01-01

Classification accuracies of a backpropagation neural network are discussed and compared with a maximum likelihood classifier (MLC) with multivariate normal class models. We have found that, because of its nonparametric nature, the neural network outperforms the MLC in this area. In addition, we discuss techniques for constructing optimal neural nets on parallel hardware like the MasPar MP-1 currently at GSFC. Other important discussions are centered around training and classification times of the two methods, and sensitivity to the training data. Finally, we discuss future work in the area of classification and neural nets.

Advanced miniature processing handware for ATR applications

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin (Inventor); Daud, Taher (Inventor); Thakoor, Anikumar (Inventor)

2003-01-01

A Hybrid Optoelectronic Neural Object Recognition System (HONORS), is disclosed, comprising two major building blocks: (1) an advanced grayscale optical correlator (OC) and (2) a massively parallel three-dimensional neural-processor. The optical correlator, with its inherent advantages in parallel processing and shift invariance, is used for target of interest (TOI) detection and segmentation. The three-dimensional neural-processor, with its robust neural learning capability, is used for target classification and identification. The hybrid optoelectronic neural object recognition system, with its powerful combination of optical processing and neural networks, enables real-time, large frame, automatic target recognition (ATR).

Glove-TalkII--a neural-network interface which maps gestures to parallel formant speech synthesizer controls.

PubMed

Fels, S S; Hinton, G E

1998-01-01

Glove-TalkII is a system which translates hand gestures to speech through an adaptive interface. Hand gestures are mapped continuously to ten control parameters of a parallel formant speech synthesizer. The mapping allows the hand to act as an artificial vocal tract that produces speech in real time. This gives an unlimited vocabulary in addition to direct control of fundamental frequency and volume. Currently, the best version of Glove-TalkII uses several input devices (including a Cyberglove, a ContactGlove, a three-space tracker, and a foot pedal), a parallel formant speech synthesizer, and three neural networks. The gesture-to-speech task is divided into vowel and consonant production by using a gating network to weight the outputs of a vowel and a consonant neural network. The gating network and the consonant network are trained with examples from the user. The vowel network implements a fixed user-defined relationship between hand position and vowel sound and does not require any training examples from the user. Volume, fundamental frequency, and stop consonants are produced with a fixed mapping from the input devices. One subject has trained to speak intelligibly with Glove-TalkII. He speaks slowly but with far more natural sounding pitch variations than a text-to-speech synthesizer.

A Decade of Neural Networks: Practical Applications and Prospects

NASA Technical Reports Server (NTRS)

Kemeny, Sabrina E.

1994-01-01

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

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.

Oscillations and chaos in neural networks: an exactly solvable model.

PubMed Central

Wang, L P; Pichler, E E; Ross, J

1990-01-01

We consider a randomly diluted higher-order network with noise, consisting of McCulloch-Pitts neurons that interact by Hebbian-type connections. For this model, exact dynamical equations are derived and solved for both parallel and random sequential updating algorithms. For parallel dynamics, we find a rich spectrum of different behaviors including static retrieving and oscillatory and chaotic phenomena in different parts of the parameter space. The bifurcation parameters include first- and second-order neuronal interaction coefficients and a rescaled noise level, which represents the combined effects of the random synaptic dilution, interference between stored patterns, and additional background noise. We show that a marked difference in terms of the occurrence of oscillations or chaos exists between neural networks with parallel and random sequential dynamics. Images PMID:2251287

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

A neural network architecture for implementation of expert systems for real time monitoring

NASA Technical Reports Server (NTRS)

Ramamoorthy, P. A.

1991-01-01

Since neural networks have the advantages of massive parallelism and simple architecture, they are good tools for implementing real time expert systems. In a rule based expert system, the antecedents of rules are in the conjunctive or disjunctive form. We constructed a multilayer feedforward type network in which neurons represent AND or OR operations of rules. Further, we developed a translator which can automatically map a given rule base into the network. Also, we proposed a new and powerful yet flexible architecture that combines the advantages of both fuzzy expert systems and neural networks. This architecture uses the fuzzy logic concepts to separate input data domains into several smaller and overlapped regions. Rule-based expert systems for time critical applications using neural networks, the automated implementation of rule-based expert systems with neural nets, and fuzzy expert systems vs. neural nets are covered.

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.

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.

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.

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.

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.

Neural networks within multi-core optic fibers

PubMed Central

Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael

2016-01-01

Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks. PMID:27383911

Neural networks within multi-core optic fibers.

PubMed

Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael

2016-07-07

Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.

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.

Classification of 2-dimensional array patterns: assembling many small neural networks is better than using a large one.

PubMed

Chen, Liang; Xue, Wei; Tokuda, Naoyuki

2010-08-01

In many pattern classification/recognition applications of artificial neural networks, an object to be classified is represented by a fixed sized 2-dimensional array of uniform type, which corresponds to the cells of a 2-dimensional grid of the same size. A general neural network structure, called an undistricted neural network, which takes all the elements in the array as inputs could be used for problems such as these. However, a districted neural network can be used to reduce the training complexity. A districted neural network usually consists of two levels of sub-neural networks. Each of the lower level neural networks, called a regional sub-neural network, takes the elements in a region of the array as its inputs and is expected to output a temporary class label, called an individual opinion, based on the partial information of the entire array. The higher level neural network, called an assembling sub-neural network, uses the outputs (opinions) of regional sub-neural networks as inputs, and by consensus derives the label decision for the object. Each of the sub-neural networks can be trained separately and thus the training is less expensive. The regional sub-neural networks can be trained and performed in parallel and independently, therefore a high speed can be achieved. We prove theoretically in this paper, using a simple model, that a districted neural network is actually more stable than an undistricted neural network in noisy environments. We conjecture that the result is valid for all neural networks. This theory is verified by experiments involving gender classification and human face recognition. We conclude that a districted neural network is highly recommended for neural network applications in recognition or classification of 2-dimensional array patterns in highly noisy environments. Copyright (c) 2010 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.

Hybrid optoelectronic neural networks using a mutually pumped phase-conjugate mirror

NASA Astrophysics Data System (ADS)

Dunning, G. J.; Owechko, Y.; Soffer, B. H.

1991-06-01

A method is described for interconnecting hybrid optoelectronic neural networks by using a mutually pumped phase conjugate mirror (MP-PCM). In this method, cross talk due to Bragg degeneracies is greatly reduced by storing each weight among many spatially and angularly multiplexed gratings. The effective weight throughput is increased by the parallel updating of weights using outer-product learning. Experiments demonstrated a high degree of interconnectivity between adjacent pixels. A diagram is presented showing the architecture for the optoelectronic neural network using an MP-PCM.

Programmable synaptic devices for electronic neural nets

NASA Technical Reports Server (NTRS)

Moopenn, A.; Thakoor, A. P.

1990-01-01

The architecture, design, and operational characteristics of custom VLSI and thin film synaptic devices are described. The devices include CMOS-based synaptic chips containing 1024 reprogrammable synapses with a 6-bit dynamic range, and nonvolatile, write-once, binary synaptic arrays based on memory switching in hydrogenated amorphous silicon films. Their suitability for embodiment of fully parallel and analog neural hardware is discussed. Specifically, a neural network solution to an assignment problem of combinatorial global optimization, implemented in fully parallel hardware using the synaptic chips, is described. The network's ability to provide optimal and near optimal solutions over a time scale of few neuron time constants has been demonstrated and suggests a speedup improvement of several orders of magnitude over conventional search methods.

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.

A review of evidence of health benefit from artificial neural networks in medical intervention.

PubMed

Lisboa, P J G

2002-01-01

The purpose of this review is to assess the evidence of healthcare benefits involving the application of artificial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The rĵle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and artificial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention.

Recognition of Telugu characters using neural networks.

PubMed

Sukhaswami, M B; Seetharamulu, P; Pujari, A K

1995-09-01

The aim of the present work is to recognize printed and handwritten Telugu characters using artificial neural networks (ANNs). Earlier work on recognition of Telugu characters has been done using conventional pattern recognition techniques. We make an initial attempt here of using neural networks for recognition with the aim of improving upon earlier methods which do not perform effectively in the presence of noise and distortion in the characters. The Hopfield model of neural network working as an associative memory is chosen for recognition purposes initially. Due to limitation in the capacity of the Hopfield neural network, we propose a new scheme named here as the Multiple Neural Network Associative Memory (MNNAM). The limitation in storage capacity has been overcome by combining multiple neural networks which work in parallel. It is also demonstrated that the Hopfield network is suitable for recognizing noisy printed characters as well as handwritten characters written by different "hands" in a variety of styles. Detailed experiments have been carried out using several learning strategies and results are reported. It is shown here that satisfactory recognition is possible using the proposed strategy. A detailed preprocessing scheme of the Telugu characters from digitized documents is also described.

A neural-network approach to robotic control

NASA Technical Reports Server (NTRS)

Graham, D. P. W.; Deleuterio, G. M. T.

1993-01-01

An artificial neural-network paradigm for the control of robotic systems is presented. The approach is based on the Cerebellar Model Articulation Controller created by James Albus and incorporates several extensions. First, recognizing the essential structure of multibody equations of motion, two parallel modules are used that directly reflect the dynamical characteristics of multibody systems. Second, the architecture of the proposed network is imbued with a self-organizational capability which improves efficiency and accuracy. Also, the networks can be arranged in hierarchical fashion with each subsequent network providing finer and finer resolution.

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.

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.

Learning in Neural Networks: VLSI Implementation Strategies

NASA Technical Reports Server (NTRS)

Duong, Tuan Anh

1995-01-01

Fully-parallel hardware neural network implementations may be applied to high-speed recognition, classification, and mapping tasks in areas such as vision, or can be used as low-cost self-contained units for tasks such as error detection in mechanical systems (e.g. autos). Learning is required not only to satisfy application requirements, but also to overcome hardware-imposed limitations such as reduced dynamic range of connections.

The Development of a Research Environment for Neural Networks: Instantiating Neocognitions

DTIC Science & Technology

1990-12-21

interactive activation to adaptive reso- nance. Cognitive Science, 11:23-63. Reprinted in (Grossberg, 1988). Grossberg, S., editor (1988). Neural...higher order correlation network. Physica 22D, pages 276-306. Rosenblatt, F. (1962). Principles of Neurodynamics : Perceptrons and the Theory of Brain...and the PDP Research Group (1986b). Parallel Dis- tributed Processing: Ezplorations in the Microstructures of Cognition , volume 1: Foun- dations

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.

Optical resonators and neural networks

NASA Astrophysics Data System (ADS)

Anderson, Dana Z.

1986-08-01

It may be possible to implement neural network models using continuous field optical architectures. These devices offer the inherent parallelism of propagating waves and an information density in principle dictated by the wavelength of light and the quality of the bulk optical elements. Few components are needed to construct a relatively large equivalent network. Various associative memories based on optical resonators have been demonstrated in the literature, a ring resonator design is discussed in detail here. Information is stored in a holographic medium and recalled through a competitive processes in the gain medium supplying energy to the ring rsonator. The resonator memory is the first realized example of a neural network function implemented with this kind of architecture.

A Stochastic Spiking Neural Network for Virtual Screening.

PubMed

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

2018-04-01

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

Learning, memory, and the role of neural network architecture.

PubMed

Hermundstad, Ann M; Brown, Kevin S; Bassett, Danielle S; Carlson, Jean M

2011-06-01

The performance of information processing systems, from artificial neural networks to natural neuronal ensembles, depends heavily on the underlying system architecture. In this study, we compare the performance of parallel and layered network architectures during sequential tasks that require both acquisition and retention of information, thereby identifying tradeoffs between learning and memory processes. During the task of supervised, sequential function approximation, networks produce and adapt representations of external information. Performance is evaluated by statistically analyzing the error in these representations while varying the initial network state, the structure of the external information, and the time given to learn the information. We link performance to complexity in network architecture by characterizing local error landscape curvature. We find that variations in error landscape structure give rise to tradeoffs in performance; these include the ability of the network to maximize accuracy versus minimize inaccuracy and produce specific versus generalizable representations of information. Parallel networks generate smooth error landscapes with deep, narrow minima, enabling them to find highly specific representations given sufficient time. While accurate, however, these representations are difficult to generalize. In contrast, layered networks generate rough error landscapes with a variety of local minima, allowing them to quickly find coarse representations. Although less accurate, these representations are easily adaptable. The presence of measurable performance tradeoffs in both layered and parallel networks has implications for understanding the behavior of a wide variety of natural and artificial learning systems.

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.

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.

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.

Hardware Neural Network for a Visual Inspection System

NASA Astrophysics Data System (ADS)

Chun, Seungwoo; Hayakawa, Yoshihiro; Nakajima, Koji

The visual inspection of defects in products is heavily dependent on human experience and instinct. In this situation, it is difficult to reduce the production costs and to shorten the inspection time and hence the total process time. Consequently people involved in this area desire an automatic inspection system. In this paper, we propose a hardware neural network, which is expected to provide high-speed operation for automatic inspection of products. Since neural networks can learn, this is a suitable method for self-adjustment of criteria for classification. To achieve high-speed operation, we use parallel and pipelining techniques. Furthermore, we use a piecewise linear function instead of a conventional activation function in order to save hardware resources. Consequently, our proposed hardware neural network achieved 6GCPS and 2GCUPS, which in our test sample proved to be sufficiently fast.

Rotation and scale change invariant point pattern relaxation matching by the Hopfield neural network

NASA Astrophysics Data System (ADS)

Sang, Nong; Zhang, Tianxu

1997-12-01

Relaxation matching is one of the most relevant methods for image matching. The original relaxation matching technique using point patterns is sensitive to rotations and scale changes. We improve the original point pattern relaxation matching technique to be invariant to rotations and scale changes. A method that makes the Hopfield neural network perform this matching process is discussed. An advantage of this is that the relaxation matching process can be performed in real time with the neural network's massively parallel capability to process information. Experimental results with large simulated images demonstrate the effectiveness and feasibility of the method to perform point patten relaxation matching invariant to rotations and scale changes and the method to perform this matching by the Hopfield neural network. In addition, we show that the method presented can be tolerant to small random error.

Infant Joint Attention, Neural Networks and Social Cognition

PubMed Central

Mundy, Peter; Jarrold, William

2010-01-01

Neural network models of attention can provide a unifying approach to the study of human cognitive and emotional development (Posner & Rothbart, 2007). This paper we argue that a neural networks approach to the infant development of joint attention can inform our understanding of the nature of human social learning, symbolic thought process and social cognition. At its most basic, joint attention involves the capacity to coordinate one’s own visual attention with that of another person. We propose that joint attention development involves increments in the capacity to engage in simultaneous or parallel processing of information about one’s own attention and the attention of other people. Infant practice with joint attention is both a consequence and organizer of the development of a distributed and integrated brain network involving frontal and parietal cortical systems. This executive distributed network first serves to regulate the capacity of infants to respond to and direct the overt behavior of other people in order to share experience with others through the social coordination of visual attention. In this paper we describe this parallel and distributed neural network model of joint attention development and discuss two hypotheses that stem from this model. One is that activation of this distributed network during coordinated attention enhances to depth of information processing and encoding beginning in the first year of life. We also propose that with development joint attention becomes internalized as the capacity to socially coordinate mental attention to internal representations. As this occurs the executive joint attention network makes vital contributions to the development of human symbolic thinking and social cognition. PMID:20884172

A neural network for controlling the configuration of frame structure with elastic members

NASA Technical Reports Server (NTRS)

Tsutsumi, Kazuyoshi

1989-01-01

A neural network for controlling the configuration of frame structure with elastic members is proposed. In the present network, the structure is modeled not by using the relative angles of the members but by using the distances between the joint locations alone. The relationship between the environment and the joints is also defined by their mutual distances. The analog neural network attains the reaching motion of the manipulator as a minimization problem of the energy constructed by the distances between the joints, the target, and the obstacles. The network can generate not only the final but also the transient configurations and the trajectory. This framework with flexibility and parallelism is very suitable for controlling the Space Telerobotic systems with many degrees of freedom.

Massively-Parallel Architectures for Automatic Recognition of Visual Speech Signals

DTIC Science & Technology

1988-10-12

Secusrity Clamifieation, Nlassively-Parallel Architectures for Automa ic Recognitio of Visua, Speech Signals 12. PERSONAL AUTHOR(S) Terrence J...characteristics of speech from tJhe, visual speech signals. Neural networks have been trained on a database of vowels. The rqw images of faces , aligned and...images of faces , aligned and preprocessed, were used as input to these network which were trained to estimate the corresponding envelope of the

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.

Biologically driven neural platform invoking parallel electrophoretic separation and urinary metabolite screening.

PubMed

Page, Tessa; Nguyen, Huong Thi Huynh; Hilts, Lindsey; Ramos, Lorena; Hanrahan, Grady

2012-06-01

This work reveals a computational framework for parallel electrophoretic separation of complex biological macromolecules and model urinary metabolites. More specifically, the implementation of a particle swarm optimization (PSO) algorithm on a neural network platform for multiparameter optimization of multiplexed 24-capillary electrophoresis technology with UV detection is highlighted. Two experimental systems were examined: (1) separation of purified rabbit metallothioneins and (2) separation of model toluene urinary metabolites and selected organic acids. Results proved superior to the use of neural networks employing standard back propagation when examining training error, fitting response, and predictive abilities. Simulation runs were obtained as a result of metaheuristic examination of the global search space with experimental responses in good agreement with predicted values. Full separation of selected analytes was realized after employing optimal model conditions. This framework provides guidance for the application of metaheuristic computational tools to aid in future studies involving parallel chemical separation and screening. Adaptable pseudo-code is provided to enable users of varied software packages and modeling framework to implement the PSO algorithm for their desired use.

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

PubMed

Zenke, Friedemann; Gerstner, Wulfram

2014-01-01

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

Analog Delta-Back-Propagation Neural-Network Circuitry

NASA Technical Reports Server (NTRS)

Eberhart, Silvio

1990-01-01

Changes in synapse weights due to circuit drifts suppressed. Proposed fully parallel analog version of electronic neural-network processor based on delta-back-propagation algorithm. Processor able to "learn" when provided with suitable combinations of inputs and enforced outputs. Includes programmable resistive memory elements (corresponding to synapses), conductances (synapse weights) adjusted during learning. Buffer amplifiers, summing circuits, and sample-and-hold circuits arranged in layers of electronic neurons in accordance with delta-back-propagation algorithm.

The control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle using a CMAC neural network.

PubMed

Harmon, Frederick G; Frank, Andrew A; Joshi, Sanjay S

2005-01-01

A Simulink model, a propulsion energy optimization algorithm, and a CMAC controller were developed for a small parallel hybrid-electric unmanned aerial vehicle (UAV). The hybrid-electric UAV is intended for military, homeland security, and disaster-monitoring missions involving intelligence, surveillance, and reconnaissance (ISR). The Simulink model is a forward-facing simulation program used to test different control strategies. The flexible energy optimization algorithm for the propulsion system allows relative importance to be assigned between the use of gasoline, electricity, and recharging. A cerebellar model arithmetic computer (CMAC) neural network approximates the energy optimization results and is used to control the parallel hybrid-electric propulsion system. The hybrid-electric UAV with the CMAC controller uses 67.3% less energy than a two-stroke gasoline-powered UAV during a 1-h ISR mission and 37.8% less energy during a longer 3-h ISR mission.

Rapid automated classification of anesthetic depth levels using GPU based parallelization of neural networks.

PubMed

Peker, Musa; Şen, Baha; Gürüler, Hüseyin

2015-02-01

The effect of anesthesia on the patient is referred to as depth of anesthesia. Rapid classification of appropriate depth level of anesthesia is a matter of great importance in surgical operations. Similarly, accelerating classification algorithms is important for the rapid solution of problems in the field of biomedical signal processing. However numerous, time-consuming mathematical operations are required when training and testing stages of the classification algorithms, especially in neural networks. In this study, to accelerate the process, parallel programming and computing platform (Nvidia CUDA) facilitates dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU) was utilized. The system was employed to detect anesthetic depth level on related electroencephalogram (EEG) data set. This dataset is rather complex and large. Moreover, the achieving more anesthetic levels with rapid response is critical in anesthesia. The proposed parallelization method yielded high accurate classification results in a faster time.

Neural Networks For Demodulation Of Phase-Modulated Signals

NASA Technical Reports Server (NTRS)

Altes, Richard A.

1995-01-01

Hopfield neural networks proposed for demodulating quadrature phase-shift-keyed (QPSK) signals carrying digital information. Networks solve nonlinear integral equations prior demodulation circuits cannot solve. Consists of set of N operational amplifiers connected in parallel, with weighted feedback from output terminal of each amplifier to input terminals of other amplifiers. Used to solve signal processing problems. Implemented as analog very-large-scale integrated circuit that achieves rapid convergence. Alternatively, implemented as digital simulation of such circuit. Also used to improve phase estimation performance over that of phase-locked loop.

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.

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.

Associative memory in an analog iterated-map neural network

NASA Astrophysics Data System (ADS)

Marcus, C. M.; Waugh, F. R.; Westervelt, R. M.

1990-03-01

The behavior of an analog neural network with parallel dynamics is studied analytically and numerically for two associative-memory learning algorithms, the Hebb rule and the pseudoinverse rule. Phase diagrams in the parameter space of analog gain β and storage ratio α are presented. For both learning rules, the networks have large ``recall'' phases in which retrieval states exist and convergence to a fixed point is guaranteed by a global stability criterion. We also demonstrate numerically that using a reduced analog gain increases the probability of recall starting from a random initial state. This phenomenon is comparable to thermal annealing used to escape local minima but has the advantage of being deterministic, and therefore easily implemented in electronic hardware. Similarities and differences between analog neural networks and networks with two-state neurons at finite temperature are also discussed.

Infant joint attention, neural networks and social cognition.

PubMed

Mundy, Peter; Jarrold, William

2010-01-01

Neural network models of attention can provide a unifying approach to the study of human cognitive and emotional development (Posner & Rothbart, 2007). In this paper we argue that a neural network approach to the infant development of joint attention can inform our understanding of the nature of human social learning, symbolic thought process and social cognition. At its most basic, joint attention involves the capacity to coordinate one's own visual attention with that of another person. We propose that joint attention development involves increments in the capacity to engage in simultaneous or parallel processing of information about one's own attention and the attention of other people. Infant practice with joint attention is both a consequence and an organizer of the development of a distributed and integrated brain network involving frontal and parietal cortical systems. This executive distributed network first serves to regulate the capacity of infants to respond to and direct the overt behavior of other people in order to share experience with others through the social coordination of visual attention. In this paper we describe this parallel and distributed neural network model of joint attention development and discuss two hypotheses that stem from this model. One is that activation of this distributed network during coordinated attention enhances the depth of information processing and encoding beginning in the first year of life. We also propose that with development, joint attention becomes internalized as the capacity to socially coordinate mental attention to internal representations. As this occurs the executive joint attention network makes vital contributions to the development of human symbolic thinking and social cognition. Copyright © 2010 Elsevier Ltd. All rights reserved.

Lidar detection of underwater objects using a neuro-SVM-based architecture.

PubMed

Mitra, Vikramjit; Wang, Chia-Jiu; Banerjee, Satarupa

2006-05-01

This paper presents a neural network architecture using a support vector machine (SVM) as an inference engine (IE) for classification of light detection and ranging (Lidar) data. Lidar data gives a sequence of laser backscatter intensities obtained from laser shots generated from an airborne object at various altitudes above the earth surface. Lidar data is pre-filtered to remove high frequency noise. As the Lidar shots are taken from above the earth surface, it has some air backscatter information, which is of no importance for detecting underwater objects. Because of these, the air backscatter information is eliminated from the data and a segment of this data is subsequently selected to extract features for classification. This is then encoded using linear predictive coding (LPC) and polynomial approximation. The coefficients thus generated are used as inputs to the two branches of a parallel neural architecture. The decisions obtained from the two branches are vector multiplied and the result is fed to an SVM-based IE that presents the final inference. Two parallel neural architectures using multilayer perception (MLP) and hybrid radial basis function (HRBF) are considered in this paper. The proposed structure fits the Lidar data classification task well due to the inherent classification efficiency of neural networks and accurate decision-making capability of SVM. A Bayesian classifier and a quadratic classifier were considered for the Lidar data classification task but they failed to offer high prediction accuracy. Furthermore, a single-layered artificial neural network (ANN) classifier was also considered and it failed to offer good accuracy. The parallel ANN architecture proposed in this paper offers high prediction accuracy (98.9%) and is found to be the most suitable architecture for the proposed task of Lidar data classification.

Software Design Challenges in Time Series Prediction Systems Using Parallel Implementation of Artificial Neural Networks.

PubMed

Manikandan, Narayanan; Subha, Srinivasan

2016-01-01

Software development life cycle has been characterized by destructive disconnects between activities like planning, analysis, design, and programming. Particularly software developed with prediction based results is always a big challenge for designers. Time series data forecasting like currency exchange, stock prices, and weather report are some of the areas where an extensive research is going on for the last three decades. In the initial days, the problems with financial analysis and prediction were solved by statistical models and methods. For the last two decades, a large number of Artificial Neural Networks based learning models have been proposed to solve the problems of financial data and get accurate results in prediction of the future trends and prices. This paper addressed some architectural design related issues for performance improvement through vectorising the strengths of multivariate econometric time series models and Artificial Neural Networks. It provides an adaptive approach for predicting exchange rates and it can be called hybrid methodology for predicting exchange rates. This framework is tested for finding the accuracy and performance of parallel algorithms used.

Software Design Challenges in Time Series Prediction Systems Using Parallel Implementation of Artificial Neural Networks

PubMed Central

Manikandan, Narayanan; Subha, Srinivasan

2016-01-01

Software development life cycle has been characterized by destructive disconnects between activities like planning, analysis, design, and programming. Particularly software developed with prediction based results is always a big challenge for designers. Time series data forecasting like currency exchange, stock prices, and weather report are some of the areas where an extensive research is going on for the last three decades. In the initial days, the problems with financial analysis and prediction were solved by statistical models and methods. For the last two decades, a large number of Artificial Neural Networks based learning models have been proposed to solve the problems of financial data and get accurate results in prediction of the future trends and prices. This paper addressed some architectural design related issues for performance improvement through vectorising the strengths of multivariate econometric time series models and Artificial Neural Networks. It provides an adaptive approach for predicting exchange rates and it can be called hybrid methodology for predicting exchange rates. This framework is tested for finding the accuracy and performance of parallel algorithms used. PMID:26881271

Simulation of an array-based neural net model

NASA Technical Reports Server (NTRS)

Barnden, John A.

1987-01-01

Research in cognitive science suggests that much of cognition involves the rapid manipulation of complex data structures. However, it is very unclear how this could be realized in neural networks or connectionist systems. A core question is: how could the interconnectivity of items in an abstract-level data structure be neurally encoded? The answer appeals mainly to positional relationships between activity patterns within neural arrays, rather than directly to neural connections in the traditional way. The new method was initially devised to account for abstract symbolic data structures, but it also supports cognitively useful spatial analogue, image-like representations. As the neural model is based on massive, uniform, parallel computations over 2D arrays, the massively parallel processor is a convenient tool for simulation work, although there are complications in using the machine to the fullest advantage. An MPP Pascal simulation program for a small pilot version of the model is running.

Edge-preserving image compression for magnetic-resonance images using dynamic associative neural networks (DANN)-based neural networks

NASA Astrophysics Data System (ADS)

Wan, Tat C.; Kabuka, Mansur R.

1994-05-01

With the tremendous growth in imaging applications and the development of filmless radiology, the need for compression techniques that can achieve high compression ratios with user specified distortion rates becomes necessary. Boundaries and edges in the tissue structures are vital for detection of lesions and tumors, which in turn requires the preservation of edges in the image. The proposed edge preserving image compressor (EPIC) combines lossless compression of edges with neural network compression techniques based on dynamic associative neural networks (DANN), to provide high compression ratios with user specified distortion rates in an adaptive compression system well-suited to parallel implementations. Improvements to DANN-based training through the use of a variance classifier for controlling a bank of neural networks speed convergence and allow the use of higher compression ratios for `simple' patterns. The adaptation and generalization capabilities inherent in EPIC also facilitate progressive transmission of images through varying the number of quantization levels used to represent compressed patterns. Average compression ratios of 7.51:1 with an averaged average mean squared error of 0.0147 were achieved.

Overview of artificial neural networks.

PubMed

Zou, Jinming; Han, Yi; So, Sung-Sau

2008-01-01

The artificial neural network (ANN), or simply neural network, is a machine learning method evolved from the idea of simulating the human brain. The data explosion in modem drug discovery research requires sophisticated analysis methods to uncover the hidden causal relationships between single or multiple responses and a large set of properties. The ANN is one of many versatile tools to meet the demand in drug discovery modeling. Compared to a traditional regression approach, the ANN is capable of modeling complex nonlinear relationships. The ANN also has excellent fault tolerance and is fast and highly scalable with parallel processing. This chapter introduces the background of ANN development and outlines the basic concepts crucially important for understanding more sophisticated ANN. Several commonly used learning methods and network setups are discussed briefly at the end of the chapter.

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.

High-speed all-optical DNA local sequence alignment based on a three-dimensional artificial neural network.

PubMed

Maleki, Ehsan; Babashah, Hossein; Koohi, Somayyeh; Kavehvash, Zahra

2017-07-01

This paper presents an optical processing approach for exploring a large number of genome sequences. Specifically, we propose an optical correlator for global alignment and an extended moiré matching technique for local analysis of spatially coded DNA, whose output is fed to a novel three-dimensional artificial neural network for local DNA alignment. All-optical implementation of the proposed 3D artificial neural network is developed and its accuracy is verified in Zemax. Thanks to its parallel processing capability, the proposed structure performs local alignment of 4 million sequences of 150 base pairs in a few seconds, which is much faster than its electrical counterparts, such as the basic local alignment search tool.

Pulse-coupled neural network implementation in FPGA

NASA Astrophysics Data System (ADS)

Waldemark, Joakim T. A.; Lindblad, Thomas; Lindsey, Clark S.; Waldemark, Karina E.; Oberg, Johnny; Millberg, Mikael

1998-03-01

Pulse Coupled Neural Networks (PCNN) are biologically inspired neural networks, mainly based on studies of the visual cortex of small mammals. The PCNN is very well suited as a pre- processor for image processing, particularly in connection with object isolation, edge detection and segmentation. Several implementations of PCNN on von Neumann computers, as well as on special parallel processing hardware devices (e.g. SIMD), exist. However, these implementations are not as flexible as required for many applications. Here we present an implementation in Field Programmable Gate Arrays (FPGA) together with a performance analysis. The FPGA hardware implementation may be considered a platform for further, extended implementations and easily expanded into various applications. The latter may include advanced on-line image analysis with close to real-time performance.

Inversion of quasi-3D DC resistivity imaging data using artificial neural networks

NASA Astrophysics Data System (ADS)

Neyamadpour, Ahmad; Wan Abdullah, W. A. T.; Taib, Samsudin

2010-02-01

The objective of this paper is to investigate the applicability of artificial neural networks in inverting quasi-3D DC resistivity imaging data. An electrical resistivity imaging survey was carried out along seven parallel lines using a dipole-dipole array to confirm the validation of the results of an inversion using an artificial neural network technique. The model used to produce synthetic data to train the artificial neural network was a homogeneous medium of 100Ωm resistivity with an embedded anomalous body of 1000Ωm resistivity. The network was trained using 21 datasets (comprising 12159 data points) and tested on another 11 synthetic datasets (comprising 6369 data points) and on real field data. Another 24 test datasets (comprising 13896 data points) consisting of different resistivities for the background and the anomalous bodies were used in order to test the interpolation and extrapolation of network properties. Different learning paradigms were tried in the training process of the neural network, with the resilient propagation paradigm being the most efficient. The number of nodes, hidden layers, and efficient values for learning rate and momentum coefficient have been studied. Although a significant correlation between results of the neural network and the conventional robust inversion technique was found, the ANN results show more details of the subsurface structure, and the RMS misfits for the results of the neural network are less than seen with conventional methods. The interpreted results show that the trained network was able to invert quasi-3D electrical resistivity imaging data obtained by dipole-dipole configuration both rapidly and accurately.

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

A General Connectionist Model of Attitude Structure and Change: The ACS (Attitudes as Constraint Satisfaction) Model

ERIC Educational Resources Information Center

Monroe, Brian M.; Read, Stephen J.

2008-01-01

A localist, parallel constraint satisfaction, artificial neural network model is presented that accounts for a broad collection of attitude and attitude-change phenomena. The network represents the attitude object and cognitions and beliefs related to the attitude, as well as how to integrate a persuasive message into this network. Short-term…

Parallel Distributed Processing at 25: Further Explorations in the Microstructure of Cognition

ERIC Educational Resources Information Center

Rogers, Timothy T.; McClelland, James L.

2014-01-01

This paper introduces a special issue of "Cognitive Science" initiated on the 25th anniversary of the publication of "Parallel Distributed Processing" (PDP), a two-volume work that introduced the use of neural network models as vehicles for understanding cognition. The collection surveys the core commitments of the PDP…

Center for Parallel Optimization.

DTIC Science & Technology

1996-03-19

A NEW OPTIMIZATION BASED APPROACH TO IMPROVING GENERALIZATION IN MACHINE LEARNING HAS BEEN PROPOSED AND COMPUTATIONALLY VALIDATED ON SIMPLE LINEAR MODELS AS WELL AS ON HIGHLY NONLINEAR SYSTEMS SUCH AS NEURAL NETWORKS.

3-DIMENSIONAL Optoelectronic

NASA Astrophysics Data System (ADS)

Krishnamoorthy, Ashok Venketaraman

This thesis covers the design, analysis, optimization, and implementation of optoelectronic (N,M,F) networks. (N,M,F) networks are generic space-division networks that are well suited to implementation using optoelectronic integrated circuits and free-space optical interconnects. An (N,M,F) networks consists of N input channels each having a fanout F_{rm o}, M output channels each having a fanin F_{rm i}, and Log_{rm K}(N/F) stages of K x K switches. The functionality of the fanout, switching, and fanin stages depends on the specific application. Three applications of optoelectronic (N,M,F) networks are considered. The first is an optoelectronic (N,1,1) content -addressable memory system that achieves associative recall on two-dimensional images retrieved from a parallel-access optical memory. The design and simulation of the associative memory are discussed, and an experimental emulation of a prototype system using images from a parallel-readout optical disk is presented. The system design provides superior performance to existing electronic content-addressable memory chips in terms of capacity and search rate, and uses readily available optical disk and VLSI technologies. Next, a scalable optoelectronic (N,M,F) neural network that uses free-space holographic optical interconnects is presented. The neural architecture minimizes the number of optical transmitters needed, and provides accurate electronic fanin with low signal skew, and dendritic-type fan-in processing capability in a compact layout. Optimal data-encoding methods and circuit techniques are discussed. The implementation of an prototype optoelectronic neural system, and its application to a simple recognition task is demonstrated. Finally, the design, analysis, and optimization of a (N,N,F) self-routing, packet-switched multistage interconnection network is described. The network is suitable for parallel computing and broadband switching applications. The tradeoff between optical and electronic interconnects is examined quantitatively by varying the electronic switch size K. The performance of the (N,N,F) network versus the fanning parameter F, is also analyzed. It is shown that the optoelectronic (N,N,F) networks provide a range of performance-cost alternatives, and offer superior performance-per-cost to fully electronic switching networks and to previous networks designs.

Computer model of a reverberant and parallel circuit coupling

NASA Astrophysics Data System (ADS)

Kalil, Camila de Andrade; de Castro, Maria Clícia Stelling; Cortez, Célia Martins

2017-11-01

The objective of the present study was to deepen the knowledge about the functioning of the neural circuits by implementing a signal transmission model using the Graph Theory in a small network of neurons composed of an interconnected reverberant and parallel circuit, in order to investigate the processing of the signals in each of them and the effects on the output of the network. For this, a program was developed in C language and simulations were done using neurophysiological data obtained in the literature.

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

PubMed

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

2015-01-01

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

A 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.

Neural network control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle

NASA Astrophysics Data System (ADS)

Harmon, Frederick G.

2005-11-01

Parallel hybrid-electric propulsion systems would be beneficial for small unmanned aerial vehicles (UAVs) used for military, homeland security, and disaster-monitoring missions. The benefits, due to the hybrid and electric-only modes, include increased time-on-station and greater range as compared to electric-powered UAVs and stealth modes not available with gasoline-powered UAVs. This dissertation contributes to the research fields of small unmanned aerial vehicles, hybrid-electric propulsion system control, and intelligent control. A conceptual design of a small UAV with a parallel hybrid-electric propulsion system is provided. The UAV is intended for intelligence, surveillance, and reconnaissance (ISR) missions. A conceptual design reveals the trade-offs that must be considered to take advantage of the hybrid-electric propulsion system. The resulting hybrid-electric propulsion system is a two-point design that includes an engine primarily sized for cruise speed and an electric motor and battery pack that are primarily sized for a slower endurance speed. The electric motor provides additional power for take-off, climbing, and acceleration and also serves as a generator during charge-sustaining operation or regeneration. The intelligent control of the hybrid-electric propulsion system is based on an instantaneous optimization algorithm that generates a hyper-plane from the nonlinear efficiency maps for the internal combustion engine, electric motor, and lithium-ion battery pack. The hyper-plane incorporates charge-depletion and charge-sustaining strategies. The optimization algorithm is flexible and allows the operator/user to assign relative importance between the use of gasoline, electricity, and recharging depending on the intended mission. A MATLAB/Simulink model was developed to test the control algorithms. The Cerebellar Model Arithmetic Computer (CMAC) associative memory neural network is applied to the control of the UAVs parallel hybrid-electric propulsion system. The CMAC neural network approximates the hyper-plane generated from the instantaneous optimization algorithm and produces torque commands for the internal combustion engine and electric motor. The CMAC neural network controller saves on the required memory as compared to a large look-up table by two orders of magnitude. The CMAC controller also prevents the need to compute a hyper-plane or complex logic every time step.

How to cluster in parallel with neural networks

NASA Technical Reports Server (NTRS)

Kamgar-Parsi, Behzad; Gualtieri, J. A.; Devaney, Judy E.; Kamgar-Parsi, Behrooz

1988-01-01

Partitioning a set of N patterns in a d-dimensional metric space into K clusters - in a way that those in a given cluster are more similar to each other than the rest - is a problem of interest in astrophysics, image analysis and other fields. As there are approximately K(N)/K (factorial) possible ways of partitioning the patterns among K clusters, finding the best solution is beyond exhaustive search when N is large. Researchers show that this problem can be formulated as an optimization problem for which very good, but not necessarily optimal solutions can be found by using a neural network. To do this the network must start from many randomly selected initial states. The network is simulated on the MPP (a 128 x 128 SIMD array machine), where researchers use the massive parallelism not only in solving the differential equations that govern the evolution of the network, but also by starting the network from many initial states at once, thus obtaining many solutions in one run. Researchers obtain speedups of two to three orders of magnitude over serial implementations and the promise through Analog VLSI implementations of speedups comensurate with human perceptual abilities.

Neural synchronization as a hypothetical explanation of the psychoanalytic unconscious.

PubMed

Ceylan, Mehmet Emin; Dönmez, Aslıhan; Ünsalver, Barış Önen; Evrensel, Alper

2016-02-01

Cognitive scientists have tried to explain the neural mechanisms of unconscious mental states such as coma, epileptic seizures, and anesthesia-induced unconsciousness. However these types of unconscious states are different from the psychoanalytic unconscious. In this review, we aim to present our hypothesis about the neural correlates underlying psychoanalytic unconscious. To fulfill this aim, we firstly review the previous explanations about the neural correlates of conscious and unconscious mental states, such as brain oscillations, synchronicity of neural networks, and cognitive binding. By doing so, we hope to lay a neuroscientific ground for our hypothesis about neural correlates of psychoanalytic unconscious; parallel but unsynchronized neural networks between different layers of consciousness and unconsciousness. Next, we propose a neuroscientific mechanism about how the repressed mental events reach the conscious awareness; the lock of neural synchronization between two mental layers of conscious and unconscious. At the last section, we will discuss the data about schizophrenia as a clinical example of our proposed hypothesis. Copyright © 2015 Elsevier Inc. All rights reserved.

Wavelet Transforms in Parallel Image Processing

DTIC Science & Technology

1994-01-27

NUMBER OF PAGES Object Segmentation, Texture Segmentation, Image Compression, Image 137 Halftoning , Neural Network, Parallel Algorithms, 2D and 3D...Vector Quantization of Wavelet Transform Coefficients ........ ............................. 57 B.1.f Adaptive Image Halftoning based on Wavelet...application has been directed to the adaptive image halftoning . The gray information at a pixel, including its gray value and gradient, is represented by

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.

Neural Networks and other Techniques for Fault Identification and Isolation of Aircraft Systems

NASA Technical Reports Server (NTRS)

Innocenti, M.; Napolitano, M.

2003-01-01

Fault identification, isolation, and accomodation have become critical issues in the overall performance of advanced aircraft systems. Neural Networks have shown to be a very attractive alternative to classic adaptation methods for identification and control of non-linear dynamic systems. The purpose of this paper is to show the improvements in neural network applications achievable through the use of learning algorithms more efficient than the classic Back-Propagation, and through the implementation of the neural schemes in parallel hardware. The results of the analysis of a scheme for Sensor Failure, Detection, Identification and Accommodation (SFDIA) using experimental flight data of a research aircraft model are presented. Conventional approaches to the problem are based on observers and Kalman Filters while more recent methods are based on neural approximators. The work described in this paper is based on the use of neural networks (NNs) as on-line learning non-linear approximators. The performances of two different neural architectures were compared. The first architecture is based on a Multi Layer Perceptron (MLP) NN trained with the Extended Back Propagation algorithm (EBPA). The second architecture is based on a Radial Basis Function (RBF) NN trained with the Extended-MRAN (EMRAN) algorithms. In addition, alternative methods for communications links fault detection and accomodation are presented, relative to multiple unmanned aircraft applications.

