Sequential and parallel image restoration: neural network implementations.

PubMed

Figueiredo, M T; Leitao, J N

1994-01-01

Sequential and parallel image restoration algorithms and their implementations on neural networks are proposed. For images degraded by linear blur and contaminated by additive white Gaussian noise, maximum a posteriori (MAP) estimation and regularization theory lead to the same high dimension convex optimization problem. The commonly adopted strategy (in using neural networks for image restoration) is to map the objective function of the optimization problem into the energy of a predefined network, taking advantage of its energy minimization properties. Departing from this approach, we propose neural implementations of iterative minimization algorithms which are first proved to converge. The developed schemes are based on modified Hopfield (1985) networks of graded elements, with both sequential and parallel updating schedules. An algorithm supported on a fully standard Hopfield network (binary elements and zero autoconnections) is also considered. Robustness with respect to finite numerical precision is studied, and examples with real images are presented.

An Application Development Platform for Neuromorphic Computing

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

Dean, Mark; Chan, Jason; Daffron, Christopher

2016-01-01

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

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.

Optical interconnections and networks; Proceedings of the Meeting, The Hague, Netherlands, Mar. 14, 15, 1990

NASA Technical Reports Server (NTRS)

Bartelt, Hartmut (Editor)

1990-01-01

The conference presents papers on interconnections, clock distribution, neural networks, and components and materials. Particular attention is given to a comparison of optical and electrical data interconnections at the board and backplane levels, a wafer-level optical interconnection network layout, an analysis and simulation of photonic switch networks, and the integration of picosecond GaAs photoconductive devices with silicon circuits for optical clocking and interconnects. Consideration is also given to the optical implementation of neural networks, invariance in an optoelectronic implementation of neural networks, and the recording of reversible patterns in polymer lightguides.

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.

An FPGA Implementation of a Polychronous Spiking Neural Network with Delay Adaptation.

PubMed

Wang, Runchun; Cohen, Gregory; Stiefel, Klaus M; Hamilton, Tara Julia; Tapson, Jonathan; van Schaik, André

2013-01-01

We present an FPGA implementation of a re-configurable, polychronous spiking neural network with a large capacity for spatial-temporal patterns. The proposed neural network generates delay paths de novo, so that only connections that actually appear in the training patterns will be created. This allows the proposed network to use all the axons (variables) to store information. Spike Timing Dependent Delay Plasticity is used to fine-tune and add dynamics to the network. We use a time multiplexing approach allowing us to achieve 4096 (4k) neurons and up to 1.15 million programmable delay axons on a Virtex 6 FPGA. Test results show that the proposed neural network is capable of successfully recalling more than 95% of all spikes for 96% of the stored patterns. The tests also show that the neural network is robust to noise from random input spikes.

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.

A mixed-signal implementation of a polychronous spiking neural network with delay adaptation

PubMed Central

Wang, Runchun M.; Hamilton, Tara J.; Tapson, Jonathan C.; van Schaik, André

2014-01-01

We present a mixed-signal implementation of a re-configurable polychronous spiking neural network capable of storing and recalling spatio-temporal patterns. The proposed neural network contains one neuron array and one axon array. Spike Timing Dependent Delay Plasticity is used to fine-tune delays and add dynamics to the network. In our mixed-signal implementation, the neurons and axons have been implemented as both analog and digital circuits. The system thus consists of one FPGA, containing the digital neuron array and the digital axon array, and one analog IC containing the analog neuron array and the analog axon array. The system can be easily configured to use different combinations of each. We present and discuss the experimental results of all combinations of the analog and digital axon arrays and the analog and digital neuron arrays. The test results show that the proposed neural network is capable of successfully recalling more than 85% of stored patterns using both analog and digital circuits. PMID:24672422

A mixed-signal implementation of a polychronous spiking neural network with delay adaptation.

PubMed

Wang, Runchun M; Hamilton, Tara J; Tapson, Jonathan C; van Schaik, André

2014-01-01

We present a mixed-signal implementation of a re-configurable polychronous spiking neural network capable of storing and recalling spatio-temporal patterns. The proposed neural network contains one neuron array and one axon array. Spike Timing Dependent Delay Plasticity is used to fine-tune delays and add dynamics to the network. In our mixed-signal implementation, the neurons and axons have been implemented as both analog and digital circuits. The system thus consists of one FPGA, containing the digital neuron array and the digital axon array, and one analog IC containing the analog neuron array and the analog axon array. The system can be easily configured to use different combinations of each. We present and discuss the experimental results of all combinations of the analog and digital axon arrays and the analog and digital neuron arrays. The test results show that the proposed neural network is capable of successfully recalling more than 85% of stored patterns using both analog and digital circuits.

Towards a feasible implementation of quantum neural networks using quantum dots

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

Altaisky, Mikhail V., E-mail: altaisky@mx.iki.rssi.ru, E-mail: nzolnik@iki.rssi.ru; Zolnikova, Nadezhda N., E-mail: altaisky@mx.iki.rssi.ru, E-mail: nzolnik@iki.rssi.ru; Kaputkina, Natalia E., E-mail: nataly@misis.ru

2016-03-07

We propose an implementation of quantum neural networks using an array of quantum dots with dipole-dipole interactions. We demonstrate that this implementation is both feasible and versatile by studying it within the framework of GaAs based quantum dot qubits coupled to a reservoir of acoustic phonons. Using numerically exact Feynman integral calculations, we have found that the quantum coherence in our neural networks survive for over a hundred ps even at liquid nitrogen temperatures (77 K), which is three orders of magnitude higher than current implementations, which are based on SQUID-based systems operating at temperatures in the mK range.

Auto-programmable impulse neural circuits

NASA Technical Reports Server (NTRS)

Watula, D.; Meador, J.

1990-01-01

Impulse neural networks use pulse trains to communicate neuron activation levels. Impulse neural circuits emulate natural neurons at a more detailed level than that typically employed by contemporary neural network implementation methods. An impulse neural circuit which realizes short term memory dynamics is presented. The operation of that circuit is then characterized in terms of pulse frequency modulated signals. Both fixed and programmable synapse circuits for realizing long term memory are also described. The implementation of a simple and useful unsupervised learning law is then presented. The implementation of a differential Hebbian learning rule for a specific mean-frequency signal interpretation is shown to have a straightforward implementation using digital combinational logic with a variation of a previously developed programmable synapse circuit. This circuit is expected to be exploited for simple and straightforward implementation of future auto-adaptive neural circuits.

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.