Self-organization in neural networks - Applications in structural optimization

NASA Technical Reports Server (NTRS)

Hajela, Prabhat; Fu, B.; Berke, Laszlo

1993-01-01

The present paper discusses the applicability of ART (Adaptive Resonance Theory) networks, and the Hopfield and Elastic networks, in problems of structural analysis and design. A characteristic of these network architectures is the ability to classify patterns presented as inputs into specific categories. The categories may themselves represent distinct procedural solution strategies. The paper shows how this property can be adapted in the structural analysis and design problem. A second application is the use of Hopfield and Elastic networks in optimization problems. Of particular interest are problems characterized by the presence of discrete and integer design variables. The parallel computing architecture that is typical of neural networks is shown to be effective in such problems. Results of preliminary implementations in structural design problems are also included in the paper.

A comparison between HMLP and HRBF for attitude control.

PubMed

Fortuna, L; Muscato, G; Xibilia, M G

2001-01-01

In this paper the problem of controlling the attitude of a rigid body, such as a Spacecraft, in three-dimensional space is approached by introducing two new control strategies developed in hypercomplex algebra. The proposed approaches are based on two parallel controllers, both derived in quaternion algebra. The first is a feedback controller of the proportional derivative (PD) type, while the second is a feedforward controller, which is implemented either by means of a hypercomplex multilayer perceptron (HMLP) neural network or by means of a hypercomplex radial basis function (HRBF) neural network. Several simulations show the performance of the two approaches. The results are also compared with a classical PD controller and with an adaptive controller, showing the improvements obtained by using neural networks, especially when an external disturbance acts on the rigid body. In particular the HMLP network gave better results when considering trajectories not presented during the learning phase.

Change detection in multitemporal synthetic aperture radar images using dual-channel convolutional neural network

NASA Astrophysics Data System (ADS)

Liu, Tao; Li, Ying; Cao, Ying; Shen, Qiang

2017-10-01

This paper proposes a model of dual-channel convolutional neural network (CNN) that is designed for change detection in SAR images, in an effort to acquire higher detection accuracy and lower misclassification rate. This network model contains two parallel CNN channels, which can extract deep features from two multitemporal SAR images. For comparison and validation, the proposed method is tested along with other change detection algorithms on both simulated SAR images and real-world SAR images captured by different sensors. The experimental results demonstrate that the presented method outperforms the state-of-the-art techniques by a considerable margin.

Optimal mapping of neural-network learning on message-passing multicomputers

NASA Technical Reports Server (NTRS)

Chu, Lon-Chan; Wah, Benjamin W.

1992-01-01

A minimization of learning-algorithm completion time is sought in the present optimal-mapping study of the learning process in multilayer feed-forward artificial neural networks (ANNs) for message-passing multicomputers. A novel approximation algorithm for mappings of this kind is derived from observations of the dominance of a parallel ANN algorithm over its communication time. Attention is given to both static and dynamic mapping schemes for systems with static and dynamic background workloads, as well as to experimental results obtained for simulated mappings on multicomputers with dynamic background workloads.

Low Temperature Performance of High-Speed Neural Network Circuits

NASA Technical Reports Server (NTRS)

Duong, T.; Tran, M.; Daud, T.; Thakoor, A.

1995-01-01

Artificial neural networks, derived from their biological counterparts, offer a new and enabling computing paradigm specially suitable for such tasks as image and signal processing with feature classification/object recognition, global optimization, and adaptive control. When implemented in fully parallel electronic hardware, it offers orders of magnitude speed advantage. Basic building blocks of the new architecture are the processing elements called neurons implemented as nonlinear operational amplifiers with sigmoidal transfer function, interconnected through weighted connections called synapses implemented using circuitry for weight storage and multiply functions either in an analog, digital, or hybrid scheme.

Non-parametric analysis of LANDSAT maps using neural nets and parallel computers

NASA Technical Reports Server (NTRS)

Salu, Yehuda; Tilton, James

1991-01-01

Nearest neighbor approaches and a new neural network, the Binary Diamond, are used for the classification of images of ground pixels obtained by LANDSAT satellite. The performances are evaluated by comparing classifications of a scene in the vicinity of Washington DC. The problem of optimal selection of categories is addressed as a step in the classification process.

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.

Brainlab: A Python Toolkit to Aid in the Design, Simulation, and Analysis of Spiking Neural Networks with the NeoCortical Simulator.

PubMed

Drewes, Rich; Zou, Quan; Goodman, Philip H

2009-01-01

Neuroscience modeling experiments often involve multiple complex neural network and cell model variants, complex input stimuli and input protocols, followed by complex data analysis. Coordinating all this complexity becomes a central difficulty for the experimenter. The Python programming language, along with its extensive library packages, has emerged as a leading "glue" tool for managing all sorts of complex programmatic tasks. This paper describes a toolkit called Brainlab, written in Python, that leverages Python's strengths for the task of managing the general complexity of neuroscience modeling experiments. Brainlab was also designed to overcome the major difficulties of working with the NCS (NeoCortical Simulator) environment in particular. Brainlab is an integrated model-building, experimentation, and data analysis environment for the powerful parallel spiking neural network simulator system NCS.

Brainlab: A Python Toolkit to Aid in the Design, Simulation, and Analysis of Spiking Neural Networks with the NeoCortical Simulator

PubMed Central

Drewes, Rich; Zou, Quan; Goodman, Philip H.

2008-01-01

Neuroscience modeling experiments often involve multiple complex neural network and cell model variants, complex input stimuli and input protocols, followed by complex data analysis. Coordinating all this complexity becomes a central difficulty for the experimenter. The Python programming language, along with its extensive library packages, has emerged as a leading “glue” tool for managing all sorts of complex programmatic tasks. This paper describes a toolkit called Brainlab, written in Python, that leverages Python's strengths for the task of managing the general complexity of neuroscience modeling experiments. Brainlab was also designed to overcome the major difficulties of working with the NCS (NeoCortical Simulator) environment in particular. Brainlab is an integrated model-building, experimentation, and data analysis environment for the powerful parallel spiking neural network simulator system NCS. PMID:19506707

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

PubMed Central

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

2017-01-01

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

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

PubMed

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

2017-01-01

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

Phase synchronization motion and neural coding in dynamic transmission of neural information.

PubMed

Wang, Rubin; Zhang, Zhikang; Qu, Jingyi; Cao, Jianting

2011-07-01

In order to explore the dynamic characteristics of neural coding in the transmission of neural information in the brain, a model of neural network consisting of three neuronal populations is proposed in this paper using the theory of stochastic phase dynamics. Based on the model established, the neural phase synchronization motion and neural coding under spontaneous activity and stimulation are examined, for the case of varying network structure. Our analysis shows that, under the condition of spontaneous activity, the characteristics of phase neural coding are unrelated to the number of neurons participated in neural firing within the neuronal populations. The result of numerical simulation supports the existence of sparse coding within the brain, and verifies the crucial importance of the magnitudes of the coupling coefficients in neural information processing as well as the completely different information processing capability of neural information transmission in both serial and parallel couplings. The result also testifies that under external stimulation, the bigger the number of neurons in a neuronal population, the more the stimulation influences the phase synchronization motion and neural coding evolution in other neuronal populations. We verify numerically the experimental result in neurobiology that the reduction of the coupling coefficient between neuronal populations implies the enhancement of lateral inhibition function in neural networks, with the enhancement equivalent to depressing neuronal excitability threshold. Thus, the neuronal populations tend to have a stronger reaction under the same stimulation, and more neurons get excited, leading to more neurons participating in neural coding and phase synchronization motion.

PCSIM: A Parallel Simulation Environment for Neural Circuits Fully Integrated with Python

PubMed Central

Pecevski, Dejan; Natschläger, Thomas; Schuch, Klaus

2008-01-01

The Parallel Circuit SIMulator (PCSIM) is a software package for simulation of neural circuits. It is primarily designed for distributed simulation of large scale networks of spiking point neurons. Although its computational core is written in C++, PCSIM's primary interface is implemented in the Python programming language, which is a powerful programming environment and allows the user to easily integrate the neural circuit simulator with data analysis and visualization tools to manage the full neural modeling life cycle. The main focus of this paper is to describe PCSIM's full integration into Python and the benefits thereof. In particular we will investigate how the automatically generated bidirectional interface and PCSIM's object-oriented modular framework enable the user to adopt a hybrid modeling approach: using and extending PCSIM's functionality either employing pure Python or C++ and thus combining the advantages of both worlds. Furthermore, we describe several supplementary PCSIM packages written in pure Python and tailored towards setting up and analyzing neural simulations. PMID:19543450

Real-Time Decentralized Neural Control via Backstepping for a Robotic Arm Powered by Industrial Servomotors.

PubMed

Vazquez, Luis A; Jurado, Francisco; Castaneda, Carlos E; Santibanez, Victor

2018-02-01

This paper presents a continuous-time decentralized neural control scheme for trajectory tracking of a two degrees of freedom direct drive vertical robotic arm. A decentralized recurrent high-order neural network (RHONN) structure is proposed to identify online, in a series-parallel configuration and using the filtered error learning law, the dynamics of the plant. Based on the RHONN subsystems, a local neural controller is derived via backstepping approach. The effectiveness of the decentralized neural controller is validated on a robotic arm platform, of our own design and unknown parameters, which uses industrial servomotors to drive the joints.

Neural Networks: An Overview

DTIC Science & Technology

1991-05-01

Hall, 1967. 6. Rosenblatt, F., Principles of Neurodynamics , Spartan Books, 1962. 7. Minsky, M. and Papert, S., Perceptrons, MIT Press, Revised Edition...sentations by Error Propagation, Rumelhart and McClelland (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition , Vol

Neural network for control of rearrangeable Clos networks.

PubMed

Park, Y K; Cherkassky, V

1994-09-01

Rapid evolution in the field of communication networks requires high speed switching technologies. This involves a high degree of parallelism in switching control and routing performed at the hardware level. The multistage crossbar networks have always been attractive to switch designers. In this paper a neural network approach to controlling a three-stage Clos network in real time is proposed. This controller provides optimal routing of communication traffic requests on a call-by-call basis by rearranging existing connections, with a minimum length of rearrangement sequence so that a new blocked call request can be accommodated. The proposed neural network controller uses Paull's rearrangement algorithm, along with the special (least used) switch selection rule in order to minimize the length of rearrangement sequences. The functional behavior of our model is verified by simulations and it is shown that the convergence time required for finding an optimal solution is constant, regardless of the switching network size. The performance is evaluated for random traffic with various traffic loads. Simulation results show that applying the least used switch selection rule increases the efficiency in switch rearrangements, reducing the network convergence time. The implementation aspects are also discussed to show the feasibility of the proposed approach.

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

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

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.

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.

NeuroFlow: A General Purpose Spiking Neural Network Simulation Platform using Customizable Processors.

PubMed

Cheung, Kit; Schultz, Simon R; Luk, Wayne

2015-01-01

NeuroFlow is a scalable spiking neural network simulation platform for off-the-shelf high performance computing systems using customizable hardware processors such as Field-Programmable Gate Arrays (FPGAs). Unlike multi-core processors and application-specific integrated circuits, the processor architecture of NeuroFlow can be redesigned and reconfigured to suit a particular simulation to deliver optimized performance, such as the degree of parallelism to employ. The compilation process supports using PyNN, a simulator-independent neural network description language, to configure the processor. NeuroFlow supports a number of commonly used current or conductance based neuronal models such as integrate-and-fire and Izhikevich models, and the spike-timing-dependent plasticity (STDP) rule for learning. A 6-FPGA system can simulate a network of up to ~600,000 neurons and can achieve a real-time performance of 400,000 neurons. Using one FPGA, NeuroFlow delivers a speedup of up to 33.6 times the speed of an 8-core processor, or 2.83 times the speed of GPU-based platforms. With high flexibility and throughput, NeuroFlow provides a viable environment for large-scale neural network simulation.

NeuroFlow: A General Purpose Spiking Neural Network Simulation Platform using Customizable Processors

PubMed Central

Cheung, Kit; Schultz, Simon R.; Luk, Wayne

2016-01-01

NeuroFlow is a scalable spiking neural network simulation platform for off-the-shelf high performance computing systems using customizable hardware processors such as Field-Programmable Gate Arrays (FPGAs). Unlike multi-core processors and application-specific integrated circuits, the processor architecture of NeuroFlow can be redesigned and reconfigured to suit a particular simulation to deliver optimized performance, such as the degree of parallelism to employ. The compilation process supports using PyNN, a simulator-independent neural network description language, to configure the processor. NeuroFlow supports a number of commonly used current or conductance based neuronal models such as integrate-and-fire and Izhikevich models, and the spike-timing-dependent plasticity (STDP) rule for learning. A 6-FPGA system can simulate a network of up to ~600,000 neurons and can achieve a real-time performance of 400,000 neurons. Using one FPGA, NeuroFlow delivers a speedup of up to 33.6 times the speed of an 8-core processor, or 2.83 times the speed of GPU-based platforms. With high flexibility and throughput, NeuroFlow provides a viable environment for large-scale neural network simulation. PMID:26834542

Muscle networks: Connectivity analysis of EMG activity during postural control

NASA Astrophysics Data System (ADS)

Boonstra, Tjeerd W.; Danna-Dos-Santos, Alessander; Xie, Hong-Bo; Roerdink, Melvyn; Stins, John F.; Breakspear, Michael

2015-12-01

Understanding the mechanisms that reduce the many degrees of freedom in the musculoskeletal system remains an outstanding challenge. Muscle synergies reduce the dimensionality and hence simplify the control problem. How this is achieved is not yet known. Here we use network theory to assess the coordination between multiple muscles and to elucidate the neural implementation of muscle synergies. We performed connectivity analysis of surface EMG from ten leg muscles to extract the muscle networks while human participants were standing upright in four different conditions. We observed widespread connectivity between muscles at multiple distinct frequency bands. The network topology differed significantly between frequencies and between conditions. These findings demonstrate how muscle networks can be used to investigate the neural circuitry of motor coordination. The presence of disparate muscle networks across frequencies suggests that the neuromuscular system is organized into a multiplex network allowing for parallel and hierarchical control structures.

SNAVA-A real-time multi-FPGA multi-model spiking neural network simulation architecture.

PubMed

Sripad, Athul; Sanchez, Giovanny; Zapata, Mireya; Pirrone, Vito; Dorta, Taho; Cambria, Salvatore; Marti, Albert; Krishnamourthy, Karthikeyan; Madrenas, Jordi

2018-01-01

Spiking Neural Networks (SNN) for Versatile Applications (SNAVA) simulation platform is a scalable and programmable parallel architecture that supports real-time, large-scale, multi-model SNN computation. This parallel architecture is implemented in modern Field-Programmable Gate Arrays (FPGAs) devices to provide high performance execution and flexibility to support large-scale SNN models. Flexibility is defined in terms of programmability, which allows easy synapse and neuron implementation. This has been achieved by using a special-purpose Processing Elements (PEs) for computing SNNs, and analyzing and customizing the instruction set according to the processing needs to achieve maximum performance with minimum resources. The parallel architecture is interfaced with customized Graphical User Interfaces (GUIs) to configure the SNN's connectivity, to compile the neuron-synapse model and to monitor SNN's activity. Our contribution intends to provide a tool that allows to prototype SNNs faster than on CPU/GPU architectures but significantly cheaper than fabricating a customized neuromorphic chip. This could be potentially valuable to the computational neuroscience and neuromorphic engineering communities. Copyright © 2017 Elsevier Ltd. All rights reserved.

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.

Vision-Based Navigation and Parallel Computing

DTIC Science & Technology

1990-08-01

33 5.8. Behizad Kamgar-Parsi and Behrooz Karngar-Parsi,"On Problem 5- lving with Hopfield Neural Networks", CAR-TR-462, CS-TR...Second. the hypercube connections support logarithmic implementations of fundamental parallel algorithms. such as grid permutations and scan...the pose space. It also uses a set of virtual processors to represent an orthogonal projection grid , and projections of the six dimensional pose space

Data fusion with artificial neural networks (ANN) for classification of earth surface from microwave satellite measurements

NASA Technical Reports Server (NTRS)

Lure, Y. M. Fleming; Grody, Norman C.; Chiou, Y. S. Peter; Yeh, H. Y. Michael

1993-01-01

A data fusion system with artificial neural networks (ANN) is used for fast and accurate classification of five earth surface conditions and surface changes, based on seven SSMI multichannel microwave satellite measurements. The measurements include brightness temperatures at 19, 22, 37, and 85 GHz at both H and V polarizations (only V at 22 GHz). The seven channel measurements are processed through a convolution computation such that all measurements are located at same grid. Five surface classes including non-scattering surface, precipitation over land, over ocean, snow, and desert are identified from ground-truth observations. The system processes sensory data in three consecutive phases: (1) pre-processing to extract feature vectors and enhance separability among detected classes; (2) preliminary classification of Earth surface patterns using two separate and parallely acting classifiers: back-propagation neural network and binary decision tree classifiers; and (3) data fusion of results from preliminary classifiers to obtain the optimal performance in overall classification. Both the binary decision tree classifier and the fusion processing centers are implemented by neural network architectures. The fusion system configuration is a hierarchical neural network architecture, in which each functional neural net will handle different processing phases in a pipelined fashion. There is a total of around 13,500 samples for this analysis, of which 4 percent are used as the training set and 96 percent as the testing set. After training, this classification system is able to bring up the detection accuracy to 94 percent compared with 88 percent for back-propagation artificial neural networks and 80 percent for binary decision tree classifiers. The neural network data fusion classification is currently under progress to be integrated in an image processing system at NOAA and to be implemented in a prototype of a massively parallel and dynamically reconfigurable Modular Neural Ring (MNR).

Modeling and simulation of permanent magnet synchronous motor based on neural network control strategy

NASA Astrophysics Data System (ADS)

Luo, Bingyang; Chi, Shangjie; Fang, Man; Li, Mengchao

2017-03-01

Permanent magnet synchronous motor is used widely in industry, the performance requirements wouldn't be met by adopting traditional PID control in some of the occasions with high requirements. In this paper, a hybrid control strategy - nonlinear neural network PID and traditional PID parallel control are adopted. The high stability and reliability of traditional PID was combined with the strong adaptive ability and robustness of neural network. The permanent magnet synchronous motor will get better control performance when switch different working modes according to different controlled object conditions. As the results showed, the speed response adopting the composite control strategy in this paper was faster than the single control strategy. And in the case of sudden disturbance, the recovery time adopting the composite control strategy designed in this paper was shorter, the recovery ability and the robustness were stronger.

Goal-seeking neural net for recall and recognition

NASA Astrophysics Data System (ADS)

Omidvar, Omid M.

1990-07-01

Neural networks have been used to mimic cognitive processes which take place in animal brains. The learning capability inherent in neural networks makes them suitable candidates for adaptive tasks such as recall and recognition. The synaptic reinforcements create a proper condition for adaptation, which results in memorization, formation of perception, and higher order information processing activities. In this research a model of a goal seeking neural network is studied and the operation of the network with regard to recall and recognition is analyzed. In these analyses recall is defined as retrieval of stored information where little or no matching is involved. On the other hand recognition is recall with matching; therefore it involves memorizing a piece of information with complete presentation. This research takes the generalized view of reinforcement in which all the signals are potential reinforcers. The neuronal response is considered to be the source of the reinforcement. This local approach to adaptation leads to the goal seeking nature of the neurons as network components. In the proposed model all the synaptic strengths are reinforced in parallel while the reinforcement among the layers is done in a distributed fashion and pipeline mode from the last layer inward. A model of complex neuron with varying threshold is developed to account for inhibitory and excitatory behavior of real neuron. A goal seeking model of a neural network is presented. This network is utilized to perform recall and recognition tasks. The performance of the model with regard to the assigned tasks is presented.

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.

Identification and interpretation of patterns in rocket engine data: Artificial intelligence and neural network approaches

NASA Technical Reports Server (NTRS)

Ali, Moonis; Whitehead, Bruce; Gupta, Uday K.; Ferber, Harry

1989-01-01

This paper describes an expert system which is designed to perform automatic data analysis, identify anomalous events, and determine the characteristic features of these events. We have employed both artificial intelligence and neural net approaches in the design of this expert system. The artificial intelligence approach is useful because it provides (1) the use of human experts' knowledge of sensor behavior and faulty engine conditions in interpreting data; (2) the use of engine design knowledge and physical sensor locations in establishing relationships among the events of multiple sensors; (3) the use of stored analysis of past data of faulty engine conditions; and (4) the use of knowledge-based reasoning in distinguishing sensor failure from actual faults. The neural network approach appears promising because neural nets (1) can be trained on extremely noisy data and produce classifications which are more robust under noisy conditions than other classification techniques; (2) avoid the necessity of noise removal by digital filtering and therefore avoid the need to make assumptions about frequency bands or other signal characteristics of anomalous behavior; (3) can, in effect, generate their own feature detectors based on the characteristics of the sensor data used in training; and (4) are inherently parallel and therefore are potentially implementable in special-purpose parallel hardware.

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

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

Morris, A.S.; Khemaissia, S.

2000-01-01

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

Optical Interconnection Via Computer-Generated Holograms

NASA Technical Reports Server (NTRS)

Liu, Hua-Kuang; Zhou, Shaomin

1995-01-01

Method of free-space optical interconnection developed for data-processing applications like parallel optical computing, neural-network computing, and switching in optical communication networks. In method, multiple optical connections between multiple sources of light in one array and multiple photodetectors in another array made via computer-generated holograms in electrically addressed spatial light modulators (ESLMs). Offers potential advantages of massive parallelism, high space-bandwidth product, high time-bandwidth product, low power consumption, low cross talk, and low time skew. Also offers advantage of programmability with flexibility of reconfiguration, including variation of strengths of optical connections in real time.

Structure and function of complex brain networks

PubMed Central

Sporns, Olaf

2013-01-01

An increasing number of theoretical and empirical studies approach the function of the human brain from a network perspective. The analysis of brain networks is made feasible by the development of new imaging acquisition methods as well as new tools from graph theory and dynamical systems. This review surveys some of these methodological advances and summarizes recent findings on the architecture of structural and functional brain networks. Studies of the structural connectome reveal several modules or network communities that are interlinked by hub regions mediating communication processes between modules. Recent network analyses have shown that network hubs form a densely linked collective called a “rich club,” centrally positioned for attracting and dispersing signal traffic. In parallel, recordings of resting and task-evoked neural activity have revealed distinct resting-state networks that contribute to functions in distinct cognitive domains. Network methods are increasingly applied in a clinical context, and their promise for elucidating neural substrates of brain and mental disorders is discussed. PMID:24174898

Function Prediction Using Recurrent Neural Networks

DTIC Science & Technology

1991-12-01

of Neurodynamics : Perceptrons and the Theory of Brain Mechanisms. Washington: Spartan Books, 1959. 16. Ruck, Dennis W. Characterization of Multilayer...Computing, 2(2) (Fall 1990). 18. Rumelhart, David E., et al. Parallel Distributed Processing: Explorations in the Microstructure of Cognition , Volume 1

An FPGA-Based Massively Parallel Neuromorphic Cortex Simulator

PubMed Central

Wang, Runchun M.; Thakur, Chetan S.; van Schaik, André

2018-01-01

This paper presents a massively parallel and scalable neuromorphic cortex simulator designed for simulating large and structurally connected spiking neural networks, such as complex models of various areas of the cortex. The main novelty of this work is the abstraction of a neuromorphic architecture into clusters represented by minicolumns and hypercolumns, analogously to the fundamental structural units observed in neurobiology. Without this approach, simulating large-scale fully connected networks needs prohibitively large memory to store look-up tables for point-to-point connections. Instead, we use a novel architecture, based on the structural connectivity in the neocortex, such that all the required parameters and connections can be stored in on-chip memory. The cortex simulator can be easily reconfigured for simulating different neural networks without any change in hardware structure by programming the memory. A hierarchical communication scheme allows one neuron to have a fan-out of up to 200 k neurons. As a proof-of-concept, an implementation on one Altera Stratix V FPGA was able to simulate 20 million to 2.6 billion leaky-integrate-and-fire (LIF) neurons in real time. We verified the system by emulating a simplified auditory cortex (with 100 million neurons). This cortex simulator achieved a low power dissipation of 1.62 μW per neuron. With the advent of commercially available FPGA boards, our system offers an accessible and scalable tool for the design, real-time simulation, and analysis of large-scale spiking neural networks. PMID:29692702

An FPGA-Based Massively Parallel Neuromorphic Cortex Simulator.

PubMed

Wang, Runchun M; Thakur, Chetan S; van Schaik, André

2018-01-01

This paper presents a massively parallel and scalable neuromorphic cortex simulator designed for simulating large and structurally connected spiking neural networks, such as complex models of various areas of the cortex. The main novelty of this work is the abstraction of a neuromorphic architecture into clusters represented by minicolumns and hypercolumns, analogously to the fundamental structural units observed in neurobiology. Without this approach, simulating large-scale fully connected networks needs prohibitively large memory to store look-up tables for point-to-point connections. Instead, we use a novel architecture, based on the structural connectivity in the neocortex, such that all the required parameters and connections can be stored in on-chip memory. The cortex simulator can be easily reconfigured for simulating different neural networks without any change in hardware structure by programming the memory. A hierarchical communication scheme allows one neuron to have a fan-out of up to 200 k neurons. As a proof-of-concept, an implementation on one Altera Stratix V FPGA was able to simulate 20 million to 2.6 billion leaky-integrate-and-fire (LIF) neurons in real time. We verified the system by emulating a simplified auditory cortex (with 100 million neurons). This cortex simulator achieved a low power dissipation of 1.62 μW per neuron. With the advent of commercially available FPGA boards, our system offers an accessible and scalable tool for the design, real-time simulation, and analysis of large-scale spiking neural networks.

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.

(abstract) A High Throughput 3-D Inner Product Processor

NASA Technical Reports Server (NTRS)

Daud, Tuan

1996-01-01

A particularily challenging image processing application is the real time scene acquisition and object discrimination. It requires spatio-temporal recognition of point and resolved objects at high speeds with parallel processing algorithms. Neural network paradigms provide fine grain parallism and, when implemented in hardware, offer orders of magnitude speed up. However, neural networks implemented on a VLSI chip are planer architectures capable of efficient processing of linear vector signals rather than 2-D images. Therefore, for processing of images, a 3-D stack of neural-net ICs receiving planar inputs and consuming minimal power are required. Details of the circuits with chip architectures will be described with need to develop ultralow-power electronics. Further, use of the architecture in a system for high-speed processing will be illustrated.

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

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

Design of a universal two-layered neural network derived from the PLI theory

NASA Astrophysics Data System (ADS)

Hu, Chia-Lun J.

2004-05-01

The if-and-only-if (IFF) condition that a set of M analog-to-digital vector-mapping relations can be learned by a one-layered-feed-forward neural network (OLNN) is that all the input analog vectors dichotomized by the i-th output bit must be positively, linearly independent, or PLI. If they are not PLI, then the OLNN just cannot learn no matter what learning rules is employed because the solution of the connection matrix does not exist mathematically. However, in this case, one can still design a parallel-cascaded, two-layered, perceptron (PCTLP) to acheive this general mapping goal. The design principle of this "universal" neural network is derived from the major mathematical properties of the PLI theory - changing the output bits of the dependent relations existing among the dichotomized input vectors to make the PLD relations PLI. Then with a vector concatenation technique, the required mapping can still be learned by this PCTLP system with very high efficiency. This paper will report in detail the mathematical derivation of the general design principle and the design procedures of the PCTLP neural network system. It then will be verified in general by a practical numerical example.

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

PubMed

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

2017-06-01

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

Binary synaptic connections based on memory switching in a-Si:H for artificial neural networks

NASA Technical Reports Server (NTRS)

Thakoor, A. P.; Lamb, J. L.; Moopenn, A.; Khanna, S. K.

1987-01-01

A scheme for nonvolatile associative electronic memory storage with high information storage density is proposed which is based on neural network models and which uses a matrix of two-terminal passive interconnections (synapses). It is noted that the massive parallelism in the architecture would require the ON state of a synaptic connection to be unusually weak (highly resistive). Memory switching using a-Si:H along with ballast resistors patterned from amorphous Ge-metal alloys is investigated for a binary programmable read only memory matrix. The fabrication of a 1600 synapse test array of uniform connection strengths and a-Si:H switching elements is discussed.

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 Neural Network Architecture For Rapid Model Indexing In Computer Vision Systems

NASA Astrophysics Data System (ADS)

Pawlicki, Ted

1988-03-01

Models of objects stored in memory have been shown to be useful for guiding the processing of computer vision systems. A major consideration in such systems, however, is how stored models are initially accessed and indexed by the system. As the number of stored models increases, the time required to search memory for the correct model becomes high. Parallel distributed, connectionist, neural networks' have been shown to have appealing content addressable memory properties. This paper discusses an architecture for efficient storage and reference of model memories stored as stable patterns of activity in a parallel, distributed, connectionist, neural network. The emergent properties of content addressability and resistance to noise are exploited to perform indexing of the appropriate object centered model from image centered primitives. The system consists of three network modules each of which represent information relative to a different frame of reference. The model memory network is a large state space vector where fields in the vector correspond to ordered component objects and relative, object based spatial relationships between the component objects. The component assertion network represents evidence about the existence of object primitives in the input image. It establishes local frames of reference for object primitives relative to the image based frame of reference. The spatial relationship constraint network is an intermediate representation which enables the association between the object based and the image based frames of reference. This intermediate level represents information about possible object orderings and establishes relative spatial relationships from the image based information in the component assertion network below. It is also constrained by the lawful object orderings in the model memory network above. The system design is consistent with current psychological theories of recognition by component. It also seems to support Marr's notions of hierarchical indexing. (i.e. the specificity, adjunct, and parent indices) It supports the notion that multiple canonical views of an object may have to be stored in memory to enable its efficient identification. The use of variable fields in the state space vectors appears to keep the number of required nodes in the network down to a tractable number while imposing a semantic value on different areas of the state space. This semantic imposition supports an interface between the analogical aspects of neural networks and the propositional paradigms of symbolic processing.

DynaSim: A MATLAB Toolbox for Neural Modeling and Simulation

PubMed Central

Sherfey, Jason S.; Soplata, Austin E.; Ardid, Salva; Roberts, Erik A.; Stanley, David A.; Pittman-Polletta, Benjamin R.; Kopell, Nancy J.

2018-01-01

DynaSim is an open-source MATLAB/GNU Octave toolbox for rapid prototyping of neural models and batch simulation management. It is designed to speed up and simplify the process of generating, sharing, and exploring network models of neurons with one or more compartments. Models can be specified by equations directly (similar to XPP or the Brian simulator) or by lists of predefined or custom model components. The higher-level specification supports arbitrarily complex population models and networks of interconnected populations. DynaSim also includes a large set of features that simplify exploring model dynamics over parameter spaces, running simulations in parallel using both multicore processors and high-performance computer clusters, and analyzing and plotting large numbers of simulated data sets in parallel. It also includes a graphical user interface (DynaSim GUI) that supports full functionality without requiring user programming. The software has been implemented in MATLAB to enable advanced neural modeling using MATLAB, given its popularity and a growing interest in modeling neural systems. The design of DynaSim incorporates a novel schema for model specification to facilitate future interoperability with other specifications (e.g., NeuroML, SBML), simulators (e.g., NEURON, Brian, NEST), and web-based applications (e.g., Geppetto) outside MATLAB. DynaSim is freely available at http://dynasimtoolbox.org. This tool promises to reduce barriers for investigating dynamics in large neural models, facilitate collaborative modeling, and complement other tools being developed in the neuroinformatics community. PMID:29599715

DynaSim: A MATLAB Toolbox for Neural Modeling and Simulation.

PubMed

Sherfey, Jason S; Soplata, Austin E; Ardid, Salva; Roberts, Erik A; Stanley, David A; Pittman-Polletta, Benjamin R; Kopell, Nancy J

2018-01-01

DynaSim is an open-source MATLAB/GNU Octave toolbox for rapid prototyping of neural models and batch simulation management. It is designed to speed up and simplify the process of generating, sharing, and exploring network models of neurons with one or more compartments. Models can be specified by equations directly (similar to XPP or the Brian simulator) or by lists of predefined or custom model components. The higher-level specification supports arbitrarily complex population models and networks of interconnected populations. DynaSim also includes a large set of features that simplify exploring model dynamics over parameter spaces, running simulations in parallel using both multicore processors and high-performance computer clusters, and analyzing and plotting large numbers of simulated data sets in parallel. It also includes a graphical user interface (DynaSim GUI) that supports full functionality without requiring user programming. The software has been implemented in MATLAB to enable advanced neural modeling using MATLAB, given its popularity and a growing interest in modeling neural systems. The design of DynaSim incorporates a novel schema for model specification to facilitate future interoperability with other specifications (e.g., NeuroML, SBML), simulators (e.g., NEURON, Brian, NEST), and web-based applications (e.g., Geppetto) outside MATLAB. DynaSim is freely available at http://dynasimtoolbox.org. This tool promises to reduce barriers for investigating dynamics in large neural models, facilitate collaborative modeling, and complement other tools being developed in the neuroinformatics community.

Parallel Fixed Point Implementation of a Radial Basis Function Network in an FPGA

PubMed Central

de Souza, Alisson C. D.; Fernandes, Marcelo A. C.

2014-01-01

This paper proposes a parallel fixed point radial basis function (RBF) artificial neural network (ANN), implemented in a field programmable gate array (FPGA) trained online with a least mean square (LMS) algorithm. The processing time and occupied area were analyzed for various fixed point formats. The problems of precision of the ANN response for nonlinear classification using the XOR gate and interpolation using the sine function were also analyzed in a hardware implementation. The entire project was developed using the System Generator platform (Xilinx), with a Virtex-6 xc6vcx240t-1ff1156 as the target FPGA. PMID:25268918

First Annual Workshop on Space Operations Automation and Robotics (SOAR 87)

NASA Technical Reports Server (NTRS)

Griffin, Sandy (Editor)

1987-01-01

Several topics relative to automation and robotics technology are discussed. Automation of checkout, ground support, and logistics; automated software development; man-machine interfaces; neural networks; systems engineering and distributed/parallel processing architectures; and artificial intelligence/expert systems are among the topics covered.

Multi-Sensor Data Fusion Identification for Shearer Cutting Conditions Based on Parallel Quasi-Newton Neural Networks and the Dempster-Shafer Theory.

PubMed

Si, Lei; Wang, Zhongbin; Liu, Xinhua; Tan, Chao; Xu, Jing; Zheng, Kehong

2015-11-13

In order to efficiently and accurately identify the cutting condition of a shearer, this paper proposed an intelligent multi-sensor data fusion identification method using the parallel quasi-Newton neural network (PQN-NN) and the Dempster-Shafer (DS) theory. The vibration acceleration signals and current signal of six cutting conditions were collected from a self-designed experimental system and some special state features were extracted from the intrinsic mode functions (IMFs) based on the ensemble empirical mode decomposition (EEMD). In the experiment, three classifiers were trained and tested by the selected features of the measured data, and the DS theory was used to combine the identification results of three single classifiers. Furthermore, some comparisons with other methods were carried out. The experimental results indicate that the proposed method performs with higher detection accuracy and credibility than the competing algorithms. Finally, an industrial application example in the fully mechanized coal mining face was demonstrated to specify the effect of the proposed system.

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).

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.

Development of on-line monitoring system for Nuclear Power Plant (NPP) using neuro-expert, noise analysis, and modified neural networks

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

Subekti, M.; Center for Development of Reactor Safety Technology, National Nuclear Energy Agency of Indonesia, Puspiptek Complex BO.80, Serpong-Tangerang, 15340; Ohno, T.

2006-07-01

The neuro-expert has been utilized in previous monitoring-system research of Pressure Water Reactor (PWR). The research improved the monitoring system by utilizing neuro-expert, conventional noise analysis and modified neural networks for capability extension. The parallel method applications required distributed architecture of computer-network for performing real-time tasks. The research aimed to improve the previous monitoring system, which could detect sensor degradation, and to perform the monitoring demonstration in High Temperature Engineering Tested Reactor (HTTR). The developing monitoring system based on some methods that have been tested using the data from online PWR simulator, as well as RSG-GAS (30 MW research reactormore » in Indonesia), will be applied in HTTR for more complex monitoring. (authors)« less

An analog neural hardware implementation using charge-injection multipliers and neutron-specific gain control.

PubMed

Massengill, L W; Mundie, D B

1992-01-01

A neural network IC based on a dynamic charge injection is described. The hardware design is space and power efficient, and achieves massive parallelism of analog inner products via charge-based multipliers and spatially distributed summing buses. Basic synaptic cells are constructed of exponential pulse-decay modulation (EPDM) dynamic injection multipliers operating sequentially on propagating signal vectors and locally stored analog weights. Individually adjustable gain controls on each neutron reduce the effects of limited weight dynamic range. A hardware simulator/trainer has been developed which incorporates the physical (nonideal) characteristics of actual circuit components into the training process, thus absorbing nonlinearities and parametric deviations into the macroscopic performance of the network. Results show that charge-based techniques may achieve a high degree of neural density and throughput using standard CMOS processes.

VINE: A Variational Inference -Based Bayesian Neural Network Engine

DTIC Science & Technology

2018-01-01

networks are trained using the same dataset and hyper parameter settings as discussed. Table 1 Performance evaluation of the proposed transfer learning...multiplication/addition/subtraction. These operations can be implemented using nested loops in which various iterations of a loop are independent of...each other. This introduces an opportunity for optimization where a loop may be unrolled fully or partially to increase parallelism at the cost of

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.

Searching for patterns in remote sensing image databases using neural networks

NASA Technical Reports Server (NTRS)

Paola, Justin D.; Schowengerdt, Robert A.

1995-01-01

We have investigated a method, based on a successful neural network multispectral image classification system, of searching for single patterns in remote sensing databases. While defining the pattern to search for and the feature to be used for that search (spectral, spatial, temporal, etc.) is challenging, a more difficult task is selecting competing patterns to train against the desired pattern. Schemes for competing pattern selection, including random selection and human interpreted selection, are discussed in the context of an example detection of dense urban areas in Landsat Thematic Mapper imagery. When applying the search to multiple images, a simple normalization method can alleviate the problem of inconsistent image calibration. Another potential problem, that of highly compressed data, was found to have a minimal effect on the ability to detect the desired pattern. The neural network algorithm has been implemented using the PVM (Parallel Virtual Machine) library and nearly-optimal speedups have been obtained that help alleviate the long process of searching through imagery.

Toward Petascale Biologically Plausible Neural Networks

NASA Astrophysics Data System (ADS)

Long, Lyle

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

Electronic neural network for dynamic resource allocation

NASA Technical Reports Server (NTRS)

Thakoor, A. P.; Eberhardt, S. P.; Daud, T.

1991-01-01

A VLSI implementable neural network architecture for dynamic assignment is presented. The resource allocation problems involve assigning members of one set (e.g. resources) to those of another (e.g. consumers) such that the global 'cost' of the associations is minimized. The network consists of a matrix of sigmoidal processing elements (neurons), where the rows of the matrix represent resources and columns represent consumers. Unlike previous neural implementations, however, association costs are applied directly to the neurons, reducing connectivity of the network to VLSI-compatible 0 (number of neurons). Each row (and column) has an additional neuron associated with it to independently oversee activations of all the neurons in each row (and each column), providing a programmable 'k-winner-take-all' function. This function simultaneously enforces blocking (excitatory/inhibitory) constraints during convergence to control the number of active elements in each row and column within desired boundary conditions. Simulations show that the network, when implemented in fully parallel VLSI hardware, offers optimal (or near-optimal) solutions within only a fraction of a millisecond, for problems up to 128 resources and 128 consumers, orders of magnitude faster than conventional computing or heuristic search methods.

Learning and optimization with cascaded VLSI neural network building-block chips

NASA Technical Reports Server (NTRS)

Duong, T.; Eberhardt, S. P.; Tran, M.; Daud, T.; Thakoor, A. P.

1992-01-01

To demonstrate the versatility of the building-block approach, two neural network applications were implemented on cascaded analog VLSI chips. Weights were implemented using 7-b multiplying digital-to-analog converter (MDAC) synapse circuits, with 31 x 32 and 32 x 32 synapses per chip. A novel learning algorithm compatible with analog VLSI was applied to the two-input parity problem. The algorithm combines dynamically evolving architecture with limited gradient-descent backpropagation for efficient and versatile supervised learning. To implement the learning algorithm in hardware, synapse circuits were paralleled for additional quantization levels. The hardware-in-the-loop learning system allocated 2-5 hidden neurons for parity problems. Also, a 7 x 7 assignment problem was mapped onto a cascaded 64-neuron fully connected feedback network. In 100 randomly selected problems, the network found optimal or good solutions in most cases, with settling times in the range of 7-100 microseconds.

Silicon nanodisk array with a fin field-effect transistor for time-domain weighted sum calculation toward massively parallel spiking neural networks

NASA Astrophysics Data System (ADS)

Tohara, Takashi; Liang, Haichao; Tanaka, Hirofumi; Igarashi, Makoto; Samukawa, Seiji; Endo, Kazuhiko; Takahashi, Yasuo; Morie, Takashi

2016-03-01

A nanodisk array connected with a fin field-effect transistor is fabricated and analyzed for spiking neural network applications. This nanodevice performs weighted sums in the time domain using rising slopes of responses triggered by input spike pulses. The nanodisk arrays, which act as a resistance of several giga-ohms, are fabricated using a self-assembly bio-nano-template technique. Weighted sums are achieved with an energy dissipation on the order of 1 fJ, where the number of inputs can be more than one hundred. This amount of energy is several orders of magnitude lower than that of conventional digital processors.

A framework for plasticity implementation on the SpiNNaker neural architecture.

PubMed

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

2014-01-01

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

A framework for plasticity implementation on the SpiNNaker neural architecture

PubMed Central

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

2015-01-01

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

Resting state neural networks for visual Chinese word processing in Chinese adults and children.

PubMed

Li, Ling; Liu, Jiangang; Chen, Feiyan; Feng, Lu; Li, Hong; Tian, Jie; Lee, Kang

2013-07-01

This study examined the resting state neural networks for visual Chinese word processing in Chinese children and adults. Both the functional connectivity (FC) and amplitude of low frequency fluctuation (ALFF) approaches were used to analyze the fMRI data collected when Chinese participants were not engaged in any specific explicit tasks. We correlated time series extracted from the visual word form area (VWFA) with those in other regions in the brain. We also performed ALFF analysis in the resting state FC networks. The FC results revealed that, regarding the functionally connected brain regions, there exist similar intrinsically organized resting state networks for visual Chinese word processing in adults and children, suggesting that such networks may already be functional after 3-4 years of informal exposure to reading plus 3-4 years formal schooling. The ALFF results revealed that children appear to recruit more neural resources than adults in generally reading-irrelevant brain regions. Differences between child and adult ALFF results suggest that children's intrinsic word processing network during the resting state, though similar in functional connectivity, is still undergoing development. Further exposure to visual words and experience with reading are needed for children to develop a mature intrinsic network for word processing. The developmental course of the intrinsically organized word processing network may parallel that of the explicit word processing network. Copyright © 2013 Elsevier Ltd. All rights reserved.

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.

Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

PubMed Central

Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

2017-01-01

In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures. PMID:29066942

Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices.

PubMed

Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

2017-01-01

In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

Hippocampal and posterior parietal contributions to developmental increases in visual short-term memory capacity.

PubMed

von Allmen, David Yoh; Wurmitzer, Karoline; Klaver, Peter

2014-10-01

Developmental increases in visual short-term memory (VSTM) capacity have been associated with changes in attention processing limitations and changes in neural activity within neural networks including the posterior parietal cortex (PPC). A growing body of evidence suggests that the hippocampus plays a role in VSTM, but it is unknown whether the hippocampus contributes to the capacity increase across development. We investigated the functional development of the hippocampus and PPC in 57 children, adolescents and adults (age 8-27 years) who performed a visuo-spatial change detection task. A negative relationship between age and VSTM related activity was found in the right posterior hippocampus that was paralleled by a positive age-activity relationship in the right PPC. In the posterior hippocampus, VSTM related activity predicted individual capacity in children, whereas neural activity in the right anterior hippocampus predicted individual capacity in adults. The findings provide first evidence that VSTM development is supported by an integrated neural network that involves hippocampal and posterior parietal regions.

A real time neural net estimator of fatigue life

NASA Technical Reports Server (NTRS)

Troudet, T.; Merrill, W.

1990-01-01

A neural network architecture is proposed to estimate, in real-time, the fatigue life of mechanical components, as part of the intelligent Control System for Reusable Rocket Engines. Arbitrary component loading values were used as input to train a two hidden-layer feedforward neural net to estimate component fatigue damage. The ability of the net to learn, based on a local strain approach, the mapping between load sequence and fatigue damage has been demonstrated for a uniaxial specimen. Because of its demonstrated performance, the neural computation may be extended to complex cases where the loads are biaxial or triaxial, and the geometry of the component is complex (e.g., turbopumps blades). The generality of the approach is such that load/damage mappings can be directly extracted from experimental data without requiring any knowledge of the stress/strain profile of the component. In addition, the parallel network architecture allows real-time life calculations even for high-frequency vibrations. Owing to its distributed nature, the neural implementation will be robust and reliable, enabling its use in hostile environments such as rocket engines.

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.

Multilayer perceptron architecture optimization using parallel computing techniques.

PubMed

Castro, Wilson; Oblitas, Jimy; Santa-Cruz, Roberto; Avila-George, Himer

2017-01-01

The objective of this research was to develop a methodology for optimizing multilayer-perceptron-type neural networks by evaluating the effects of three neural architecture parameters, namely, number of hidden layers (HL), neurons per hidden layer (NHL), and activation function type (AF), on the sum of squares error (SSE). The data for the study were obtained from quality parameters (physicochemical and microbiological) of milk samples. Architectures or combinations were organized in groups (G1, G2, and G3) generated upon interspersing one, two, and three layers. Within each group, the networks had three neurons in the input layer, six neurons in the output layer, three to twenty-seven NHL, and three AF (tan-sig, log-sig, and linear) types. The number of architectures was determined using three factorial-type experimental designs, which reached 63, 2 187, and 50 049 combinations for G1, G2 and G3, respectively. Using MATLAB 2015a, a logical sequence was designed and implemented for constructing, training, and evaluating multilayer-perceptron-type neural networks using parallel computing techniques. The results show that HL and NHL have a statistically relevant effect on SSE, and from two hidden layers, AF also has a significant effect; thus, both AF and NHL can be evaluated to determine the optimal combination per group. Moreover, in the three study groups, it is observed that there is an inverse relationship between the number of processors and the total optimization time.

Multilayer perceptron architecture optimization using parallel computing techniques

PubMed Central

Castro, Wilson; Oblitas, Jimy; Santa-Cruz, Roberto; Avila-George, Himer

2017-01-01

The objective of this research was to develop a methodology for optimizing multilayer-perceptron-type neural networks by evaluating the effects of three neural architecture parameters, namely, number of hidden layers (HL), neurons per hidden layer (NHL), and activation function type (AF), on the sum of squares error (SSE). The data for the study were obtained from quality parameters (physicochemical and microbiological) of milk samples. Architectures or combinations were organized in groups (G1, G2, and G3) generated upon interspersing one, two, and three layers. Within each group, the networks had three neurons in the input layer, six neurons in the output layer, three to twenty-seven NHL, and three AF (tan-sig, log-sig, and linear) types. The number of architectures was determined using three factorial-type experimental designs, which reached 63, 2 187, and 50 049 combinations for G1, G2 and G3, respectively. Using MATLAB 2015a, a logical sequence was designed and implemented for constructing, training, and evaluating multilayer-perceptron-type neural networks using parallel computing techniques. The results show that HL and NHL have a statistically relevant effect on SSE, and from two hidden layers, AF also has a significant effect; thus, both AF and NHL can be evaluated to determine the optimal combination per group. Moreover, in the three study groups, it is observed that there is an inverse relationship between the number of processors and the total optimization time. PMID:29236744

A New Neural Network Approach Including First-Guess for Retrieval of Atmospheric Water Vapor, Cloud Liquid Water Path, Surface Temperature and Emissivities Over Land From Satellite Microwave Observations

NASA Technical Reports Server (NTRS)

Aires, F.; Prigent, C.; Rossow, W. B.; Rothstein, M.; Hansen, James E. (Technical Monitor)

2000-01-01

The analysis of microwave observations over land to determine atmospheric and surface parameters is still limited due to the complexity of the inverse problem. Neural network techniques have already proved successful as the basis of efficient retrieval methods for non-linear cases, however, first-guess estimates, which are used in variational methods to avoid problems of solution non-uniqueness or other forms of solution irregularity, have up to now not been used with neural network methods. In this study, a neural network approach is developed that uses a first-guess. Conceptual bridges are established between the neural network and variational methods. The new neural method retrieves the surface skin temperature, the integrated water vapor content, the cloud liquid water path and the microwave surface emissivities between 19 and 85 GHz over land from SSM/I observations. The retrieval, in parallel, of all these quantities improves the results for consistency reasons. A data base to train the neural network is calculated with a radiative transfer model and a a global collection of coincident surface and atmospheric parameters extracted from the National Center for Environmental Prediction reanalysis, from the International Satellite Cloud Climatology Project data and from microwave emissivity atlases previously calculated. The results of the neural network inversion are very encouraging. The r.m.s. error of the surface temperature retrieval over the globe is 1.3 K in clear sky conditions and 1.6 K in cloudy scenes. Water vapor is retrieved with a r.m.s. error of 3.8 kg/sq m in clear conditions and 4.9 kg/sq m in cloudy situations. The r.m.s. error in cloud liquid water path is 0.08 kg/sq m . The surface emissivities are retrieved with an accuracy of better than 0.008 in clear conditions and 0.010 in cloudy conditions. Microwave land surface temperature retrieval presents a very attractive complement to the infrared estimates in cloudy areas: time record of land surface temperature will be produced.

Parallel and orthogonal stimulus in ultradiluted neural networks

NASA Astrophysics Data System (ADS)

Sobral, G. A., Jr.; Vieira, V. M.; Lyra, M. L.; da Silva, C. R.

2006-10-01

Extending a model due to Derrida, Gardner, and Zippelius, we have studied the recognition ability of an extreme and asymmetrically diluted version of the Hopfield model for associative memory by including the effect of a stimulus in the dynamics of the system. We obtain exact results for the dynamic evolution of the average network superposition. The stimulus field was considered as proportional to the overlapping of the state of the system with a particular stimulated pattern. Two situations were analyzed, namely, the external stimulus acting on the initialization pattern (parallel stimulus) and the external stimulus acting on a pattern orthogonal to the initialization one (orthogonal stimulus). In both cases, we obtained the complete phase diagram in the parameter space composed of the stimulus field, thermal noise, and network capacity. Our results show that the system improves its recognition ability for parallel stimulus. For orthogonal stimulus two recognition phases emerge with the system locking at the initialization or stimulated pattern. We confront our analytical results with numerical simulations for the noiseless case T=0 .

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.

Highly parallel computation

NASA Technical Reports Server (NTRS)

Denning, Peter J.; Tichy, Walter F.

1990-01-01

Highly parallel computing architectures are the only means to achieve the computation rates demanded by advanced scientific problems. A decade of research has demonstrated the feasibility of such machines and current research focuses on which architectures designated as multiple instruction multiple datastream (MIMD) and single instruction multiple datastream (SIMD) have produced the best results to date; neither shows a decisive advantage for most near-homogeneous scientific problems. For scientific problems with many dissimilar parts, more speculative architectures such as neural networks or data flow may be needed.

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

NASA Astrophysics Data System (ADS)

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

1992-03-01

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

Neurocomputing strategies in decomposition based structural design

NASA Technical Reports Server (NTRS)

Szewczyk, Z.; Hajela, P.

1993-01-01

The present paper explores the applicability of neurocomputing strategies in decomposition based structural optimization problems. It is shown that the modeling capability of a backpropagation neural network can be used to detect weak couplings in a system, and to effectively decompose it into smaller, more tractable, subsystems. When such partitioning of a design space is possible, parallel optimization can be performed in each subsystem, with a penalty term added to its objective function to account for constraint violations in all other subsystems. Dependencies among subsystems are represented in terms of global design variables, and a neural network is used to map the relations between these variables and all subsystem constraints. A vector quantization technique, referred to as a z-Network, can effectively be used for this purpose. The approach is illustrated with applications to minimum weight sizing of truss structures with multiple design constraints.

A symbolic/subsymbolic interface protocol for cognitive modeling

PubMed Central

Simen, Patrick; Polk, Thad

2009-01-01

Researchers studying complex cognition have grown increasingly interested in mapping symbolic cognitive architectures onto subsymbolic brain models. Such a mapping seems essential for understanding cognition under all but the most extreme viewpoints (namely, that cognition consists exclusively of digitally implemented rules; or instead, involves no rules whatsoever). Making this mapping reduces to specifying an interface between symbolic and subsymbolic descriptions of brain activity. To that end, we propose parameterization techniques for building cognitive models as programmable, structured, recurrent neural networks. Feedback strength in these models determines whether their components implement classically subsymbolic neural network functions (e.g., pattern recognition), or instead, logical rules and digital memory. These techniques support the implementation of limited production systems. Though inherently sequential and symbolic, these neural production systems can exploit principles of parallel, analog processing from decision-making models in psychology and neuroscience to explain the effects of brain damage on problem solving behavior. PMID:20711520

Neural Network Control of a Parallel Hybrid-Electric Propulsion System for a Small Unmanned Aerial Vehicle

DTIC Science & Technology

2004-01-01

ion battery pack sized for endurance speed. The flexible optimization routine allows relative importance to be assigned between the use of gasoline...simulation results are provided. The two-point conceptual design includes an internal combustion engine sized for cruise and an electric motor and lithium

Schemas in Problem Solving: An Integrated Model of Learning, Memory, and Instruction

DTIC Science & Technology

1992-01-01

reflected in the title of a recent article: "lybid Coupation, in Cognitive Science: Neural Networks ad Symbl (3. A Andesson, 1990). And, Marvin Mtuky...Rumneihart, D. E (1989). Explorations in parallel distributed processing: A handbook of models, programs, and exercises. Cambridge, MA: The MrT Press. Minsky

Feature Extraction and Classification of FLIR Imagery Using Relative Locations of Non-Homogeneous Regions with Feedforward Neural Networks

DTIC Science & Technology

1992-04-01

Proceedings of Tri-Service Data Fusion Symposium, Johns Hopkins University, May 1989. 39. F. Rosenblatt. Principles of Neurodynamics : Perceptrons and the...104 47. David E. Rummelhart and James L. McClelland. Parallel Distributed Processing: Explorations in the Microstructure of Cognition , volume 1. The

First CLIPS Conference Proceedings, volume 2

NASA Technical Reports Server (NTRS)

1990-01-01

The topics of volume 2 of First CLIPS Conference are associated with following applications: quality control; intelligent data bases and networks; Space Station Freedom; Space Shuttle and satellite; user interface; artificial neural systems and fuzzy logic; parallel and distributed processing; enchancements to CLIPS; aerospace; simulation and defense; advisory systems and tutors; and intelligent control.

Multi-Sensor Data Fusion Identification for Shearer Cutting Conditions Based on Parallel Quasi-Newton Neural Networks and the Dempster-Shafer Theory

PubMed Central

Si, Lei; Wang, Zhongbin; Liu, Xinhua; Tan, Chao; Xu, Jing; Zheng, Kehong

2015-01-01

In order to efficiently and accurately identify the cutting condition of a shearer, this paper proposed an intelligent multi-sensor data fusion identification method using the parallel quasi-Newton neural network (PQN-NN) and the Dempster-Shafer (DS) theory. The vibration acceleration signals and current signal of six cutting conditions were collected from a self-designed experimental system and some special state features were extracted from the intrinsic mode functions (IMFs) based on the ensemble empirical mode decomposition (EEMD). In the experiment, three classifiers were trained and tested by the selected features of the measured data, and the DS theory was used to combine the identification results of three single classifiers. Furthermore, some comparisons with other methods were carried out. The experimental results indicate that the proposed method performs with higher detection accuracy and credibility than the competing algorithms. Finally, an industrial application example in the fully mechanized coal mining face was demonstrated to specify the effect of the proposed system. PMID:26580620

Ensembles of Spiking Neurons with Noise Support Optimal Probabilistic Inference in a Dynamically Changing Environment

PubMed Central

Legenstein, Robert; Maass, Wolfgang

2014-01-01

It has recently been shown that networks of spiking neurons with noise can emulate simple forms of probabilistic inference through “neural sampling”, i.e., by treating spikes as samples from a probability distribution of network states that is encoded in the network. Deficiencies of the existing model are its reliance on single neurons for sampling from each random variable, and the resulting limitation in representing quickly varying probabilistic information. We show that both deficiencies can be overcome by moving to a biologically more realistic encoding of each salient random variable through the stochastic firing activity of an ensemble of neurons. The resulting model demonstrates that networks of spiking neurons with noise can easily track and carry out basic computational operations on rapidly varying probability distributions, such as the odds of getting rewarded for a specific behavior. We demonstrate the viability of this new approach towards neural coding and computation, which makes use of the inherent parallelism of generic neural circuits, by showing that this model can explain experimentally observed firing activity of cortical neurons for a variety of tasks that require rapid temporal integration of sensory information. PMID:25340749

Rapid, parallel path planning by propagating wavefronts of spiking neural activity

PubMed Central

Ponulak, Filip; Hopfield, John J.

2013-01-01

Efficient path planning and navigation is critical for animals, robotics, logistics and transportation. We study a model in which spatial navigation problems can rapidly be solved in the brain by parallel mental exploration of alternative routes using propagating waves of neural activity. A wave of spiking activity propagates through a hippocampus-like network, altering the synaptic connectivity. The resulting vector field of synaptic change then guides a simulated animal to the appropriate selected target locations. We demonstrate that the navigation problem can be solved using realistic, local synaptic plasticity rules during a single passage of a wavefront. Our model can find optimal solutions for competing possible targets or learn and navigate in multiple environments. The model provides a hypothesis on the possible computational mechanisms for optimal path planning in the brain, at the same time it is useful for neuromorphic implementations, where the parallelism of information processing proposed here can fully be harnessed in hardware. PMID:23882213

Parallel Evolutionary Optimization for Neuromorphic Network Training

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

Schuman, Catherine D; Disney, Adam; Singh, Susheela

One of the key impediments to the success of current neuromorphic computing architectures is the issue of how best to program them. Evolutionary optimization (EO) is one promising programming technique; in particular, its wide applicability makes it especially attractive for neuromorphic architectures, which can have many different characteristics. In this paper, we explore different facets of EO on a spiking neuromorphic computing model called DANNA. We focus on the performance of EO in the design of our DANNA simulator, and on how to structure EO on both multicore and massively parallel computing systems. We evaluate how our parallel methods impactmore » the performance of EO on Titan, the U.S.'s largest open science supercomputer, and BOB, a Beowulf-style cluster of Raspberry Pi's. We also focus on how to improve the EO by evaluating commonality in higher performing neural networks, and present the result of a study that evaluates the EO performed by Titan.« less

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

PubMed

Zhao, Haiquan; Zeng, Xiangping; He, Zhengyou

2011-09-01

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

Nonlinear identification using a B-spline neural network and chaotic immune approaches

NASA Astrophysics Data System (ADS)

dos Santos Coelho, Leandro; Pessôa, Marcelo Wicthoff

2009-11-01

One of the important applications of B-spline neural network (BSNN) is to approximate nonlinear functions defined on a compact subset of a Euclidean space in a highly parallel manner. Recently, BSNN, a type of basis function neural network, has received increasing attention and has been applied in the field of nonlinear identification. BSNNs have the potential to "learn" the process model from input-output data or "learn" fault knowledge from past experience. BSNN can be used as function approximators to construct the analytical model for residual generation too. However, BSNN is trained by gradient-based methods that may fall into local minima during the learning procedure. When using feed-forward BSNNs, the quality of approximation depends on the control points (knots) placement of spline functions. This paper describes the application of a modified artificial immune network inspired optimization method - the opt-aiNet - combined with sequences generate by Hénon map to provide a stochastic search to adjust the control points of a BSNN. The numerical results presented here indicate that artificial immune network optimization methods are useful for building good BSNN model for the nonlinear identification of two case studies: (i) the benchmark of Box and Jenkins gas furnace, and (ii) an experimental ball-and-tube system.

Retrieving infinite numbers of patterns in a spin-glass model of immune networks

NASA Astrophysics Data System (ADS)

Agliari, E.; Annibale, A.; Barra, A.; Coolen, A. C. C.; Tantari, D.

2017-01-01

The similarity between neural and (adaptive) immune networks has been known for decades, but so far we did not understand the mechanism that allows the immune system, unlike associative neural networks, to recall and execute a large number of memorized defense strategies in parallel. The explanation turns out to lie in the network topology. Neurons interact typically with a large number of other neurons, whereas interactions among lymphocytes in immune networks are very specific, and described by graphs with finite connectivity. In this paper we use replica techniques to solve a statistical mechanical immune network model with “coordinator branches” (T-cells) and “effector branches” (B-cells), and show how the finite connectivity enables the coordinators to manage an extensive number of effectors simultaneously, even above the percolation threshold (where clonal cross-talk is not negligible). A consequence of its underlying topological sparsity is that the adaptive immune system exhibits only weak ergodicity breaking, so that also spontaneous switch-like effects as bi-stabilities are present: the latter may play a significant role in the maintenance of immune homeostasis.

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.

Optics in neural computation

NASA Astrophysics Data System (ADS)

Levene, Michael John

In all attempts to emulate the considerable powers of the brain, one is struck by both its immense size, parallelism, and complexity. While the fields of neural networks, artificial intelligence, and neuromorphic engineering have all attempted oversimplifications on the considerable complexity, all three can benefit from the inherent scalability and parallelism of optics. This thesis looks at specific aspects of three modes in which optics, and particularly volume holography, can play a part in neural computation. First, holography serves as the basis of highly-parallel correlators, which are the foundation of optical neural networks. The huge input capability of optical neural networks make them most useful for image processing and image recognition and tracking. These tasks benefit from the shift invariance of optical correlators. In this thesis, I analyze the capacity of correlators, and then present several techniques for controlling the amount of shift invariance. Of particular interest is the Fresnel correlator, in which the hologram is displaced from the Fourier plane. In this case, the amount of shift invariance is limited not just by the thickness of the hologram, but by the distance of the hologram from the Fourier plane. Second, volume holography can provide the huge storage capacity and high speed, parallel read-out necessary to support large artificial intelligence systems. However, previous methods for storing data in volume holograms have relied on awkward beam-steering or on as-yet non- existent cheap, wide-bandwidth, tunable laser sources. This thesis presents a new technique, shift multiplexing, which is capable of very high densities, but which has the advantage of a very simple implementation. In shift multiplexing, the reference wave consists of a focused spot a few millimeters in front of the hologram. Multiplexing is achieved by simply translating the hologram a few tens of microns or less. This thesis describes the theory for how shift multiplexing works based on an unconventional, but very intuitive, analysis of the optical far-field. A more detailed analysis based on a path-integral interpretation of the Born approximation is also derived. The capacity of shift multiplexing is compared with that of angle and wavelength multiplexing. The last part of this thesis deals with the role of optics in neuromorphic engineering. Up until now, most neuromorphic engineering has involved one or a few VLSI circuits emulating early sensory systems. However, optical interconnects will be required in order to push towards more ambitious goals, such as the simulation of early visual cortex. I describe a preliminary approach to designing such a system, and show how shift multiplexing can be used to simultaneously store and implement the immense interconnections required by such a project.

Semantic disturbance in schizophrenia and its relationship to the cognitive neuroscience of attention

PubMed Central

Nestor, P.G.; Han, S.D.; Niznikiewicz, M.; Salisbury, D.; Spencer, K.; Shenton, M.E.; McCarley, R.W.

2010-01-01

We view schizophrenia as producing a failure of attentional modulation that leads to a breakdown in the selective enhancement or inhibition of semantic/lexical representations whose biological substrata are widely distributed across left (dominant) temporal and frontal lobes. Supporting behavioral evidence includes word recall studies that have pointed to a disturbance in connectivity (associative strength) but not network size (number of associates) in patients with schizophrenia. Paralleling these findings are recent neural network simulation studies of the abnormal connectivity effect in schizophrenia through ‘lesioning’ network connection weights while holding constant network size. Supporting evidence at the level of biology are in vitro studies examining N-methyl-d-aspartate (NMDA) receptor antagonists on recurrent inhibition; simulations in neural populations with realistically modeled biophysical properties show NMDA antagonists produce a schizophrenia-like disturbance in pattern association. We propose a similar failure of NMDA-mediated recurrent inhibition as a candidate biological substrate for attention and semantic anomalies of schizophrenia. PMID:11454433

The Basal Ganglia and Adaptive Motor Control

NASA Astrophysics Data System (ADS)

Graybiel, Ann M.; Aosaki, Toshihiko; Flaherty, Alice W.; Kimura, Minoru

1994-09-01

The basal ganglia are neural structures within the motor and cognitive control circuits in the mammalian forebrain and are interconnected with the neocortex by multiple loops. Dysfunction in these parallel loops caused by damage to the striatum results in major defects in voluntary movement, exemplified in Parkinson's disease and Huntington's disease. These parallel loops have a distributed modular architecture resembling local expert architectures of computational learning models. During sensorimotor learning, such distributed networks may be coordinated by widely spaced striatal interneurons that acquire response properties on the basis of experienced reward.

Hyperspectral Image Classification using a Self-Organizing Map

NASA Technical Reports Server (NTRS)

Martinez, P.; Gualtieri, J. A.; Aguilar, P. L.; Perez, R. M.; Linaje, M.; Preciado, J. C.; Plaza, A.

2001-01-01

The use of hyperspectral data to determine the abundance of constituents in a certain portion of the Earth's surface relies on the capability of imaging spectrometers to provide a large amount of information at each pixel of a certain scene. Today, hyperspectral imaging sensors are capable of generating unprecedented volumes of radiometric data. The Airborne Visible/Infrared Imaging Spectrometer (AVIRIS), for example, routinely produces image cubes with 224 spectral bands. This undoubtedly opens a wide range of new possibilities, but the analysis of such a massive amount of information is not an easy task. In fact, most of the existing algorithms devoted to analyzing multispectral images are not applicable in the hyperspectral domain, because of the size and high dimensionality of the images. The application of neural networks to perform unsupervised classification of hyperspectral data has been tested by several authors and also by us in some previous work. We have also focused on analyzing the intrinsic capability of neural networks to parallelize the whole hyperspectral unmixing process. The results shown in this work indicate that neural network models are able to find clusters of closely related hyperspectral signatures, and thus can be used as a powerful tool to achieve the desired classification. The present work discusses the possibility of using a Self Organizing neural network to perform unsupervised classification of hyperspectral images. In sections 3 and 4, the topology of the proposed neural network and the training algorithm are respectively described. Section 5 provides the results we have obtained after applying the proposed methodology to real hyperspectral data, described in section 2. Different parameters in the learning stage have been modified in order to obtain a detailed description of their influence on the final results. Finally, in section 6 we provide the conclusions at which we have arrived.

Performance Comparison of the Digital Neuromorphic Hardware SpiNNaker and the Neural Network Simulation Software NEST for a Full-Scale Cortical Microcircuit Model

PubMed Central

van Albada, Sacha J.; Rowley, Andrew G.; Senk, Johanna; Hopkins, Michael; Schmidt, Maximilian; Stokes, Alan B.; Lester, David R.; Diesmann, Markus; Furber, Steve B.

2018-01-01

The digital neuromorphic hardware SpiNNaker has been developed with the aim of enabling large-scale neural network simulations in real time and with low power consumption. Real-time performance is achieved with 1 ms integration time steps, and thus applies to neural networks for which faster time scales of the dynamics can be neglected. By slowing down the simulation, shorter integration time steps and hence faster time scales, which are often biologically relevant, can be incorporated. We here describe the first full-scale simulations of a cortical microcircuit with biological time scales on SpiNNaker. Since about half the synapses onto the neurons arise within the microcircuit, larger cortical circuits have only moderately more synapses per neuron. Therefore, the full-scale microcircuit paves the way for simulating cortical circuits of arbitrary size. With approximately 80, 000 neurons and 0.3 billion synapses, this model is the largest simulated on SpiNNaker to date. The scale-up is enabled by recent developments in the SpiNNaker software stack that allow simulations to be spread across multiple boards. Comparison with simulations using the NEST software on a high-performance cluster shows that both simulators can reach a similar accuracy, despite the fixed-point arithmetic of SpiNNaker, demonstrating the usability of SpiNNaker for computational neuroscience applications with biological time scales and large network size. The runtime and power consumption are also assessed for both simulators on the example of the cortical microcircuit model. To obtain an accuracy similar to that of NEST with 0.1 ms time steps, SpiNNaker requires a slowdown factor of around 20 compared to real time. The runtime for NEST saturates around 3 times real time using hybrid parallelization with MPI and multi-threading. However, achieving this runtime comes at the cost of increased power and energy consumption. The lowest total energy consumption for NEST is reached at around 144 parallel threads and 4.6 times slowdown. At this setting, NEST and SpiNNaker have a comparable energy consumption per synaptic event. Our results widen the application domain of SpiNNaker and help guide its development, showing that further optimizations such as synapse-centric network representation are necessary to enable real-time simulation of large biological neural networks. PMID:29875620

Memory and neural networks on the basis of color centers in solids.

PubMed

Winnacker, Albrecht; Osvet, Andres

2009-11-01

Optical data recording is one of the most widely used and efficient systems of memory in the non-living world. The application of color centers in this context offers not only systems of high speed in writing and read-out due to a high degree of parallelism in data handling but also a possibility to set up models of neural networks. In this way, systems with a high potential for image processing, pattern recognition and logical operations can be constructed. A limitation to storage density is given by the diffraction limit of optical data recording. It is shown that this limitation can at least in principle be overcome by the principle of spectral hole burning, which results in systems of storage capacities close to the human brain system.

Volumetric multimodality neural network for brain tumor segmentation

NASA Astrophysics Data System (ADS)

Silvana Castillo, Laura; Alexandra Daza, Laura; Carlos Rivera, Luis; Arbeláez, Pablo

2017-11-01

Brain lesion segmentation is one of the hardest tasks to be solved in computer vision with an emphasis on the medical field. We present a convolutional neural network that produces a semantic segmentation of brain tumors, capable of processing volumetric data along with information from multiple MRI modalities at the same time. This results in the ability to learn from small training datasets and highly imbalanced data. Our method is based on DeepMedic, the state of the art in brain lesion segmentation. We develop a new architecture with more convolutional layers, organized in three parallel pathways with different input resolution, and additional fully connected layers. We tested our method over the 2015 BraTS Challenge dataset, reaching an average dice coefficient of 84%, while the standard DeepMedic implementation reached 74%.

Molecular parallels between neural and vascular development.

PubMed

Eichmann, Anne; Thomas, Jean-Léon

2013-01-01

The human central nervous system (CNS) features a network of ~400 miles of blood vessels that receives >20% of the body's cardiac output and uses most of its blood glucose. Many human diseases, including stroke, retinopathy, and cancer, are associated with the biology of CNS blood vessels. These vessels originate from extrinsic cell populations, including endothelial cells and pericytes that colonize the CNS and interact with glia and neurons to establish the blood-brain barrier and control cerebrovascular exchanges. Neurovascular interactions also play important roles in adult neurogenic niches, which harbor a unique population of neural stem cells that are intimately associated with blood vessels. We here review the cellular and molecular mechanisms required to establish the CNS vascular network, with a special focus on neurovascular interactions and the functions of vascular endothelial growth factors.

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

PubMed

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

2016-08-01

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

Neuronal integration of dynamic sources: Bayesian learning and Bayesian inference.

PubMed

Siegelmann, Hava T; Holzman, Lars E

2010-09-01

One of the brain's most basic functions is integrating sensory data from diverse sources. This ability causes us to question whether the neural system is computationally capable of intelligently integrating data, not only when sources have known, fixed relative dependencies but also when it must determine such relative weightings based on dynamic conditions, and then use these learned weightings to accurately infer information about the world. We suggest that the brain is, in fact, fully capable of computing this parallel task in a single network and describe a neural inspired circuit with this property. Our implementation suggests the possibility that evidence learning requires a more complex organization of the network than was previously assumed, where neurons have different specialties, whose emergence brings the desired adaptivity seen in human online inference.

Neural Parallel Engine: A toolbox for massively parallel neural signal processing.

PubMed

Tam, Wing-Kin; Yang, Zhi

2018-05-01

Large-scale neural recordings provide detailed information on neuronal activities and can help elicit the underlying neural mechanisms of the brain. However, the computational burden is also formidable when we try to process the huge data stream generated by such recordings. In this study, we report the development of Neural Parallel Engine (NPE), a toolbox for massively parallel neural signal processing on graphical processing units (GPUs). It offers a selection of the most commonly used routines in neural signal processing such as spike detection and spike sorting, including advanced algorithms such as exponential-component-power-component (EC-PC) spike detection and binary pursuit spike sorting. We also propose a new method for detecting peaks in parallel through a parallel compact operation. Our toolbox is able to offer a 5× to 110× speedup compared with its CPU counterparts depending on the algorithms. A user-friendly MATLAB interface is provided to allow easy integration of the toolbox into existing workflows. Previous efforts on GPU neural signal processing only focus on a few rudimentary algorithms, are not well-optimized and often do not provide a user-friendly programming interface to fit into existing workflows. There is a strong need for a comprehensive toolbox for massively parallel neural signal processing. A new toolbox for massively parallel neural signal processing has been created. It can offer significant speedup in processing signals from large-scale recordings up to thousands of channels. Copyright © 2018 Elsevier B.V. All rights reserved.

Unsupervised learning of contextual constraints in neural networks for simultaneous visual processing of multiple objects

NASA Astrophysics Data System (ADS)

Marshall, Jonathan A.

1992-12-01

A simple self-organizing neural network model, called an EXIN network, that learns to process sensory information in a context-sensitive manner, is described. EXIN networks develop efficient representation structures for higher-level visual tasks such as segmentation, grouping, transparency, depth perception, and size perception. Exposure to a perceptual environment during a developmental period serves to configure the network to perform appropriate organization of sensory data. A new anti-Hebbian inhibitory learning rule permits superposition of multiple simultaneous neural activations (multiple winners), while maintaining contextual consistency constraints, instead of forcing winner-take-all pattern classifications. The activations can represent multiple patterns simultaneously and can represent uncertainty. The network performs parallel parsing, credit attribution, and simultaneous constraint satisfaction. EXIN networks can learn to represent multiple oriented edges even where they intersect and can learn to represent multiple transparently overlaid surfaces defined by stereo or motion cues. In the case of stereo transparency, the inhibitory learning implements both a uniqueness constraint and permits coactivation of cells representing multiple disparities at the same image location. Thus two or more disparities can be active simultaneously without interference. This behavior is analogous to that of Prazdny's stereo vision algorithm, with the bonus that each binocular point is assigned a unique disparity. In a large implementation, such a NN would also be able to represent effectively the disparities of a cloud of points at random depths, like human observers, and unlike Prazdny's method

Configurable analog-digital conversion using the neural engineering framework

PubMed Central

Mayr, Christian G.; Partzsch, Johannes; Noack, Marko; Schüffny, Rene

2014-01-01

Efficient Analog-Digital Converters (ADC) are one of the mainstays of mixed-signal integrated circuit design. Besides the conventional ADCs used in mainstream ICs, there have been various attempts in the past to utilize neuromorphic networks to accomplish an efficient crossing between analog and digital domains, i.e., to build neurally inspired ADCs. Generally, these have suffered from the same problems as conventional ADCs, that is they require high-precision, handcrafted analog circuits and are thus not technology portable. In this paper, we present an ADC based on the Neural Engineering Framework (NEF). It carries out a large fraction of the overall ADC process in the digital domain, i.e., it is easily portable across technologies. The analog-digital conversion takes full advantage of the high degree of parallelism inherent in neuromorphic networks, making for a very scalable ADC. In addition, it has a number of features not commonly found in conventional ADCs, such as a runtime reconfigurability of the ADC sampling rate, resolution and transfer characteristic. PMID:25100933

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

NASA Technical Reports Server (NTRS)

Rai, Man Mohan

2006-01-01

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

Neural networks for dimensionality reduction of fluorescence spectra and prediction of drinking water disinfection by-products.

PubMed

Peleato, Nicolas M; Legge, Raymond L; Andrews, Robert C

2018-06-01

The use of fluorescence data coupled with neural networks for improved predictability of drinking water disinfection by-products (DBPs) was investigated. Novel application of autoencoders to process high-dimensional fluorescence data was related to common dimensionality reduction techniques of parallel factors analysis (PARAFAC) and principal component analysis (PCA). The proposed method was assessed based on component interpretability as well as for prediction of organic matter reactivity to formation of DBPs. Optimal prediction accuracies on a validation dataset were observed with an autoencoder-neural network approach or by utilizing the full spectrum without pre-processing. Latent representation by an autoencoder appeared to mitigate overfitting when compared to other methods. Although DBP prediction error was minimized by other pre-processing techniques, PARAFAC yielded interpretable components which resemble fluorescence expected from individual organic fluorophores. Through analysis of the network weights, fluorescence regions associated with DBP formation can be identified, representing a potential method to distinguish reactivity between fluorophore groupings. However, distinct results due to the applied dimensionality reduction approaches were observed, dictating a need for considering the role of data pre-processing in the interpretability of the results. In comparison to common organic measures currently used for DBP formation prediction, fluorescence was shown to improve prediction accuracies, with improvements to DBP prediction best realized when appropriate pre-processing and regression techniques were applied. The results of this study show promise for the potential application of neural networks to best utilize fluorescence EEM data for prediction of organic matter reactivity. Copyright © 2018 Elsevier Ltd. All rights reserved.

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

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks.

PubMed

Carpenter, Gail A.

1997-11-01

A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multilayer perceptrons. With a winner-take-all code, the unsupervised model dART reduces to fuzzy ART and the supervised model dARTMAP reduces to fuzzy ARTMAP. With a distributed code, these networks automatically apportion learned changes according to the degree of activation of each coding node, which permits fast as well as slow learning without catastrophic forgetting. Distributed ART models replace the traditional neural network path weight with a dynamic weight equal to the rectified difference between coding node activation and an adaptive threshold. Thresholds increase monotonically during learning according to a principle of atrophy due to disuse. However, monotonic change at the synaptic level manifests itself as bidirectional change at the dynamic level, where the result of adaptation resembles long-term potentiation (LTP) for single-pulse or low frequency test inputs but can resemble long-term depression (LTD) for higher frequency test inputs. This paradoxical behavior is traced to dual computational properties of phasic and tonic coding signal components. A parallel distributed match-reset-search process also helps stabilize memory. Without the match-reset-search system, dART becomes a type of distributed competitive learning network.

Computed tomography of x-ray images using neural networks

NASA Astrophysics Data System (ADS)

Allred, Lloyd G.; Jones, Martin H.; Sheats, Matthew J.; Davis, Anthony W.

2000-03-01

Traditional CT reconstruction is done using the technique of Filtered Backprojection. While this technique is widely employed in industrial and medical applications, it is not generally understood that FB has a fundamental flaw. Gibbs phenomena states any Fourier reconstruction will produce errors in the vicinity of all discontinuities, and that the error will equal 28 percent of the discontinuity. A number of years back, one of the authors proposed a biological perception model whereby biological neural networks perceive 3D images from stereo vision. The perception model proports an internal hard-wired neural network which emulates the external physical process. A process is repeated whereby erroneous unknown internal values are used to generate an emulated signal with is compared to external sensed data, generating an error signal. Feedback from the error signal is then sued to update the erroneous internal values. The process is repeated until the error signal no longer decrease. It was soon realized that the same method could be used to obtain CT from x-rays without having to do Fourier transforms. Neural networks have the additional potential for handling non-linearities and missing data. The technique has been applied to some coral images, collected at the Los Alamos high-energy x-ray facility. The initial images show considerable promise, in some instances showing more detail than the FB images obtained from the same data. Although routine production using this new method would require a massively parallel computer, the method shows promise, especially where refined detail is required.

On the Biological Plausibility of Grandmother Cells: Implications for Neural Network Theories in Psychology and Neuroscience

ERIC Educational Resources Information Center

Bowers, Jeffrey S.

2009-01-01

A fundamental claim associated with parallel distributed processing (PDP) theories of cognition is that knowledge is coded in a distributed manner in mind and brain. This approach rejects the claim that knowledge is coded in a localist fashion, with words, objects, and simple concepts (e.g. "dog"), that is, coded with their own dedicated…

Analog hardware for delta-backpropagation neural networks

NASA Technical Reports Server (NTRS)

Eberhardt, Silvio P. (Inventor)

1992-01-01

This is a fully parallel analog backpropagation learning processor which comprises a plurality of programmable resistive memory elements serving as synapse connections whose values can be weighted during learning with buffer amplifiers, summing circuits, and sample-and-hold circuits arranged in a plurality of neuron layers in accordance with delta-backpropagation algorithms modified so as to control weight changes due to circuit drift.

A Two-dimensional Version of the Niblett-Bostick Transformation for Magnetotelluric Interpretations

NASA Astrophysics Data System (ADS)

Esparza, F.

2005-05-01

An imaging technique for two-dimensional magnetotelluric interpretations is developed following the well known Niblett-Bostick transformation for one-dimensional profiles. The algorithm uses a Hopfield artificial neural network to process series and parallel magnetotelluric impedances along with their analytical influence functions. The adaptive, weighted average approximation preserves part of the nonlinearity of the original problem. No initial model in the usual sense is required for the recovery of a functional model. Rather, the built-in relationship between model and data considers automatically, all at the same time, many half spaces whose electrical conductivities vary according to the data. The use of series and parallel impedances, a self-contained pair of invariants of the impedance tensor, avoids the need to decide on best angles of rotation for TE and TM separations. Field data from a given profile can thus be fed directly into the algorithm without much processing. The solutions offered by the Hopfield neural network correspond to spatial averages computed through rectangular windows that can be chosen at will. Applications of the algorithm to simple synthetic models and to the COPROD2 data set illustrate the performance of the approximation.

Bio-Inspired Neural Model for Learning Dynamic Models

NASA Technical Reports Server (NTRS)

Duong, Tuan; Duong, Vu; Suri, Ronald

2009-01-01

A neural-network mathematical model that, relative to prior such models, places greater emphasis on some of the temporal aspects of real neural physical processes, has been proposed as a basis for massively parallel, distributed algorithms that learn dynamic models of possibly complex external processes by means of learning rules that are local in space and time. The algorithms could be made to perform such functions as recognition and prediction of words in speech and of objects depicted in video images. The approach embodied in this model is said to be "hardware-friendly" in the following sense: The algorithms would be amenable to execution by special-purpose computers implemented as very-large-scale integrated (VLSI) circuits that would operate at relatively high speeds and low power demands.

Distributed neural control of a hexapod walking vehicle

NASA Technical Reports Server (NTRS)

Beer, R. D.; Sterling, L. S.; Quinn, R. D.; Chiel, H. J.; Ritzmann, R.

1989-01-01

There has been a long standing interest in the design of controllers for multilegged vehicles. The approach is to apply distributed control to this problem, rather than using parallel computing of a centralized algorithm. Researchers describe a distributed neural network controller for hexapod locomotion which is based on the neural control of locomotion in insects. The model considers the simplified kinematics with two degrees of freedom per leg, but the model includes the static stability constraint. Through simulation, it is demonstrated that this controller can generate a continuous range of statically stable gaits at different speeds by varying a single control parameter. In addition, the controller is extremely robust, and can continue the function even after several of its elements have been disabled. Researchers are building a small hexapod robot whose locomotion will be controlled by this network. Researchers intend to extend their model to the dynamic control of legs with more than two degrees of freedom by using data on the control of multisegmented insect legs. Another immediate application of this neural control approach is also exhibited in biology: the escape reflex. Advanced robots are being equipped with tactile sensing and machine vision so that the sensory inputs to the robot controller are vast and complex. Neural networks are ideal for a lower level safety reflex controller because of their extremely fast response time. The combination of robotics, computer modeling, and neurobiology has been remarkably fruitful, and is likely to lead to deeper insights into the problems of real time sensorimotor control.