Spin switches for compact implementation of neuron and synapse

NASA Astrophysics Data System (ADS)

Quang Diep, Vinh; Sutton, Brian; Behin-Aein, Behtash; Datta, Supriyo

2014-06-01

Nanomagnets driven by spin currents provide a natural implementation for a neuron and a synapse: currents allow convenient summation of multiple inputs, while the magnet provides the threshold function. The objective of this paper is to explore the possibility of a hardware neural network implementation using a spin switch (SS) as its basic building block. SS is a recently proposed device based on established technology with a transistor-like gain and input-output isolation. This allows neural networks to be constructed with purely passive interconnections without intervening clocks or amplifiers. The weights for the neural network are conveniently adjusted through analog voltages that can be stored in a non-volatile manner in an underlying CMOS layer using a floating gate low dropout voltage regulator. The operation of a multi-layer SS neural network designed for character recognition is demonstrated using a standard simulation model based on coupled Landau-Lifshitz-Gilbert equations, one for each magnet in the network.

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

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1988-01-01

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

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

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1988-01-01

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

RRAM-based hardware implementations of artificial neural networks: progress update and challenges ahead

NASA Astrophysics Data System (ADS)

Prezioso, M.; Merrikh-Bayat, F.; Chakrabarti, B.; Strukov, D.

2016-02-01

Artificial neural networks have been receiving increasing attention due to their superior performance in many information processing tasks. Typically, scaling up the size of the network results in better performance and richer functionality. However, large neural networks are challenging to implement in software and customized hardware are generally required for their practical implementations. In this work, we will discuss our group's recent efforts on the development of such custom hardware circuits, based on hybrid CMOS/memristor circuits, in particular of CMOL variety. We will start by reviewing the basics of memristive devices and of CMOL circuits. We will then discuss our recent progress towards demonstration of hybrid circuits, focusing on the experimental and theoretical results for artificial neural networks based on crossbarintegrated metal oxide memristors. We will conclude presentation with the discussion of the remaining challenges and the most pressing research needs.

Implementing neural nets with programmable logic

NASA Technical Reports Server (NTRS)

Vidal, Jacques J.

1988-01-01

Networks of Boolean programmable logic modules are presented as one purely digital class of artificial neural nets. The approach contrasts with the continuous analog framework usually suggested. Programmable logic networks are capable of handling many neural-net applications. They avoid some of the limitations of threshold logic networks and present distinct opportunities. The network nodes are called dynamically programmable logic modules. They can be implemented with digitally controlled demultiplexers. Each node performs a Boolean function of its inputs which can be dynamically assigned. The overall network is therefore a combinational circuit and its outputs are Boolean global functions of the network's input variables. The approach offers definite advantages for VLSI implementation, namely, a regular architecture with limited connectivity, simplicity of the control machinery, natural modularity, and the support of a mature technology.

Pulse-firing winner-take-all networks

NASA Technical Reports Server (NTRS)

Meador, Jack L.

1991-01-01

Winner-take-all (WTA) neural networks using pulse-firing processing elements are introduced. In the pulse-firing WTA (PWTA) networks described, input and activation signal shunting is controlled by one shared lateral inhibition signal. This organization yields an O(n) area complexity that is convenient for integrated circuit implementation. Appropriately specified network parameters allow for the accurate continuous evaluation of inputs using a signal representation compatible with established pulse-firing neural network implementations.

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

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.

A neural network device for on-line particle identification in cosmic ray experiments

NASA Astrophysics Data System (ADS)

Scrimaglio, R.; Finetti, N.; D'Altorio, L.; Rantucci, E.; Raso, M.; Segreto, E.; Tassoni, A.; Cardarilli, G. C.

2004-05-01

On-line particle identification is one of the main goals of many experiments in space both for rare event studies and for optimizing measurements along the orbital trajectory. Neural networks can be a useful tool for signal processing and real time data analysis in such experiments. In this document we report on the performances of a programmable neural device which was developed in VLSI analog/digital technology. Neurons and synapses were accomplished by making use of Operational Transconductance Amplifier (OTA) structures. In this paper we report on the results of measurements performed in order to verify the agreement of the characteristic curves of each elementary cell with simulations and on the device performances obtained by implementing simple neural structures on the VLSI chip. A feed-forward neural network (Multi-Layer Perceptron, MLP) was implemented on the VLSI chip and trained to identify particles by processing the signals of two-dimensional position-sensitive Si detectors. The radiation monitoring device consisted of three double-sided silicon strip detectors. From the analysis of a set of simulated data it was found that the MLP implemented on the neural device gave results comparable with those obtained with the standard method of analysis confirming that the implemented neural network could be employed for real time particle identification.

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.

Efficient implementation of neural network deinterlacing

NASA Astrophysics Data System (ADS)

Seo, Guiwon; Choi, Hyunsoo; Lee, Chulhee

2009-02-01

Interlaced scanning has been widely used in most broadcasting systems. However, there are some undesirable artifacts such as jagged patterns, flickering, and line twitters. Moreover, most recent TV monitors utilize flat panel display technologies such as LCD or PDP monitors and these monitors require progressive formats. Consequently, the conversion of interlaced video into progressive video is required in many applications and a number of deinterlacing methods have been proposed. Recently deinterlacing methods based on neural network have been proposed with good results. On the other hand, with high resolution video contents such as HDTV, the amount of video data to be processed is very large. As a result, the processing time and hardware complexity become an important issue. In this paper, we propose an efficient implementation of neural network deinterlacing using polynomial approximation of the sigmoid function. Experimental results show that these approximations provide equivalent performance with a considerable reduction of complexity. This implementation of neural network deinterlacing can be efficiently incorporated in HW implementation.

Neural network applications in telecommunications

NASA Technical Reports Server (NTRS)

Alspector, Joshua

1994-01-01

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

Neuromorphic Computing for Temporal Scientific Data Classification

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

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

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

Hardware implementation of an adaptive resonance theory (ART) neural network using compensated operational amplifiers

NASA Astrophysics Data System (ADS)

Ho, Ching S.; Liou, Juin J.; Georgiopoulos, Michael; Christodoulou, Christos G.

1994-03-01

This paper presents an analog circuit design and implementation for an adaptive resonance theory neural network architecture called the augmented ART1 neural network (AART1-NN). Practical monolithic operational amplifiers (Op-Amps) LM741 and LM318 are selected to implement the circuit, and a simple compensation scheme is developed to adjust the Op-Amp electrical characteristics to meet the design requirement. A 7-node prototype circuit has been designed and verified using the Pspice circuit simulator run on a Sun workstation. Results simulated from the AART1-NN circuit using the LM741, LM318, and ideal Op-Amps are presented and compared.

Standard cell-based implementation of a digital optoelectronic neural-network hardware.