SKYNET: an efficient and robust neural network training tool for machine learning in astronomy

NASA Astrophysics Data System (ADS)

Graff, Philip; Feroz, Farhan; Hobson, Michael P.; Lasenby, Anthony

2014-06-01

We present the first public release of our generic neural network training algorithm, called SKYNET. This efficient and robust machine learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SKYNET uses a `pre-training' method to obtain a set of network parameters that has empirically been shown to be close to a good solution, followed by further optimization using a regularized variant of Newton's method, where the level of regularization is determined and adjusted automatically; the latter uses second-order derivative information to improve convergence, but without the need to evaluate or store the full Hessian matrix, by using a fast approximate method to calculate Hessian-vector products. This combination of methods allows for the training of complicated networks that are difficult to optimize using standard backpropagation techniques. SKYNET employs convergence criteria that naturally prevent overfitting, and also includes a fast algorithm for estimating the accuracy of network outputs. The utility and flexibility of SKYNET are demonstrated by application to a number of toy problems, and to astronomical problems focusing on the recovery of structure from blurred and noisy images, the identification of gamma-ray bursters, and the compression and denoising of galaxy images. The SKYNET software, which is implemented in standard ANSI C and fully parallelized using MPI, is available at http://www.mrao.cam.ac.uk/software/skynet/.

Highly-Parallel, Highly-Compact Computing Structures Implemented in Nanotechnology

NASA Technical Reports Server (NTRS)

Crawley, D. G.; Duff, M. J. B.; Fountain, T. J.; Moffat, C. D.; Tomlinson, C. D.

1995-01-01

In this paper, we describe work in which we are evaluating how the evolving properties of nano-electronic devices could best be utilized in highly parallel computing structures. Because of their combination of high performance, low power, and extreme compactness, such structures would have obvious applications in spaceborne environments, both for general mission control and for on-board data analysis. However, the anticipated properties of nano-devices mean that the optimum architecture for such systems is by no means certain. Candidates include single instruction multiple datastream (SIMD) arrays, neural networks, and multiple instruction multiple datastream (MIMD) assemblies.

A neurally inspired musical instrument classification system based upon the sound onset.

PubMed

Newton, Michael J; Smith, Leslie S

2012-06-01

Physiological evidence suggests that sound onset detection in the auditory system may be performed by specialized neurons as early as the cochlear nucleus. Psychoacoustic evidence shows that the sound onset can be important for the recognition of musical sounds. Here the sound onset is used in isolation to form tone descriptors for a musical instrument classification task. The task involves 2085 isolated musical tones from the McGill dataset across five instrument categories. A neurally inspired tone descriptor is created using a model of the auditory system's response to sound onset. A gammatone filterbank and spiking onset detectors, built from dynamic synapses and leaky integrate-and-fire neurons, create parallel spike trains that emphasize the sound onset. These are coded as a descriptor called the onset fingerprint. Classification uses a time-domain neural network, the echo state network. Reference strategies, based upon mel-frequency cepstral coefficients, evaluated either over the whole tone or only during the sound onset, provide context to the method. Classification success rates for the neurally-inspired method are around 75%. The cepstral methods perform between 73% and 76%. Further testing with tones from the Iowa MIS collection shows that the neurally inspired method is considerably more robust when tested with data from an unrelated dataset.

Molecular Parallels between Neural and Vascular Development

PubMed Central

Eichmann, Anne; Thomas, Jean-Léon

2013-01-01

The human central nervous system (CNS) features a network of ∼400 miles of blood vessels that receives >20% of the body’s cardiac output and uses most of its blood glucose. Many human diseases, including stroke, retinopathy, and cancer, are associated with the biology of CNS blood vessels. These vessels originate from extrinsic cell populations, including endothelial cells and pericytes that colonize the CNS and interact with glia and neurons to establish the blood–brain barrier and control cerebrovascular exchanges. Neurovascular interactions also play important roles in adult neurogenic niches, which harbor a unique population of neural stem cells that are intimately associated with blood vessels. We here review the cellular and molecular mechanisms required to establish the CNS vascular network, with a special focus on neurovascular interactions and the functions of vascular endothelial growth factors. PMID:23024177

Global Detection of Live Virtual Machine Migration Based on Cellular Neural Networks

PubMed Central

Xie, Kang; Yang, Yixian; Zhang, Ling; Jing, Maohua; Xin, Yang; Li, Zhongxian

2014-01-01

In order to meet the demands of operation monitoring of large scale, autoscaling, and heterogeneous virtual resources in the existing cloud computing, a new method of live virtual machine (VM) migration detection algorithm based on the cellular neural networks (CNNs), is presented. Through analyzing the detection process, the parameter relationship of CNN is mapped as an optimization problem, in which improved particle swarm optimization algorithm based on bubble sort is used to solve the problem. Experimental results demonstrate that the proposed method can display the VM migration processing intuitively. Compared with the best fit heuristic algorithm, this approach reduces the processing time, and emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI) implementation allowing the VM migration detection to be performed better. PMID:24959631

Global detection of live virtual machine migration based on cellular neural networks.

PubMed

Xie, Kang; Yang, Yixian; Zhang, Ling; Jing, Maohua; Xin, Yang; Li, Zhongxian

2014-01-01

In order to meet the demands of operation monitoring of large scale, autoscaling, and heterogeneous virtual resources in the existing cloud computing, a new method of live virtual machine (VM) migration detection algorithm based on the cellular neural networks (CNNs), is presented. Through analyzing the detection process, the parameter relationship of CNN is mapped as an optimization problem, in which improved particle swarm optimization algorithm based on bubble sort is used to solve the problem. Experimental results demonstrate that the proposed method can display the VM migration processing intuitively. Compared with the best fit heuristic algorithm, this approach reduces the processing time, and emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI) implementation allowing the VM migration detection to be performed better.

Using NCAR Yellowstone for PhotoVoltaic Power Forecasts with Artificial Neural Networks and an Analog Ensemble

NASA Astrophysics Data System (ADS)

Cervone, G.; Clemente-Harding, L.; Alessandrini, S.; Delle Monache, L.

2016-12-01

A methodology based on Artificial Neural Networks (ANN) and an Analog Ensemble (AnEn) is presented to generate 72-hour deterministic and probabilistic forecasts of power generated by photovoltaic (PV) power plants using input from a numerical weather prediction model and computed astronomical variables. ANN and AnEn are used individually and in combination to generate forecasts for three solar power plant located in Italy. The computational scalability of the proposed solution is tested using synthetic data simulating 4,450 PV power stations. The NCAR Yellowstone supercomputer is employed to test the parallel implementation of the proposed solution, ranging from 1 node (32 cores) to 4,450 nodes (141,140 cores). Results show that a combined AnEn + ANN solution yields best results, and that the proposed solution is well suited for massive scale computation.

Sensorimotor Learning Biases Choice Behavior: A Learning Neural Field Model for Decision Making

PubMed Central

Schöner, Gregor; Gail, Alexander

2012-01-01

According to a prominent view of sensorimotor processing in primates, selection and specification of possible actions are not sequential operations. Rather, a decision for an action emerges from competition between different movement plans, which are specified and selected in parallel. For action choices which are based on ambiguous sensory input, the frontoparietal sensorimotor areas are considered part of the common underlying neural substrate for selection and specification of action. These areas have been shown capable of encoding alternative spatial motor goals in parallel during movement planning, and show signatures of competitive value-based selection among these goals. Since the same network is also involved in learning sensorimotor associations, competitive action selection (decision making) should not only be driven by the sensory evidence and expected reward in favor of either action, but also by the subject's learning history of different sensorimotor associations. Previous computational models of competitive neural decision making used predefined associations between sensory input and corresponding motor output. Such hard-wiring does not allow modeling of how decisions are influenced by sensorimotor learning or by changing reward contingencies. We present a dynamic neural field model which learns arbitrary sensorimotor associations with a reward-driven Hebbian learning algorithm. We show that the model accurately simulates the dynamics of action selection with different reward contingencies, as observed in monkey cortical recordings, and that it correctly predicted the pattern of choice errors in a control experiment. With our adaptive model we demonstrate how network plasticity, which is required for association learning and adaptation to new reward contingencies, can influence choice behavior. The field model provides an integrated and dynamic account for the operations of sensorimotor integration, working memory and action selection required for decision making in ambiguous choice situations. PMID:23166483

Study of the Gray Scale, Polychromatic, Distortion Invariant Neural Networks Using the Ipa Model.

NASA Astrophysics Data System (ADS)

Uang, Chii-Maw

Research in the optical neural network field is primarily motivated by the fact that humans recognize objects better than the conventional digital computers and the massively parallel inherent nature of optics. This research represents a continuous effort during the past several years in the exploitation of using neurocomputing for pattern recognition. Based on the interpattern association (IPA) model and Hamming net model, many new systems and applications are introduced. A gray level discrete associative memory that is based on object decomposition/composition is proposed for recognizing gray-level patterns. This technique extends the processing ability from the binary mode to gray-level mode, and thus the information capacity is increased. Two polychromatic optical neural networks using color liquid crystal television (LCTV) panels for color pattern recognition are introduced. By introducing a color encoding technique in conjunction with the interpattern associative algorithm, a color associative memory was realized. Based on the color decomposition and composition technique, a color exemplar-based Hamming net was built for color image classification. A shift-invariant neural network is presented through use of the translation invariant property of the modulus of the Fourier transformation and the hetero-associative interpattern association (IPA) memory. To extract the main features, a quadrantal sampling method is used to sampled data and then replace the training patterns. Using the concept of hetero-associative memory to recall the distorted object. A shift and rotation invariant neural network using an interpattern hetero-association (IHA) model is presented. To preserve the shift and rotation invariant properties, a set of binarized-encoded circular harmonic expansion (CHE) functions at the Fourier domain is used as the training set. We use the shift and symmetric properties of the modulus of the Fourier spectrum to avoid the problem of centering the CHE functions. Almost all neural networks have the positive and negative weights, which increases the difficulty of optical implementation. A method to construct a unipolar IPA IWM is discussed. By searching the redundant interconnection links, an effective way that removes all negative links is discussed.

Synaptogenesis Is Modulated by Heparan Sulfate in Caenorhabditis elegans

PubMed Central

Lázaro-Peña, María I.; Díaz-Balzac, Carlos A.; Bülow, Hannes E.; Emmons, Scott W.

2018-01-01

The nervous system regulates complex behaviors through a network of neurons interconnected by synapses. How specific synaptic connections are genetically determined is still unclear. Male mating is the most complex behavior in Caenorhabditis elegans. It is composed of sequential steps that are governed by > 3000 chemical connections. Here, we show that heparan sulfates (HS) play a role in the formation and function of the male neural network. HS, sulfated in position 3 by the HS modification enzyme HST-3.1/HS 3-O-sulfotransferase and attached to the HS proteoglycan glypicans LON-2/glypican and GPN-1/glypican, functions cell-autonomously and nonautonomously for response to hermaphrodite contact during mating. Loss of 3-O sulfation resulted in the presynaptic accumulation of RAB-3, a molecule that localizes to synaptic vesicles, and disrupted the formation of synapses in a component of the mating circuits. We also show that the neural cell adhesion protein NRX-1/neurexin promotes and the neural cell adhesion protein NLG-1/neuroligin inhibits the formation of the same set of synapses in a parallel pathway. Thus, neural cell adhesion proteins and extracellular matrix components act together in the formation of synaptic connections. PMID:29559501

Using parallel evolutionary development for a biologically-inspired computer vision system for mobile robots.

PubMed

Wright, Cameron H G; Barrett, Steven F; Pack, Daniel J

2005-01-01

We describe a new approach to attacking the problem of robust computer vision for mobile robots. The overall strategy is to mimic the biological evolution of animal vision systems. Our basic imaging sensor is based upon the eye of the common house fly, Musca domestica. The computational algorithms are a mix of traditional image processing, subspace techniques, and multilayer neural networks.

Hardware-based Artificial Neural Networks for Size, Weight, and Power Constrained Platforms (Preprint)

DTIC Science & Technology

2012-11-01

few sensors/complex computations, and many sensors/simple computation. II. CHALLENGES WITH NANO-ENABLED NEUROMORPHIC CHIPS A wide variety of...scenarios. Neuromorphic processors, which are based on the highly parallelized computing architecture of the mammalian brain, show great promise in...in the brain. This fundamentally different approach, frequently referred to as neuromorphic computing, is thought to be better able to solve fuzzy

VLSI neuroprocessors

NASA Technical Reports Server (NTRS)

Kemeny, Sabrina E.

1994-01-01

Electronic and optoelectronic hardware implementations of highly parallel computing architectures address several ill-defined and/or computation-intensive problems not easily solved by conventional computing techniques. The concurrent processing architectures developed are derived from a variety of advanced computing paradigms including neural network models, fuzzy logic, and cellular automata. Hardware implementation technologies range from state-of-the-art digital/analog custom-VLSI to advanced optoelectronic devices such as computer-generated holograms and e-beam fabricated Dammann gratings. JPL's concurrent processing devices group has developed a broad technology base in hardware implementable parallel algorithms, low-power and high-speed VLSI designs and building block VLSI chips, leading to application-specific high-performance embeddable processors. Application areas include high throughput map-data classification using feedforward neural networks, terrain based tactical movement planner using cellular automata, resource optimization (weapon-target assignment) using a multidimensional feedback network with lateral inhibition, and classification of rocks using an inner-product scheme on thematic mapper data. In addition to addressing specific functional needs of DOD and NASA, the JPL-developed concurrent processing device technology is also being customized for a variety of commercial applications (in collaboration with industrial partners), and is being transferred to U.S. industries. This viewgraph p resentation focuses on two application-specific processors which solve the computation intensive tasks of resource allocation (weapon-target assignment) and terrain based tactical movement planning using two extremely different topologies. Resource allocation is implemented as an asynchronous analog competitive assignment architecture inspired by the Hopfield network. Hardware realization leads to a two to four order of magnitude speed-up over conventional techniques and enables multiple assignments, (many to many), not achievable with standard statistical approaches. Tactical movement planning (finding the best path from A to B) is accomplished with a digital two-dimensional concurrent processor array. By exploiting the natural parallel decomposition of the problem in silicon, a four order of magnitude speed-up over optimized software approaches has been demonstrated.

[Not Available].

PubMed

Pecevski, Dejan; Natschläger, Thomas; Schuch, Klaus

2009-01-01

The Parallel Circuit SIMulator (PCSIM) is a software package for simulation of neural circuits. It is primarily designed for distributed simulation of large scale networks of spiking point neurons. Although its computational core is written in C++, PCSIM's primary interface is implemented in the Python programming language, which is a powerful programming environment and allows the user to easily integrate the neural circuit simulator with data analysis and visualization tools to manage the full neural modeling life cycle. The main focus of this paper is to describe PCSIM's full integration into Python and the benefits thereof. In particular we will investigate how the automatically generated bidirectional interface and PCSIM's object-oriented modular framework enable the user to adopt a hybrid modeling approach: using and extending PCSIM's functionality either employing pure Python or C++ and thus combining the advantages of both worlds. Furthermore, we describe several supplementary PCSIM packages written in pure Python and tailored towards setting up and analyzing neural simulations.

Pictures of pain: their contribution to the neuroscience of empathy.

PubMed

Schott, G D

2015-03-01

The study of empathy, a translation of the term 'Einfühlung', originated in 19th century Germany in the sphere of aesthetics, and was followed by studies in psychology and then neuroscience. During the past decade the links between empathy and art have started to be investigated, but now from the neuroscientific perspective, and two different approaches have emerged. Recently, the primacy of the mirror neuron system and its association with automaticity and imitative, simulated movement has been envisaged. But earlier, a number of eminent art historians had pointed to the importance of cognitive responses to art; these responses might plausibly be subserved by alternative neural networks. Focusing here mainly on pictures depicting pain and evoking empathy, both approaches are considered by summarizing the evidence that either supports the involvement of the mirror neuron system, or alternatively suggests other neural networks are likely to be implicated. The use of such pictures in experimental studies exploring the underlying neural processes, however, raises a number of concerns, and suggests caution is exercised in drawing conclusions concerning the networks that might be engaged. These various networks are discussed next, taking into account the affective and sensory components of the pain experience, before concluding that both mirror neuron and alternative neural networks are likelyto be enlisted in the empathetic response to images of pain. A somewhat similar duality of spontaneous and cognitive processes may perhaps also be paralleled in the creation of such images. While noting that some have repudiated the neuroscientific approach to the subject, pictures are nevertheless shown here to represent an unusual but invaluable tool in the study of pain and empathy. © The Author (2015). Published by Oxford University Press on behalf of the Guarantors of Brain. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Network architectures and circuit function: testing alternative hypotheses in multifunctional networks.

PubMed

Leonard, J L

2000-05-01

Understanding how species-typical movement patterns are organized in the nervous system is a central question in neurobiology. The current explanations involve 'alphabet' models in which an individual neuron may participate in the circuit for several behaviors but each behavior is specified by a specific neural circuit. However, not all of the well-studied model systems fit the 'alphabet' model. The 'equation' model provides an alternative possibility, whereby a system of parallel motor neurons, each with a unique (but overlapping) field of innervation, can account for the production of stereotyped behavior patterns by variable circuits. That is, it is possible for such patterns to arise as emergent properties of a generalized neural network in the absence of feedback, a simple version of a 'self-organizing' behavioral system. Comparison of systems of identified neurons suggest that the 'alphabet' model may account for most observations where CPGs act to organize motor patterns. Other well-known model systems, involving architectures corresponding to feed-forward neural networks with a hidden layer, may organize patterned behavior in a manner consistent with the 'equation' model. Such architectures are found in the Mauthner and reticulospinal circuits, 'escape' locomotion in cockroaches, CNS control of Aplysia gill, and may also be important in the coordination of sensory information and motor systems in insect mushroom bodies and the vertebrate hippocampus. The hidden layer of such networks may serve as an 'internal representation' of the behavioral state and/or body position of the animal, allowing the animal to fine-tune oriented, or particularly context-sensitive, movements to the prevalent conditions. Experiments designed to distinguish between the two models in cases where they make mutually exclusive predictions provide an opportunity to elucidate the neural mechanisms by which behavior is organized in vivo and in vitro. Copyright 2000 S. Karger AG, Basel

Pictures of pain: their contribution to the neuroscience of empathy

PubMed Central

2015-01-01

The study of empathy, a translation of the term ‘Einfühlung’, originated in 19th century Germany in the sphere of aesthetics, and was followed by studies in psychology and then neuroscience. During the past decade the links between empathy and art have started to be investigated, but now from the neuroscientific perspective, and two different approaches have emerged. Recently, the primacy of the mirror neuron system and its association with automaticity and imitative, simulated movement has been envisaged. But earlier, a number of eminent art historians had pointed to the importance of cognitive responses to art; these responses might plausibly be subserved by alternative neural networks. Focusing here mainly on pictures depicting pain and evoking empathy, both approaches are considered by summarizing the evidence that either supports the involvement of the mirror neuron system, or alternatively suggests other neural networks are likely to be implicated. The use of such pictures in experimental studies exploring the underlying neural processes, however, raises a number of concerns, and suggests caution is exercised in drawing conclusions concerning the networks that might be engaged. These various networks are discussed next, taking into account the affective and sensory components of the pain experience, before concluding that both mirror neuron and alternative neural networks are likelyto be enlisted in the empathetic response to images of pain. A somewhat similar duality of spontaneous and cognitive processes may perhaps also be paralleled in the creation of such images. While noting that some have repudiated the neuroscientific approach to the subject, pictures are nevertheless shown here to represent an unusual but invaluable tool in the study of pain and empathy. PMID:25614024

Identifying Corresponding Patches in SAR and Optical Images With a Pseudo-Siamese CNN

NASA Astrophysics Data System (ADS)

Hughes, Lloyd H.; Schmitt, Michael; Mou, Lichao; Wang, Yuanyuan; Zhu, Xiao Xiang

2018-05-01

In this letter, we propose a pseudo-siamese convolutional neural network (CNN) architecture that enables to solve the task of identifying corresponding patches in very-high-resolution (VHR) optical and synthetic aperture radar (SAR) remote sensing imagery. Using eight convolutional layers each in two parallel network streams, a fully connected layer for the fusion of the features learned in each stream, and a loss function based on binary cross-entropy, we achieve a one-hot indication if two patches correspond or not. The network is trained and tested on an automatically generated dataset that is based on a deterministic alignment of SAR and optical imagery via previously reconstructed and subsequently co-registered 3D point clouds. The satellite images, from which the patches comprising our dataset are extracted, show a complex urban scene containing many elevated objects (i.e. buildings), thus providing one of the most difficult experimental environments. The achieved results show that the network is able to predict corresponding patches with high accuracy, thus indicating great potential for further development towards a generalized multi-sensor key-point matching procedure. Index Terms-synthetic aperture radar (SAR), optical imagery, data fusion, deep learning, convolutional neural networks (CNN), image matching, deep matching

Modulation of attention network activation under antidepressant agents in healthy subjects.

PubMed

Graf, Heiko; Abler, Birgit; Hartmann, Antonie; Metzger, Coraline D; Walter, Martin

2013-07-01

While antidepressants are supposed to exert similar effects on mood and drive via various mechanisms of action, diverging effects are observed regarding side-effects and accordingly on neural correlates of motivation, emotion, reward and salient stimuli processing as a function of the drugs impact on neurotransmission. In the context of erotic stimulation, a unidirectional modulation of attentional functioning despite opposite effects on sexual arousal has been suggested for the selective serotonin reuptake-inhibitor (SSRI) paroxetine and the selective dopamine and noradrenaline reuptake-inhibitor (SDNRI) bupropion. To further elucidate the effects of antidepressant-related alterations of neural attention networks, we investigated 18 healthy males under subchronic administration (7 d) of paroxetine (20 mg), bupropion (150 mg) and placebo within a randomized placebo-controlled cross-over double-blind functional magnetic resonance imaging (fMRI) design during an established preceding attention task. Neuropsychological effects beyond the fMRI-paradigm were assessed by measuring alertness and divided attention. Comparing preceding attention periods of salient vs. neutral pictures, we revealed congruent effects of both drugs vs. placebo within the anterior midcingulate cortex, dorsolateral prefrontal cortex, anterior prefrontal cortex, superior temporal gyrus, anterior insula and the thalamus. Relatively decreased activation in this network was paralleled by slower reaction times in the divided attention task in both verum conditions compared to placebo. Our results suggest similar effects of antidepressant treatments on behavioural and neural attentional functioning by diverging neurochemical pathways. Concurrent alterations of brain regions within a fronto-parietal and cingulo-opercular attention network for top-down control could point to basic neural mechanisms of antidepressant action irrespective of receptor profiles.

All-optical bidirectional neural interfacing using hybrid multiphoton holographic optogenetic stimulation.

PubMed

Paluch-Siegler, Shir; Mayblum, Tom; Dana, Hod; Brosh, Inbar; Gefen, Inna; Shoham, Shy

2015-07-01

Our understanding of neural information processing could potentially be advanced by combining flexible three-dimensional (3-D) neuroimaging and stimulation. Recent developments in optogenetics suggest that neurophotonic approaches are in principle highly suited for noncontact stimulation of network activity patterns. In particular, two-photon holographic optical neural stimulation (2P-HONS) has emerged as a leading approach for multisite 3-D excitation, and combining it with temporal focusing (TF) further enables axially confined yet spatially extended light patterns. Here, we study key steps toward bidirectional cell-targeted 3-D interfacing by introducing and testing a hybrid new 2P-TF-HONS stimulation path for accurate parallel optogenetic excitation into a recently developed hybrid multiphoton 3-D imaging system. The system is shown to allow targeted all-optical probing of in vitro cortical networks expressing channelrhodopsin-2 using a regeneratively amplified femtosecond laser source tuned to 905 nm. These developments further advance a prospective new tool for studying and achieving distributed control over 3-D neuronal circuits both in vitro and in vivo.

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems

PubMed Central

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-01

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems. PMID:28079187

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems.

PubMed

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-12

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems.

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems

NASA Astrophysics Data System (ADS)

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-01

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems.

Using the ADAP Learning Algorithm to Forecast the Onset of Diabetes Mellitus

PubMed Central

Smith, Jack W.; Everhart, J.E.; Dickson, W.C.; Knowler, W.C.; Johannes, R.S.

1988-01-01

Neural networks or connectionist models for parallel processing are not new. However, a resurgence of interest in the past half decade has occurred. In part, this is related to a better understanding of what are now referred to as hidden nodes. These algorithms are considered to be of marked value in pattern recognition problems. Because of that, we tested the ability of an early neural network model, ADAP, to forecast the onset of diabetes mellitus in a high risk population of Pima Indians. The algorithm's performance was analyzed using standard measures for clinical tests: sensitivity, specificity, and a receiver operating characteristic curve. The crossover point for sensitivity and specificity is 0.76. We are currently further examining these methods by comparing the ADAP results with those obtained from logistic regression and linear perceptron models using precisely the same training and forecasting sets. A description of the algorithm is included.

Smart-Pixel Array Processors Based on Optimal Cellular Neural Networks for Space Sensor Applications

NASA Technical Reports Server (NTRS)

Fang, Wai-Chi; Sheu, Bing J.; Venus, Holger; Sandau, Rainer

1997-01-01

A smart-pixel cellular neural network (CNN) with hardware annealing capability, digitally programmable synaptic weights, and multisensor parallel interface has been under development for advanced space sensor applications. The smart-pixel CNN architecture is a programmable multi-dimensional array of optoelectronic neurons which are locally connected with their local neurons and associated active-pixel sensors. Integration of the neuroprocessor in each processor node of a scalable multiprocessor system offers orders-of-magnitude computing performance enhancements for on-board real-time intelligent multisensor processing and control tasks of advanced small satellites. The smart-pixel CNN operation theory, architecture, design and implementation, and system applications are investigated in detail. The VLSI (Very Large Scale Integration) implementation feasibility was illustrated by a prototype smart-pixel 5x5 neuroprocessor array chip of active dimensions 1380 micron x 746 micron in a 2-micron CMOS technology.

Parallel processing and learning in simple systems. Annual report, 10 January 1987-9 January 1988

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

Mpitsos, G.J.

1988-03-11

To date it has been demonstrated that an experimental animal, the sea slug Pleurobranchaea, is capable of one-trial food-aversion learning, and that the muscarinic antagonist scopolamine in low doses causes an enhancement of learning. Pharmacologic binding studies using a new, /sup 125/I-form of quinuclidinyl benzilate, in addition to studies using the /sup 3/H form of this ligand, have uncovered not only the classical types of muscarinic receptors that are typical of vertebrate cortex, but also a new form that is not found in other invertebrates tested. Usually muscarinic receptors are found in low densities in invertebrate neural membranes, but themore » density of the new form in this animal's neural membranes is similar to the density of the classic receptors in mammalian cortex. Neurophysiological studies of individual neurons in small groups of identifiable neurons have shown that their activity is variable, as is the behavior that they take part in generating, and that the variability fits the definition of low-dimensional chaos. Findings show that such variability is an important feature of the emergence of adaptive responses arising from parallel, distributed neural networks in biological systems.« less

Evolution of central pattern generators and rhythmic behaviours

PubMed Central

Katz, Paul S.

2016-01-01

Comparisons of rhythmic movements and the central pattern generators (CPGs) that control them uncover principles about the evolution of behaviour and neural circuits. Over the course of evolutionary history, gradual evolution of behaviours and their neural circuitry within any lineage of animals has been a predominant occurrence. Small changes in gene regulation can lead to divergence of circuit organization and corresponding changes in behaviour. However, some behavioural divergence has resulted from large-scale rewiring of the neural network. Divergence of CPG circuits has also occurred without a corresponding change in behaviour. When analogous rhythmic behaviours have evolved independently, it has generally been with different neural mechanisms. Repeated evolution of particular rhythmic behaviours has occurred within some lineages due to parallel evolution or latent CPGs. Particular motor pattern generating mechanisms have also evolved independently in separate lineages. The evolution of CPGs and rhythmic behaviours shows that although most behaviours and neural circuits are highly conserved, the nature of the behaviour does not dictate the neural mechanism and that the presence of homologous neural components does not determine the behaviour. This suggests that although behaviour is generated by neural circuits, natural selection can act separately on these two levels of biological organization. PMID:26598733

Evolution of central pattern generators and rhythmic behaviours.

PubMed

Katz, Paul S

2016-01-05

Comparisons of rhythmic movements and the central pattern generators (CPGs) that control them uncover principles about the evolution of behaviour and neural circuits. Over the course of evolutionary history, gradual evolution of behaviours and their neural circuitry within any lineage of animals has been a predominant occurrence. Small changes in gene regulation can lead to divergence of circuit organization and corresponding changes in behaviour. However, some behavioural divergence has resulted from large-scale rewiring of the neural network. Divergence of CPG circuits has also occurred without a corresponding change in behaviour. When analogous rhythmic behaviours have evolved independently, it has generally been with different neural mechanisms. Repeated evolution of particular rhythmic behaviours has occurred within some lineages due to parallel evolution or latent CPGs. Particular motor pattern generating mechanisms have also evolved independently in separate lineages. The evolution of CPGs and rhythmic behaviours shows that although most behaviours and neural circuits are highly conserved, the nature of the behaviour does not dictate the neural mechanism and that the presence of homologous neural components does not determine the behaviour. This suggests that although behaviour is generated by neural circuits, natural selection can act separately on these two levels of biological organization. © 2015 The Author(s).

Nonlinear autoregressive neural networks with external inputs for forecasting of typhoon inundation level.

PubMed

Ouyang, Huei-Tau

2017-08-01

Accurate inundation level forecasting during typhoon invasion is crucial for organizing response actions such as the evacuation of people from areas that could potentially flood. This paper explores the ability of nonlinear autoregressive neural networks with exogenous inputs (NARX) to predict inundation levels induced by typhoons. Two types of NARX architecture were employed: series-parallel (NARX-S) and parallel (NARX-P). Based on cross-correlation analysis of rainfall and water-level data from historical typhoon records, 10 NARX models (five of each architecture type) were constructed. The forecasting ability of each model was assessed by considering coefficient of efficiency (CE), relative time shift error (RTS), and peak water-level error (PE). The results revealed that high CE performance could be achieved by employing more model input variables. Comparisons of the two types of model demonstrated that the NARX-S models outperformed the NARX-P models in terms of CE and RTS, whereas both performed exceptionally in terms of PE and without significant difference. The NARX-S and NARX-P models with the highest overall performance were identified and their predictions were compared with those of traditional ARX-based models. The NARX-S model outperformed the ARX-based models in all three indexes, whereas the NARX-P model exhibited comparable CE performance and superior RTS and PE performance.

Classification of time-of-flight secondary ion mass spectrometry spectra from complex Cu-Fe sulphides by principal component analysis and artificial neural networks.

PubMed

Kalegowda, Yogesh; Harmer, Sarah L

2013-01-08

Artificial neural network (ANN) and a hybrid principal component analysis-artificial neural network (PCA-ANN) classifiers have been successfully implemented for classification of static time-of-flight secondary ion mass spectrometry (ToF-SIMS) mass spectra collected from complex Cu-Fe sulphides (chalcopyrite, bornite, chalcocite and pyrite) at different flotation conditions. ANNs are very good pattern classifiers because of: their ability to learn and generalise patterns that are not linearly separable; their fault and noise tolerance capability; and high parallelism. In the first approach, fragments from the whole ToF-SIMS spectrum were used as input to the ANN, the model yielded high overall correct classification rates of 100% for feed samples, 88% for conditioned feed samples and 91% for Eh modified samples. In the second approach, the hybrid pattern classifier PCA-ANN was integrated. PCA is a very effective multivariate data analysis tool applied to enhance species features and reduce data dimensionality. Principal component (PC) scores which accounted for 95% of the raw spectral data variance, were used as input to the ANN, the model yielded high overall correct classification rates of 88% for conditioned feed samples and 95% for Eh modified samples. Copyright © 2012 Elsevier B.V. All rights reserved.

Implantable fiber-optic interface for parallel multisite long-term optical dynamic brain interrogation in freely moving mice

PubMed Central

Doronina-Amitonova, L. V.; Fedotov, I. V.; Ivashkina, O. I.; Zots, M. A.; Fedotov, A. B.; Anokhin, K. V.; Zheltikov, A. M.

2013-01-01

Seeing the big picture of functional responses within large neural networks in a freely functioning brain is crucial for understanding the cellular mechanisms behind the higher nervous activity, including the most complex brain functions, such as cognition and memory. As a breakthrough toward meeting this challenge, implantable fiber-optic interfaces integrating advanced optogenetic technologies and cutting-edge fiber-optic solutions have been demonstrated, enabling a long-term optogenetic manipulation of neural circuits in freely moving mice. Here, we show that a specifically designed implantable fiber-optic interface provides a powerful tool for parallel long-term optical interrogation of distinctly separate, functionally different sites in the brain of freely moving mice. This interface allows the same groups of neurons lying deeply in the brain of a freely behaving mouse to be reproducibly accessed and optically interrogated over many weeks, providing a long-term dynamic detection of genome activity in response to a broad variety of pharmacological and physiological stimuli. PMID:24253232

Implantable fiber-optic interface for parallel multisite long-term optical dynamic brain interrogation in freely moving mice

NASA Astrophysics Data System (ADS)

Doronina-Amitonova, L. V.; Fedotov, I. V.; Ivashkina, O. I.; Zots, M. A.; Fedotov, A. B.; Anokhin, K. V.; Zheltikov, A. M.

2013-11-01

Seeing the big picture of functional responses within large neural networks in a freely functioning brain is crucial for understanding the cellular mechanisms behind the higher nervous activity, including the most complex brain functions, such as cognition and memory. As a breakthrough toward meeting this challenge, implantable fiber-optic interfaces integrating advanced optogenetic technologies and cutting-edge fiber-optic solutions have been demonstrated, enabling a long-term optogenetic manipulation of neural circuits in freely moving mice. Here, we show that a specifically designed implantable fiber-optic interface provides a powerful tool for parallel long-term optical interrogation of distinctly separate, functionally different sites in the brain of freely moving mice. This interface allows the same groups of neurons lying deeply in the brain of a freely behaving mouse to be reproducibly accessed and optically interrogated over many weeks, providing a long-term dynamic detection of genome activity in response to a broad variety of pharmacological and physiological stimuli.

Decoding of finger trajectory from ECoG using deep learning.

PubMed

Xie, Ziqian; Schwartz, Odelia; Prasad, Abhishek

2018-06-01

Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.

Decoding of finger trajectory from ECoG using deep learning

NASA Astrophysics Data System (ADS)

Xie, Ziqian; Schwartz, Odelia; Prasad, Abhishek

2018-06-01

Objective. Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. Approach. We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. Main results. We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. Significance. This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.

ELIPS: Toward a Sensor Fusion Processor on a Chip

NASA Technical Reports Server (NTRS)

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

1998-01-01

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

Self-referenced processing, neurodevelopment and joint attention in autism.

PubMed

Mundy, Peter; Gwaltney, Mary; Henderson, Heather

2010-09-01

This article describes a parallel and distributed processing model (PDPM) of joint attention, self-referenced processing and autism. According to this model, autism involves early impairments in the capacity for rapid, integrated processing of self-referenced (proprioceptive and interoceptive) and other-referenced (exteroceptive) information. Measures of joint attention have proven useful in research on autism because they are sensitive to the early development of the 'parallel' and integrated processing of self- and other-referenced stimuli. Moreover, joint attention behaviors are a consequence, but also an organizer of the functional development of a distal distributed cortical system involving anterior networks including the prefrontal and insula cortices, as well as posterior neural networks including the temporal and parietal cortices. Measures of joint attention provide early behavioral indicators of atypical development in this parallel and distributed processing system in autism. In addition it is proposed that an early, chronic disturbance in the capacity for integrating self- and other-referenced information may have cascading effects on the development of self awareness in autism. The assumptions, empirical support and future research implications of this model are discussed.

Energy-efficient STDP-based learning circuits with memristor synapses

NASA Astrophysics Data System (ADS)

Wu, Xinyu; Saxena, Vishal; Campbell, Kristy A.

2014-05-01

It is now accepted that the traditional von Neumann architecture, with processor and memory separation, is ill suited to process parallel data streams which a mammalian brain can efficiently handle. Moreover, researchers now envision computing architectures which enable cognitive processing of massive amounts of data by identifying spatio-temporal relationships in real-time and solving complex pattern recognition problems. Memristor cross-point arrays, integrated with standard CMOS technology, are expected to result in massively parallel and low-power Neuromorphic computing architectures. Recently, significant progress has been made in spiking neural networks (SNN) which emulate data processing in the cortical brain. These architectures comprise of a dense network of neurons and the synapses formed between the axons and dendrites. Further, unsupervised or supervised competitive learning schemes are being investigated for global training of the network. In contrast to a software implementation, hardware realization of these networks requires massive circuit overhead for addressing and individually updating network weights. Instead, we employ bio-inspired learning rules such as the spike-timing-dependent plasticity (STDP) to efficiently update the network weights locally. To realize SNNs on a chip, we propose to use densely integrating mixed-signal integrate-andfire neurons (IFNs) and cross-point arrays of memristors in back-end-of-the-line (BEOL) of CMOS chips. Novel IFN circuits have been designed to drive memristive synapses in parallel while maintaining overall power efficiency (<1 pJ/spike/synapse), even at spike rate greater than 10 MHz. We present circuit design details and simulation results of the IFN with memristor synapses, its response to incoming spike trains and STDP learning characterization.

Photonic reservoir computing: a new approach to optical information processing

NASA Astrophysics Data System (ADS)

Vandoorne, Kristof; Fiers, Martin; Verstraeten, David; Schrauwen, Benjamin; Dambre, Joni; Bienstman, Peter

2010-06-01

Despite ever increasing computational power, recognition and classification problems remain challenging to solve. Recently, advances have been made by the introduction of the new concept of reservoir computing. This is a methodology coming from the field of machine learning and neural networks that has been successfully used in several pattern classification problems, like speech and image recognition. Thus far, most implementations have been in software, limiting their speed and power efficiency. Photonics could be an excellent platform for a hardware implementation of this concept because of its inherent parallelism and unique nonlinear behaviour. Moreover, a photonic implementation offers the promise of massively parallel information processing with low power and high speed. We propose using a network of coupled Semiconductor Optical Amplifiers (SOA) and show in simulation that it could be used as a reservoir by comparing it to conventional software implementations using a benchmark speech recognition task. In spite of the differences with classical reservoir models, the performance of our photonic reservoir is comparable to that of conventional implementations and sometimes slightly better. As our implementation uses coherent light for information processing, we find that phase tuning is crucial to obtain high performance. In parallel we investigate the use of a network of photonic crystal cavities. The coupled mode theory (CMT) is used to investigate these resonators. A new framework is designed to model networks of resonators and SOAs. The same network topologies are used, but feedback is added to control the internal dynamics of the system. By adjusting the readout weights of the network in a controlled manner, we can generate arbitrary periodic patterns.

Learning-based computing techniques in geoid modeling for precise height transformation

NASA Astrophysics Data System (ADS)

Erol, B.; Erol, S.

2013-03-01

Precise determination of local geoid is of particular importance for establishing height control in geodetic GNSS applications, since the classical leveling technique is too laborious. A geoid model can be accurately obtained employing properly distributed benchmarks having GNSS and leveling observations using an appropriate computing algorithm. Besides the classical multivariable polynomial regression equations (MPRE), this study attempts an evaluation of learning based computing algorithms: artificial neural networks (ANNs), adaptive network-based fuzzy inference system (ANFIS) and especially the wavelet neural networks (WNNs) approach in geoid surface approximation. These algorithms were developed parallel to advances in computer technologies and recently have been used for solving complex nonlinear problems of many applications. However, they are rather new in dealing with precise modeling problem of the Earth gravity field. In the scope of the study, these methods were applied to Istanbul GPS Triangulation Network data. The performances of the methods were assessed considering the validation results of the geoid models at the observation points. In conclusion the ANFIS and WNN revealed higher prediction accuracies compared to ANN and MPRE methods. Beside the prediction capabilities, these methods were also compared and discussed from the practical point of view in conclusions.

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

NASA Astrophysics Data System (ADS)

Javidi, Bahram

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

Optical computing and image processing using photorefractive gallium arsenide

NASA Technical Reports Server (NTRS)

Cheng, Li-Jen; Liu, Duncan T. H.

1990-01-01

Recent experimental results on matrix-vector multiplication and multiple four-wave mixing using GaAs are presented. Attention is given to a simple concept of using two overlapping holograms in GaAs to do two matrix-vector multiplication processes operating in parallel with a common input vector. This concept can be used to construct high-speed, high-capacity, reconfigurable interconnection and multiplexing modules, important for optical computing and neural-network applications.

A comparison study between MLP and convolutional neural network models for character recognition

NASA Astrophysics Data System (ADS)

Ben Driss, S.; Soua, M.; Kachouri, R.; Akil, M.

2017-05-01

Optical Character Recognition (OCR) systems have been designed to operate on text contained in scanned documents and images. They include text detection and character recognition in which characters are described then classified. In the classification step, characters are identified according to their features or template descriptions. Then, a given classifier is employed to identify characters. In this context, we have proposed the unified character descriptor (UCD) to represent characters based on their features. Then, matching was employed to ensure the classification. This recognition scheme performs a good OCR Accuracy on homogeneous scanned documents, however it cannot discriminate characters with high font variation and distortion.3 To improve recognition, classifiers based on neural networks can be used. The multilayer perceptron (MLP) ensures high recognition accuracy when performing a robust training. Moreover, the convolutional neural network (CNN), is gaining nowadays a lot of popularity for its high performance. Furthermore, both CNN and MLP may suffer from the large amount of computation in the training phase. In this paper, we establish a comparison between MLP and CNN. We provide MLP with the UCD descriptor and the appropriate network configuration. For CNN, we employ the convolutional network designed for handwritten and machine-printed character recognition (Lenet-5) and we adapt it to support 62 classes, including both digits and characters. In addition, GPU parallelization is studied to speed up both of MLP and CNN classifiers. Based on our experimentations, we demonstrate that the used real-time CNN is 2x more relevant than MLP when classifying characters.

Parallel approach to identifying the well-test interpretation model using a neurocomputer

NASA Astrophysics Data System (ADS)

May, Edward A., Jr.; Dagli, Cihan H.

1996-03-01

The well test is one of the primary diagnostic and predictive tools used in the analysis of oil and gas wells. In these tests, a pressure recording device is placed in the well and the pressure response is recorded over time under controlled flow conditions. The interpreted results are indicators of the well's ability to flow and the damage done to the formation surrounding the wellbore during drilling and completion. The results are used for many purposes, including reservoir modeling (simulation) and economic forecasting. The first step in the analysis is the identification of the Well-Test Interpretation (WTI) model, which determines the appropriate solution method. Mis-identification of the WTI model occurs due to noise and non-ideal reservoir conditions. Previous studies have shown that a feed-forward neural network using the backpropagation algorithm can be used to identify the WTI model. One of the drawbacks to this approach is, however, training time, which can run into days of CPU time on personal computers. In this paper a similar neural network is applied using both a personal computer and a neurocomputer. Input data processing, network design, and performance are discussed and compared. The results show that the neurocomputer greatly eases the burden of training and allows the network to outperform a similar network running on a personal computer.

Neurological impressions on the organization of language networks in the human brain.

PubMed

Oliveira, Fabricio Ferreira de; Marin, Sheilla de Medeiros Correia; Bertolucci, Paulo Henrique Ferreira

2017-01-01

More than 95% of right-handed individuals, as well as almost 80% of left-handed individuals, have left hemisphere dominance for language. The perisylvian networks of the dominant hemisphere tend to be the most important language systems in human brains, usually connected by bidirectional fibres originated from the superior longitudinal fascicle/arcuate fascicle system and potentially modifiable by learning. Neuroplasticity mechanisms take place to preserve neural functions after brain injuries. Language is dependent on a hierarchical interlinkage of serial and parallel processing areas in distinct brain regions considered to be elementary processing units. Whereas aphasic syndromes typically result from injuries to the dominant hemisphere, the extent of the distribution of language functions seems to be variable for each individual. Review of the literature Results: Several theories try to explain the organization of language networks in the human brain from a point of view that involves either modular or distributed processing or sometimes both. The most important evidence for each approach is discussed under the light of modern theories of organization of neural networks. Understanding the connectivity patterns of language networks may provide deeper insights into language functions, supporting evidence-based rehabilitation strategies that focus on the enhancement of language organization for patients with aphasic syndromes.

An Investigation of the Application of Artificial Neural Networks to Adaptive Optics Imaging Systems

DTIC Science & Technology

1991-12-01

neural network and the feedforward neural network studied is the single layer perceptron artificial neural network . The recurrent artificial neural network input...features are the wavefront sensor slope outputs and neighboring actuator feedback commands. The feedforward artificial neural network input

Neural convergence for language comprehension and grammatical class production in highly proficient bilinguals is independent of age of acquisition.

PubMed

Consonni, Monica; Cafiero, Riccardo; Marin, Dario; Tettamanti, Marco; Iadanza, Antonella; Fabbro, Franco; Perani, Daniela

2013-05-01

In bilinguals, native (L1) and second (L2) languages are processed by the same neural resources that can be modulated by age of second language acquisition (AOA), proficiency level, and daily language exposure and usage. AOA seems to particularly affect grammar processing, where a complete neural convergence has been shown only in bilinguals with parallel language acquisition from birth. Despite the fact that proficiency-related neuroanatomical differences have been well documented in language comprehension (LC) and production, few reports have addressed the influence of language exposure. A still unanswered question pertains to the role of AOA, when proficiency is comparably high across languages, with respect to its modulator effects both on LC and production. Here, we evaluated with fMRI during sentence comprehension and verb and noun production tasks, two groups of highly proficient bilinguals only differing in AOA. One group learned Italian and Friulian in parallel from birth, whereas the second group learned Italian between 3 and 6 years. All participants were highly exposed to both languages, but more to Italian than Friulian. The results indicate a complete overlap of neural activations for the comprehension of both languages, not only in bilinguals from birth, but also in late bilinguals. A slightly extra activation in the left thalamus for the less-exposed language confirms that exposure may affect language processing. Noteworthy, we report for the first time that, when proficiency and exposure are kept high, noun and verb production recruit the same neural networks for L1 and L2, independently of AOA. These results support the neural convergence hypothesis. Copyright © 2012 Elsevier Ltd. All rights reserved.

The neural correlates of statistical learning in a word segmentation task: An fMRI study

PubMed Central

Karuza, Elisabeth A.; Newport, Elissa L.; Aslin, Richard N.; Starling, Sarah J.; Tivarus, Madalina E.; Bavelier, Daphne

2013-01-01

Functional magnetic resonance imaging (fMRI) was used to assess neural activation as participants learned to segment continuous streams of speech containing syllable sequences varying in their transitional probabilities. Speech streams were presented in four runs, each followed by a behavioral test to measure the extent of learning over time. Behavioral performance indicated that participants could discriminate statistically coherent sequences (words) from less coherent sequences (partwords). Individual rates of learning, defined as the difference in ratings for words and partwords, were used as predictors of neural activation to ask which brain areas showed activity associated with these measures. Results showed significant activity in the pars opercularis and pars triangularis regions of the left inferior frontal gyrus (LIFG). The relationship between these findings and prior work on the neural basis of statistical learning is discussed, and parallels to the frontal/subcortical network involved in other forms of implicit sequence learning are considered. PMID:23312790

Advanced Aeroservoelastic Testing and Data Analysis (Les Essais Aeroservoelastiques et l’Analyse des Donnees).

DTIC Science & Technology

1995-11-01

network - based AFS concepts. Neural networks can addition of vanes in each engine exhaust for thrust provide...parameter estimation programs 19-11 8.6 Neural Network Based Methods unknown parameters of the postulated state space model Artificial neural network ...Forward Neural Network the network that the applicability of the recurrent neural and ii) Recurrent Neural Network [117-119]. network to

Autoplan: A self-processing network model for an extended blocks world planning environment

NASA Technical Reports Server (NTRS)

Dautrechy, C. Lynne; Reggia, James A.; Mcfadden, Frank

1990-01-01

Self-processing network models (neural/connectionist models, marker passing/message passing networks, etc.) are currently undergoing intense investigation for a variety of information processing applications. These models are potentially very powerful in that they support a large amount of explicit parallel processing, and they cleanly integrate high level and low level information processing. However they are currently limited by a lack of understanding of how to apply them effectively in many application areas. The formulation of self-processing network methods for dynamic, reactive planning is studied. The long-term goal is to formulate robust, computationally effective information processing methods for the distributed control of semiautonomous exploration systems, e.g., the Mars Rover. The current research effort is focusing on hierarchical plan generation, execution and revision through local operations in an extended blocks world environment. This scenario involves many challenging features that would be encountered in a real planning and control environment: multiple simultaneous goals, parallel as well as sequential action execution, action sequencing determined not only by goals and their interactions but also by limited resources (e.g., three tasks, two acting agents), need to interpret unanticipated events and react appropriately through replanning, etc.

Neuron splitting in compute-bound parallel network simulations enables runtime scaling with twice as many processors.

PubMed

Hines, Michael L; Eichner, Hubert; Schürmann, Felix

2008-08-01

Neuron tree topology equations can be split into two subtrees and solved on different processors with no change in accuracy, stability, or computational effort; communication costs involve only sending and receiving two double precision values by each subtree at each time step. Splitting cells is useful in attaining load balance in neural network simulations, especially when there is a wide range of cell sizes and the number of cells is about the same as the number of processors. For compute-bound simulations load balance results in almost ideal runtime scaling. Application of the cell splitting method to two published network models exhibits good runtime scaling on twice as many processors as could be effectively used with whole-cell balancing.

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

NASA Astrophysics Data System (ADS)

Ebrahimi, Mehdi; Jahangirian, Alireza

2017-12-01

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

Neural networks for aircraft control

NASA Technical Reports Server (NTRS)

Linse, Dennis

1990-01-01

Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.

Deep Neural Network Emulation of a High-Order, WENO-Limited, Space-Time Reconstruction

NASA Astrophysics Data System (ADS)

Norman, M. R.; Hall, D. M.

2017-12-01

Deep Neural Networks (DNNs) have been used to emulate a number of processes in atmospheric models, including radiation and even so-called super-parameterization of moist convection. In each scenario, the DNN provides a good representation of the process even for inputs that have not been encountered before. More notably, they provide an emulation at a fraction of the cost of the original routine, giving speed-ups of 30× and even up to 200× compared to the runtime costs of the original routines. However, to our knowledge there has not been an investigation into using DNNs to emulate the dynamics. The most likely reason for this is that dynamics operators are typically both linear and low cost, meaning they cannot be sped up by a non-linear DNN emulation. However, there exist high-cost non-linear space-time dynamics operators that significantly reduce the number of parallel data transfers necessary to complete an atmospheric simulation. The WENO-limited Finite-Volume method with ADER-DT time integration is a prime example of this - needing only two parallel communications per large, fully limited time step. However, it comes at a high cost in terms of computation, which is why many would hesitate to use it. This talk investigates DNN emulation of the WENO-limited space-time finite-volume reconstruction procedure - the most expensive portion of this method, which densely clusters a large amount of non-linear computation. Different training techniques and network architectures are tested, and the accuracy and speed-up of each is given.

Comparison of neural network applications for channel assignment in cellular TDMA networks and dynamically sectored PCS networks

NASA Astrophysics Data System (ADS)

Hortos, William S.

1997-04-01

The use of artificial neural networks (NNs) to address the channel assignment problem (CAP) for cellular time-division multiple access and code-division multiple access networks has previously been investigated by this author and many others. The investigations to date have been based on a hexagonal cell structure established by omnidirectional antennas at the base stations. No account was taken of the use of spatial isolation enabled by directional antennas to reduce interference between mobiles. Any reduction in interference translates into increased capacity and consequently alters the performance of the NNs. Previous studies have sought to improve the performance of Hopfield- Tank network algorithms and self-organizing feature map algorithms applied primarily to static channel assignment (SCA) for cellular networks that handle uniformly distributed, stationary traffic in each cell for a single type of service. The resulting algorithms minimize energy functions representing interference constraint and ad hoc conditions that promote convergence to optimal solutions. While the structures of the derived neural network algorithms (NNAs) offer the potential advantages of inherent parallelism and adaptability to changing system conditions, this potential has yet to be fulfilled the CAP for emerging mobile networks. The next-generation communication infrastructures must accommodate dynamic operating conditions. Macrocell topologies are being refined to microcells and picocells that can be dynamically sectored by adaptively controlled, directional antennas and programmable transceivers. These networks must support the time-varying demands for personal communication services (PCS) that simultaneously carry voice, data and video and, thus, require new dynamic channel assignment (DCA) algorithms. This paper examines the impact of dynamic cell sectoring and geometric conditioning on NNAs developed for SCA in omnicell networks with stationary traffic to improve the metrics of convergence rate and call blocking. Genetic algorithms (GAs) are also considered in PCS networks as a means to overcome the known weakness of Hopfield NNAs in determining global minima. The resulting GAs for DCA in PCS networks are compared to improved DCA algorithms based on Hopfield NNs for stationary cellular networks. Algorithm performance is compared on the basis of rate of convergence, blocking probability, analytic complexity, and parametric sensitivity to transient traffic demands and channel interference.

Time Series Neural Network Model for Part-of-Speech Tagging Indonesian Language

NASA Astrophysics Data System (ADS)

Tanadi, Theo

2018-03-01

Part-of-speech tagging (POS tagging) is an important part in natural language processing. Many methods have been used to do this task, including neural network. This paper models a neural network that attempts to do POS tagging. A time series neural network is modelled to solve the problems that a basic neural network faces when attempting to do POS tagging. In order to enable the neural network to have text data input, the text data will get clustered first using Brown Clustering, resulting a binary dictionary that the neural network can use. To further the accuracy of the neural network, other features such as the POS tag, suffix, and affix of previous words would also be fed to the neural network.

Use of artificial intelligence in analytical systems for the clinical laboratory

PubMed Central

Truchaud, Alain; Ozawa, Kyoichi; Pardue, Harry; Schnipelsky, Paul

1995-01-01

The incorporation of information-processing technology into analytical systems in the form of standard computing software has recently been advanced by the introduction of artificial intelligence (AI), both as expert systems and as neural networks. This paper considers the role of software in system operation, control and automation, and attempts to define intelligence. AI is characterized by its ability to deal with incomplete and imprecise information and to accumulate knowledge. Expert systems, building on standard computing techniques, depend heavily on the domain experts and knowledge engineers that have programmed them to represent the real world. Neural networks are intended to emulate the pattern-recognition and parallel processing capabilities of the human brain and are taught rather than programmed. The future may lie in a combination of the recognition ability of the neural network and the rationalization capability of the expert system. In the second part of the paper, examples are given of applications of AI in stand-alone systems for knowledge engineering and medical diagnosis and in embedded systems for failure detection, image analysis, user interfacing, natural language processing, robotics and machine learning, as related to clinical laboratories. It is concluded that AI constitutes a collective form of intellectual propery, and that there is a need for better documentation, evaluation and regulation of the systems already being used in clinical laboratories. PMID:18924784

Fitting neuron models to spike trains.

PubMed

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

2011-01-01

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

Analysis of fault-tolerant neurocontrol architectures

NASA Technical Reports Server (NTRS)

Troudet, T.; Merrill, W.

1992-01-01

The fault-tolerance of analog parallel distributed implementations of a multivariable aircraft neurocontroller is analyzed by simulating weight and neuron failures in a simplified scheme of analog processing based on the functional architecture of the ETANN chip (Electrically Trainable Artificial Neural Network). The neural information processing is found to be only partially distributed throughout the set of weights of the neurocontroller synthesized with the backpropagation algorithm. Although the degree of distribution of the neural processing, and consequently the fault-tolerance of the neurocontroller, could be enhanced using Locally Distributed Weight and Neuron Approaches, a satisfactory level of fault-tolerance could only be obtained by retraining the degrated VLSI neurocontroller. The possibility of maintaining neurocontrol performance and stability in the presence of single weight of neuron failures was demonstrated through an automated retraining procedure of the neurocontroller based on a pre-programmed choice and sequence of the training parameters.

High Performance Computing for Medical Image Interpretation

DTIC Science & Technology

1993-10-01

programme for some key companies in the health care industries (Dumay et al., (1993)). With the modules developed for the "Smart Surgeon" an anatomical model...Interpretation System" (HIPMI 2S) geoft FEL-TNO do mogelijkheid omn haar expertise amn to bieden amn do Nederlandse, en Europese civiole medische industrie ...Spin-off 23 3 HIGH PERFORMANCE COMPUTING 24 3.1 Introduction 24 3.2 Parallel processing 24 3.3 Artificial Neural Networks 25 3.4 European Industry

Integration of photoactive and electroactive components with vertical cavity surface emitting lasers

DOEpatents

Bryan, R.P.; Esherick, P.; Jewell, J.L.; Lear, K.L.; Olbright, G.R.

1997-04-29

A monolithically integrated optoelectronic device is provided which integrates a vertical cavity surface emitting laser and either a photosensitive or an electrosensitive device either as input or output to the vertical cavity surface emitting laser either in parallel or series connection. Both vertical and side-by-side arrangements are disclosed, and optical and electronic feedback means are provided. Arrays of these devices can be configured to enable optical computing and neural network applications. 9 figs.

Integration of photoactive and electroactive components with vertical cavity surface emitting lasers

DOEpatents

Bryan, Robert P.; Esherick, Peter; Jewell, Jack L.; Lear, Kevin L.; Olbright, Gregory R.

1997-01-01

A monolithically integrated optoelectronic device is provided which integrates a vertical cavity surface emitting laser and either a photosensitive or an electrosensitive device either as input or output to the vertical cavity surface emitting laser either in parallel or series connection. Both vertical and side-by-side arrangements are disclosed, and optical and electronic feedback means are provided. Arrays of these devices can be configured to enable optical computing and neural network applications.

Neural Network Control of a Parallel Hybrid-Electric Propulsion System for a Small Unmanned Aerial Vehicle

DTIC Science & Technology

2005-01-01

Eppler , or Selig airfoil [147, 148] to be used. Other high lift wings could be used such as the low Reynolds number NASA LRN-I-1010 airfoil used in...Fraser, Airfoils at Low Speeds. Virginia Beach, VA: H.A. Stokely, 1989. [148] R. Eppler , Airfoil Design and Data. Berlin, Germany: Springer-Verlag... 61 Figure 3-4: RMS Error for CMAC Approximation (L=3) .......................................... 61 Figure 3-5: CMAC

Cascaded VLSI neural network architecture for on-line learning

NASA Technical Reports Server (NTRS)

Thakoor, Anilkumar P. (Inventor); Duong, Tuan A. (Inventor); Daud, Taher (Inventor)

1992-01-01

High-speed, analog, fully-parallel, and asynchronous building blocks are cascaded for larger sizes and enhanced resolution. A hardware compatible algorithm permits hardware-in-the-loop learning despite limited weight resolution. A computation intensive feature classification application was demonstrated with this flexible hardware and new algorithm at high speed. This result indicates that these building block chips can be embedded as an application specific coprocessor for solving real world problems at extremely high data rates.

Cascaded VLSI neural network architecture for on-line learning

NASA Technical Reports Server (NTRS)

Duong, Tuan A. (Inventor); Daud, Taher (Inventor); Thakoor, Anilkumar P. (Inventor)

1995-01-01

High-speed, analog, fully-parallel and asynchronous building blocks are cascaded for larger sizes and enhanced resolution. A hardware-compatible algorithm permits hardware-in-the-loop learning despite limited weight resolution. A comparison-intensive feature classification application has been demonstrated with this flexible hardware and new algorithm at high speed. This result indicates that these building block chips can be embedded as application-specific-coprocessors for solving real-world problems at extremely high data rates.

A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images.

PubMed

Pang, Shuchao; Yu, Zhezhou; Orgun, Mehmet A

2017-03-01

Highly accurate classification of biomedical images is an essential task in the clinical diagnosis of numerous medical diseases identified from those images. Traditional image classification methods combined with hand-crafted image feature descriptors and various classifiers are not able to effectively improve the accuracy rate and meet the high requirements of classification of biomedical images. The same also holds true for artificial neural network models directly trained with limited biomedical images used as training data or directly used as a black box to extract the deep features based on another distant dataset. In this study, we propose a highly reliable and accurate end-to-end classifier for all kinds of biomedical images via deep learning and transfer learning. We first apply domain transferred deep convolutional neural network for building a deep model; and then develop an overall deep learning architecture based on the raw pixels of original biomedical images using supervised training. In our model, we do not need the manual design of the feature space, seek an effective feature vector classifier or segment specific detection object and image patches, which are the main technological difficulties in the adoption of traditional image classification methods. Moreover, we do not need to be concerned with whether there are large training sets of annotated biomedical images, affordable parallel computing resources featuring GPUs or long times to wait for training a perfect deep model, which are the main problems to train deep neural networks for biomedical image classification as observed in recent works. With the utilization of a simple data augmentation method and fast convergence speed, our algorithm can achieve the best accuracy rate and outstanding classification ability for biomedical images. We have evaluated our classifier on several well-known public biomedical datasets and compared it with several state-of-the-art approaches. We propose a robust automated end-to-end classifier for biomedical images based on a domain transferred deep convolutional neural network model that shows a highly reliable and accurate performance which has been confirmed on several public biomedical image datasets. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

DOE PAGES

Gawande, Nitin A.; Daily, Jeff A.; Siegel, Charles; ...

2018-05-05

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consistsmore » of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.« less

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

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

Gawande, Nitin A.; Daily, Jeff A.; Siegel, Charles

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consistsmore » of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.« less

Parallel trends in cortical gray and white matter architecture and connections in primates allow fine study of pathways in humans and reveal network disruptions in autism

PubMed Central

García-Cabezas, Miguel Ángel; Barbas, Helen

2018-01-01

Noninvasive imaging and tractography methods have yielded information on broad communication networks but lack resolution to delineate intralaminar cortical and subcortical pathways in humans. An important unanswered question is whether we can use the wealth of precise information on pathways from monkeys to understand connections in humans. We addressed this question within a theoretical framework of systematic cortical variation and used identical high-resolution methods to compare the architecture of cortical gray matter and the white matter beneath, which gives rise to short- and long-distance pathways in humans and rhesus monkeys. We used the prefrontal cortex as a model system because of its key role in attention, emotions, and executive function, which are processes often affected in brain diseases. We found striking parallels and consistent trends in the gray and white matter architecture in humans and monkeys and between the architecture and actual connections mapped with neural tracers in rhesus monkeys and, by extension, in humans. Using the novel architectonic portrait as a base, we found significant changes in pathways between nearby prefrontal and distant areas in autism. Our findings reveal that a theoretical framework allows study of normal neural communication in humans at high resolution and specific disruptions in diverse psychiatric and neurodegenerative diseases. PMID:29401206

Interactions between Depression and Facilitation within Neural Networks: Updating the Dual-Process Theory of Plasticity

PubMed Central

Prescott, Steven A.

1998-01-01

Repetitive stimulation often results in habituation of the elicited response. However, if the stimulus is sufficiently strong, habituation may be preceded by transient sensitization or even replaced by enduring sensitization. In 1970, Groves and Thompson formulated the dual-process theory of plasticity to explain these characteristic behavioral changes on the basis of competition between decremental plasticity (depression) and incremental plasticity (facilitation) occurring within the neural network. Data from both vertebrate and invertebrate systems are reviewed and indicate that the effects of depression and facilitation are not exclusively additive but, rather, that those processes interact in a complex manner. Serial ordering of induction of learning, in which a depressing locus precedes the modulatory system responsible for inducing facilitation, causes the facilitation to wane. The parallel and/or serial expression of depression and waning facilitation within the stimulus–response pathway culminates in the behavioral changes that characterize dual-process learning. A mathematical model is presented to formally express and extend understanding of the interactions between depression and facilitation. PMID:10489261

High resolution ultrasonic spectroscopy system for nondestructive evaluation

NASA Technical Reports Server (NTRS)

Chen, C. H.

1991-01-01

With increased demand for high resolution ultrasonic evaluation, computer based systems or work stations become essential. The ultrasonic spectroscopy method of nondestructive evaluation (NDE) was used to develop a high resolution ultrasonic inspection system supported by modern signal processing, pattern recognition, and neural network technologies. The basic system which was completed consists of a 386/20 MHz PC (IBM AT compatible), a pulser/receiver, a digital oscilloscope with serial and parallel communications to the computer, an immersion tank with motor control of X-Y axis movement, and the supporting software package, IUNDE, for interactive ultrasonic evaluation. Although the hardware components are commercially available, the software development is entirely original. By integrating signal processing, pattern recognition, maximum entropy spectral analysis, and artificial neural network functions into the system, many NDE tasks can be performed. The high resolution graphics capability provides visualization of complex NDE problems. The phase 3 efforts involve intensive marketing of the software package and collaborative work with industrial sectors.

Information flow in layered networks of non-monotonic units

NASA Astrophysics Data System (ADS)

Schittler Neves, Fabio; Martim Schubert, Benno; Erichsen, Rubem, Jr.

2015-07-01

Layered neural networks are feedforward structures that yield robust parallel and distributed pattern recognition. Even though much attention has been paid to pattern retrieval properties in such systems, many aspects of their dynamics are not yet well characterized or understood. In this work we study, at different temperatures, the memory activity and information flows through layered networks in which the elements are the simplest binary odd non-monotonic function. Our results show that, considering a standard Hebbian learning approach, the network information content has its maximum always at the monotonic limit, even though the maximum memory capacity can be found at non-monotonic values for small enough temperatures. Furthermore, we show that such systems exhibit rich macroscopic dynamics, including not only fixed point solutions of its iterative map, but also cyclic and chaotic attractors that also carry information.

Selection of neural network structure for system error correction of electro-optical tracker system with horizontal gimbal

NASA Astrophysics Data System (ADS)

Liu, Xing-fa; Cen, Ming

2007-12-01

Neural Network system error correction method is more precise than lest square system error correction method and spheric harmonics function system error correction method. The accuracy of neural network system error correction method is mainly related to the frame of Neural Network. Analysis and simulation prove that both BP neural network system error correction method and RBF neural network system error correction method have high correction accuracy; it is better to use RBF Network system error correction method than BP Network system error correction method for little studying stylebook considering training rate and neural network scale.

A novel recurrent neural network with finite-time convergence for linear programming.

PubMed

Liu, Qingshan; Cao, Jinde; Chen, Guanrong

2010-11-01

In this letter, a novel recurrent neural network based on the gradient method is proposed for solving linear programming problems. Finite-time convergence of the proposed neural network is proved by using the Lyapunov method. Compared with the existing neural networks for linear programming, the proposed neural network is globally convergent to exact optimal solutions in finite time, which is remarkable and rare in the literature of neural networks for optimization. Some numerical examples are given to show the effectiveness and excellent performance of the new recurrent neural network.

Modular, Hierarchical Learning By Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Baldi, Pierre F.; Toomarian, Nikzad

1996-01-01

Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.

Neuromimetic Circuits with Synaptic Devices Based on Strongly Correlated Electron Systems

NASA Astrophysics Data System (ADS)

Ha, Sieu D.; Shi, Jian; Meroz, Yasmine; Mahadevan, L.; Ramanathan, Shriram

2014-12-01

Strongly correlated electron systems such as the rare-earth nickelates (R NiO3 , R denotes a rare-earth element) can exhibit synapselike continuous long-term potentiation and depression when gated with ionic liquids; exploiting the extreme sensitivity of coupled charge, spin, orbital, and lattice degrees of freedom to stoichiometry. We present experimental real-time, device-level classical conditioning and unlearning using nickelate-based synaptic devices in an electronic circuit compatible with both excitatory and inhibitory neurons. We establish a physical model for the device behavior based on electric-field-driven coupled ionic-electronic diffusion that can be utilized for design of more complex systems. We use the model to simulate a variety of associate and nonassociative learning mechanisms, as well as a feedforward recurrent network for storing memory. Our circuit intuitively parallels biological neural architectures, and it can be readily generalized to other forms of cellular learning and extinction. The simulation of neural function with electronic device analogs may provide insight into biological processes such as decision making, learning, and adaptation, while facilitating advanced parallel information processing in hardware.

Linear matrix inequality approach to exponential synchronization of a class of chaotic neural networks with time-varying delays

NASA Astrophysics Data System (ADS)

Wu, Wei; Cui, Bao-Tong

2007-07-01

In this paper, a synchronization scheme for a class of chaotic neural networks with time-varying delays is presented. This class of chaotic neural networks covers several well-known neural networks, such as Hopfield neural networks, cellular neural networks, and bidirectional associative memory networks. The obtained criteria are expressed in terms of linear matrix inequalities, thus they can be efficiently verified. A comparison between our results and the previous results shows that our results are less restrictive.

Retrieval of Sentence Sequences for an Image Stream via Coherence Recurrent Convolutional Networks.

PubMed

Park, Cesc Chunseong; Kim, Youngjin; Kim, Gunhee

2018-04-01

We propose an approach for retrieving a sequence of natural sentences for an image stream. Since general users often take a series of pictures on their experiences, much online visual information exists in the form of image streams, for which it would better take into consideration of the whole image stream to produce natural language descriptions. While almost all previous studies have dealt with the relation between a single image and a single natural sentence, our work extends both input and output dimension to a sequence of images and a sequence of sentences. For retrieving a coherent flow of multiple sentences for a photo stream, we propose a multimodal neural architecture called coherence recurrent convolutional network (CRCN), which consists of convolutional neural networks, bidirectional long short-term memory (LSTM) networks, and an entity-based local coherence model. Our approach directly learns from vast user-generated resource of blog posts as text-image parallel training data. We collect more than 22 K unique blog posts with 170 K associated images for the travel topics of NYC, Disneyland , Australia, and Hawaii. We demonstrate that our approach outperforms other state-of-the-art image captioning methods for text sequence generation, using both quantitative measures and user studies via Amazon Mechanical Turk.

Acceleration of spiking neural network based pattern recognition on NVIDIA graphics processors.

PubMed

Han, Bing; Taha, Tarek M

2010-04-01

There is currently a strong push in the research community to develop biological scale implementations of neuron based vision models. Systems at this scale are computationally demanding and generally utilize more accurate neuron models, such as the Izhikevich and the Hodgkin-Huxley models, in favor of the more popular integrate and fire model. We examine the feasibility of using graphics processing units (GPUs) to accelerate a spiking neural network based character recognition network to enable such large scale systems. Two versions of the network utilizing the Izhikevich and Hodgkin-Huxley models are implemented. Three NVIDIA general-purpose (GP) GPU platforms are examined, including the GeForce 9800 GX2, the Tesla C1060, and the Tesla S1070. Our results show that the GPGPUs can provide significant speedup over conventional processors. In particular, the fastest GPGPU utilized, the Tesla S1070, provided a speedup of 5.6 and 84.4 over highly optimized implementations on the fastest central processing unit (CPU) tested, a quadcore 2.67 GHz Xeon processor, for the Izhikevich and the Hodgkin-Huxley models, respectively. The CPU implementation utilized all four cores and the vector data parallelism offered by the processor. The results indicate that GPUs are well suited for this application domain.

The neural network to determine the mechanical properties of the steels

NASA Astrophysics Data System (ADS)

Yemelyanov, Vitaliy; Yemelyanova, Nataliya; Safonova, Marina; Nedelkin, Aleksey

2018-04-01

The authors describe the neural network structure and software that is designed and developed to determine the mechanical properties of steels. The neural network is developed to refine upon the values of the steels properties. The results of simulations of the developed neural network are shown. The authors note the low standard error of the proposed neural network. To realize the proposed neural network the specialized software has been developed.

A Digital Liquid State Machine With Biologically Inspired Learning and Its Application to Speech Recognition.

PubMed

Zhang, Yong; Li, Peng; Jin, Yingyezhe; Choe, Yoonsuck

2015-11-01

This paper presents a bioinspired digital liquid-state machine (LSM) for low-power very-large-scale-integration (VLSI)-based machine learning applications. To the best of the authors' knowledge, this is the first work that employs a bioinspired spike-based learning algorithm for the LSM. With the proposed online learning, the LSM extracts information from input patterns on the fly without needing intermediate data storage as required in offline learning methods such as ridge regression. The proposed learning rule is local such that each synaptic weight update is based only upon the firing activities of the corresponding presynaptic and postsynaptic neurons without incurring global communications across the neural network. Compared with the backpropagation-based learning, the locality of computation in the proposed approach lends itself to efficient parallel VLSI implementation. We use subsets of the TI46 speech corpus to benchmark the bioinspired digital LSM. To reduce the complexity of the spiking neural network model without performance degradation for speech recognition, we study the impacts of synaptic models on the fading memory of the reservoir and hence the network performance. Moreover, we examine the tradeoffs between synaptic weight resolution, reservoir size, and recognition performance and present techniques to further reduce the overhead of hardware implementation. Our simulation results show that in terms of isolated word recognition evaluated using the TI46 speech corpus, the proposed digital LSM rivals the state-of-the-art hidden Markov-model-based recognizer Sphinx-4 and outperforms all other reported recognizers including the ones that are based upon the LSM or neural networks.

Optical Symbolic Computing

NASA Astrophysics Data System (ADS)

Neff, John A.

1989-12-01

Experiments originating from Gestalt psychology have shown that representing information in a symbolic form provides a more effective means to understanding. Computer scientists have been struggling for the last two decades to determine how best to create, manipulate, and store collections of symbolic structures. In the past, much of this struggling led to software innovations because that was the path of least resistance. For example, the development of heuristics for organizing the searching through knowledge bases was much less expensive than building massively parallel machines that could search in parallel. That is now beginning to change with the emergence of parallel architectures which are showing the potential for handling symbolic structures. This paper will review the relationships between symbolic computing and parallel computing architectures, and will identify opportunities for optics to significantly impact the performance of such computing machines. Although neural networks are an exciting subset of massively parallel computing structures, this paper will not touch on this area since it is receiving a great deal of attention in the literature. That is, the concepts presented herein do not consider the distributed representation of knowledge.

Speed challenge: a case for hardware implementation in soft-computing

NASA Technical Reports Server (NTRS)

Daud, T.; Stoica, A.; Duong, T.; Keymeulen, D.; Zebulum, R.; Thomas, T.; Thakoor, A.

2000-01-01

For over a decade, JPL has been actively involved in soft computing research on theory, architecture, applications, and electronics hardware. The driving force in all our research activities, in addition to the potential enabling technology promise, has been creation of a niche that imparts orders of magnitude speed advantage by implementation in parallel processing hardware with algorithms made especially suitable for hardware implementation. We review our work on neural networks, fuzzy logic, and evolvable hardware with selected application examples requiring real time response capabilities.

Bit-serial neuroprocessor architecture

NASA Technical Reports Server (NTRS)

Tawel, Raoul (Inventor)

2001-01-01

A neuroprocessor architecture employs a combination of bit-serial and serial-parallel techniques for implementing the neurons of the neuroprocessor. The neuroprocessor architecture includes a neural module containing a pool of neurons, a global controller, a sigmoid activation ROM look-up-table, a plurality of neuron state registers, and a synaptic weight RAM. The neuroprocessor reduces the number of neurons required to perform the task by time multiplexing groups of neurons from a fixed pool of neurons to achieve the successive hidden layers of a recurrent network topology.

Automated video surveillance: teaching an old dog new tricks

NASA Astrophysics Data System (ADS)

McLeod, Alastair

1993-12-01

The automated video surveillance market is booming with new players, new systems, new hardware and software, and an extended range of applications. This paper reviews available technology, and describes the features required for a good automated surveillance system. Both hardware and software are discussed. An overview of typical applications is also given. A shift towards PC-based hybrid systems, use of parallel processing, neural networks, and exploitation of modern telecomms are introduced, highlighting the evolution modern video surveillance systems.

Parallel and patterned optogenetic manipulation of neurons in the brain slice using a DMD-based projector.

PubMed

Sakai, Seiichiro; Ueno, Kenichi; Ishizuka, Toru; Yawo, Hiromu

2013-01-01

Optical manipulation technologies greatly advanced the understanding of the neuronal network and its dysfunctions. To achieve patterned and parallel optical switching, we developed a microscopic illumination system using a commercial DMD-based projector and a software program. The spatiotemporal patterning of the system was evaluated using acute slices of the hippocampus. The neural activity was optically manipulated, positively by the combination of channelrhodopsin-2 (ChR2) and blue light, and negatively by the combination of archaerhodopsin-T (ArchT) and green light. It is suggested that our projector-managing optical system (PMOS) would effectively facilitate the optogenetic analyses of neurons and their circuits. Copyright © 2012 Elsevier Ireland Ltd and the Japan Neuroscience Society. All rights reserved.

Overcoming rule-based rigidity and connectionist limitations through massively-parallel case-based reasoning

NASA Technical Reports Server (NTRS)

Barnden, John; Srinivas, Kankanahalli

1990-01-01

Symbol manipulation as used in traditional Artificial Intelligence has been criticized by neural net researchers for being excessively inflexible and sequential. On the other hand, the application of neural net techniques to the types of high-level cognitive processing studied in traditional artificial intelligence presents major problems as well. A promising way out of this impasse is to build neural net models that accomplish massively parallel case-based reasoning. Case-based reasoning, which has received much attention recently, is essentially the same as analogy-based reasoning, and avoids many of the problems leveled at traditional artificial intelligence. Further problems are avoided by doing many strands of case-based reasoning in parallel, and by implementing the whole system as a neural net. In addition, such a system provides an approach to some aspects of the problems of noise, uncertainty and novelty in reasoning systems. The current neural net system (Conposit), which performs standard rule-based reasoning, is being modified into a massively parallel case-based reasoning version.

Empirical Mode Decomposition and Neural Networks on FPGA for Fault Diagnosis in Induction Motors

PubMed Central

Garcia-Perez, Arturo; Osornio-Rios, Roque Alfredo; Romero-Troncoso, Rene de Jesus

2014-01-01

Nowadays, many industrial applications require online systems that combine several processing techniques in order to offer solutions to complex problems as the case of detection and classification of multiple faults in induction motors. In this work, a novel digital structure to implement the empirical mode decomposition (EMD) for processing nonstationary and nonlinear signals using the full spline-cubic function is presented; besides, it is combined with an adaptive linear network (ADALINE)-based frequency estimator and a feed forward neural network (FFNN)-based classifier to provide an intelligent methodology for the automatic diagnosis during the startup transient of motor faults such as: one and two broken rotor bars, bearing defects, and unbalance. Moreover, the overall methodology implementation into a field-programmable gate array (FPGA) allows an online and real-time operation, thanks to its parallelism and high-performance capabilities as a system-on-a-chip (SoC) solution. The detection and classification results show the effectiveness of the proposed fused techniques; besides, the high precision and minimum resource usage of the developed digital structures make them a suitable and low-cost solution for this and many other industrial applications. PMID:24678281

Empirical mode decomposition and neural networks on FPGA for fault diagnosis in induction motors.

PubMed

Camarena-Martinez, David; Valtierra-Rodriguez, Martin; Garcia-Perez, Arturo; Osornio-Rios, Roque Alfredo; Romero-Troncoso, Rene de Jesus

2014-01-01

Nowadays, many industrial applications require online systems that combine several processing techniques in order to offer solutions to complex problems as the case of detection and classification of multiple faults in induction motors. In this work, a novel digital structure to implement the empirical mode decomposition (EMD) for processing nonstationary and nonlinear signals using the full spline-cubic function is presented; besides, it is combined with an adaptive linear network (ADALINE)-based frequency estimator and a feed forward neural network (FFNN)-based classifier to provide an intelligent methodology for the automatic diagnosis during the startup transient of motor faults such as: one and two broken rotor bars, bearing defects, and unbalance. Moreover, the overall methodology implementation into a field-programmable gate array (FPGA) allows an online and real-time operation, thanks to its parallelism and high-performance capabilities as a system-on-a-chip (SoC) solution. The detection and classification results show the effectiveness of the proposed fused techniques; besides, the high precision and minimum resource usage of the developed digital structures make them a suitable and low-cost solution for this and many other industrial applications.

Neural Networks for Segregation of Multiple Objects: Visual Figure-Ground Separation and Auditory Pitch Perception.

NASA Astrophysics Data System (ADS)

Wyse, Lonce

An important component of perceptual object recognition is the segmentation into coherent perceptual units of the "blooming buzzing confusion" that bombards the senses. The work presented herein develops neural network models of some key processes of pre-attentive vision and audition that serve this goal. A neural network model, called an FBF (Feature -Boundary-Feature) network, is proposed for automatic parallel separation of multiple figures from each other and their backgrounds in noisy images. Figure-ground separation is accomplished by iterating operations of a Boundary Contour System (BCS) that generates a boundary segmentation of a scene, and a Feature Contour System (FCS) that compensates for variable illumination and fills-in surface properties using boundary signals. A key new feature is the use of the FBF filling-in process for the figure-ground separation of connected regions, which are subsequently more easily recognized. The new CORT-X 2 model is a feed-forward version of the BCS that is designed to detect, regularize, and complete boundaries in up to 50 percent noise. It also exploits the complementary properties of on-cells and off -cells to generate boundary segmentations and to compensate for boundary gaps during filling-in. In the realm of audition, many sounds are dominated by energy at integer multiples, or "harmonics", of a fundamental frequency. For such sounds (e.g., vowels in speech), the individual frequency components fuse, so that they are perceived as one sound source with a pitch at the fundamental frequency. Pitch is integral to separating auditory sources, as well as to speaker identification and speech understanding. A neural network model of pitch perception called SPINET (SPatial PItch NETwork) is developed and used to simulate a broader range of perceptual data than previous spectral models. The model employs a bank of narrowband filters as a simple model of basilar membrane mechanics, spectral on-center off-surround competitive interactions, and a "harmonic sieve" mechanism whereby the strength of a pitch depends only on spectral regions near harmonics. The model is evaluated using data involving mistuned components, shifted harmonics, complex tones with varying phase relationships, and continuous spectra such as rippled noise and narrow noise bands.

Region stability analysis and tracking control of memristive recurrent neural network.

PubMed

Bao, Gang; Zeng, Zhigang; Shen, Yanjun

2018-02-01

Memristor is firstly postulated by Leon Chua and realized by Hewlett-Packard (HP) laboratory. Research results show that memristor can be used to simulate the synapses of neurons. This paper presents a class of recurrent neural network with HP memristors. Firstly, it shows that memristive recurrent neural network has more compound dynamics than the traditional recurrent neural network by simulations. Then it derives that n dimensional memristive recurrent neural network is composed of [Formula: see text] sub neural networks which do not have a common equilibrium point. By designing the tracking controller, it can make memristive neural network being convergent to the desired sub neural network. At last, two numerical examples are given to verify the validity of our result. Copyright © 2017 Elsevier Ltd. All rights reserved.

A recurrent neural network for nonlinear optimization with a continuously differentiable objective function and bound constraints.

PubMed

Liang, X B; Wang, J

2000-01-01

This paper presents a continuous-time recurrent neural-network model for nonlinear optimization with any continuously differentiable objective function and bound constraints. Quadratic optimization with bound constraints is a special problem which can be solved by the recurrent neural network. The proposed recurrent neural network has the following characteristics. 1) It is regular in the sense that any optimum of the objective function with bound constraints is also an equilibrium point of the neural network. If the objective function to be minimized is convex, then the recurrent neural network is complete in the sense that the set of optima of the function with bound constraints coincides with the set of equilibria of the neural network. 2) The recurrent neural network is primal and quasiconvergent in the sense that its trajectory cannot escape from the feasible region and will converge to the set of equilibria of the neural network for any initial point in the feasible bound region. 3) The recurrent neural network has an attractivity property in the sense that its trajectory will eventually converge to the feasible region for any initial states even at outside of the bounded feasible region. 4) For minimizing any strictly convex quadratic objective function subject to bound constraints, the recurrent neural network is globally exponentially stable for almost any positive network parameters. Simulation results are given to demonstrate the convergence and performance of the proposed recurrent neural network for nonlinear optimization with bound constraints.