PubMed

Maier, K D; Beckstein, C; Blickhan, R; Erhard, W

2001-03-10

A standard cell-based implementation of a digital optoelectronic neural-network architecture is presented. The overall structure of the multilayer perceptron network that was used, the optoelectronic interconnection system between the layers, and all components required in each layer are defined. The design process from VHDL-based modeling from synthesis and partly automatic placing and routing to the final editing of one layer of the circuit of the multilayer perceptrons are described. A suitable approach for the standard cell-based design of optoelectronic systems is presented, and shortcomings of the design tool that was used are pointed out. The layout for the microelectronic circuit of one layer in a multilayer perceptron neural network with a performance potential 1 magnitude higher than neural networks that are purely electronic based has been successfully designed.

DCS-Neural-Network Program for Aircraft Control and Testing

NASA Technical Reports Server (NTRS)

Jorgensen, Charles C.

2006-01-01

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

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

PubMed

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

2012-10-18

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

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

PubMed Central

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

2012-01-01

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

Hebbian based learning with winner-take-all for spiking neural networks

NASA Astrophysics Data System (ADS)

Gupta, Ankur; Long, Lyle

2009-03-01

Learning methods for spiking neural networks are not as well developed as the traditional neural networks that widely use back-propagation training. We propose and implement a Hebbian based learning method with winner-take-all competition for spiking neural networks. This approach is spike time dependent which makes it naturally well suited for a network of spiking neurons. Homeostasis with Hebbian learning is implemented which ensures stability and quicker learning. Homeostasis implies that the net sum of incoming weights associated with a neuron remains the same. Winner-take-all is also implemented for competitive learning between output neurons. We implemented this learning rule on a biologically based vision processing system that we are developing, and use layers of leaky integrate and fire neurons. The network when presented with 4 bars (or Gabor filters) of different orientation learns to recognize the bar orientations (or Gabor filters). After training, each output neuron learns to recognize a bar at specific orientation and responds by firing more vigorously to that bar and less vigorously to others. These neurons are found to have bell shaped tuning curves and are similar to the simple cells experimentally observed by Hubel and Wiesel in the striate cortex of cat and monkey.

Spin switches for compact implementation of neuron and synapse

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

Quang Diep, Vinh, E-mail: vdiep@purdue.edu; Sutton, Brian; Datta, Supriyo

2014-06-02

Nanomagnets driven by spin currents provide a natural implementation for a neuron and a synapse: currents allow convenient summation of multiple inputs, while the magnet provides the threshold function. The objective of this paper is to explore the possibility of a hardware neural network implementation using a spin switch (SS) as its basic building block. SS is a recently proposed device based on established technology with a transistor-like gain and input-output isolation. This allows neural networks to be constructed with purely passive interconnections without intervening clocks or amplifiers. The weights for the neural network are conveniently adjusted through analog voltagesmore » that can be stored in a non-volatile manner in an underlying CMOS layer using a floating gate low dropout voltage regulator. The operation of a multi-layer SS neural network designed for character recognition is demonstrated using a standard simulation model based on coupled Landau-Lifshitz-Gilbert equations, one for each magnet in the network.« less

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.

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.

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.

Relaxed fault-tolerant hardware implementation of neural networks in the presence of multiple transient errors.

PubMed

Mahdiani, Hamid Reza; Fakhraie, Sied Mehdi; Lucas, Caro

2012-08-01

Reliability should be identified as the most important challenge in future nano-scale very large scale integration (VLSI) implementation technologies for the development of complex integrated systems. Normally, fault tolerance (FT) in a conventional system is achieved by increasing its redundancy, which also implies higher implementation costs and lower performance that sometimes makes it even infeasible. In contrast to custom approaches, a new class of applications is categorized in this paper, which is inherently capable of absorbing some degrees of vulnerability and providing FT based on their natural properties. Neural networks are good indicators of imprecision-tolerant applications. We have also proposed a new class of FT techniques called relaxed fault-tolerant (RFT) techniques which are developed for VLSI implementation of imprecision-tolerant applications. The main advantage of RFT techniques with respect to traditional FT solutions is that they exploit inherent FT of different applications to reduce their implementation costs while improving their performance. To show the applicability as well as the efficiency of the RFT method, the experimental results for implementation of a face-recognition computationally intensive neural network and its corresponding RFT realization are presented in this paper. The results demonstrate promising higher performance of artificial neural network VLSI solutions for complex applications in faulty nano-scale implementation environments.

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

PubMed

Gisiger, Thomas; Boukadoum, Mounir

2018-02-01

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

Efficient Cancer Detection Using Multiple Neural Networks.

PubMed

Shell, John; Gregory, William D

2017-01-01

The inspection of live excised tissue specimens to ascertain malignancy is a challenging task in dermatopathology and generally in histopathology. We introduce a portable desktop prototype device that provides highly accurate neural network classification of malignant and benign tissue. The handheld device collects 47 impedance data samples from 1 Hz to 32 MHz via tetrapolar blackened platinum electrodes. The data analysis was implemented with six different backpropagation neural networks (BNN). A data set consisting of 180 malignant and 180 benign breast tissue data files in an approved IRB study at the Aurora Medical Center, Milwaukee, WI, USA, were utilized as a neural network input. The BNN structure consisted of a multi-tiered consensus approach autonomously selecting four of six neural networks to determine a malignant or benign classification. The BNN analysis was then compared with the histology results with consistent sensitivity of 100% and a specificity of 100%. This implementation successfully relied solely on statistical variation between the benign and malignant impedance data and intricate neural network configuration. This device and BNN implementation provides a novel approach that could be a valuable tool to augment current medical practice assessment of the health of breast, squamous, and basal cell carcinoma and other excised tissue without requisite tissue specimen expertise. It has the potential to provide clinical management personnel with a fast non-invasive accurate assessment of biopsied or sectioned excised tissue in various clinical settings.

Efficient Cancer Detection Using Multiple Neural Networks

PubMed Central

Gregory, William D.