Neural network-based nonlinear model predictive control vs. linear quadratic gaussian control

USGS Publications Warehouse

Cho, C.; Vance, R.; Mardi, N.; Qian, Z.; Prisbrey, K.

1997-01-01

One problem with the application of neural networks to the multivariable control of mineral and extractive processes is determining whether and how to use them. The objective of this investigation was to compare neural network control to more conventional strategies and to determine if there are any advantages in using neural network control in terms of set-point tracking, rise time, settling time, disturbance rejection and other criteria. The procedure involved developing neural network controllers using both historical plant data and simulation models. Various control patterns were tried, including both inverse and direct neural network plant models. These were compared to state space controllers that are, by nature, linear. For grinding and leaching circuits, a nonlinear neural network-based model predictive control strategy was superior to a state space-based linear quadratic gaussian controller. The investigation pointed out the importance of incorporating state space into neural networks by making them recurrent, i.e., feeding certain output state variables into input nodes in the neural network. It was concluded that neural network controllers can have better disturbance rejection, set-point tracking, rise time, settling time and lower set-point overshoot, and it was also concluded that neural network controllers can be more reliable and easy to implement in complex, multivariable plants.

An Introduction to Neural Networks for Hearing Aid Noise Recognition.

ERIC Educational Resources Information Center

Kim, Jun W.; Tyler, Richard S.

1995-01-01

This article introduces the use of multilayered artificial neural networks in hearing aid noise recognition. It reviews basic principles of neural networks, and offers an example of an application in which a neural network is used to identify the presence or absence of noise in speech. The ability of neural networks to "learn" the…

Quantized Synchronization of Chaotic Neural Networks With Scheduled Output Feedback Control.

PubMed

Wan, Ying; Cao, Jinde; Wen, Guanghui

In this paper, the synchronization problem of master-slave chaotic neural networks with remote sensors, quantization process, and communication time delays is investigated. The information communication channel between the master chaotic neural network and slave chaotic neural network consists of several remote sensors, with each sensor able to access only partial knowledge of output information of the master neural network. At each sampling instants, each sensor updates its own measurement and only one sensor is scheduled to transmit its latest information to the controller's side in order to update the control inputs for the slave neural network. Thus, such communication process and control strategy are much more energy-saving comparing with the traditional point-to-point scheme. Sufficient conditions for output feedback control gain matrix, allowable length of sampling intervals, and upper bound of network-induced delays are derived to ensure the quantized synchronization of master-slave chaotic neural networks. Lastly, Chua's circuit system and 4-D Hopfield neural network are simulated to validate the effectiveness of the main results.In this paper, the synchronization problem of master-slave chaotic neural networks with remote sensors, quantization process, and communication time delays is investigated. The information communication channel between the master chaotic neural network and slave chaotic neural network consists of several remote sensors, with each sensor able to access only partial knowledge of output information of the master neural network. At each sampling instants, each sensor updates its own measurement and only one sensor is scheduled to transmit its latest information to the controller's side in order to update the control inputs for the slave neural network. Thus, such communication process and control strategy are much more energy-saving comparing with the traditional point-to-point scheme. Sufficient conditions for output feedback control gain matrix, allowable length of sampling intervals, and upper bound of network-induced delays are derived to ensure the quantized synchronization of master-slave chaotic neural networks. Lastly, Chua's circuit system and 4-D Hopfield neural network are simulated to validate the effectiveness of the main results.

A z-Vertex Trigger for Belle II

NASA Astrophysics Data System (ADS)

Skambraks, S.; Abudinén, F.; Chen, Y.; Feindt, M.; Frühwirth, R.; Heck, M.; Kiesling, C.; Knoll, A.; Neuhaus, S.; Paul, S.; Schieck, J.

2015-08-01

The Belle II experiment will go into operation at the upgraded SuperKEKB collider in 2016. SuperKEKB is designed to deliver an instantaneous luminosity L = 8 ×1035 cm - 2 s - 1. The experiment will therefore have to cope with a much larger machine background than its predecessor Belle, in particular from events outside of the interaction region. We present the concept of a track trigger, based on a neural network approach, that is able to suppress a large fraction of this background by reconstructing the z (longitudinal) position of the event vertex within the latency of the first level trigger. The trigger uses the hit information from the Central Drift Chamber (CDC) of Belle II within narrow cones in polar and azimuthal angle as well as in transverse momentum (“sectors”), and estimates the z-vertex without explicit track reconstruction. The preprocessing for the track trigger is based on the track information provided by the standard CDC trigger. It takes input from the 2D track finder, adds information from the stereo wires of the CDC, and finds the appropriate sectors in the CDC for each track. Within the sector, the z-vertex is estimated by a specialized neural network, with the drift times from the CDC as input and a continuous output corresponding to the scaled z-vertex. The neural algorithm will be implemented in programmable hardware. To this end a Virtex 7 FPGA board will be used, which provides at present the most promising solution for a fully parallelized implementation of neural networks or alternative multivariate methods. A high speed interface for external memory will be integrated into the platform, to be able to store the O(109) parameters required. The contribution presents the results of our feasibility studies and discusses the details of the envisaged hardware solution.

Control of magnetic bearing systems via the Chebyshev polynomial-based unified model (CPBUM) neural network.

PubMed

Jeng, J T; Lee, T T

2000-01-01

A Chebyshev polynomial-based unified model (CPBUM) neural network is introduced and applied to control a magnetic bearing systems. First, we show that the CPBUM neural network not only has the same capability of universal approximator, but also has faster learning speed than conventional feedforward/recurrent neural network. It turns out that the CPBUM neural network is more suitable in the design of controller than the conventional feedforward/recurrent neural network. Second, we propose the inverse system method, based on the CPBUM neural networks, to control a magnetic bearing system. The proposed controller has two structures; namely, off-line and on-line learning structures. We derive a new learning algorithm for each proposed structure. The experimental results show that the proposed neural network architecture provides a greater flexibility and better performance in controlling magnetic bearing systems.

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.

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.

A Search for the tt¯H (H → bb) Large Hadron Collider with the atlas detector using a matrix element method

NASA Astrophysics Data System (ADS)

Basye, Austin T.

A matrix element method analysis of the Standard Model Higgs boson, produced in association with two top quarks decaying to the lepton-plus-jets channel is presented. Based on 20.3 fb--1 of s=8 TeV data, produced at the Large Hadron Collider and collected by the ATLAS detector, this analysis utilizes multiple advanced techniques to search for ttH signatures with a 125 GeV Higgs boson decaying to two b -quarks. After categorizing selected events based on their jet and b-tag multiplicities, signal rich regions are analyzed using the matrix element method. Resulting variables are then propagated to two parallel multivariate analyses utilizing Neural Networks and Boosted Decision Trees respectively. As no significant excess is found, an observed (expected) limit of 3.4 (2.2) times the Standard Model cross-section is determined at 95% confidence, using the CLs method, for the Neural Network analysis. For the Boosted Decision Tree analysis, an observed (expected) limit of 5.2 (2.7) times the Standard Model cross-section is determined at 95% confidence, using the CLs method. Corresponding unconstrained fits of the Higgs boson signal strength to the observed data result in the measured signal cross-section to Standard Model cross-section prediction of mu = 1.2 +/- 1.3(total) +/- 0.7(stat.) for the Neural Network analysis, and mu = 2.9 +/- 1.4(total) +/- 0.8(stat.) for the Boosted Decision Tree analysis.

Nested Neural Networks

NASA Technical Reports Server (NTRS)

Baram, Yoram

1992-01-01

Report presents analysis of nested neural networks, consisting of interconnected subnetworks. Analysis based on simplified mathematical models more appropriate for artificial electronic neural networks, partly applicable to biological neural networks. Nested structure allows for retrieval of individual subpatterns. Requires fewer wires and connection devices than fully connected networks, and allows for local reconstruction of damaged subnetworks without rewiring entire network.

Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science.

PubMed

Mocanu, Decebal Constantin; Mocanu, Elena; Stone, Peter; Nguyen, Phuong H; Gibescu, Madeleine; Liotta, Antonio

2018-06-19

Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g. sparsity, scale-freeness), we argue that (contrary to general practice) artificial neural networks, too, should not have fully-connected layers. Here we propose sparse evolutionary training of artificial neural networks, an algorithm which evolves an initial sparse topology (Erdős-Rényi random graph) of two consecutive layers of neurons into a scale-free topology, during learning. Our method replaces artificial neural networks fully-connected layers with sparse ones before training, reducing quadratically the number of parameters, with no decrease in accuracy. We demonstrate our claims on restricted Boltzmann machines, multi-layer perceptrons, and convolutional neural networks for unsupervised and supervised learning on 15 datasets. Our approach has the potential to enable artificial neural networks to scale up beyond what is currently possible.

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.

4-dimensional functional profiling in the convulsant-treated larval zebrafish brain.

PubMed

Winter, Matthew J; Windell, Dylan; Metz, Jeremy; Matthews, Peter; Pinion, Joe; Brown, Jonathan T; Hetheridge, Malcolm J; Ball, Jonathan S; Owen, Stewart F; Redfern, Will S; Moger, Julian; Randall, Andrew D; Tyler, Charles R

2017-07-26

Functional neuroimaging, using genetically-encoded Ca 2+ sensors in larval zebrafish, offers a powerful combination of high spatiotemporal resolution and higher vertebrate relevance for quantitative neuropharmacological profiling. Here we use zebrafish larvae with pan-neuronal expression of GCaMP6s, combined with light sheet microscopy and a novel image processing pipeline, for the 4D profiling of chemoconvulsant action in multiple brain regions. In untreated larvae, regions associated with autonomic functionality, sensory processing and stress-responsiveness, consistently exhibited elevated spontaneous activity. The application of drugs targeting different convulsant mechanisms (4-Aminopyridine, Pentylenetetrazole, Pilocarpine and Strychnine) resulted in distinct spatiotemporal patterns of activity. These activity patterns showed some interesting parallels with what is known of the distribution of their respective molecular targets, but crucially also revealed system-wide neural circuit responses to stimulation or suppression. Drug concentration-response curves of neural activity were identified in a number of anatomically-defined zebrafish brain regions, and in vivo larval electrophysiology, also conducted in 4dpf larvae, provided additional measures of neural activity. Our quantification of network-wide chemoconvulsant drug activity in the whole zebrafish brain illustrates the power of this approach for neuropharmacological profiling in applications ranging from accelerating studies of drug safety and efficacy, to identifying pharmacologically-altered networks in zebrafish models of human neurological disorders.

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.

The role of symmetry in neural networks and their Laplacian spectra.

PubMed

de Lange, Siemon C; van den Heuvel, Martijn P; de Reus, Marcel A

2016-11-01

Human and animal nervous systems constitute complexly wired networks that form the infrastructure for neural processing and integration of information. The organization of these neural networks can be analyzed using the so-called Laplacian spectrum, providing a mathematical tool to produce systems-level network fingerprints. In this article, we examine a characteristic central peak in the spectrum of neural networks, including anatomical brain network maps of the mouse, cat and macaque, as well as anatomical and functional network maps of human brain connectivity. We link the occurrence of this central peak to the level of symmetry in neural networks, an intriguing aspect of network organization resulting from network elements that exhibit similar wiring patterns. Specifically, we propose a measure to capture the global level of symmetry of a network and show that, for both empirical networks and network models, the height of the main peak in the Laplacian spectrum is strongly related to node symmetry in the underlying network. Moreover, examination of spectra of duplication-based model networks shows that neural spectra are best approximated using a trade-off between duplication and diversification. Taken together, our results facilitate a better understanding of neural network spectra and the importance of symmetry in neural networks. Copyright © 2016 Elsevier Inc. All rights reserved.

A real time neural net estimator of fatigue life

NASA Technical Reports Server (NTRS)

Troudet, T.; Merrill, W.

1990-01-01

A neural net architecture is proposed to estimate, in real-time, the fatigue life of mechanical components, as part of the Intelligent Control System for Reusable Rocket Engines. Arbitrary component loading values were used as input to train a two hidden-layer feedforward neural net to estimate component fatigue damage. The ability of the net to learn, based on a local strain approach, the mapping between load sequence and fatigue damage has been demonstrated for a uniaxial specimen. Because of its demonstrated performance, the neural computation may be extended to complex cases where the loads are biaxial or triaxial, and the geometry of the component is complex (e.g., turbopump blades). The generality of the approach is such that load/damage mappings can be directly extracted from experimental data without requiring any knowledge of the stress/strain profile of the component. In addition, the parallel network architecture allows real-time life calculations even for high frequency vibrations. Owing to its distributed nature, the neural implementation will be robust and reliable, enabling its use in hostile environments such as rocket engines. This neural net estimator of fatigue life is seen as the enabling technology to achieve component life prognosis, and therefore would be an important part of life extending control for reusable rocket engines.

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.

Synchronization Control of Neural Networks With State-Dependent Coefficient Matrices.

PubMed

Zhang, Junfeng; Zhao, Xudong; Huang, Jun

2016-11-01

This brief is concerned with synchronization control of a class of neural networks with state-dependent coefficient matrices. Being different from the existing drive-response neural networks in the literature, a novel model of drive-response neural networks is established. The concepts of uniformly ultimately bounded (UUB) synchronization and convex hull Lyapunov function are introduced. Then, by using the convex hull Lyapunov function approach, the UUB synchronization design of the drive-response neural networks is proposed, and a delay-independent control law guaranteeing the bounded synchronization of the neural networks is constructed. All present conditions are formulated in terms of bilinear matrix inequalities. By comparison, it is shown that the neural networks obtained in this brief are less conservative than those ones in the literature, and the bounded synchronization is suitable for the novel drive-response neural networks. Finally, an illustrative example is given to verify the validity of the obtained results.

The Laplacian spectrum of neural networks

PubMed Central

de Lange, Siemon C.; de Reus, Marcel A.; van den Heuvel, Martijn P.

2014-01-01

The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these “conventional” graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network's structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks. PMID:24454286

Learning control of inverted pendulum system by neural network driven fuzzy reasoning: The learning function of NN-driven fuzzy reasoning under changes of reasoning environment

NASA Technical Reports Server (NTRS)

Hayashi, Isao; Nomura, Hiroyoshi; Wakami, Noboru

1991-01-01

Whereas conventional fuzzy reasonings are associated with tuning problems, which are lack of membership functions and inference rule designs, a neural network driven fuzzy reasoning (NDF) capable of determining membership functions by neural network is formulated. In the antecedent parts of the neural network driven fuzzy reasoning, the optimum membership function is determined by a neural network, while in the consequent parts, an amount of control for each rule is determined by other plural neural networks. By introducing an algorithm of neural network driven fuzzy reasoning, inference rules for making a pendulum stand up from its lowest suspended point are determined for verifying the usefulness of the algorithm.

Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases

PubMed Central

Ritchie, Marylyn D; White, Bill C; Parker, Joel S; Hahn, Lance W; Moore, Jason H

2003-01-01

Background Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining. This can be challenging when the underlying model of the data is unknown. The goal of this study was to determine whether optimizing neural network architecture using genetic programming as a machine learning strategy would improve the ability of neural networks to model and detect nonlinear interactions among genes in studies of common human diseases. Results Using simulated data, we show that a genetic programming optimized neural network approach is able to model gene-gene interactions as well as a traditional back propagation neural network. Furthermore, the genetic programming optimized neural network is better than the traditional back propagation neural network approach in terms of predictive ability and power to detect gene-gene interactions when non-functional polymorphisms are present. Conclusion This study suggests that a machine learning strategy for optimizing neural network architecture may be preferable to traditional trial-and-error approaches for the identification and characterization of gene-gene interactions in common, complex human diseases. PMID:12846935

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.

Color encoding in biologically-inspired convolutional neural networks.

PubMed

Rafegas, Ivet; Vanrell, Maria

2018-05-11

Convolutional Neural Networks have been proposed as suitable frameworks to model biological vision. Some of these artificial networks showed representational properties that rival primate performances in object recognition. In this paper we explore how color is encoded in a trained artificial network. It is performed by estimating a color selectivity index for each neuron, which allows us to describe the neuron activity to a color input stimuli. The index allows us to classify whether they are color selective or not and if they are of a single or double color. We have determined that all five convolutional layers of the network have a large number of color selective neurons. Color opponency clearly emerges in the first layer, presenting 4 main axes (Black-White, Red-Cyan, Blue-Yellow and Magenta-Green), but this is reduced and rotated as we go deeper into the network. In layer 2 we find a denser hue sampling of color neurons and opponency is reduced almost to one new main axis, the Bluish-Orangish coinciding with the dataset bias. In layers 3, 4 and 5 color neurons are similar amongst themselves, presenting different type of neurons that detect specific colored objects (e.g., orangish faces), specific surrounds (e.g., blue sky) or specific colored or contrasted object-surround configurations (e.g. blue blob in a green surround). Overall, our work concludes that color and shape representation are successively entangled through all the layers of the studied network, revealing certain parallelisms with the reported evidences in primate brains that can provide useful insight into intermediate hierarchical spatio-chromatic representations. Copyright © 2018 Elsevier Ltd. All rights reserved.

Neural-network-directed alignment of optical systems using the laser-beam spatial filter as an example

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Krasowski, Michael J.; Weiland, Kenneth E.

1993-01-01

This report describes an effort at NASA Lewis Research Center to use artificial neural networks to automate the alignment and control of optical measurement systems. Specifically, it addresses the use of commercially available neural network software and hardware to direct alignments of the common laser-beam-smoothing spatial filter. The report presents a general approach for designing alignment records and combining these into training sets to teach optical alignment functions to neural networks and discusses the use of these training sets to train several types of neural networks. Neural network configurations used include the adaptive resonance network, the back-propagation-trained network, and the counter-propagation network. This work shows that neural networks can be used to produce robust sequencers. These sequencers can learn by example to execute the step-by-step procedures of optical alignment and also can learn adaptively to correct for environmentally induced misalignment. The long-range objective is to use neural networks to automate the alignment and operation of optical measurement systems in remote, harsh, or dangerous aerospace environments. This work also shows that when neural networks are trained by a human operator, training sets should be recorded, training should be executed, and testing should be done in a manner that does not depend on intellectual judgments of the human operator.

Resolution of Singularities Introduced by Hierarchical Structure in Deep Neural Networks.

PubMed

Nitta, Tohru

2017-10-01

We present a theoretical analysis of singular points of artificial deep neural networks, resulting in providing deep neural network models having no critical points introduced by a hierarchical structure. It is considered that such deep neural network models have good nature for gradient-based optimization. First, we show that there exist a large number of critical points introduced by a hierarchical structure in deep neural networks as straight lines, depending on the number of hidden layers and the number of hidden neurons. Second, we derive a sufficient condition for deep neural networks having no critical points introduced by a hierarchical structure, which can be applied to general deep neural networks. It is also shown that the existence of critical points introduced by a hierarchical structure is determined by the rank and the regularity of weight matrices for a specific class of deep neural networks. Finally, two kinds of implementation methods of the sufficient conditions to have no critical points are provided. One is a learning algorithm that can avoid critical points introduced by the hierarchical structure during learning (called avoidant learning algorithm). The other is a neural network that does not have some critical points introduced by the hierarchical structure as an inherent property (called avoidant neural network).

The effect of the neural activity on topological properties of growing neural networks.

PubMed

Gafarov, F M; Gafarova, V R

2016-09-01

The connectivity structure in cortical networks defines how information is transmitted and processed, and it is a source of the complex spatiotemporal patterns of network's development, and the process of creation and deletion of connections is continuous in the whole life of the organism. In this paper, we study how neural activity influences the growth process in neural networks. By using a two-dimensional activity-dependent growth model we demonstrated the neural network growth process from disconnected neurons to fully connected networks. For making quantitative investigation of the network's activity influence on its topological properties we compared it with the random growth network not depending on network's activity. By using the random graphs theory methods for the analysis of the network's connections structure it is shown that the growth in neural networks results in the formation of a well-known "small-world" network.

LavaNet—Neural network development environment in a general mine planning package

NASA Astrophysics Data System (ADS)

Kapageridis, Ioannis Konstantinou; Triantafyllou, A. G.

2011-04-01

LavaNet is a series of scripts written in Perl that gives access to a neural network simulation environment inside a general mine planning package. A well known and a very popular neural network development environment, the Stuttgart Neural Network Simulator, is used as the base for the development of neural networks. LavaNet runs inside VULCAN™—a complete mine planning package with advanced database, modelling and visualisation capabilities. LavaNet is taking advantage of VULCAN's Perl based scripting environment, Lava, to bring all the benefits of neural network development and application to geologists, mining engineers and other users of the specific mine planning package. LavaNet enables easy development of neural network training data sets using information from any of the data and model structures available, such as block models and drillhole databases. Neural networks can be trained inside VULCAN™ and the results be used to generate new models that can be visualised in 3D. Direct comparison of developed neural network models with conventional and geostatistical techniques is now possible within the same mine planning software package. LavaNet supports Radial Basis Function networks, Multi-Layer Perceptrons and Self-Organised Maps.

Fitting Neuron Models to Spike Trains

PubMed Central

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

2011-01-01

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

Creative-Dynamics Approach To Neural Intelligence

NASA Technical Reports Server (NTRS)

Zak, Michail A.

1992-01-01

Paper discusses approach to mathematical modeling of artificial neural networks exhibiting complicated behaviors reminiscent of creativity and intelligence of biological neural networks. Neural network treated as non-Lipschitzian dynamical system - as described in "Non-Lipschitzian Dynamics For Modeling Neural Networks" (NPO-17814). System serves as tool for modeling of temporal-pattern memories and recognition of complicated spatial patterns.

An Attractor-Based Complexity Measurement for Boolean Recurrent Neural Networks

PubMed Central

Cabessa, Jérémie; Villa, Alessandro E. P.

2014-01-01

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

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…

Target recognition of ladar range images using even-order Zernike moments.

PubMed

Liu, Zheng-Jun; Li, Qi; Xia, Zhi-Wei; Wang, Qi

2012-11-01

Ladar range images have attracted considerable attention in automatic target recognition fields. In this paper, Zernike moments (ZMs) are applied to classify the target of the range image from an arbitrary azimuth angle. However, ZMs suffer from high computational costs. To improve the performance of target recognition based on small samples, even-order ZMs with serial-parallel backpropagation neural networks (BPNNs) are applied to recognize the target of the range image. It is found that the rotation invariance and classified performance of the even-order ZMs are both better than for odd-order moments and for moments compressed by principal component analysis. The experimental results demonstrate that combining the even-order ZMs with serial-parallel BPNNs can significantly improve the recognition rate for small samples.

Pattern classification by memristive crossbar circuits using ex situ and in situ training.

PubMed

Alibart, Fabien; Zamanidoost, Elham; Strukov, Dmitri B

2013-01-01

Memristors are memory resistors that promise the efficient implementation of synaptic weights in artificial neural networks. Whereas demonstrations of the synaptic operation of memristors already exist, the implementation of even simple networks is more challenging and has yet to be reported. Here we demonstrate pattern classification using a single-layer perceptron network implemented with a memrisitive crossbar circuit and trained using the perceptron learning rule by ex situ and in situ methods. In the first case, synaptic weights, which are realized as conductances of titanium dioxide memristors, are calculated on a precursor software-based network and then imported sequentially into the crossbar circuit. In the second case, training is implemented in situ, so the weights are adjusted in parallel. Both methods work satisfactorily despite significant variations in the switching behaviour of the memristors. These results give hope for the anticipated efficient implementation of artificial neuromorphic networks and pave the way for dense, high-performance information processing systems.

Pattern classification by memristive crossbar circuits using ex situ and in situ training

NASA Astrophysics Data System (ADS)

Alibart, Fabien; Zamanidoost, Elham; Strukov, Dmitri B.

2013-06-01

Memristors are memory resistors that promise the efficient implementation of synaptic weights in artificial neural networks. Whereas demonstrations of the synaptic operation of memristors already exist, the implementation of even simple networks is more challenging and has yet to be reported. Here we demonstrate pattern classification using a single-layer perceptron network implemented with a memrisitive crossbar circuit and trained using the perceptron learning rule by ex situ and in situ methods. In the first case, synaptic weights, which are realized as conductances of titanium dioxide memristors, are calculated on a precursor software-based network and then imported sequentially into the crossbar circuit. In the second case, training is implemented in situ, so the weights are adjusted in parallel. Both methods work satisfactorily despite significant variations in the switching behaviour of the memristors. These results give hope for the anticipated efficient implementation of artificial neuromorphic networks and pave the way for dense, high-performance information processing systems.

Neural network to diagnose lining condition

NASA Astrophysics Data System (ADS)

Yemelyanov, V. A.; Yemelyanova, N. Y.; Nedelkin, A. A.; Zarudnaya, M. V.

2018-03-01

The paper presents data on the problem of diagnosing the lining condition at the iron and steel works. The authors describe the neural network structure and software that are designed and developed to determine the lining burnout zones. The simulation results of the proposed neural networks are presented. The authors note the low learning and classification errors of the proposed neural networks. To realize the proposed neural network, the specialized software has been developed.

[Measurement and performance analysis of functional neural network].

PubMed

Li, Shan; Liu, Xinyu; Chen, Yan; Wan, Hong

2018-04-01

The measurement of network is one of the important researches in resolving neuronal population information processing mechanism using complex network theory. For the quantitative measurement problem of functional neural network, the relation between the measure indexes, i.e. the clustering coefficient, the global efficiency, the characteristic path length and the transitivity, and the network topology was analyzed. Then, the spike-based functional neural network was established and the simulation results showed that the measured network could represent the original neural connections among neurons. On the basis of the former work, the coding of functional neural network in nidopallium caudolaterale (NCL) about pigeon's motion behaviors was studied. We found that the NCL functional neural network effectively encoded the motion behaviors of the pigeon, and there were significant differences in four indexes among the left-turning, the forward and the right-turning. Overall, the establishment method of spike-based functional neural network is available and it is an effective tool to parse the brain information processing mechanism.

Macular Bioaccelerometers on Earth and in Space

NASA Technical Reports Server (NTRS)

Ross, M. D.; Cutler, L.; Meyer, G.; Vazin, P.; Lam, T.

1991-01-01

Space flight offers the opportunity to study linear bioaccelerometers (vestibular maculas) in the virtual absence of a primary stimulus, gravitational acceleration. Macular research in space is particularly important to NASA because the bioaccelerometers are proving to be weighted neural networks in which information is distributed for parallel processing. Neural networks are plastic and highly adaptive to new environments. Combined morphological-physiological studies of maculas fixed in space and following flight should reveal macular adaptive responses to microgravity, and their time-course. Ground-based research, already begun, using computer-assisted, 3-dimensional reconstruction of macular terminal fields will lead to development of computer models of functioning maculas. This research should continue in conjunction with physiological studies, including work with multichannel electrodes. The results of such a combined effort could usher in a new era in understanding vestibular function on Earth and in space. They can also provide a rational basis for counter-measures to space motion sickness, which may prove troublesome as space voyager encounter new gravitational fields on planets, or must re-adapt to 1 g upon return to earth.

Style-based classification of Chinese ink and wash paintings

NASA Astrophysics Data System (ADS)

Sheng, Jiachuan; Jiang, Jianmin

2013-09-01

Following the fact that a large collection of ink and wash paintings (IWP) is being digitized and made available on the Internet, their automated content description, analysis, and management are attracting attention across research communities. While existing research in relevant areas is primarily focused on image processing approaches, a style-based algorithm is proposed to classify IWPs automatically by their authors. As IWPs do not have colors or even tones, the proposed algorithm applies edge detection to locate the local region and detect painting strokes to enable histogram-based feature extraction and capture of important cues to reflect the styles of different artists. Such features are then applied to drive a number of neural networks in parallel to complete the classification, and an information entropy balanced fusion is proposed to make an integrated decision for the multiple neural network classification results in which the entropy is used as a pointer to combine the global and local features. Evaluations via experiments support that the proposed algorithm achieves good performances, providing excellent potential for computerized analysis and management of IWPs.

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

DOE PAGES

Farrell, Steven; Anderson, Dustin; Calafiura, Paolo; ...

2017-08-08

Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-the-art techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problemmore » thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. Furthermore, we will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.« less

Prediction of Soil Deformation in Tunnelling Using Artificial Neural Networks.

PubMed

Lai, Jinxing; Qiu, Junling; Feng, Zhihua; Chen, Jianxun; Fan, Haobo

2016-01-01

In the past few decades, as a new tool for analysis of the tough geotechnical problems, artificial neural networks (ANNs) have been successfully applied to address a number of engineering problems, including deformation due to tunnelling in various types of rock mass. Unlike the classical regression methods in which a certain form for the approximation function must be presumed, ANNs do not require the complex constitutive models. Additionally, it is traced that the ANN prediction system is one of the most effective ways to predict the rock mass deformation. Furthermore, it could be envisaged that ANNs would be more feasible for the dynamic prediction of displacements in tunnelling in the future, especially if ANN models are combined with other research methods. In this paper, we summarized the state-of-the-art and future research challenges of ANNs on the tunnel deformation prediction. And the application cases as well as the improvement of ANN models were also presented. The presented ANN models can serve as a benchmark for effective prediction of the tunnel deformation with characters of nonlinearity, high parallelism, fault tolerance, learning, and generalization capability.

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

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

Farrell, Steven; Anderson, Dustin; Calafiura, Paolo

Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-the-art techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problemmore » thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. Furthermore, we will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.« less

Implementation of Sensor and Control Designs for Bioregenerative Systems

NASA Technical Reports Server (NTRS)

Rodriguez, Pedro R. (Editor)

1990-01-01

The goal of the Spring 1990 EGM 4001 Design class was to design, fabricate, and test sensors and control systems for a closed loop life support system (CLLSS). The designs investigated were to contribute to the development of NASA's Controlled Ecological Life Support System (CELSS) at Kennedy Space Center (KSC). Designs included a seed moisture content sensor, a porous medium wetness sensor, a plant health sensor, and a neural network control system. The seed group focused on the design and implementation of a sensor that could detect the moisture content of a seed batch. The porous medium wetness group concentrated on the development of a sensor to monitor the amount of nutrient solution within a porous plate incorporating either infrared reflectance or thermal conductance properties. The plant health group examined the possibility of remotely monitoring the health of the plants within the Biomass Production Chamber (BPC) using infrared reflectance properties. Finally, the neural network group concentrated on the ability to use parallel processing in order to control a robot arm and analyze the data from the health sensor to detect regions of a plant.

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

NASA Astrophysics Data System (ADS)

Farrell, Steven; Anderson, Dustin; Calafiura, Paolo; Cerati, Giuseppe; Gray, Lindsey; Kowalkowski, Jim; Mudigonda, Mayur; Prabhat; Spentzouris, Panagiotis; Spiropoulou, Maria; Tsaris, Aristeidis; Vlimant, Jean-Roch; Zheng, Stephan

2017-08-01

Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-the-art techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problem thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. We will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.

Prediction of Soil Deformation in Tunnelling Using Artificial Neural Networks

PubMed Central

Lai, Jinxing

2016-01-01

In the past few decades, as a new tool for analysis of the tough geotechnical problems, artificial neural networks (ANNs) have been successfully applied to address a number of engineering problems, including deformation due to tunnelling in various types of rock mass. Unlike the classical regression methods in which a certain form for the approximation function must be presumed, ANNs do not require the complex constitutive models. Additionally, it is traced that the ANN prediction system is one of the most effective ways to predict the rock mass deformation. Furthermore, it could be envisaged that ANNs would be more feasible for the dynamic prediction of displacements in tunnelling in the future, especially if ANN models are combined with other research methods. In this paper, we summarized the state-of-the-art and future research challenges of ANNs on the tunnel deformation prediction. And the application cases as well as the improvement of ANN models were also presented. The presented ANN models can serve as a benchmark for effective prediction of the tunnel deformation with characters of nonlinearity, high parallelism, fault tolerance, learning, and generalization capability. PMID:26819587

Neural network error correction for solving coupled ordinary differential equations

NASA Technical Reports Server (NTRS)

Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

1992-01-01

A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

Artificial and Bayesian Neural Networks

PubMed

Korhani Kangi, Azam; Bahrampour, Abbas

2018-02-26

Introduction and purpose: In recent years the use of neural networks without any premises for investigation of prognosis in analyzing survival data has increased. Artificial neural networks (ANN) use small processors with a continuous network to solve problems inspired by the human brain. Bayesian neural networks (BNN) constitute a neural-based approach to modeling and non-linearization of complex issues using special algorithms and statistical methods. Gastric cancer incidence is the first and third ranking for men and women in Iran, respectively. The aim of the present study was to assess the value of an artificial neural network and a Bayesian neural network for modeling and predicting of probability of gastric cancer patient death. Materials and Methods: In this study, we used information on 339 patients aged from 20 to 90 years old with positive gastric cancer, referred to Afzalipoor and Shahid Bahonar Hospitals in Kerman City from 2001 to 2015. The three layers perceptron neural network (ANN) and the Bayesian neural network (BNN) were used for predicting the probability of mortality using the available data. To investigate differences between the models, sensitivity, specificity, accuracy and the area under receiver operating characteristic curves (AUROCs) were generated. Results: In this study, the sensitivity and specificity of the artificial neural network and Bayesian neural network models were 0.882, 0.903 and 0.954, 0.909, respectively. Prediction accuracy and the area under curve ROC for the two models were 0.891, 0.944 and 0.935, 0.961. The age at diagnosis of gastric cancer was most important for predicting survival, followed by tumor grade, morphology, gender, smoking history, opium consumption, receiving chemotherapy, presence of metastasis, tumor stage, receiving radiotherapy, and being resident in a village. Conclusion: The findings of the present study indicated that the Bayesian neural network is preferable to an artificial neural network for predicting survival of gastric cancer patients in Iran. Creative Commons Attribution License

Model Of Neural Network With Creative Dynamics

NASA Technical Reports Server (NTRS)

Zak, Michail; Barhen, Jacob

1993-01-01

Paper presents analysis of mathematical model of one-neuron/one-synapse neural network featuring coupled activation and learning dynamics and parametrical periodic excitation. Demonstrates self-programming, partly random behavior of suitable designed neural network; believed to be related to spontaneity and creativity of biological neural networks.

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.

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.

An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation.

PubMed

Hoseini, Farnaz; Shahbahrami, Asadollah; Bayat, Peyman

2018-02-27

Image segmentation is one of the most common steps in digital image processing, classifying a digital image into different segments. The main goal of this paper is to segment brain tumors in magnetic resonance images (MRI) using deep learning. Tumors having different shapes, sizes, brightness and textures can appear anywhere in the brain. These complexities are the reasons to choose a high-capacity Deep Convolutional Neural Network (DCNN) containing more than one layer. The proposed DCNN contains two parts: architecture and learning algorithms. The architecture and the learning algorithms are used to design a network model and to optimize parameters for the network training phase, respectively. The architecture contains five convolutional layers, all using 3 × 3 kernels, and one fully connected layer. Due to the advantage of using small kernels with fold, it allows making the effect of larger kernels with smaller number of parameters and fewer computations. Using the Dice Similarity Coefficient metric, we report accuracy results on the BRATS 2016, brain tumor segmentation challenge dataset, for the complete, core, and enhancing regions as 0.90, 0.85, and 0.84 respectively. The learning algorithm includes the task-level parallelism. All the pixels of an MR image are classified using a patch-based approach for segmentation. We attain a good performance and the experimental results show that the proposed DCNN increases the segmentation accuracy compared to previous techniques.

Determining geophysical properties from well log data using artificial neural networks and fuzzy inference systems

NASA Astrophysics Data System (ADS)

Chang, Hsien-Cheng

Two novel synergistic systems consisting of artificial neural networks and fuzzy inference systems are developed to determine geophysical properties by using well log data. These systems are employed to improve the determination accuracy in carbonate rocks, which are generally more complex than siliciclastic rocks. One system, consisting of a single adaptive resonance theory (ART) neural network and three fuzzy inference systems (FISs), is used to determine the permeability category. The other system, which is composed of three ART neural networks and a single FIS, is employed to determine the lithofacies. The geophysical properties studied in this research, permeability category and lithofacies, are treated as categorical data. The permeability values are transformed into a "permeability category" to account for the effects of scale differences between core analyses and well logs, and heterogeneity in the carbonate rocks. The ART neural networks dynamically cluster the input data sets into different groups. The FIS is used to incorporate geologic experts' knowledge, which is usually in linguistic forms, into systems. These synergistic systems thus provide viable alternative solutions to overcome the effects of heterogeneity, the uncertainties of carbonate rock depositional environments, and the scarcity of well log data. The results obtained in this research show promising improvements over backpropagation neural networks. For the permeability category, the prediction accuracies are 68.4% and 62.8% for the multiple-single ART neural network-FIS and a single backpropagation neural network, respectively. For lithofacies, the prediction accuracies are 87.6%, 79%, and 62.8% for the single-multiple ART neural network-FIS, a single ART neural network, and a single backpropagation neural network, respectively. The sensitivity analysis results show that the multiple-single ART neural networks-FIS and a single ART neural network possess the same matching trends in determining lithofacies. This research shows that the adaptive resonance theory neural networks enable decision-makers to clearly distinguish the importance of different pieces of data which are useful in three-dimensional subsurface modeling. Geologic experts' knowledge can be easily applied and maintained by using the fuzzy inference systems.

Application of the ANNA neural network chip to high-speed character recognition.

PubMed

Sackinger, E; Boser, B E; Bromley, J; Lecun, Y; Jackel, L D

1992-01-01

A neural network with 136000 connections for recognition of handwritten digits has been implemented using a mixed analog/digital neural network chip. The neural network chip is capable of processing 1000 characters/s. The recognition system has essentially the same rate (5%) as a simulation of the network with 32-b floating-point precision.

Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks

PubMed Central

Mostafa, Hesham; Pedroni, Bruno; Sheik, Sadique; Cauwenberghs, Gert

2017-01-01

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing custom silicon devices to accelerate inference in ANNs. Accelerating the training phase, however, has attracted relatively little attention. In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation. Learning is performed in parallel with inference in the forward pass, removing the need for an explicit backward pass and requiring no extra weight lookup. By using binary state variables in the feedforward network and ternary errors in truncated-error backpropagation, the need for any multiplications in the forward and backward passes is removed, and memory requirements for the pipelining are drastically reduced. Further reduction in addition operations owing to the sparsity in the forward neural and backpropagating error signal paths contributes to highly efficient hardware implementation. For proof-of-concept validation, we demonstrate on-line learning of MNIST handwritten digit classification on a Spartan 6 FPGA interfacing with an external 1Gb DDR2 DRAM, that shows small degradation in test error performance compared to an equivalently sized binary ANN trained off-line using standard back-propagation and exact errors. Our results highlight an attractive synergy between pipelined backpropagation and binary-state networks in substantially reducing computation and memory requirements, making pipelined on-line learning practical in deep networks. PMID:28932180

Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks.

PubMed

Mostafa, Hesham; Pedroni, Bruno; Sheik, Sadique; Cauwenberghs, Gert

2017-01-01

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing custom silicon devices to accelerate inference in ANNs. Accelerating the training phase, however, has attracted relatively little attention. In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation. Learning is performed in parallel with inference in the forward pass, removing the need for an explicit backward pass and requiring no extra weight lookup. By using binary state variables in the feedforward network and ternary errors in truncated-error backpropagation, the need for any multiplications in the forward and backward passes is removed, and memory requirements for the pipelining are drastically reduced. Further reduction in addition operations owing to the sparsity in the forward neural and backpropagating error signal paths contributes to highly efficient hardware implementation. For proof-of-concept validation, we demonstrate on-line learning of MNIST handwritten digit classification on a Spartan 6 FPGA interfacing with an external 1Gb DDR2 DRAM, that shows small degradation in test error performance compared to an equivalently sized binary ANN trained off-line using standard back-propagation and exact errors. Our results highlight an attractive synergy between pipelined backpropagation and binary-state networks in substantially reducing computation and memory requirements, making pipelined on-line learning practical in deep networks.

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.

Using fuzzy logic to integrate neural networks and knowledge-based systems

NASA Technical Reports Server (NTRS)

Yen, John

1991-01-01

Outlined here is a novel hybrid architecture that uses fuzzy logic to integrate neural networks and knowledge-based systems. The author's approach offers important synergistic benefits to neural nets, approximate reasoning, and symbolic processing. Fuzzy inference rules extend symbolic systems with approximate reasoning capabilities, which are used for integrating and interpreting the outputs of neural networks. The symbolic system captures meta-level information about neural networks and defines its interaction with neural networks through a set of control tasks. Fuzzy action rules provide a robust mechanism for recognizing the situations in which neural networks require certain control actions. The neural nets, on the other hand, offer flexible classification and adaptive learning capabilities, which are crucial for dynamic and noisy environments. By combining neural nets and symbolic systems at their system levels through the use of fuzzy logic, the author's approach alleviates current difficulties in reconciling differences between low-level data processing mechanisms of neural nets and artificial intelligence systems.

A neural network application to classification of health status of HIV/AIDS patients.

PubMed

Kwak, N K; Lee, C

1997-04-01

This paper presents an application of neural networks to classify and to predict the health status of HIV/AIDS patients. A neural network model in classifying both the well and not-well health status of HIV/AIDS patients is developed and evaluated in terms of validity and reliability of the test. Several different neural network topologies are applied to AIDS Cost and Utilization Survey (ACSUS) datasets in order to demonstrate the neural network's capability.

Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

NASA Astrophysics Data System (ADS)

Chernoded, Andrey; Dudko, Lev; Myagkov, Igor; Volkov, Petr

2017-10-01

Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.