2017-01-01

The inspection of live excised tissue specimens to ascertain malignancy is a challenging task in dermatopathology and generally in histopathology. We introduce a portable desktop prototype device that provides highly accurate neural network classification of malignant and benign tissue. The handheld device collects 47 impedance data samples from 1 Hz to 32 MHz via tetrapolar blackened platinum electrodes. The data analysis was implemented with six different backpropagation neural networks (BNN). A data set consisting of 180 malignant and 180 benign breast tissue data files in an approved IRB study at the Aurora Medical Center, Milwaukee, WI, USA, were utilized as a neural network input. The BNN structure consisted of a multi-tiered consensus approach autonomously selecting four of six neural networks to determine a malignant or benign classification. The BNN analysis was then compared with the histology results with consistent sensitivity of 100% and a specificity of 100%. This implementation successfully relied solely on statistical variation between the benign and malignant impedance data and intricate neural network configuration. This device and BNN implementation provides a novel approach that could be a valuable tool to augment current medical practice assessment of the health of breast, squamous, and basal cell carcinoma and other excised tissue without requisite tissue specimen expertise. It has the potential to provide clinical management personnel with a fast non-invasive accurate assessment of biopsied or sectioned excised tissue in various clinical settings. PMID:29282435

Local interconnection neural networks

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

Zhang Jiajun; Zhang Li; Yan Dapen

1993-06-01

The idea of a local interconnection neural network (LINN) is presentd and compared with the globally interconnected Hopfield model. Under the storage limit requirement, LINN is shown to offer the same associative memory capability as the global interconnection neural network while having a much smaller interconnection matrix. LINN can be readily implemented optically using the currently available spatial light modulators. 15 refs.

On the complexity of neural network classifiers: a comparison between shallow and deep architectures.

PubMed

Bianchini, Monica; Scarselli, Franco

2014-08-01

Recently, researchers in the artificial neural network field have focused their attention on connectionist models composed by several hidden layers. In fact, experimental results and heuristic considerations suggest that deep architectures are more suitable than shallow ones for modern applications, facing very complex problems, e.g., vision and human language understanding. However, the actual theoretical results supporting such a claim are still few and incomplete. In this paper, we propose a new approach to study how the depth of feedforward neural networks impacts on their ability in implementing high complexity functions. First, a new measure based on topological concepts is introduced, aimed at evaluating the complexity of the function implemented by a neural network, used for classification purposes. Then, deep and shallow neural architectures with common sigmoidal activation functions are compared, by deriving upper and lower bounds on their complexity, and studying how the complexity depends on the number of hidden units and the used activation function. The obtained results seem to support the idea that deep networks actually implements functions of higher complexity, so that they are able, with the same number of resources, to address more difficult problems.

Neural network-based retrieval from software reuse repositories

NASA Technical Reports Server (NTRS)

Eichmann, David A.; Srinivas, Kankanahalli

1992-01-01

A significant hurdle confronts the software reuser attempting to select candidate components from a software repository - discriminating between those components without resorting to inspection of the implementation(s). We outline an approach to this problem based upon neural networks which avoids requiring the repository administrators to define a conceptual closeness graph for the classification vocabulary.

Harmonic Training and the Formation of Pitch Representation in a Neural Network Model of the Auditory Brain

PubMed Central

Ahmad, Nasir; Higgins, Irina; Walker, Kerry M. M.; Stringer, Simon M.

2016-01-01

Attempting to explain the perceptual qualities of pitch has proven to be, and remains, a difficult problem. The wide range of sounds which elicit pitch and a lack of agreement across neurophysiological studies on how pitch is encoded by the brain have made this attempt more difficult. In describing the potential neural mechanisms by which pitch may be processed, a number of neural networks have been proposed and implemented. However, no unsupervised neural networks with biologically accurate cochlear inputs have yet been demonstrated. This paper proposes a simple system in which pitch representing neurons are produced in a biologically plausible setting. Purely unsupervised regimes of neural network learning are implemented and these prove to be sufficient in identifying the pitch of sounds with a variety of spectral profiles, including sounds with missing fundamental frequencies and iterated rippled noises. PMID:27047368

NETS

NASA Technical Reports Server (NTRS)

Baffes, Paul T.

1993-01-01

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

Spiking Neural Network Decoder for Brain-Machine Interfaces.

PubMed

Dethier, Julie; Gilja, Vikash; Nuyujukian, Paul; Elassaad, Shauki A; Shenoy, Krishna V; Boahen, Kwabena

2011-01-01

We used a spiking neural network (SNN) to decode neural data recorded from a 96-electrode array in premotor/motor cortex while a rhesus monkey performed a point-to-point reaching arm movement task. We mapped a Kalman-filter neural prosthetic decode algorithm developed to predict the arm's velocity on to the SNN using the Neural Engineering Framework and simulated it using Nengo , a freely available software package. A 20,000-neuron network matched the standard decoder's prediction to within 0.03% (normalized by maximum arm velocity). A 1,600-neuron version of this network was within 0.27%, and run in real-time on a 3GHz PC. These results demonstrate that a SNN can implement a statistical signal processing algorithm widely used as the decoder in high-performance neural prostheses (Kalman filter), and achieve similar results with just a few thousand neurons. Hardware SNN implementations-neuromorphic chips-may offer power savings, essential for realizing fully-implantable cortically controlled prostheses.

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

NASA Technical Reports Server (NTRS)

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

1992-01-01

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

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

NASA Astrophysics Data System (ADS)

Hsu, Ken-Yuh; Liu, Hua-Kuang

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

Decoding small surface codes with feedforward neural networks

NASA Astrophysics Data System (ADS)

Varsamopoulos, Savvas; Criger, Ben; Bertels, Koen

2018-01-01

Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.

Deep learning with coherent nanophotonic circuits

NASA Astrophysics Data System (ADS)

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

2017-07-01

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

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

PubMed Central

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

1991-01-01

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

Cascade Back-Propagation Learning in Neural Networks

NASA Technical Reports Server (NTRS)

Duong, Tuan A.

2003-01-01

The cascade back-propagation (CBP) algorithm is the basis of a conceptual design for accelerating learning in artificial neural networks. The neural networks would be implemented as analog very-large-scale integrated (VLSI) circuits, and circuits to implement the CBP algorithm would be fabricated on the same VLSI circuit chips with the neural networks. Heretofore, artificial neural networks have learned slowly because it has been necessary to train them via software, for lack of a good on-chip learning technique. The CBP algorithm is an on-chip technique that provides for continuous learning in real time. Artificial neural networks are trained by example: A network is presented with training inputs for which the correct outputs are known, and the algorithm strives to adjust the weights of synaptic connections in the network to make the actual outputs approach the correct outputs. The input data are generally divided into three parts. Two of the parts, called the "training" and "cross-validation" sets, respectively, must be such that the corresponding input/output pairs are known. During training, the cross-validation set enables verification of the status of the input-to-output transformation learned by the network to avoid over-learning. The third part of the data, termed the "test" set, consists of the inputs that are required to be transformed into outputs; this set may or may not include the training set and/or the cross-validation set. Proposed neural-network circuitry for on-chip learning would be divided into two distinct networks; one for training and one for validation. Both networks would share the same synaptic weights.

Neural networks: Application to medical imaging

NASA Technical Reports Server (NTRS)

Clarke, Laurence P.

1994-01-01

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

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.

Application of artificial neural networks in nonlinear analysis of trusses

NASA Technical Reports Server (NTRS)

Alam, J.; Berke, L.

1991-01-01

A method is developed to incorporate neural network model based upon the Backpropagation algorithm for material response into nonlinear elastic truss analysis using the initial stiffness method. Different network configurations are developed to assess the accuracy of neural network modeling of nonlinear material response. In addition to this, a scheme based upon linear interpolation for material data, is also implemented for comparison purposes. It is found that neural network approach can yield very accurate results if used with care. For the type of problems under consideration, it offers a viable alternative to other material modeling methods.

Design of a MIMD neural network processor

NASA Astrophysics Data System (ADS)

Saeks, Richard E.; Priddy, Kevin L.; Pap, Robert M.; Stowell, S.

1994-03-01

The Accurate Automation Corporation (AAC) neural network processor (NNP) module is a fully programmable multiple instruction multiple data (MIMD) parallel processor optimized for the implementation of neural networks. The AAC NNP design fully exploits the intrinsic sparseness of neural network topologies. Moreover, by using a MIMD parallel processing architecture one can update multiple neurons in parallel with efficiency approaching 100 percent as the size of the network increases. Each AAC NNP module has 8 K neurons and 32 K interconnections and is capable of 140,000,000 connections per second with an eight processor array capable of over one billion connections per second.

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

Design and implementation of a random neural network routing engine.

PubMed

Kocak, T; Seeber, J; Terzioglu, H

2003-01-01

Random neural network (RNN) is an analytically tractable spiked neural network model that has been implemented in software for a wide range of applications for over a decade. This paper presents the hardware implementation of the RNN model. Recently, cognitive packet networks (CPN) is proposed as an alternative packet network architecture where there is no routing table, instead the RNN based reinforcement learning is used to route packets. Particularly, we describe implementation details for the RNN based routing engine of a CPN network processor chip: the smart packet processor (SPP). The SPP is a dual port device that stores, modifies, and interprets the defining characteristics of multiple RNN models. In addition to hardware design improvements over the software implementation such as the dual access memory, output calculation step, and reduced output calculation module, this paper introduces a major modification to the reinforcement learning algorithm used in the original CPN specification such that the number of weight terms are reduced from 2n/sup 2/ to 2n. This not only yields significant memory savings, but it also simplifies the calculations for the steady state probabilities (neuron outputs in RNN). Simulations have been conducted to confirm the proper functionality for the isolated SPP design as well as for the multiple SPP's in a networked environment.

Real-time biomimetic Central Pattern Generators in an FPGA for hybrid experiments

PubMed Central

Ambroise, Matthieu; Levi, Timothée; Joucla, Sébastien; Yvert, Blaise; Saïghi, Sylvain

2013-01-01

This investigation of the leech heartbeat neural network system led to the development of a low resources, real-time, biomimetic digital hardware for use in hybrid experiments. The leech heartbeat neural network is one of the simplest central pattern generators (CPG). In biology, CPG provide the rhythmic bursts of spikes that form the basis for all muscle contraction orders (heartbeat) and locomotion (walking, running, etc.). The leech neural network system was previously investigated and this CPG formalized in the Hodgkin–Huxley neural model (HH), the most complex devised to date. However, the resources required for a neural model are proportional to its complexity. In response to this issue, this article describes a biomimetic implementation of a network of 240 CPGs in an FPGA (Field Programmable Gate Array), using a simple model (Izhikevich) and proposes a new synapse model: activity-dependent depression synapse. The network implementation architecture operates on a single computation core. This digital system works in real-time, requires few resources, and has the same bursting activity behavior as the complex model. The implementation of this CPG was initially validated by comparing it with a simulation of the complex model. Its activity was then matched with pharmacological data from the rat spinal cord activity. This digital system opens the way for future hybrid experiments and represents an important step toward hybridization of biological tissue and artificial neural networks. This CPG network is also likely to be useful for mimicking the locomotion activity of various animals and developing hybrid experiments for neuroprosthesis development. PMID:24319408

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.

Improving Maritime Domain Awareness Using Neural Networks for Target of Interest Classification

DTIC Science & Technology

2015-03-01

spreading SCG scaled conjugate gradient xv THIS PAGE INTENTIONALLY LEFT BLANK xvi EXECUTIVE SUMMARY The research detailed in this thesis is a...algorithms were explored for training the neural networks: resilient backpropagation (RP) and scaled conjugate gradient backpropagation ( SCG ). The...results of the neural network training performance are presented using mean squared error convergence plots. In all implementations, the SCG learning

Emergent latent symbol systems in recurrent neural networks

NASA Astrophysics Data System (ADS)

Monner, Derek; Reggia, James A.

2012-12-01

Fodor and Pylyshyn [(1988). Connectionism and cognitive architecture: A critical analysis. Cognition, 28(1-2), 3-71] famously argued that neural networks cannot behave systematically short of implementing a combinatorial symbol system. A recent response from Frank et al. [(2009). Connectionist semantic systematicity. Cognition, 110(3), 358-379] claimed to have trained a neural network to behave systematically without implementing a symbol system and without any in-built predisposition towards combinatorial representations. We believe systems like theirs may in fact implement a symbol system on a deeper and more interesting level: one where the symbols are latent - not visible at the level of network structure. In order to illustrate this possibility, we demonstrate our own recurrent neural network that learns to understand sentence-level language in terms of a scene. We demonstrate our model's learned understanding by testing it on novel sentences and scenes. By paring down our model into an architecturally minimal version, we demonstrate how it supports combinatorial computation over distributed representations by using the associative memory operations of Vector Symbolic Architectures. Knowledge of the model's memory scheme gives us tools to explain its errors and construct superior future models. We show how the model designs and manipulates a latent symbol system in which the combinatorial symbols are patterns of activation distributed across the layers of a neural network, instantiating a hybrid of classical symbolic and connectionist representations that combines advantages of both.

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.

Spatial-Temporal Reasoning Applications of Computational Intelligence in the Game of Go and Computer Networks

DTIC Science & Technology

2012-01-01

dimensionality, Tesauro used a backpropagation- based , three-layer neural network and implemented the outcome from a self-play game as the reinforcement signal...a school of fish, flock of birds, and colony of ants. Our literature review reveals that no one has used PSO to train the neural network ...trained with a variant of PSO called cellular PSO (CPSO). CSRN is a supervised learning neural network (SLNN). The proposed algorithm for the

Modeling the dynamics of evaluation: a multilevel neural network implementation of the iterative reprocessing model.