Improvement of the Hopfield Neural Network by MC-Adaptation Rule

NASA Astrophysics Data System (ADS)

Zhou, Zhen; Zhao, Hong

2006-06-01

We show that the performance of the Hopfield neural networks, especially the quality of the recall and the capacity of the effective storing, can be greatly improved by making use of a recently presented neural network designing method without altering the whole structure of the network. In the improved neural network, a memory pattern is recalled exactly from initial states having a given degree of similarity with the memory pattern, and thus one can avoids to apply the overlap criterion as carried out in the Hopfield neural networks.

The Energy Coding of a Structural Neural Network Based on the Hodgkin-Huxley Model.

PubMed

Zhu, Zhenyu; Wang, Rubin; Zhu, Fengyun

2018-01-01

Based on the Hodgkin-Huxley model, the present study established a fully connected structural neural network to simulate the neural activity and energy consumption of the network by neural energy coding theory. The numerical simulation result showed that the periodicity of the network energy distribution was positively correlated to the number of neurons and coupling strength, but negatively correlated to signal transmitting delay. Moreover, a relationship was established between the energy distribution feature and the synchronous oscillation of the neural network, which showed that when the proportion of negative energy in power consumption curve was high, the synchronous oscillation of the neural network was apparent. In addition, comparison with the simulation result of structural neural network based on the Wang-Zhang biophysical model of neurons showed that both models were essentially consistent.

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.

Constraint satisfaction adaptive neural network and heuristics combined approaches for generalized job-shop scheduling.

PubMed

Yang, S; Wang, D

2000-01-01

This paper presents a constraint satisfaction adaptive neural network, together with several heuristics, to solve the generalized job-shop scheduling problem, one of NP-complete constraint satisfaction problems. The proposed neural network can be easily constructed and can adaptively adjust its weights of connections and biases of units based on the sequence and resource constraints of the job-shop scheduling problem during its processing. Several heuristics that can be combined with the neural network are also presented. In the combined approaches, the neural network is used to obtain feasible solutions, the heuristic algorithms are used to improve the performance of the neural network and the quality of the obtained solutions. Simulations have shown that the proposed neural network and its combined approaches are efficient with respect to the quality of solutions and the solving speed.

Financial time series prediction using spiking neural networks.

PubMed

Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam

2014-01-01

In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two "traditional", rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments.

On the biological plausibility of grandmother cells: implications for neural network theories in psychology and neuroscience.

PubMed

Bowers, Jeffrey S

2009-01-01

A fundamental claim associated with parallel distributed processing (PDP) theories of cognition is that knowledge is coded in a distributed manner in mind and brain. This approach rejects the claim that knowledge is coded in a localist fashion, with words, objects, and simple concepts (e.g. "dog"), that is, coded with their own dedicated representations. One of the putative advantages of this approach is that the theories are biologically plausible. Indeed, advocates of the PDP approach often highlight the close parallels between distributed representations learned in connectionist models and neural coding in brain and often dismiss localist (grandmother cell) theories as biologically implausible. The author reviews a range a data that strongly challenge this claim and shows that localist models provide a better account of single-cell recording studies. The author also contrast local and alternative distributed coding schemes (sparse and coarse coding) and argues that common rejection of grandmother cell theories in neuroscience is due to a misunderstanding about how localist models behave. The author concludes that the localist representations embedded in theories of perception and cognition are consistent with neuroscience; biology only calls into question the distributed representations often learned in PDP models.

Non-Intrusive Gaze Tracking Using Artificial Neural Networks

DTIC Science & Technology

1994-01-05

We have developed an artificial neural network based gaze tracking, system which can be customized to individual users. A three layer feed forward...empirical analysis of the performance of a large number of artificial neural network architectures for this task. Suggestions for further explorations...for neurally based gaze trackers are presented, and are related to other similar artificial neural network applications such as autonomous road following.

Neural dynamics based on the recognition of neural fingerprints

PubMed Central

Carrillo-Medina, José Luis; Latorre, Roberto

2015-01-01

Experimental evidence has revealed the existence of characteristic spiking features in different neural signals, e.g., individual neural signatures identifying the emitter or functional signatures characterizing specific tasks. These neural fingerprints may play a critical role in neural information processing, since they allow receptors to discriminate or contextualize incoming stimuli. This could be a powerful strategy for neural systems that greatly enhances the encoding and processing capacity of these networks. Nevertheless, the study of information processing based on the identification of specific neural fingerprints has attracted little attention. In this work, we study (i) the emerging collective dynamics of a network of neurons that communicate with each other by exchange of neural fingerprints and (ii) the influence of the network topology on the self-organizing properties within the network. Complex collective dynamics emerge in the network in the presence of stimuli. Predefined inputs, i.e., specific neural fingerprints, are detected and encoded into coexisting patterns of activity that propagate throughout the network with different spatial organization. The patterns evoked by a stimulus can survive after the stimulation is over, which provides memory mechanisms to the network. The results presented in this paper suggest that neural information processing based on neural fingerprints can be a plausible, flexible, and powerful strategy. PMID:25852531

Structural reliability calculation method based on the dual neural network and direct integration method.

PubMed

Li, Haibin; He, Yun; Nie, Xiaobo

2018-01-01

Structural reliability analysis under uncertainty is paid wide attention by engineers and scholars due to reflecting the structural characteristics and the bearing actual situation. The direct integration method, started from the definition of reliability theory, is easy to be understood, but there are still mathematics difficulties in the calculation of multiple integrals. Therefore, a dual neural network method is proposed for calculating multiple integrals in this paper. Dual neural network consists of two neural networks. The neural network A is used to learn the integrand function, and the neural network B is used to simulate the original function. According to the derivative relationships between the network output and the network input, the neural network B is derived from the neural network A. On this basis, the performance function of normalization is employed in the proposed method to overcome the difficulty of multiple integrations and to improve the accuracy for reliability calculations. The comparisons between the proposed method and Monte Carlo simulation method, Hasofer-Lind method, the mean value first-order second moment method have demonstrated that the proposed method is an efficient and accurate reliability method for structural reliability problems.

Patterns of synchrony for feed-forward and auto-regulation feed-forward neural networks.

PubMed

Aguiar, Manuela A D; Dias, Ana Paula S; Ferreira, Flora

2017-01-01

We consider feed-forward and auto-regulation feed-forward neural (weighted) coupled cell networks. In feed-forward neural networks, cells are arranged in layers such that the cells of the first layer have empty input set and cells of each other layer receive only inputs from cells of the previous layer. An auto-regulation feed-forward neural coupled cell network is a feed-forward neural network where additionally some cells of the first layer have auto-regulation, that is, they have a self-loop. Given a network structure, a robust pattern of synchrony is a space defined in terms of equalities of cell coordinates that is flow-invariant for any coupled cell system (with additive input structure) associated with the network. In this paper, we describe the robust patterns of synchrony for feed-forward and auto-regulation feed-forward neural networks. Regarding feed-forward neural networks, we show that only cells in the same layer can synchronize. On the other hand, in the presence of auto-regulation, we prove that cells in different layers can synchronize in a robust way and we give a characterization of the possible patterns of synchrony that can occur for auto-regulation feed-forward neural networks.

Pattern classification and recognition of invertebrate functional groups using self-organizing neural networks.

PubMed

Zhang, WenJun

2007-07-01

Self-organizing neural networks can be used to mimic non-linear systems. The main objective of this study is to make pattern classification and recognition on sampling information using two self-organizing neural network models. Invertebrate functional groups sampled in the irrigated rice field were classified and recognized using one-dimensional self-organizing map and self-organizing competitive learning neural networks. Comparisons between neural network models, distance (similarity) measures, and number of neurons were conducted. The results showed that self-organizing map and self-organizing competitive learning neural network models were effective in pattern classification and recognition of sampling information. Overall the performance of one-dimensional self-organizing map neural network was better than self-organizing competitive learning neural network. The number of neurons could determine the number of classes in the classification. Different neural network models with various distance (similarity) measures yielded similar classifications. Some differences, dependent upon the specific network structure, would be found. The pattern of an unrecognized functional group was recognized with the self-organizing neural network. A relative consistent classification indicated that the following invertebrate functional groups, terrestrial blood sucker; terrestrial flyer; tourist (nonpredatory species with no known functional role other than as prey in ecosystem); gall former; collector (gather, deposit feeder); predator and parasitoid; leaf miner; idiobiont (acarine ectoparasitoid), were classified into the same group, and the following invertebrate functional groups, external plant feeder; terrestrial crawler, walker, jumper or hunter; neustonic (water surface) swimmer (semi-aquatic), were classified into another group. It was concluded that reliable conclusions could be drawn from comparisons of different neural network models that use different distance (similarity) measures. Results with the larger consistency will be more reliable.

Accelerating Learning By Neural Networks

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad; Barhen, Jacob

1992-01-01

Electronic neural networks made to learn faster by use of terminal teacher forcing. Method of supervised learning involves addition of teacher forcing functions to excitations fed as inputs to output neurons. Initially, teacher forcing functions are strong enough to force outputs to desired values; subsequently, these functions decay with time. When learning successfully completed, terminal teacher forcing vanishes, and dynamics or neural network become equivalent to those of conventional neural network. Simulated neural network with terminal teacher forcing learned to produce close approximation of circular trajectory in 400 iterations.

Decoding the cortical transformations for visually guided reaching in 3D space.

PubMed

Blohm, Gunnar; Keith, Gerald P; Crawford, J Douglas

2009-06-01

To explore the possible cortical mechanisms underlying the 3-dimensional (3D) visuomotor transformation for reaching, we trained a 4-layer feed-forward artificial neural network to compute a reach vector (output) from the visual positions of both the hand and target viewed from different eye and head orientations (inputs). The emergent properties of the intermediate layers reflected several known neurophysiological findings, for example, gain field-like modulations and position-dependent shifting of receptive fields (RFs). We performed a reference frame analysis for each individual network unit, simulating standard electrophysiological experiments, that is, RF mapping (unit input), motor field mapping, and microstimulation effects (unit outputs). At the level of individual units (in both intermediate layers), the 3 different electrophysiological approaches identified different reference frames, demonstrating that these techniques reveal different neuronal properties and suggesting that a comparison across these techniques is required to understand the neural code of physiological networks. This analysis showed fixed input-output relationships within each layer and, more importantly, within each unit. These local reference frame transformation modules provide the basic elements for the global transformation; their parallel contributions are combined in a gain field-like fashion at the population level to implement both the linear and nonlinear elements of the 3D visuomotor transformation.

Deep learning for medical image segmentation - using the IBM TrueNorth neurosynaptic system

NASA Astrophysics Data System (ADS)

Moran, Steven; Gaonkar, Bilwaj; Whitehead, William; Wolk, Aidan; Macyszyn, Luke; Iyer, Subramanian S.

2018-03-01

Deep convolutional neural networks have found success in semantic image segmentation tasks in computer vision and medical imaging. These algorithms are executed on conventional von Neumann processor architectures or GPUs. This is suboptimal. Neuromorphic processors that replicate the structure of the brain are better-suited to train and execute deep learning models for image segmentation by relying on massively-parallel processing. However, given that they closely emulate the human brain, on-chip hardware and digital memory limitations also constrain them. Adapting deep learning models to execute image segmentation tasks on such chips, requires specialized training and validation. In this work, we demonstrate for the first-time, spinal image segmentation performed using a deep learning network implemented on neuromorphic hardware of the IBM TrueNorth Neurosynaptic System and validate the performance of our network by comparing it to human-generated segmentations of spinal vertebrae and disks. To achieve this on neuromorphic hardware, the training model constrains the coefficients of individual neurons to {-1,0,1} using the Energy Efficient Deep Neuromorphic (EEDN)1 networks training algorithm. Given the 1 million neurons and 256 million synapses, the scale and size of the neural network implemented by the IBM TrueNorth allows us to execute the requisite mapping between segmented images and non-uniform intensity MR images >20 times faster than on a GPU-accelerated network and using <0.1 W. This speed and efficiency implies that a trained neuromorphic chip can be deployed in intra-operative environments where real-time medical image segmentation is necessary.

Thermoelastic steam turbine rotor control based on neural network

NASA Astrophysics Data System (ADS)

Rzadkowski, Romuald; Dominiczak, Krzysztof; Radulski, Wojciech; Szczepanik, R.

2015-12-01

Considered here are Nonlinear Auto-Regressive neural networks with eXogenous inputs (NARX) as a mathematical model of a steam turbine rotor for controlling steam turbine stress on-line. In order to obtain neural networks that locate critical stress and temperature points in the steam turbine during transient states, an FE rotor model was built. This model was used to train the neural networks on the basis of steam turbine transient operating data. The training included nonlinearity related to steam turbine expansion, heat exchange and rotor material properties during transients. Simultaneous neural networks are algorithms which can be implemented on PLC controllers. This allows for the application neural networks to control steam turbine stress in industrial power plants.

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.

Research on artificial neural network intrusion detection photochemistry based on the improved wavelet analysis and transformation

NASA Astrophysics Data System (ADS)

Li, Hong; Ding, Xue

2017-03-01

This paper combines wavelet analysis and wavelet transform theory with artificial neural network, through the pretreatment on point feature attributes before in intrusion detection, to make them suitable for improvement of wavelet neural network. The whole intrusion classification model gets the better adaptability, self-learning ability, greatly enhances the wavelet neural network for solving the problem of field detection invasion, reduces storage space, contributes to improve the performance of the constructed neural network, and reduces the training time. Finally the results of the KDDCup99 data set simulation experiment shows that, this method reduces the complexity of constructing wavelet neural network, but also ensures the accuracy of the intrusion classification.

Fundamental physics issues of multilevel logic in developing a parallel processor.

NASA Astrophysics Data System (ADS)

Bandyopadhyay, Anirban; Miki, Kazushi

2007-06-01

In the last century, On and Off physical switches, were equated with two decisions 0 and 1 to express every information in terms of binary digits and physically realize it in terms of switches connected in a circuit. Apart from memory-density increase significantly, more possible choices in particular space enables pattern-logic a reality, and manipulation of pattern would allow controlling logic, generating a new kind of processor. Neumann's computer is based on sequential logic, processing bits one by one. But as pattern-logic is generated on a surface, viewing whole pattern at a time is a truly parallel processing. Following Neumann's and Shannons fundamental thermodynamical approaches we have built compatible model based on series of single molecule based multibit logic systems of 4-12 bits in an UHV-STM. On their monolayer multilevel communication and pattern formation is experimentally verified. Furthermore, the developed intelligent monolayer is trained by Artificial Neural Network. Therefore fundamental weak interactions for the building of truly parallel processor are explored here physically and theoretically.

Brian hears: online auditory processing using vectorization over channels.

PubMed

Fontaine, Bertrand; Goodman, Dan F M; Benichoux, Victor; Brette, Romain

2011-01-01

The human cochlea includes about 3000 inner hair cells which filter sounds at frequencies between 20 Hz and 20 kHz. This massively parallel frequency analysis is reflected in models of auditory processing, which are often based on banks of filters. However, existing implementations do not exploit this parallelism. Here we propose algorithms to simulate these models by vectorizing computation over frequency channels, which are implemented in "Brian Hears," a library for the spiking neural network simulator package "Brian." This approach allows us to use high-level programming languages such as Python, because with vectorized operations, the computational cost of interpretation represents a small fraction of the total cost. This makes it possible to define and simulate complex models in a simple way, while all previous implementations were model-specific. In addition, we show that these algorithms can be naturally parallelized using graphics processing units, yielding substantial speed improvements. We demonstrate these algorithms with several state-of-the-art cochlear models, and show that they compare favorably with existing, less flexible, implementations.

A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all application.

PubMed

Li, Shuai; Li, Yangming; Wang, Zheng

2013-03-01

This paper presents a class of recurrent neural networks to solve quadratic programming problems. Different from most existing recurrent neural networks for solving quadratic programming problems, the proposed neural network model converges in finite time and the activation function is not required to be a hard-limiting function for finite convergence time. The stability, finite-time convergence property and the optimality of the proposed neural network for solving the original quadratic programming problem are proven in theory. Extensive simulations are performed to evaluate the performance of the neural network with different parameters. In addition, the proposed neural network is applied to solving the k-winner-take-all (k-WTA) problem. Both theoretical analysis and numerical simulations validate the effectiveness of our method for solving the k-WTA problem. Copyright © 2012 Elsevier Ltd. All rights reserved.

Satellite image analysis using neural networks

NASA Technical Reports Server (NTRS)

Sheldon, Roger A.

1990-01-01

The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, SIANN (Satellite Image Analysis using Neural Networks) that integrates the technologies necessary to satisfy NASA's science data analysis requirements for the next generation of satellites. SIANN will enable scientists to train a neural network to recognize image data containing scenes of interest and then rapidly search data archives for all such images. The approach combines conventional image processing technology with recent advances in neural networks to provide improved classification capabilities. SIANN allows users to proceed through a four step process of image classification: filtering and enhancement, creation of neural network training data via application of feature extraction algorithms, configuring and training a neural network model, and classification of images by application of the trained neural network. A prototype experimentation testbed was completed and applied to climatological data.

Firing patterns transition and desynchronization induced by time delay in neural networks

NASA Astrophysics Data System (ADS)

Huang, Shoufang; Zhang, Jiqian; Wang, Maosheng; Hu, Chin-Kun

2018-06-01

We used the Hindmarsh-Rose (HR) model (Hindmarsh and Rose, 1984) to study the effect of time delay on the transition of firing behaviors and desynchronization in neural networks. As time delay is increased, neural networks exhibit diversity of firing behaviors, including regular spiking or bursting and firing patterns transitions (FPTs). Meanwhile, the desynchronization of firing and unstable bursting with decreasing amplitude in neural system, are also increasingly enhanced with the increase of time delay. Furthermore, we also studied the effect of coupling strength and network randomness on these phenomena. Our results imply that time delays can induce transition and desynchronization of firing behaviors in neural networks. These findings provide new insight into the role of time delay in the firing activities of neural networks, and can help to better understand the firing phenomena in complex systems of neural networks. A possible mechanism in brain that can cause the increase of time delay is discussed.

A one-layer recurrent neural network for constrained pseudoconvex optimization and its application for dynamic portfolio optimization.

PubMed

Liu, Qingshan; Guo, Zhishan; Wang, Jun

2012-02-01

In this paper, a one-layer recurrent neural network is proposed for solving pseudoconvex optimization problems subject to linear equality and bound constraints. Compared with the existing neural networks for optimization (e.g., the projection neural networks), the proposed neural network is capable of solving more general pseudoconvex optimization problems with equality and bound constraints. Moreover, it is capable of solving constrained fractional programming problems as a special case. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds. Numerical examples with simulation results illustrate the effectiveness and characteristics of the proposed neural network. In addition, an application for dynamic portfolio optimization is discussed. Copyright © 2011 Elsevier Ltd. All rights reserved.

Applications of artificial neural nets in clinical biomechanics.

PubMed

Schöllhorn, W I

2004-11-01

The purpose of this article is to provide an overview of current applications of artificial neural networks in the area of clinical biomechanics. The body of literature on artificial neural networks grew intractably vast during the last 15 years. Conventional statistical models may present certain limitations that can be overcome by neural networks. Artificial neural networks in general are introduced, some limitations, and some proven benefits are discussed.

Neural Networks for Rapid Design and Analysis

NASA Technical Reports Server (NTRS)

Sparks, Dean W., Jr.; Maghami, Peiman G.

1998-01-01

Artificial neural networks have been employed for rapid and efficient dynamics and control analysis of flexible systems. Specifically, feedforward neural networks are designed to approximate nonlinear dynamic components over prescribed input ranges, and are used in simulations as a means to speed up the overall time response analysis process. To capture the recursive nature of dynamic components with artificial neural networks, recurrent networks, which use state feedback with the appropriate number of time delays, as inputs to the networks, are employed. Once properly trained, neural networks can give very good approximations to nonlinear dynamic components, and by their judicious use in simulations, allow the analyst the potential to speed up the analysis process considerably. To illustrate this potential speed up, an existing simulation model of a spacecraft reaction wheel system is executed, first conventionally, and then with an artificial neural network in place.

Generalized Adaptive Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Tawel, Raoul

1993-01-01

Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.

Optimal input sizes for neural network de-interlacing

NASA Astrophysics Data System (ADS)

Choi, Hyunsoo; Seo, Guiwon; Lee, Chulhee

2009-02-01

Neural network de-interlacing has shown promising results among various de-interlacing methods. In this paper, we investigate the effects of input size for neural networks for various video formats when the neural networks are used for de-interlacing. In particular, we investigate optimal input sizes for CIF, VGA and HD video formats.

Impact of leakage delay on bifurcation in high-order fractional BAM neural networks.

PubMed

Huang, Chengdai; Cao, Jinde

2018-02-01

The effects of leakage delay on the dynamics of neural networks with integer-order have lately been received considerable attention. It has been confirmed that fractional neural networks more appropriately uncover the dynamical properties of neural networks, but the results of fractional neural networks with leakage delay are relatively few. This paper primarily concentrates on the issue of bifurcation for high-order fractional bidirectional associative memory(BAM) neural networks involving leakage delay. The first attempt is made to tackle the stability and bifurcation of high-order fractional BAM neural networks with time delay in leakage terms in this paper. The conditions for the appearance of bifurcation for the proposed systems with leakage delay are firstly established by adopting time delay as a bifurcation parameter. Then, the bifurcation criteria of such system without leakage delay are successfully acquired. Comparative analysis wondrously detects that the stability performance of the proposed high-order fractional neural networks is critically weakened by leakage delay, they cannot be overlooked. Numerical examples are ultimately exhibited to attest the efficiency of the theoretical results. Copyright © 2017 Elsevier Ltd. All rights reserved.

Coronary Artery Diagnosis Aided by Neural Network

NASA Astrophysics Data System (ADS)

Stefko, Kamil

2007-01-01

Coronary artery disease is due to atheromatous narrowing and subsequent occlusion of the coronary vessel. Application of optimised feed forward multi-layer back propagation neural network (MLBP) for detection of narrowing in coronary artery vessels is presented in this paper. The research was performed using 580 data records from traditional ECG exercise test confirmed by coronary arteriography results. Each record of training database included description of the state of a patient providing input data for the neural network. Level and slope of ST segment of a 12 lead ECG signal recorded at rest and after effort (48 floating point values) was the main component of input data for neural network was. Coronary arteriography results (verified the existence or absence of more than 50% stenosis of the particular coronary vessels) were used as a correct neural network training output pattern. More than 96% of cases were correctly recognised by especially optimised and a thoroughly verified neural network. Leave one out method was used for neural network verification so 580 data records could be used for training as well as for verification of neural network.

Characterizing the velocity of a wandering black hole and properties of the surrounding medium using convolutional neural networks

NASA Astrophysics Data System (ADS)

González, J. A.; Guzmán, F. S.

2018-03-01

We present a method for estimating the velocity of a wandering black hole and the equation of state for the gas around it based on a catalog of numerical simulations. The method uses machine-learning methods based on convolutional neural networks applied to the classification of images resulting from numerical simulations. Specifically we focus on the supersonic velocity regime and choose the direction of the black hole to be parallel to its spin. We build a catalog of 900 simulations by numerically solving Euler's equations onto the fixed space-time background of a black hole, for two parameters: the adiabatic index Γ with values in the range [1.1, 5 /3 ], and the asymptotic relative velocity of the black hole with respect to the surroundings v∞, with values within [0.2 ,0.8 ]c . For each simulation we produce a 2D image of the gas density once the process of accretion has approached a stationary regime. The results obtained show that the implemented convolutional neural networks are able to correctly classify the adiabatic index 87.78% of the time within an uncertainty of ±0.0284 , while the prediction of the velocity is correct 96.67% of the time within an uncertainty of ±0.03 c . We expect that this combination of a massive number of numerical simulations and machine-learning methods will help us analyze more complicated scenarios related to future high-resolution observations of black holes, like those from the Event Horizon Telescope.

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.

Learning Data Set Influence on Identification Accuracy of Gas Turbine Neural Network Model

NASA Astrophysics Data System (ADS)

Kuznetsov, A. V.; Makaryants, G. M.

2018-01-01

There are many gas turbine engine identification researches via dynamic neural network models. It should minimize errors between model and real object during identification process. Questions about training data set processing of neural networks are usually missed. This article presents a study about influence of data set type on gas turbine neural network model accuracy. The identification object is thermodynamic model of micro gas turbine engine. The thermodynamic model input signal is the fuel consumption and output signal is the engine rotor rotation frequency. Four types input signals was used for creating training and testing data sets of dynamic neural network models - step, fast, slow and mixed. Four dynamic neural networks were created based on these types of training data sets. Each neural network was tested via four types test data sets. In the result 16 transition processes from four neural networks and four test data sets from analogous solving results of thermodynamic model were compared. The errors comparison was made between all neural network errors in each test data set. In the comparison result it was shown error value ranges of each test data set. It is shown that error values ranges is small therefore the influence of data set types on identification accuracy is low.

Altered Synchronizations among Neural Networks in Geriatric Depression

PubMed Central

Wang, Lihong; Chou, Ying-Hui; Potter, Guy G.; Steffens, David C.

2015-01-01

Although major depression has been considered as a manifestation of discoordinated activity between affective and cognitive neural networks, only a few studies have examined the relationships among neural networks directly. Because of the known disconnection theory, geriatric depression could be a useful model in studying the interactions among different networks. In the present study, using independent component analysis to identify intrinsically connected neural networks, we investigated the alterations in synchronizations among neural networks in geriatric depression to better understand the underlying neural mechanisms. Resting-state fMRI data was collected from thirty-two patients with geriatric depression and thirty-two age-matched never-depressed controls. We compared the resting-state activities between the two groups in the default-mode, central executive, attention, salience, and affective networks as well as correlations among these networks. The depression group showed stronger activity than the controls in an affective network, specifically within the orbitofrontal region. However, unlike the never-depressed controls, geriatric depression group lacked synchronized/antisynchronized activity between the affective network and the other networks. Those depressed patients with lower executive function has greater synchronization between the salience network with the executive and affective networks. Our results demonstrate the effectiveness of the between-network analyses in examining neural models for geriatric depression. PMID:26180795

Altered Synchronizations among Neural Networks in Geriatric Depression.

PubMed

Wang, Lihong; Chou, Ying-Hui; Potter, Guy G; Steffens, David C

2015-01-01

Although major depression has been considered as a manifestation of discoordinated activity between affective and cognitive neural networks, only a few studies have examined the relationships among neural networks directly. Because of the known disconnection theory, geriatric depression could be a useful model in studying the interactions among different networks. In the present study, using independent component analysis to identify intrinsically connected neural networks, we investigated the alterations in synchronizations among neural networks in geriatric depression to better understand the underlying neural mechanisms. Resting-state fMRI data was collected from thirty-two patients with geriatric depression and thirty-two age-matched never-depressed controls. We compared the resting-state activities between the two groups in the default-mode, central executive, attention, salience, and affective networks as well as correlations among these networks. The depression group showed stronger activity than the controls in an affective network, specifically within the orbitofrontal region. However, unlike the never-depressed controls, geriatric depression group lacked synchronized/antisynchronized activity between the affective network and the other networks. Those depressed patients with lower executive function has greater synchronization between the salience network with the executive and affective networks. Our results demonstrate the effectiveness of the between-network analyses in examining neural models for geriatric depression.

A consensual neural network

NASA Technical Reports Server (NTRS)

Benediktsson, J. A.; Ersoy, O. K.; Swain, P. H.

1991-01-01

A neural network architecture called a consensual neural network (CNN) is proposed for the classification of data from multiple sources. Its relation to hierarchical and ensemble neural networks is discussed. CNN is based on the statistical consensus theory and uses nonlinearly transformed input data. The input data are transformed several times, and the different transformed data are applied as if they were independent inputs. The independent inputs are classified using stage neural networks and outputs from the stage networks are then weighted and combined to make a decision. Experimental results based on remote-sensing data and geographic data are given.

Neural-Network Simulator

NASA Technical Reports Server (NTRS)

Mitchell, Paul H.

1991-01-01

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

Feedback modulation of neural network synchrony and seizure susceptibility by Mdm2-p53-Nedd4-2 signaling.

PubMed

Jewett, Kathryn A; Christian, Catherine A; Bacos, Jonathan T; Lee, Kwan Young; Zhu, Jiuhe; Tsai, Nien-Pei

2016-03-22

Neural network synchrony is a critical factor in regulating information transmission through the nervous system. Improperly regulated neural network synchrony is implicated in pathophysiological conditions such as epilepsy. Despite the awareness of its importance, the molecular signaling underlying the regulation of neural network synchrony, especially after stimulation, remains largely unknown. In this study, we show that elevation of neuronal activity by the GABA(A) receptor antagonist, Picrotoxin, increases neural network synchrony in primary mouse cortical neuron cultures. The elevation of neuronal activity triggers Mdm2-dependent degradation of the tumor suppressor p53. We show here that blocking the degradation of p53 further enhances Picrotoxin-induced neural network synchrony, while promoting the inhibition of p53 with a p53 inhibitor reduces Picrotoxin-induced neural network synchrony. These data suggest that Mdm2-p53 signaling mediates a feedback mechanism to fine-tune neural network synchrony after activity stimulation. Furthermore, genetically reducing the expression of a direct target gene of p53, Nedd4-2, elevates neural network synchrony basally and occludes the effect of Picrotoxin. Finally, using a kainic acid-induced seizure model in mice, we show that alterations of Mdm2-p53-Nedd4-2 signaling affect seizure susceptibility. Together, our findings elucidate a critical role of Mdm2-p53-Nedd4-2 signaling underlying the regulation of neural network synchrony and seizure susceptibility and reveal potential therapeutic targets for hyperexcitability-associated neurological disorders.

Neural network-based model reference adaptive control system.

PubMed

Patino, H D; Liu, D

2000-01-01

In this paper, an approach to model reference adaptive control based on neural networks is proposed and analyzed for a class of first-order continuous-time nonlinear dynamical systems. The controller structure can employ either a radial basis function network or a feedforward neural network to compensate adaptively the nonlinearities in the plant. A stable controller-parameter adjustment mechanism, which is determined using the Lyapunov theory, is constructed using a sigma-modification-type updating law. The evaluation of control error in terms of the neural network learning error is performed. That is, the control error converges asymptotically to a neighborhood of zero, whose size is evaluated and depends on the approximation error of the neural network. In the design and analysis of neural network-based control systems, it is important to take into account the neural network learning error and its influence on the control error of the plant. Simulation results showing the feasibility and performance of the proposed approach are given.

Space-Time Neural Networks

NASA Technical Reports Server (NTRS)

Villarreal, James A.; Shelton, Robert O.

1992-01-01

Concept of space-time neural network affords distributed temporal memory enabling such network to model complicated dynamical systems mathematically and to recognize temporally varying spatial patterns. Digital filters replace synaptic-connection weights of conventional back-error-propagation neural network.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule.

PubMed

Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin

2015-11-01

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

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

Liu, Hui; Song, Yongduan; Xue, Fangzheng

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than themore » SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.« less

Financial Time Series Prediction Using Spiking Neural Networks

PubMed Central

Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam

2014-01-01

In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two “traditional”, rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments. PMID:25170618

Qualitative analysis of Cohen-Grossberg neural networks with multiple delays

NASA Astrophysics Data System (ADS)

Ye, Hui; Michel, Anthony N.; Wang, Kaining

1995-03-01

It is well known that a class of artificial neural networks with symmetric interconnections and without transmission delays, known as Cohen-Grossberg neural networks, possesses global stability (i.e., all trajectories tend to some equilibrium). We demonstrate in the present paper that many of the qualitative properties of Cohen-Grossberg networks will not be affected by the introduction of sufficiently small delays. Specifically, we establish some bound conditions for the time delays under which a given Cohen-Grossberg network with multiple delays is globally stable and possesses the same asymptotically stable equilibria as the corresponding network without delays. An effective method of determining the asymptotic stability of an equilibrium of a Cohen-Grossberg network with multiple delays is also presented. The present results are motivated by some of the authors earlier work [Phys. Rev. E 50, 4206 (1994)] and by some of the work of Marcus and Westervelt [Phys. Rev. A 39, 347 (1989)]. These works address qualitative analyses of Hopfield neural networks with one time delay. The present work generalizes these results to Cohen-Grossberg neural networks with multiple time delays. Hopfield neural networks constitute special cases of Cohen-Grossberg neural networks.

Integrative approaches for modeling regulation and function of the respiratory system.

PubMed

Ben-Tal, Alona; Tawhai, Merryn H

2013-01-01

Mathematical models have been central to understanding the interaction between neural control and breathing. Models of the entire respiratory system-which comprises the lungs and the neural circuitry that controls their ventilation-have been derived using simplifying assumptions to compartmentalize each component of the system and to define the interactions between components. These full system models often rely-through necessity-on empirically derived relationships or parameters, in addition to physiological values. In parallel with the development of whole respiratory system models are mathematical models that focus on furthering a detailed understanding of the neural control network, or of the several functions that contribute to gas exchange within the lung. These models are biophysically based, and rely on physiological parameters. They include single-unit models for a breathing lung or neural circuit, through to spatially distributed models of ventilation and perfusion, or multicircuit models for neural control. The challenge is to bring together these more recent advances in models of neural control with models of lung function, into a full simulation for the respiratory system that builds upon the more detailed models but remains computationally tractable. This requires first understanding the mathematical models that have been developed for the respiratory system at different levels, and which could be used to study how physiological levels of O2 and CO2 in the blood are maintained. Copyright © 2013 Wiley Periodicals, Inc.

Fast reversible learning based on neurons functioning as anisotropic multiplex hubs

NASA Astrophysics Data System (ADS)

Vardi, Roni; Goldental, Amir; Sheinin, Anton; Sardi, Shira; Kanter, Ido

2017-05-01

Neural networks are composed of neurons and synapses, which are responsible for learning in a slow adaptive dynamical process. Here we experimentally show that neurons act like independent anisotropic multiplex hubs, which relay and mute incoming signals following their input directions. Theoretically, the observed information routing enriches the computational capabilities of neurons by allowing, for instance, equalization among different information routes in the network, as well as high-frequency transmission of complex time-dependent signals constructed via several parallel routes. In addition, this kind of hubs adaptively eliminate very noisy neurons from the dynamics of the network, preventing masking of information transmission. The timescales for these features are several seconds at most, as opposed to the imprint of information by the synaptic plasticity, a process which exceeds minutes. Results open the horizon to the understanding of fast and adaptive learning realities in higher cognitive brain's functionalities.

Dynamic Neural Networks Supporting Memory Retrieval

PubMed Central

St. Jacques, Peggy L.; Kragel, Philip A.; Rubin, David C.

2011-01-01

How do separate neural networks interact to support complex cognitive processes such as remembrance of the personal past? Autobiographical memory (AM) retrieval recruits a consistent pattern of activation that potentially comprises multiple neural networks. However, it is unclear how such large-scale neural networks interact and are modulated by properties of the memory retrieval process. In the present functional MRI (fMRI) study, we combined independent component analysis (ICA) and dynamic causal modeling (DCM) to understand the neural networks supporting AM retrieval. ICA revealed four task-related components consistent with the previous literature: 1) Medial Prefrontal Cortex (PFC) Network, associated with self-referential processes, 2) Medial Temporal Lobe (MTL) Network, associated with memory, 3) Frontoparietal Network, associated with strategic search, and 4) Cingulooperculum Network, associated with goal maintenance. DCM analysis revealed that the medial PFC network drove activation within the system, consistent with the importance of this network to AM retrieval. Additionally, memory accessibility and recollection uniquely altered connectivity between these neural networks. Recollection modulated the influence of the medial PFC on the MTL network during elaboration, suggesting that greater connectivity among subsystems of the default network supports greater re-experience. In contrast, memory accessibility modulated the influence of frontoparietal and MTL networks on the medial PFC network, suggesting that ease of retrieval involves greater fluency among the multiple networks contributing to AM. These results show the integration between neural networks supporting AM retrieval and the modulation of network connectivity by behavior. PMID:21550407

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

PubMed Central

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

2017-01-01

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

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.

Classification of Respiratory Sounds by Using An Artificial Neural Network

DTIC Science & Technology

2001-10-28

CLASSIFICATION OF RESPIRATORY SOUNDS BY USING AN ARTIFICIAL NEURAL NETWORK M.C. Sezgin, Z. Dokur, T. Ölmez, M. Korürek Department of Electronics and...successfully classified by the GAL network. Keywords-Respiratory Sounds, Classification of Biomedical Signals, Artificial Neural Network . I. INTRODUCTION...process, feature extraction, and classification by the artificial neural network . At first, the RS signal obtained from a real-time measurement equipment is

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

DTIC Science & Technology

1987-10-01

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

Understanding human visual systems and its impact on our intelligent instruments

NASA Astrophysics Data System (ADS)

Strojnik Scholl, Marija; Páez, Gonzalo; Scholl, Michelle K.

2013-09-01

We review the evolution of machine vision and comment on the cross-fertilization from the neural sciences onto flourishing fields of neural processing, parallel processing, and associative memory in optical sciences and computing. Then we examine how the intensive efforts in mapping the human brain have been influenced by concepts in computer sciences, control theory, and electronic circuits. We discuss two neural paths that employ the input from the vision sense to determine the navigational options and object recognition. They are ventral temporal pathway for object recognition (what?) and dorsal parietal pathway for navigation (where?), respectively. We describe the reflexive and conscious decision centers in cerebral cortex involved with visual attention and gaze control. Interestingly, these require return path though the midbrain for ocular muscle control. We find that the cognitive psychologists currently study human brain employing low-spatial-resolution fMRI with temporal response on the order of a second. In recent years, the life scientists have concentrated on insect brains to study neural processes. We discuss how reflexive and conscious gaze-control decisions are made in the frontal eye field and inferior parietal lobe, constituting the fronto-parietal attention network. We note that ethical and experiential learnings impact our conscious decisions.

A neural net approach to space vehicle guidance

NASA Technical Reports Server (NTRS)

Caglayan, Alper K.; Allen, Scott M.

1990-01-01

The space vehicle guidance problem is formulated using a neural network approach, and the appropriate neural net architecture for modeling optimum guidance trajectories is investigated. In particular, an investigation is made of the incorporation of prior knowledge about the characteristics of the optimal guidance solution into the neural network architecture. The online classification performance of the developed network is demonstrated using a synthesized network trained with a database of optimum guidance trajectories. Such a neural-network-based guidance approach can readily adapt to environment uncertainties such as those encountered by an AOTV during atmospheric maneuvers.

Neural network and its application to CT imaging

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

Nikravesh, M.; Kovscek, A.R.; Patzek, T.W.

We present an integrated approach to imaging the progress of air displacement by spontaneous imbibition of oil into sandstone. We combine Computerized Tomography (CT) scanning and neural network image processing. The main aspects of our approach are (I) visualization of the distribution of oil and air saturation by CT, (II) interpretation of CT scans using neural networks, and (III) reconstruction of 3-D images of oil saturation from the CT scans with a neural network model. Excellent agreement between the actual images and the neural network predictions is found.

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.

Quantitative analysis of volatile organic compounds using ion mobility spectra and cascade correlation neural networks

NASA Technical Reports Server (NTRS)

Harrington, Peter DEB.; Zheng, Peng

1995-01-01

Ion Mobility Spectrometry (IMS) is a powerful technique for trace organic analysis in the gas phase. Quantitative measurements are difficult, because IMS has a limited linear range. Factors that may affect the instrument response are pressure, temperature, and humidity. Nonlinear calibration methods, such as neural networks, may be ideally suited for IMS. Neural networks have the capability of modeling complex systems. Many neural networks suffer from long training times and overfitting. Cascade correlation neural networks train at very fast rates. They also build their own topology, that is a number of layers and number of units in each layer. By controlling the decay parameter in training neural networks, reproducible and general models may be obtained.

Newly developed double neural network concept for reliable fast plasma position control

NASA Astrophysics Data System (ADS)

Jeon, Young-Mu; Na, Yong-Su; Kim, Myung-Rak; Hwang, Y. S.

2001-01-01

Neural network is considered as a parameter estimation tool in plasma controls for next generation tokamak such as ITER. The neural network has been reported to be so accurate and fast for plasma equilibrium identification that it may be applied to the control of complex tokamak plasmas. For this application, the reliability of the conventional neural network needs to be improved. In this study, a new idea of double neural network is developed to achieve this. The new idea has been applied to simple plasma position identification of KSTAR tokamak for feasibility test. Characteristics of the concept show higher reliability and fault tolerance even in severe faulty conditions, which may make neural network applicable to plasma control reliably and widely in future tokamaks.

Rule extraction from minimal neural networks for credit card screening.

PubMed

Setiono, Rudy; Baesens, Bart; Mues, Christophe

2011-08-01

While feedforward neural networks have been widely accepted as effective tools for solving classification problems, the issue of finding the best network architecture remains unresolved, particularly so in real-world problem settings. We address this issue in the context of credit card screening, where it is important to not only find a neural network with good predictive performance but also one that facilitates a clear explanation of how it produces its predictions. We show that minimal neural networks with as few as one hidden unit provide good predictive accuracy, while having the added advantage of making it easier to generate concise and comprehensible classification rules for the user. To further reduce model size, a novel approach is suggested in which network connections from the input units to this hidden unit are removed by a very straightaway pruning procedure. In terms of predictive accuracy, both the minimized neural networks and the rule sets generated from them are shown to compare favorably with other neural network based classifiers. The rules generated from the minimized neural networks are concise and thus easier to validate in a real-life setting.

Optical Neural Classification Of Binary Patterns

NASA Astrophysics Data System (ADS)

Gustafson, Steven C.; Little, Gordon R.

1988-05-01

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

An improved wavelet neural network medical image segmentation algorithm with combined maximum entropy

NASA Astrophysics Data System (ADS)

Hu, Xiaoqian; Tao, Jinxu; Ye, Zhongfu; Qiu, Bensheng; Xu, Jinzhang

2018-05-01

In order to solve the problem of medical image segmentation, a wavelet neural network medical image segmentation algorithm based on combined maximum entropy criterion is proposed. Firstly, we use bee colony algorithm to optimize the network parameters of wavelet neural network, get the parameters of network structure, initial weights and threshold values, and so on, we can quickly converge to higher precision when training, and avoid to falling into relative extremum; then the optimal number of iterations is obtained by calculating the maximum entropy of the segmented image, so as to achieve the automatic and accurate segmentation effect. Medical image segmentation experiments show that the proposed algorithm can reduce sample training time effectively and improve convergence precision, and segmentation effect is more accurate and effective than traditional BP neural network (back propagation neural network : a multilayer feed forward neural network which trained according to the error backward propagation algorithm.