PubMed

Ehret, Phillip J; Monroe, Brian M; Read, Stephen J

2015-05-01

We present a neural network implementation of central components of the iterative reprocessing (IR) model. The IR model argues that the evaluation of social stimuli (attitudes, stereotypes) is the result of the IR of stimuli in a hierarchy of neural systems: The evaluation of social stimuli develops and changes over processing. The network has a multilevel, bidirectional feedback evaluation system that integrates initial perceptual processing and later developing semantic processing. The network processes stimuli (e.g., an individual's appearance) over repeated iterations, with increasingly higher levels of semantic processing over time. As a result, the network's evaluations of stimuli evolve. We discuss the implications of the network for a number of different issues involved in attitudes and social evaluation. The success of the network supports the IR model framework and provides new insights into attitude theory. © 2014 by the Society for Personality and Social Psychology, Inc.

Performance Parameters Analysis of an XD3P Peugeot Engine Using Artificial Neural Networks (ANN) Concept in MATLAB

NASA Astrophysics Data System (ADS)

Rangaswamy, T.; Vidhyashankar, S.; Madhusudan, M.; Bharath Shekar, H. R.

2015-04-01

The current trends of engineering follow the basic rule of innovation in mechanical engineering aspects. For the engineers to be efficient, problem solving aspects need to be viewed in a multidimensional perspective. One such methodology implemented is the fusion of technologies from other disciplines in order to solve the problems. This paper mainly deals with the application of Neural Networks in order to analyze the performance parameters of an XD3P Peugeot engine (used in Ministry of Defence). The basic propaganda of the work is divided into two main working stages. In the former stage, experimentation of an IC engine is carried out in order to obtain the primary data. In the latter stage the primary database formed is used to design and implement a predictive neural network in order to analyze the output parameters variation with respect to each other. A mathematical governing equation for the neural network is obtained. The obtained polynomial equation describes the characteristic behavior of the built neural network system. Finally, a comparative study of the results is carried out.

Automated road marking recognition system

NASA Astrophysics Data System (ADS)

Ziyatdinov, R. R.; Shigabiev, R. R.; Talipov, D. N.

2017-09-01

Development of the automated road marking recognition systems in existing and future vehicles control systems is an urgent task. One way to implement such systems is the use of neural networks. To test the possibility of using neural network software has been developed with the use of a single-layer perceptron. The resulting system based on neural network has successfully coped with the task both when driving in the daytime and at night.

Adiabatic superconducting cells for ultra-low-power artificial neural networks.

PubMed

Schegolev, Andrey E; Klenov, Nikolay V; Soloviev, Igor I; Tereshonok, Maxim V

2016-01-01

We propose the concept of using superconducting quantum interferometers for the implementation of neural network algorithms with extremely low power dissipation. These adiabatic elements are Josephson cells with sigmoid- and Gaussian-like activation functions. We optimize their parameters for application in three-layer perceptron and radial basis function networks.

An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures

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

Schuman, Catherine D; Plank, James; Disney, Adam

2016-01-01

As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these architectures. We present the results of this training framework on four classification data sets and compare those results to other neural network and neuromorphic implementations. We also discuss how this EO framework may be extended to other architectures.

Feed Forward Neural Network and Optimal Control Problem with Control and State Constraints

NASA Astrophysics Data System (ADS)

Kmet', Tibor; Kmet'ová, Mária

2009-09-01

A feed forward neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints. The paper extends adaptive critic neural network architecture proposed by [5] to the optimal control problems with control and state constraints. The optimal control problem is transcribed into a nonlinear programming problem which is implemented with adaptive critic neural network. The proposed simulation method is illustrated by the optimal control problem of nitrogen transformation cycle model. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.

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).

Application of neural networks with orthogonal activation functions in control of dynamical systems

NASA Astrophysics Data System (ADS)

Nikolić, Saša S.; Antić, Dragan S.; Milojković, Marko T.; Milovanović, Miroslav B.; Perić, Staniša Lj.; Mitić, Darko B.

2016-04-01

In this article, we present a new method for the synthesis of almost and quasi-orthogonal polynomials of arbitrary order. Filters designed on the bases of these functions are generators of generalised quasi-orthogonal signals for which we derived and presented necessary mathematical background. Based on theoretical results, we designed and practically implemented generalised first-order (k = 1) quasi-orthogonal filter and proved its quasi-orthogonality via performed experiments. Designed filters can be applied in many scientific areas. In this article, generated functions were successfully implemented in Nonlinear Auto Regressive eXogenous (NARX) neural network as activation functions. One practical application of the designed orthogonal neural network is demonstrated through the example of control of the complex technical non-linear system - laboratory magnetic levitation system. Obtained results were compared with neural networks with standard activation functions and orthogonal functions of trigonometric shape. The proposed network demonstrated superiority over existing solutions in the sense of system performances.

A neural network model for credit risk evaluation.

PubMed

Khashman, Adnan

2009-08-01

Credit scoring is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. This paper presents a credit risk evaluation system that uses a neural network model based on the back propagation learning algorithm. We train and implement the neural network to decide whether to approve or reject a credit application, using seven learning schemes and real world credit applications from the Australian credit approval datasets. A comparison of the system performance under the different learning schemes is provided, furthermore, we compare the performance of two neural networks; with one and two hidden layers following the ideal learning scheme. Experimental results suggest that neural networks can be effectively used in automatic processing of credit applications.

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

NASA Astrophysics Data System (ADS)

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

2017-10-01

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

Implementation of a pulse coupled neural network in FPGA.

PubMed

Waldemark, J; Millberg, M; Lindblad, T; Waldemark, K; Becanovic, V

2000-06-01

The Pulse Coupled neural network, PCNN, is a biologically inspired neural net and it can be used in various image analysis applications, e.g. time-critical applications in the field of image pre-processing like segmentation, filtering, etc. a VHDL implementation of the PCNN targeting FPGA was undertaken and the results presented here. The implementation contains many interesting features. By pipelining the PCNN structure a very high throughput of 55 million neuron iterations per second could be achieved. By making the coefficients re-configurable during operation, a complete recognition system could be implemented on one, or maybe two, chip(s). Reconsidering the ranges and resolutions of the constants may save a lot of hardware, since the higher resolution requires larger multipliers, adders, memories 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.

Neural-Network Object-Recognition Program

NASA Technical Reports Server (NTRS)

Spirkovska, L.; Reid, M. B.

1993-01-01

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

Investigation of a Neural Network Implementation of a TCP Packet Anomaly Detection System

DTIC Science & Technology

2004-05-01

reconnatre les nouvelles variantes d’attaque. Les réseaux de neurones artificiels (ANN) ont les capacités d’apprendre à partir de schémas et de...Computational Intelligence Techniques in Intrusion Detection Systems. In IASTED International Conference on Neural Networks and Computational Intelligence , pp...Neural Network Training: Overfitting May be Harder than Expected. In Proceedings of the Fourteenth National Conference on Artificial Intelligence , AAAI-97

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

PubMed

Orhan, A Emin; Ma, Wei Ji

2017-07-26

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

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.

Experimental Verification of Electric Drive Technologies Based on Artificial Intelligence Tools

NASA Technical Reports Server (NTRS)

Rubaai, Ahmed; Ricketts, Daniel; Kotaru, Raj; Thomas, Robert; Noga, Donald F. (Technical Monitor); Kankam, Mark D. (Technical Monitor)

2000-01-01

In this report, a fully integrated prototype of a flight servo control system is successfully developed and implemented using brushless dc motors. The control system is developed by the fuzzy logic theory, and implemented with a multilayer neural network. First, a neural network-based architecture is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the neural network structure. The network structure and the parameter learning are performed simultaneously and online in the fuzzy-neural network system. The structure learning is based on the partition of input space. The parameter learning is based on the supervised gradient decent method, using a delta adaptation law. Using experimental setup, the performance of the proposed control system is evaluated under various operating conditions. Test results are presented and discussed in the report. The proposed learning control system has several advantages, namely, simple structure and learning capability, robustness and high tracking performance and few nodes at hidden layers. In comparison with the PI controller, the proposed fuzzy-neural network system can yield a better dynamic performance with shorter settling time, and without overshoot. Experimental results have shown that the proposed control system is adaptive and robust in responding to a wide range of operating conditions. In summary, the goal of this study is to design and implement-advanced servosystems to actuate control surfaces for flight vehicles, namely, aircraft and helicopters, missiles and interceptors, and mini- and micro-air vehicles.

Artificial neural networks as quantum associative memory

NASA Astrophysics Data System (ADS)

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

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

Hidden Markov models and neural networks for fault detection in dynamic systems

NASA Technical Reports Server (NTRS)

Smyth, Padhraic

1994-01-01

Neural networks plus hidden Markov models (HMM) can provide excellent detection and false alarm rate performance in fault detection applications, as shown in this viewgraph presentation. Modified models allow for novelty detection. Key contributions of neural network models are: (1) excellent nonparametric discrimination capability; (2) a good estimator of posterior state probabilities, even in high dimensions, and thus can be embedded within overall probabilistic model (HMM); and (3) simple to implement compared to other nonparametric models. Neural network/HMM monitoring model is currently being integrated with the new Deep Space Network (DSN) antenna controller software and will be on-line monitoring a new DSN 34-m antenna (DSS-24) by July, 1994.

Application of the Intuitionistic Fuzzy InterCriteria Analysis Method with Triples to a Neural Network Preprocessing Procedure

PubMed Central

Atanassova, Vassia; Sotirova, Evdokia; Doukovska, Lyubka; Bureva, Veselina; Mavrov, Deyan; Tomov, Jivko

2017-01-01

The approach of InterCriteria Analysis (ICA) was applied for the aim of reducing the set of variables on the input of a neural network, taking into account the fact that their large number increases the number of neurons in the network, thus making them unusable for hardware implementation. Here, for the first time, with the help of the ICA method, correlations between triples of the input parameters for training of the neural networks were obtained. In this case, we use the approach of ICA for data preprocessing, which may yield reduction of the total time for training the neural networks, hence, the time for the network's processing of data and images. PMID:28874908

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

Neocleous, C.C.; Esat, I.I.; Schizas, C.N.

The creativity phase is identified as an integral part of the design phase. The characteristics of creative persons which are relevant to designing artificial neural networks manifesting aspects of creativity, are identified. Based on these identifications, a general framework of artificial neural network characteristics to implement such a goal are proposed.

An efficient annealing in Boltzmann machine in Hopfield neural network

NASA Astrophysics Data System (ADS)

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

2012-09-01

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

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

Application of neural networks to autonomous rendezvous and docking of space vehicles

NASA Technical Reports Server (NTRS)

Dabney, Richard W.

1992-01-01

NASA-Marshall has investigated the feasibility of numerous autonomous rendezvous and docking (ARD) candidate techniques. Neural networks have been studied as a viable basis for such systems' implementation, due to their intrinsic representation of such nonlinear functions as those for which analytical solutions are either difficult or nonexistent. Neural networks are also able to recognize and adapt to changes in their dynamic environment, thereby enhancing redundancy and fault tolerance. Outstanding performance has been obtained from ARD azimuth, elevation, and roll networks of this type.

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.

MATLAB Simulation of Gradient-Based Neural Network for Online Matrix Inversion

NASA Astrophysics Data System (ADS)

Zhang, Yunong; Chen, Ke; Ma, Weimu; Li, Xiao-Dong

This paper investigates the simulation of a gradient-based recurrent neural network for online solution of the matrix-inverse problem. Several important techniques are employed as follows to simulate such a neural system. 1) Kronecker product of matrices is introduced to transform a matrix-differential-equation (MDE) to a vector-differential-equation (VDE); i.e., finally, a standard ordinary-differential-equation (ODE) is obtained. 2) MATLAB routine "ode45" is introduced to solve the transformed initial-value ODE problem. 3) In addition to various implementation errors, different kinds of activation functions are simulated to show the characteristics of such a neural network. Simulation results substantiate the theoretical analysis and efficacy of the gradient-based neural network for online constant matrix inversion.

Self-control with spiking and non-spiking neural networks playing games.

PubMed

Christodoulou, Chris; Banfield, Gaye; Cleanthous, Aristodemos

2010-01-01

Self-control can be defined as choosing a large delayed reward over a small immediate reward, while precommitment is the making of a choice with the specific aim of denying oneself future choices. Humans recognise that they have self-control problems and attempt to overcome them by applying precommitment. Problems in exercising self-control, suggest a conflict between cognition and motivation, which has been linked to competition between higher and lower brain functions (representing the frontal lobes and the limbic system respectively). This premise of an internal process conflict, lead to a behavioural model being proposed, based on which, we implemented a computational model for studying and explaining self-control through precommitment behaviour. Our model consists of two neural networks, initially non-spiking and then spiking ones, representing the higher and lower brain systems viewed as cooperating for the benefit of the organism. The non-spiking neural networks are of simple feed forward multilayer type with reinforcement learning, one with selective bootstrap weight update rule, which is seen as myopic, representing the lower brain and the other with the temporal difference weight update rule, which is seen as far-sighted, representing the higher brain. The spiking neural networks are implemented with leaky integrate-and-fire neurons with learning based on stochastic synaptic transmission. The differentiating element between the two brain centres in this implementation is based on the memory of past actions determined by an eligibility trace time constant. As the structure of the self-control problem can be likened to the Iterated Prisoner's Dilemma (IPD) game in that cooperation is to defection what self-control is to impulsiveness or what compromising is to insisting, we implemented the neural networks as two players, learning simultaneously but independently, competing in the IPD game. With a technique resembling the precommitment effect, whereby the payoffs for the dilemma cases in the IPD payoff matrix are differentially biased (increased or decreased), it is shown that increasing the precommitment effect (through increasing the differential bias) increases the probability of cooperating with oneself in the future, irrespective of whether the implementation is with spiking or non-spiking neural networks. Copyright (c) 2009 Elsevier Ltd. All rights reserved.