Knowledge extraction from evolving spiking neural networks with rank order population coding.

PubMed

Soltic, Snjezana; Kasabov, Nikola

2010-12-01

This paper demonstrates how knowledge can be extracted from evolving spiking neural networks with rank order population coding. Knowledge discovery is a very important feature of intelligent systems. Yet, a disproportionally small amount of research is centered on the issue of knowledge extraction from spiking neural networks which are considered to be the third generation of artificial neural networks. The lack of knowledge representation compatibility is becoming a major detriment to end users of these networks. We show that a high-level knowledge can be obtained from evolving spiking neural networks. More specifically, we propose a method for fuzzy rule extraction from an evolving spiking network with rank order population coding. The proposed method was used for knowledge discovery on two benchmark taste recognition problems where the knowledge learnt by an evolving spiking neural network was extracted in the form of zero-order Takagi-Sugeno fuzzy IF-THEN rules.

Fear-potentiated startle processing in humans: Parallel fMRI and orbicularis EMG assessment during cue conditioning and extinction.

PubMed

Lindner, Katja; Neubert, Jörg; Pfannmöller, Jörg; Lotze, Martin; Hamm, Alfons O; Wendt, Julia

2015-12-01

Studying neural networks and behavioral indices such as potentiated startle responses during fear conditioning has a long tradition in both animal and human research. However, most of the studies in humans do not link startle potentiation and neural activity during fear acquisition and extinction. Therefore, we examined startle blink responses measured with electromyography (EMG) and brain activity measured with functional MRI simultaneously during differential conditioning. Furthermore, we combined these behavioral fear indices with brain network activity by analyzing the brain activity evoked by the startle probe stimulus presented during conditioned visual threat and safety cues as well as in the absence of visual stimulation. In line with previous research, we found a fear-induced potentiation of the startle blink responses when elicited during a conditioned threat stimulus and a rapid decline of amygdala activity after an initial differentiation of threat and safety cues in early acquisition trials. Increased activation during processing of threat cues was also found in the anterior insula, the anterior cingulate cortex (ACC), and the periaqueductal gray (PAG). More importantly, our results depict an increase of brain activity to probes presented during threatening in comparison to safety cues indicating an involvement of the anterior insula, the ACC, the thalamus, and the PAG in fear-potentiated startle processing during early extinction trials. Our study underlines that parallel assessment of fear-potentiated startle in fMRI paradigms can provide a helpful method to investigate common and distinct processing pathways in humans and animals and, thus, contributes to translational research. Copyright © 2015 Elsevier B.V. All rights reserved.

Efficient spiking neural network model of pattern motion selectivity in visual cortex.

PubMed

Beyeler, Michael; Richert, Micah; Dutt, Nikil D; Krichmar, Jeffrey L

2014-07-01

Simulating large-scale models of biological motion perception is challenging, due to the required memory to store the network structure and the computational power needed to quickly solve the neuronal dynamics. A low-cost yet high-performance approach to simulating large-scale neural network models in real-time is to leverage the parallel processing capability of graphics processing units (GPUs). Based on this approach, we present a two-stage model of visual area MT that we believe to be the first large-scale spiking network to demonstrate pattern direction selectivity. In this model, component-direction-selective (CDS) cells in MT linearly combine inputs from V1 cells that have spatiotemporal receptive fields according to the motion energy model of Simoncelli and Heeger. Pattern-direction-selective (PDS) cells in MT are constructed by pooling over MT CDS cells with a wide range of preferred directions. Responses of our model neurons are comparable to electrophysiological results for grating and plaid stimuli as well as speed tuning. The behavioral response of the network in a motion discrimination task is in agreement with psychophysical data. Moreover, our implementation outperforms a previous implementation of the motion energy model by orders of magnitude in terms of computational speed and memory usage. The full network, which comprises 153,216 neurons and approximately 40 million synapses, processes 20 frames per second of a 40 × 40 input video in real-time using a single off-the-shelf GPU. To promote the use of this algorithm among neuroscientists and computer vision researchers, the source code for the simulator, the network, and analysis scripts are publicly available.

Adaptive neural network motion control of manipulators with experimental evaluations.

PubMed

Puga-Guzmán, S; Moreno-Valenzuela, J; Santibáñez, V

2014-01-01

A nonlinear proportional-derivative controller plus adaptive neuronal network compensation is proposed. With the aim of estimating the desired torque, a two-layer neural network is used. Then, adaptation laws for the neural network weights are derived. Asymptotic convergence of the position and velocity tracking errors is proven, while the neural network weights are shown to be uniformly bounded. The proposed scheme has been experimentally validated in real time. These experimental evaluations were carried in two different mechanical systems: a horizontal two degrees-of-freedom robot and a vertical one degree-of-freedom arm which is affected by the gravitational force. In each one of the two experimental set-ups, the proposed scheme was implemented without and with adaptive neural network compensation. Experimental results confirmed the tracking accuracy of the proposed adaptive neural network-based controller.

Adaptive Neural Network Motion Control of Manipulators with Experimental Evaluations

PubMed Central

Puga-Guzmán, S.; Moreno-Valenzuela, J.; Santibáñez, V.

2014-01-01

A nonlinear proportional-derivative controller plus adaptive neuronal network compensation is proposed. With the aim of estimating the desired torque, a two-layer neural network is used. Then, adaptation laws for the neural network weights are derived. Asymptotic convergence of the position and velocity tracking errors is proven, while the neural network weights are shown to be uniformly bounded. The proposed scheme has been experimentally validated in real time. These experimental evaluations were carried in two different mechanical systems: a horizontal two degrees-of-freedom robot and a vertical one degree-of-freedom arm which is affected by the gravitational force. In each one of the two experimental set-ups, the proposed scheme was implemented without and with adaptive neural network compensation. Experimental results confirmed the tracking accuracy of the proposed adaptive neural network-based controller. PMID:24574910

Research on image retrieval using deep convolutional neural network combining L1 regularization and PRelu activation function

NASA Astrophysics Data System (ADS)

QingJie, Wei; WenBin, Wang

2017-06-01

In this paper, the image retrieval using deep convolutional neural network combined with regularization and PRelu activation function is studied, and improves image retrieval accuracy. Deep convolutional neural network can not only simulate the process of human brain to receive and transmit information, but also contains a convolution operation, which is very suitable for processing images. Using deep convolutional neural network is better than direct extraction of image visual features for image retrieval. However, the structure of deep convolutional neural network is complex, and it is easy to over-fitting and reduces the accuracy of image retrieval. In this paper, we combine L1 regularization and PRelu activation function to construct a deep convolutional neural network to prevent over-fitting of the network and improve the accuracy of image retrieval

Program Helps Simulate Neural Networks

NASA Technical Reports Server (NTRS)

Villarreal, James; Mcintire, Gary

1993-01-01

Neural Network Environment on Transputer System (NNETS) computer program provides users high degree of flexibility in creating and manipulating wide variety of neural-network topologies at processing speeds not found in conventional computing environments. Supports back-propagation and back-propagation-related algorithms. Back-propagation algorithm used is implementation of Rumelhart's generalized delta rule. NNETS developed on INMOS Transputer(R). Predefines back-propagation network, Jordan network, and reinforcement network to assist users in learning and defining own networks. Also enables users to configure other neural-network paradigms from NNETS basic architecture. Small portion of software written in OCCAM(R) language.

Establishing a Dynamic Self-Adaptation Learning Algorithm of the BP Neural Network and Its Applications

NASA Astrophysics Data System (ADS)

Li, Xiaofeng; Xiang, Suying; Zhu, Pengfei; Wu, Min

2015-12-01

In order to avoid the inherent deficiencies of the traditional BP neural network, such as slow convergence speed, that easily leading to local minima, poor generalization ability and difficulty in determining the network structure, the dynamic self-adaptive learning algorithm of the BP neural network is put forward to improve the function of the BP neural network. The new algorithm combines the merit of principal component analysis, particle swarm optimization, correlation analysis and self-adaptive model, hence can effectively solve the problems of selecting structural parameters, initial connection weights and thresholds and learning rates of the BP neural network. This new algorithm not only reduces the human intervention, optimizes the topological structures of BP neural networks and improves the network generalization ability, but also accelerates the convergence speed of a network, avoids trapping into local minima, and enhances network adaptation ability and prediction ability. The dynamic self-adaptive learning algorithm of the BP neural network is used to forecast the total retail sale of consumer goods of Sichuan Province, China. Empirical results indicate that the new algorithm is superior to the traditional BP network algorithm in predicting accuracy and time consumption, which shows the feasibility and effectiveness of the new algorithm.

Neural net target-tracking system using structured laser patterns

NASA Astrophysics Data System (ADS)

Cho, Jae-Wan; Lee, Yong-Bum; Lee, Nam-Ho; Park, Soon-Yong; Lee, Jongmin; Choi, Gapchu; Baek, Sunghyun; Park, Dong-Sun

1996-06-01

In this paper, we describe a robot endeffector tracking system using sensory information from recently-announced structured pattern laser diodes, which can generate images with several different types of structured pattern. The neural network approach is employed to recognize the robot endeffector covering the situation of three types of motion: translation, scaling and rotation. Features for the neural network to detect the position of the endeffector are extracted from the preprocessed images. Artificial neural networks are used to store models and to match with unknown input features recognizing the position of the robot endeffector. Since a minimal number of samples are used for different directions of the robot endeffector in the system, an artificial neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network trained with the back propagation learning is used to detect the position of the robot endeffector. Another feedforward neural network module is used to estimate the motion from a sequence of images and to control movements of the robot endeffector. COmbining the tow neural networks for recognizing the robot endeffector and estimating the motion with the preprocessing stage, the whole system keeps tracking of the robot endeffector effectively.

Chaotic simulated annealing by a neural network with a variable delay: design and application.

PubMed

Chen, Shyan-Shiou

2011-10-01

In this paper, we have three goals: the first is to delineate the advantages of a variably delayed system, the second is to find a more intuitive Lyapunov function for a delayed neural network, and the third is to design a delayed neural network for a quadratic cost function. For delayed neural networks, most researchers construct a Lyapunov function based on the linear matrix inequality (LMI) approach. However, that approach is not intuitive. We provide a alternative candidate Lyapunov function for a delayed neural network. On the other hand, if we are first given a quadratic cost function, we can construct a delayed neural network by suitably dividing the second-order term into two parts: a self-feedback connection weight and a delayed connection weight. To demonstrate the advantage of a variably delayed neural network, we propose a transiently chaotic neural network with variable delay and show numerically that the model should possess a better searching ability than Chen-Aihara's model, Wang's model, and Zhao's model. We discuss both the chaotic and the convergent phases. During the chaotic phase, we simply present bifurcation diagrams for a single neuron with a constant delay and with a variable delay. We show that the variably delayed model possesses the stochastic property and chaotic wandering. During the convergent phase, we not only provide a novel Lyapunov function for neural networks with a delay (the Lyapunov function is independent of the LMI approach) but also establish a correlation between the Lyapunov function for a delayed neural network and an objective function for the traveling salesman problem. © 2011 IEEE

Modeling and control of magnetorheological fluid dampers using neural networks

NASA Astrophysics Data System (ADS)

Wang, D. H.; Liao, W. H.

2005-02-01

Due to the inherent nonlinear nature of magnetorheological (MR) fluid dampers, one of the challenging aspects for utilizing these devices to achieve high system performance is the development of accurate models and control algorithms that can take advantage of their unique characteristics. In this paper, the direct identification and inverse dynamic modeling for MR fluid dampers using feedforward and recurrent neural networks are studied. The trained direct identification neural network model can be used to predict the damping force of the MR fluid damper on line, on the basis of the dynamic responses across the MR fluid damper and the command voltage, and the inverse dynamic neural network model can be used to generate the command voltage according to the desired damping force through supervised learning. The architectures and the learning methods of the dynamic neural network models and inverse neural network models for MR fluid dampers are presented, and some simulation results are discussed. Finally, the trained neural network models are applied to predict and control the damping force of the MR fluid damper. Moreover, validation methods for the neural network models developed are proposed and used to evaluate their performance. Validation results with different data sets indicate that the proposed direct identification dynamic model using the recurrent neural network can be used to predict the damping force accurately and the inverse identification dynamic model using the recurrent neural network can act as a damper controller to generate the command voltage when the MR fluid damper is used in a semi-active mode.

Deep neural networks for direct, featureless learning through observation: The case of two-dimensional spin models

NASA Astrophysics Data System (ADS)

Mills, Kyle; Tamblyn, Isaac

2018-03-01

We demonstrate the capability of a convolutional deep neural network in predicting the nearest-neighbor energy of the 4 ×4 Ising model. Using its success at this task, we motivate the study of the larger 8 ×8 Ising model, showing that the deep neural network can learn the nearest-neighbor Ising Hamiltonian after only seeing a vanishingly small fraction of configuration space. Additionally, we show that the neural network has learned both the energy and magnetization operators with sufficient accuracy to replicate the low-temperature Ising phase transition. We then demonstrate the ability of the neural network to learn other spin models, teaching the convolutional deep neural network to accurately predict the long-range interaction of a screened Coulomb Hamiltonian, a sinusoidally attenuated screened Coulomb Hamiltonian, and a modified Potts model Hamiltonian. In the case of the long-range interaction, we demonstrate the ability of the neural network to recover the phase transition with equivalent accuracy to the numerically exact method. Furthermore, in the case of the long-range interaction, the benefits of the neural network become apparent; it is able to make predictions with a high degree of accuracy, and do so 1600 times faster than a CUDA-optimized exact calculation. Additionally, we demonstrate how the neural network succeeds at these tasks by looking at the weights learned in a simplified demonstration.

Tensor Basis Neural Network v. 1.0 (beta)

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

Ling, Julia; Templeton, Jeremy

This software package can be used to build, train, and test a neural network machine learning model. The neural network architecture is specifically designed to embed tensor invariance properties by enforcing that the model predictions sit on an invariant tensor basis. This neural network architecture can be used in developing constitutive models for applications such as turbulence modeling, materials science, and electromagnetism.

Spatial-temporal-spectral EEG patterns of BOLD functional network connectivity dynamics

NASA Astrophysics Data System (ADS)

Lamoš, Martin; Mareček, Radek; Slavíček, Tomáš; Mikl, Michal; Rektor, Ivan; Jan, Jiří

2018-06-01

Objective. Growing interest in the examination of large-scale brain network functional connectivity dynamics is accompanied by an effort to find the electrophysiological correlates. The commonly used constraints applied to spatial and spectral domains during electroencephalogram (EEG) data analysis may leave part of the neural activity unrecognized. We propose an approach that blindly reveals multimodal EEG spectral patterns that are related to the dynamics of the BOLD functional network connectivity. Approach. The blind decomposition of EEG spectrogram by parallel factor analysis has been shown to be a useful technique for uncovering patterns of neural activity. The simultaneously acquired BOLD fMRI data were decomposed by independent component analysis. Dynamic functional connectivity was computed on the component’s time series using a sliding window correlation, and between-network connectivity states were then defined based on the values of the correlation coefficients. ANOVA tests were performed to assess the relationships between the dynamics of between-network connectivity states and the fluctuations of EEG spectral patterns. Main results. We found three patterns related to the dynamics of between-network connectivity states. The first pattern has dominant peaks in the alpha, beta, and gamma bands and is related to the dynamics between the auditory, sensorimotor, and attentional networks. The second pattern, with dominant peaks in the theta and low alpha bands, is related to the visual and default mode network. The third pattern, also with peaks in the theta and low alpha bands, is related to the auditory and frontal network. Significance. Our previous findings revealed a relationship between EEG spectral pattern fluctuations and the hemodynamics of large-scale brain networks. In this study, we suggest that the relationship also exists at the level of functional connectivity dynamics among large-scale brain networks when no standard spatial and spectral constraints are applied on the EEG data.

A renaissance of neural networks in drug discovery.

PubMed

Baskin, Igor I; Winkler, David; Tetko, Igor V

2016-08-01

Neural networks are becoming a very popular method for solving machine learning and artificial intelligence problems. The variety of neural network types and their application to drug discovery requires expert knowledge to choose the most appropriate approach. In this review, the authors discuss traditional and newly emerging neural network approaches to drug discovery. Their focus is on backpropagation neural networks and their variants, self-organizing maps and associated methods, and a relatively new technique, deep learning. The most important technical issues are discussed including overfitting and its prevention through regularization, ensemble and multitask modeling, model interpretation, and estimation of applicability domain. Different aspects of using neural networks in drug discovery are considered: building structure-activity models with respect to various targets; predicting drug selectivity, toxicity profiles, ADMET and physicochemical properties; characteristics of drug-delivery systems and virtual screening. Neural networks continue to grow in importance for drug discovery. Recent developments in deep learning suggests further improvements may be gained in the analysis of large chemical data sets. It's anticipated that neural networks will be more widely used in drug discovery in the future, and applied in non-traditional areas such as drug delivery systems, biologically compatible materials, and regenerative medicine.

Deinterlacing using modular neural network

NASA Astrophysics Data System (ADS)

Woo, Dong H.; Eom, Il K.; Kim, Yoo S.

2004-05-01

Deinterlacing is the conversion process from the interlaced scan to progressive one. While many previous algorithms that are based on weighted-sum cause blurring in edge region, deinterlacing using neural network can reduce the blurring through recovering of high frequency component by learning process, and is found robust to noise. In proposed algorithm, input image is divided into edge and smooth region, and then, to each region, one neural network is assigned. Through this process, each neural network learns only patterns that are similar, therefore it makes learning more effective and estimation more accurate. But even within each region, there are various patterns such as long edge and texture in edge region. To solve this problem, modular neural network is proposed. In proposed modular neural network, two modules are combined in output node. One is for low frequency feature of local area of input image, and the other is for high frequency feature. With this structure, each modular neural network can learn different patterns with compensating for drawback of counterpart. Therefore it can adapt to various patterns within each region effectively. In simulation, the proposed algorithm shows better performance compared with conventional deinterlacing methods and single neural network method.

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.

Single-hidden-layer feed-forward quantum neural network based on Grover learning.

PubMed

Liu, Cheng-Yi; Chen, Chein; Chang, Ching-Ter; Shih, Lun-Min

2013-09-01

In this paper, a novel single-hidden-layer feed-forward quantum neural network model is proposed based on some concepts and principles in the quantum theory. By combining the quantum mechanism with the feed-forward neural network, we defined quantum hidden neurons and connected quantum weights, and used them as the fundamental information processing unit in a single-hidden-layer feed-forward neural network. The quantum neurons make a wide range of nonlinear functions serve as the activation functions in the hidden layer of the network, and the Grover searching algorithm outstands the optimal parameter setting iteratively and thus makes very efficient neural network learning possible. The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high efficient training and prospect application in future. Some simulations are taken to investigate the performance of the proposed quantum network and the result show that it can achieve accurate learning. Copyright © 2013 Elsevier Ltd. All rights reserved.

Finite-time convergent recurrent neural network with a hard-limiting activation function for constrained optimization with piecewise-linear objective functions.

PubMed

Liu, Qingshan; Wang, Jun

2011-04-01

This paper presents a one-layer recurrent neural network for solving a class of constrained nonsmooth optimization problems with piecewise-linear objective functions. The proposed neural network is guaranteed to be globally convergent in finite time to the optimal solutions under a mild condition on a derived lower bound of a single gain parameter in the model. The number of neurons in the neural network is the same as the number of decision variables of the optimization problem. Compared with existing neural networks for optimization, the proposed neural network has a couple of salient features such as finite-time convergence and a low model complexity. Specific models for two important special cases, namely, linear programming and nonsmooth optimization, are also presented. In addition, applications to the shortest path problem and constrained least absolute deviation problem are discussed with simulation results to demonstrate the effectiveness and characteristics of the proposed neural network.

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks

PubMed Central

Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli

2016-01-01

In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423

Periodicity and stability for variable-time impulsive neural networks.

PubMed

Li, Hongfei; Li, Chuandong; Huang, Tingwen

2017-10-01

The paper considers a general neural networks model with variable-time impulses. It is shown that each solution of the system intersects with every discontinuous surface exactly once via several new well-proposed assumptions. Moreover, based on the comparison principle, this paper shows that neural networks with variable-time impulse can be reduced to the corresponding neural network with fixed-time impulses under well-selected conditions. Meanwhile, the fixed-time impulsive systems can be regarded as the comparison system of the variable-time impulsive neural networks. Furthermore, a series of sufficient criteria are derived to ensure the existence and global exponential stability of periodic solution of variable-time impulsive neural networks, and to illustrate the same stability properties between variable-time impulsive neural networks and the fixed-time ones. The new criteria are established by applying Schaefer's fixed point theorem combined with the use of inequality technique. Finally, a numerical example is presented to show the effectiveness of the proposed results. Copyright © 2017 Elsevier Ltd. All rights reserved.

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.

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.

PubMed

Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli

2016-01-01

In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.

A novel neural-wavelet approach for process diagnostics and complex system modeling

NASA Astrophysics Data System (ADS)

Gao, Rong

Neural networks have been effective in several engineering applications because of their learning abilities and robustness. However certain shortcomings, such as slow convergence and local minima, are always associated with neural networks, especially neural networks applied to highly nonlinear and non-stationary problems. These problems can be effectively alleviated by integrating a new powerful tool, wavelets, into conventional neural networks. The multi-resolution analysis and feature localization capabilities of the wavelet transform offer neural networks new possibilities for learning. A neural wavelet network approach developed in this thesis enjoys fast convergence rate with little possibility to be caught at a local minimum. It combines the localization properties of wavelets with the learning abilities of neural networks. Two different testbeds are used for testing the efficiency of the new approach. The first is magnetic flowmeter-based process diagnostics: here we extend previous work, which has demonstrated that wavelet groups contain process information, to more general process diagnostics. A loop at Applied Intelligent Systems Lab (AISL) is used for collecting and analyzing data through the neural-wavelet approach. The research is important for thermal-hydraulic processes in nuclear and other engineering fields. The neural-wavelet approach developed is also tested with data from the electric power grid. More specifically, the neural-wavelet approach is used for performing short-term and mid-term prediction of power load demand. In addition, the feasibility of determining the type of load using the proposed neural wavelet approach is also examined. The notion of cross scale product has been developed as an expedient yet reliable discriminator of loads. Theoretical issues involved in the integration of wavelets and neural networks are discussed and future work outlined.

Active Control of Wind-Tunnel Model Aeroelastic Response Using Neural Networks

NASA Technical Reports Server (NTRS)

Scott, Robert C.

2000-01-01

NASA Langley Research Center, Hampton, VA 23681 Under a joint research and development effort conducted by the National Aeronautics and Space Administration and The Boeing Company (formerly McDonnell Douglas) three neural-network based control systems were developed and tested. The control systems were experimentally evaluated using a transonic wind-tunnel model in the Langley Transonic Dynamics Tunnel. One system used a neural network to schedule flutter suppression control laws, another employed a neural network in a predictive control scheme, and the third employed a neural network in an inverse model control scheme. All three of these control schemes successfully suppressed flutter to or near the limits of the testing apparatus, and represent the first experimental applications of neural networks to flutter suppression. This paper will summarize the findings of this project.

Modeling Aircraft Wing Loads from Flight Data Using Neural Networks

NASA Technical Reports Server (NTRS)

Allen, Michael J.; Dibley, Ryan P.

2003-01-01

Neural networks were used to model wing bending-moment loads, torsion loads, and control surface hinge-moments of the Active Aeroelastic Wing (AAW) aircraft. Accurate loads models are required for the development of control laws designed to increase roll performance through wing twist while not exceeding load limits. Inputs to the model include aircraft rates, accelerations, and control surface positions. Neural networks were chosen to model aircraft loads because they can account for uncharacterized nonlinear effects while retaining the capability to generalize. The accuracy of the neural network models was improved by first developing linear loads models to use as starting points for network training. Neural networks were then trained with flight data for rolls, loaded reversals, wind-up-turns, and individual control surface doublets for load excitation. Generalization was improved by using gain weighting and early stopping. Results are presented for neural network loads models of four wing loads and four control surface hinge moments at Mach 0.90 and an altitude of 15,000 ft. An average model prediction error reduction of 18.6 percent was calculated for the neural network models when compared to the linear models. This paper documents the input data conditioning, input parameter selection, structure, training, and validation of the neural network models.

Exponential H(infinity) synchronization of general discrete-time chaotic neural networks with or without time delays.

PubMed

Qi, Donglian; Liu, Meiqin; Qiu, Meikang; Zhang, Senlin

2010-08-01

This brief studies exponential H(infinity) synchronization of a class of general discrete-time chaotic neural networks with external disturbance. On the basis of the drive-response concept and H(infinity) control theory, and using Lyapunov-Krasovskii (or Lyapunov) functional, state feedback controllers are established to not only guarantee exponential stable synchronization between two general chaotic neural networks with or without time delays, but also reduce the effect of external disturbance on the synchronization error to a minimal H(infinity) norm constraint. The proposed controllers can be obtained by solving the convex optimization problems represented by linear matrix inequalities. Most discrete-time chaotic systems with or without time delays, such as Hopfield neural networks, cellular neural networks, bidirectional associative memory networks, recurrent multilayer perceptrons, Cohen-Grossberg neural networks, Chua's circuits, etc., can be transformed into this general chaotic neural network to be H(infinity) synchronization controller designed in a unified way. Finally, some illustrated examples with their simulations have been utilized to demonstrate the effectiveness of the proposed methods.

Automated implementation of rule-based expert systems with neural networks for time-critical applications

NASA Technical Reports Server (NTRS)

Ramamoorthy, P. A.; Huang, Song; Govind, Girish

1991-01-01

In fault diagnosis, control and real-time monitoring, both timing and accuracy are critical for operators or machines to reach proper solutions or appropriate actions. Expert systems are becoming more popular in the manufacturing community for dealing with such problems. In recent years, neural networks have revived and their applications have spread to many areas of science and engineering. A method of using neural networks to implement rule-based expert systems for time-critical applications is discussed here. This method can convert a given rule-based system into a neural network with fixed weights and thresholds. The rules governing the translation are presented along with some examples. We also present the results of automated machine implementation of such networks from the given rule-base. This significantly simplifies the translation process to neural network expert systems from conventional rule-based systems. Results comparing the performance of the proposed approach based on neural networks vs. the classical approach are given. The possibility of very large scale integration (VLSI) realization of such neural network expert systems is also discussed.

Predicting Slag Generation in Sub-Scale Test Motors Using a Neural Network

NASA Technical Reports Server (NTRS)

Wiesenberg, Brent

1999-01-01

Generation of slag (aluminum oxide) is an important issue for the Reusable Solid Rocket Motor (RSRM). Thiokol performed testing to quantify the relationship between raw material variations and slag generation in solid propellants by testing sub-scale motors cast with propellant containing various combinations of aluminum fuel and ammonium perchlorate (AP) oxidizer particle sizes. The test data were analyzed using statistical methods and an artificial neural network. This paper primarily addresses the neural network results with some comparisons to the statistical results. The neural network showed that the particle sizes of both the aluminum and unground AP have a measurable effect on slag generation. The neural network analysis showed that aluminum particle size is the dominant driver in slag generation, about 40% more influential than AP. The network predictions of the amount of slag produced during firing of sub-scale motors were 16% better than the predictions of a statistically derived empirical equation. Another neural network successfully characterized the slag generated during full-scale motor tests. The success is attributable to the ability of neural networks to characterize multiple complex factors including interactions that affect slag generation.

Application of Two-Dimensional AWE Algorithm in Training Multi-Dimensional Neural Network Model

DTIC Science & Technology

2003-07-01

hybrid scheme . the general neural network method (Table 3.1). The training process of the software- ACKNOWLEDGMENT "Neuralmodeler" is shown in Fig. 3.2...engineering. Artificial neural networks (ANNs) have emerged Training a neural network model is the key of as a powerful technique for modeling general neural...coefficients am, the derivatives method of moments (MoM). The variables in the of matrix I have to be generated . A closed form model are frequency

Center for Neural Engineering at Tennessee State University, ASSERT Annual Progress Report.

DTIC Science & Technology

1995-07-01

neural networks . Their research topics are: (1) developing frequency dependent oscillatory neural networks ; (2) long term pontentiation learning rules...as applied to spatial navigation; (3) design and build a servo joint robotic arm and (4) neural network based prothesis control. One graduate student

A Feasibility Study of Synthesizing Subsurfaces Modeled with Computational Neural Networks

NASA Technical Reports Server (NTRS)

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

1998-01-01

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

Neural network based system for equipment surveillance

DOEpatents

Vilim, Richard B.; Gross, Kenneth C.; Wegerich, Stephan W.

1998-01-01

A method and system for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process.

Neural network based system for equipment surveillance

DOEpatents

Vilim, R.B.; Gross, K.C.; Wegerich, S.W.

1998-04-28

A method and system are disclosed for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process. 33 figs.

Neural networks for function approximation in nonlinear control

NASA Technical Reports Server (NTRS)

Linse, Dennis J.; Stengel, Robert F.

1990-01-01

Two neural network architectures are compared with a classical spline interpolation technique for the approximation of functions useful in a nonlinear control system. A standard back-propagation feedforward neural network and a cerebellar model articulation controller (CMAC) neural network are presented, and their results are compared with a B-spline interpolation procedure that is updated using recursive least-squares parameter identification. Each method is able to accurately represent a one-dimensional test function. Tradeoffs between size requirements, speed of operation, and speed of learning indicate that neural networks may be practical for identification and adaptation in a nonlinear control environment.

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.

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...

Artificial Neural Network Metamodels of Stochastic Computer Simulations

DTIC Science & Technology

1994-08-10

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

Research on wind field algorithm of wind lidar based on BP neural network and grey prediction

NASA Astrophysics Data System (ADS)

Chen, Yong; Chen, Chun-Li; Luo, Xiong; Zhang, Yan; Yang, Ze-hou; Zhou, Jie; Shi, Xiao-ding; Wang, Lei

2018-01-01

This paper uses the BP neural network and grey algorithm to forecast and study radar wind field. In order to reduce the residual error in the wind field prediction which uses BP neural network and grey algorithm, calculating the minimum value of residual error function, adopting the residuals of the gray algorithm trained by BP neural network, using the trained network model to forecast the residual sequence, using the predicted residual error sequence to modify the forecast sequence of the grey algorithm. The test data show that using the grey algorithm modified by BP neural network can effectively reduce the residual value and improve the prediction precision.

A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting

NASA Astrophysics Data System (ADS)

Luk, K. C.; Ball, J. E.; Sharma, A.

2000-01-01

Artificial neural networks (ANNs), which emulate the parallel distributed processing of the human nervous system, have proven to be very successful in dealing with complicated problems, such as function approximation and pattern recognition. Due to their powerful capability and functionality, ANNs provide an alternative approach for many engineering problems that are difficult to solve by conventional approaches. Rainfall forecasting has been a difficult subject in hydrology due to the complexity of the physical processes involved and the variability of rainfall in space and time. In this study, ANNs were adopted to forecast short-term rainfall for an urban catchment. The ANNs were trained to recognise historical rainfall patterns as recorded from a number of gauges in the study catchment for reproduction of relevant patterns for new rainstorm events. The primary objective of this paper is to investigate the effect of temporal and spatial information on short-term rainfall forecasting. To achieve this aim, a comparison test on the forecast accuracy was made among the ANNs configured with different orders of lag and different numbers of spatial inputs. In developing the ANNs with alternative configurations, the ANNs were trained to an optimal level to achieve good generalisation of data. It was found in this study that the ANNs provided the most accurate predictions when an optimum number of spatial inputs was included into the network, and that the network with lower lag consistently produced better performance.

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

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.

LiverTox: Advanced QSAR and Toxicogeomic Software for Hepatotoxicity Prediction

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

Lu, P-Y.; Yuracko, K.

2011-02-25

YAHSGS LLC and Oak Ridge National Laboratory (ORNL) established a CRADA in an attempt to develop a predictive system using a pre-existing ORNL computational neural network and wavelets format. This was in the interest of addressing national needs for toxicity prediction system to help overcome the significant drain of resources (money and time) being directed toward developing chemical agents for commerce. The research project has been supported through an STTR mechanism and funded by the National Institute of Environmental Health Sciences beginning Phase I in 2004 (CRADA No. ORNL-04-0688) and extending Phase II through 2007 (ORNL NFE-06-00020). To attempt themore » research objectives and aims outlined under this CRADA, state-of-the-art computational neural network and wavelet methods were used in an effort to design a predictive toxicity system that used two independent areas on which to base the system’s predictions. These two areas were quantitative structure-activity relationships and gene-expression data obtained from microarrays. A third area, using the new Massively Parallel Signature Sequencing (MPSS) technology to assess gene expression, also was attempted but had to be dropped because the company holding the rights to this promising MPSS technology went out of business. A research-scale predictive toxicity database system called Multi-Intelligent System for Toxicogenomic Applications (MISTA) was developed and its feasibility for use as a predictor of toxicological activity was tested. The fundamental focus of the CRADA was an attempt and effort to operate the MISTA database using the ORNL neural network. This effort indicated the potential that such a fully developed system might be used to assist in predicting such biological endpoints as hepatotoxcity and neurotoxicity. The MISTA/LiverTox approach if eventually fully developed might also be useful for automatic processing of microarray data to predict modes of action. A technical paper describing the methods and technology used in the CRADA has been published. This paper was entitled “A Toxicity Evaluation and Predictive System Based on Neural Networks and Wavelets” and appeared in an American Chemical Society peer-reviewed publication this year (J. Chem. Inf. Model. 47: 676685, 2007). A patent application was filed but later abandoned.« less

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.

Unfolding the neutron spectrum of a NE213 scintillator using artificial neural networks.

PubMed

Sharghi Ido, A; Bonyadi, M R; Etaati, G R; Shahriari, M

2009-10-01

Artificial neural networks technology has been applied to unfold the neutron spectra from the pulse height distribution measured with NE213 liquid scintillator. Here, both the single and multi-layer perceptron neural network models have been implemented to unfold the neutron spectrum from an Am-Be neutron source. The activation function and the connectivity of the neurons have been investigated and the results have been analyzed in terms of the network's performance. The simulation results show that the neural network that utilizes the Satlins transfer function has the best performance. In addition, omitting the bias connection of the neurons improve the performance of the network. Also, the SCINFUL code is used for generating the response functions in the training phase of the process. Finally, the results of the neural network simulation have been compared with those of the FORIST unfolding code for both (241)Am-Be and (252)Cf neutron sources. The results of neural network are in good agreement with FORIST code.

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.

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

NASA Astrophysics Data System (ADS)

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

2018-02-01

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

Plant Growth Models Using Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Bubenheim, David

1997-01-01

In this paper, we descrive our motivation and approach to devloping models and the neural network architecture. Initial use of the artificial neural network for modeling the single plant process of transpiration is presented.

Artificial Neural Network for the Prediction of Chromosomal Abnormalities in Azoospermic Males.

PubMed

Akinsal, Emre Can; Haznedar, Bulent; Baydilli, Numan; Kalinli, Adem; Ozturk, Ahmet; Ekmekçioğlu, Oğuz

2018-02-04

To evaluate whether an artifical neural network helps to diagnose any chromosomal abnormalities in azoospermic males. The data of azoospermic males attending to a tertiary academic referral center were evaluated retrospectively. Height, total testicular volume, follicle stimulating hormone, luteinising hormone, total testosterone and ejaculate volume of the patients were used for the analyses. In artificial neural network, the data of 310 azoospermics were used as the education and 115 as the test set. Logistic regression analyses and discriminant analyses were performed for statistical analyses. The tests were re-analysed with a neural network. Both logistic regression analyses and artificial neural network predicted the presence or absence of chromosomal abnormalities with more than 95% accuracy. The use of artificial neural network model has yielded satisfactory results in terms of distinguishing patients whether they have any chromosomal abnormality or not.

Synchronization criteria for generalized reaction-diffusion neural networks via periodically intermittent control.

PubMed

Gan, Qintao; Lv, Tianshi; Fu, Zhenhua

2016-04-01

In this paper, the synchronization problem for a class of generalized neural networks with time-varying delays and reaction-diffusion terms is investigated concerning Neumann boundary conditions in terms of p-norm. The proposed generalized neural networks model includes reaction-diffusion local field neural networks and reaction-diffusion static neural networks as its special cases. By establishing a new inequality, some simple and useful conditions are obtained analytically to guarantee the global exponential synchronization of the addressed neural networks under the periodically intermittent control. According to the theoretical results, the influences of diffusion coefficients, diffusion space, and control rate on synchronization are analyzed. Finally, the feasibility and effectiveness of the proposed methods are shown by simulation examples, and by choosing different diffusion coefficients, diffusion spaces, and control rates, different controlled synchronization states can be obtained.

Global exponential stability of inertial memristor-based neural networks with time-varying delays and impulses.

PubMed

Zhang, Wei; Huang, Tingwen; He, Xing; Li, Chuandong

2017-11-01

In this study, we investigate the global exponential stability of inertial memristor-based neural networks with impulses and time-varying delays. We construct inertial memristor-based neural networks based on the characteristics of the inertial neural networks and memristor. Impulses with and without delays are considered when modeling the inertial neural networks simultaneously, which are of great practical significance in the current study. Some sufficient conditions are derived under the framework of the Lyapunov stability method, as well as an extended Halanay differential inequality and a new delay impulsive differential inequality, which depend on impulses with and without delays, in order to guarantee the global exponential stability of the inertial memristor-based neural networks. Finally, two numerical examples are provided to illustrate the efficiency of the proposed methods. Copyright © 2017 Elsevier Ltd. All rights reserved.

Neural joint control for Space Shuttle Remote Manipulator System

NASA Technical Reports Server (NTRS)

Atkins, Mark A.; Cox, Chadwick J.; Lothers, Michael D.; Pap, Robert M.; Thomas, Charles R.

1992-01-01

Neural networks are being used to control a robot arm in a telerobotic operation. The concept uses neural networks for both joint and inverse kinematics in a robotic control application. An upper level neural network is trained to learn inverse kinematic mappings. The output, a trajectory, is then fed to the Decentralized Adaptive Joint Controllers. This neural network implementation has shown that the controlled arm recovers from unexpected payload changes while following the reference trajectory. The neural network-based decentralized joint controller is faster, more robust and efficient than conventional approaches. Implementations of this architecture are discussed that would relax assumptions about dynamics, obstacles, and heavy loads. This system is being developed to use with the Space Shuttle Remote Manipulator System.

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.

QSAR modelling using combined simple competitive learning networks and RBF neural networks.

PubMed

Sheikhpour, R; Sarram, M A; Rezaeian, M; Sheikhpour, E

2018-04-01

The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.

Nanophotonic particle simulation and inverse design using artificial neural networks.

PubMed

Peurifoy, John; Shen, Yichen; Jing, Li; Yang, Yi; Cano-Renteria, Fidel; DeLacy, Brendan G; Joannopoulos, John D; Tegmark, Max; Soljačić, Marin

2018-06-01

We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.

Application of Artificial Neural Networks in the Heart Electrical Axis Position Conclusion Modeling

NASA Astrophysics Data System (ADS)

Bakanovskaya, L. N.

2016-08-01

The article touches upon building of a heart electrical axis position conclusion model using an artificial neural network. The input signals of the neural network are the values of deflections Q, R and S; and the output signal is the value of the heart electrical axis position. Training of the network is carried out by the error propagation method. The test results allow concluding that the created neural network makes a conclusion with a high degree of accuracy.

Enhancement of electrical signaling in neural networks on graphene films.

PubMed

Tang, Mingliang; Song, Qin; Li, Ning; Jiang, Ziyun; Huang, Rong; Cheng, Guosheng

2013-09-01

One of the key challenges for neural tissue engineering is to exploit supporting materials with robust functionalities not only to govern cell-specific behaviors, but also to form functional neural network. The unique electrical and mechanical properties of graphene imply it as a promising candidate for neural interfaces, but little is known about the details of neural network formation on graphene as a scaffold material for tissue engineering. Therapeutic regenerative strategies aim to guide and enhance the intrinsic capacity of the neurons to reorganize by promoting plasticity mechanisms in a controllable manner. Here, we investigated the impact of graphene on the formation and performance in the assembly of neural networks in neural stem cell (NSC) culture. Using calcium imaging and electrophysiological recordings, we demonstrate the capabilities of graphene to support the growth of functional neural circuits, and improve neural performance and electrical signaling in the network. These results offer a better understanding of interactions between graphene and NSCs, also they clearly present the great potentials of graphene as neural interface in tissue engineering. Copyright © 2013 Elsevier Ltd. All rights reserved.

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.

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 Parallel and Distributed Processing Model of Joint Attention, Social-Cognition and Autism

PubMed Central

Mundy, Peter; Sullivan, Lisa; Mastergeorge, Ann M.

2009-01-01

Scientific Abstract The impaired development of joint attention is a cardinal feature of autism. Therefore, understanding the nature of joint attention is a central to research on this disorder. Joint attention may be best defined in terms of an information processing system that begins to develop by 4–6 months of age. This system integrates the parallel processing of internal information about one’s own visual attention with external information about the visual attention of other people. This type of joint encoding of information about self and other attention requires the activation of a distributed anterior and posterior cortical attention network. Genetic regulation, in conjunction with self-organizing behavioral activity guides the development of functional connectivity in this network. With practice in infancy the joint processing of self-other attention becomes automatically engaged as an executive function. It can be argued that this executive joint-attention is fundamental to human learning, as well as the development of symbolic thought, social-cognition and social-competence throughout the life span. One advantage of this parallel and distributed processing model of joint attention (PDPM) is that it directly connects theory on social pathology to a range of phenomenon in autism associated with neural connectivity, constructivist and connectionist models of cognitive development, early intervention, activity-dependent gene expression, and atypical ocular motor control. PMID:19358304