Towards cortex sized artificial neural systems.

PubMed

Johansson, Christopher; Lansner, Anders

2007-01-01

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

Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation.

PubMed

Witoonchart, Peerajak; Chongstitvatana, Prabhas

2017-08-01

In this study, for the first time, we show how to formulate a structured support vector machine (SSVM) as two layers in a convolutional neural network, where the top layer is a loss augmented inference layer and the bottom layer is the normal convolutional layer. We show that a deformable part model can be learned with the proposed structured SVM neural network by backpropagating the error of the deformable part model to the convolutional neural network. The forward propagation calculates the loss augmented inference and the backpropagation calculates the gradient from the loss augmented inference layer to the convolutional layer. Thus, we obtain a new type of convolutional neural network called an Structured SVM convolutional neural network, which we applied to the human pose estimation problem. This new neural network can be used as the final layers in deep learning. Our method jointly learns the structural model parameters and the appearance model parameters. We implemented our method as a new layer in the existing Caffe library. Copyright © 2017 Elsevier Ltd. All rights reserved.

Automated Induction Of Rule-Based Neural Networks

NASA Technical Reports Server (NTRS)

Smyth, Padhraic J.; Goodman, Rodney M.

1994-01-01

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

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.

A simple method to derive bounds on the size and to train multilayer neural networks

NASA Technical Reports Server (NTRS)

Sartori, Michael A.; Antsaklis, Panos J.

1991-01-01

A new derivation is presented for the bounds on the size of a multilayer neural network to exactly implement an arbitrary training set; namely, the training set can be implemented with zero error with two layers and with the number of the hidden-layer neurons equal to no.1 is greater than p - 1. The derivation does not require the separation of the input space by particular hyperplanes, as in previous derivations. The weights for the hidden layer can be chosen almost arbitrarily, and the weights for the output layer can be found by solving no.1 + 1 linear equations. The method presented exactly solves (M), the multilayer neural network training problem, for any arbitrary training set.

Extraction of texture features with a multiresolution neural network

NASA Astrophysics Data System (ADS)

Lepage, Richard; Laurendeau, Denis; Gagnon, Roger A.

1992-09-01

Texture is an important surface characteristic. Many industrial materials such as wood, textile, or paper are best characterized by their texture. Detection of defaults occurring on such materials or classification for quality control anD matching can be carried out through careful texture analysis. A system for the classification of pieces of wood used in the furniture industry is proposed. This paper is concerned with a neural network implementation of the features extraction and classification components of the proposed system. Texture appears differently depending at which spatial scale it is observed. A complete description of a texture thus implies an analysis at several spatial scales. We propose a compact pyramidal representation of the input image for multiresolution analysis. The feature extraction system is implemented on a multilayer artificial neural network. Each level of the pyramid, which is a representation of the input image at a given spatial resolution scale, is mapped into a layer of the neural network. A full resolution texture image is input at the base of the pyramid and a representation of the texture image at multiple resolutions is generated by the feedforward pyramid structure of the neural network. The receptive field of each neuron at a given pyramid level is preprogrammed as a discrete Gaussian low-pass filter. Meaningful characteristics of the textured image must be extracted if a good resolving power of the classifier must be achieved. Local dominant orientation is the principal feature which is extracted from the textured image. Local edge orientation is computed with a Sobel mask at four orientation angles (multiple of (pi) /4). The resulting intrinsic image, that is, the local dominant orientation image, is fed to the texture classification neural network. The classification network is a three-layer feedforward back-propagation neural network.

High quality garbage: A neural network plastic sorter in hardware and software

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

Stanton, S.L.; Alam, M.K.; Hebner, G.A.

1993-09-01

In order to produce pure polymer streams from post-consumer waste plastics, a quick, accurate and relatively inexpensive method of sorting needs to be implemented. This technology has been demonstrated by using near-infrared spectroscopy reflectance data and neural network classification techniques. Backpropagation neural network routines have been developed to run real-time sortings in the lab, using a laboratory-grade spectrometer. In addition, a new reflectance spectrometer has been developed which is fast enough for commercial use. Initial training and test sets taken with the laboratory instrument show that a network is capable of learning 100% when classifying 5 groups of plastic (HDPEmore » and LDPE combined), and up to 100% when classifying 6 groups. Initial data sets from the new instrument have classified plastics into all seven groups with varying degrees of success. One of the initial networks has been implemented in hardware, for high speed computations, and thus rapid classification. Two neural accelerator systems have been evaluated, one based on the Intel 8017ONX chip, and another on the AT&T ANNA chip.« less

Quantitative phase microscopy using deep neural networks

NASA Astrophysics Data System (ADS)

Li, Shuai; Sinha, Ayan; Lee, Justin; Barbastathis, George

2018-02-01

Deep learning has been proven to achieve ground-breaking accuracy in various tasks. In this paper, we implemented a deep neural network (DNN) to achieve phase retrieval in a wide-field microscope. Our DNN utilized the residual neural network (ResNet) architecture and was trained using the data generated by a phase SLM. The results showed that our DNN was able to reconstruct the profile of the phase target qualitatively. In the meantime, large error still existed, which indicated that our approach still need to be improved.

A training rule which guarantees finite-region stability for a class of closed-loop neural-network control systems.

PubMed

Kuntanapreeda, S; Fullmer, R R

1996-01-01

A training method for a class of neural network controllers is presented which guarantees closed-loop system stability. The controllers are assumed to be nonlinear, feedforward, sampled-data, full-state regulators implemented as single hidden-layer neural networks. The controlled systems must be locally hermitian and observable. Stability of the closed-loop system is demonstrated by determining a Lyapunov function, which can be used to identify a finite stability region about the regulator point.

Some properties of asymmetric Hopfield neural networks with finite time of transition between states

NASA Astrophysics Data System (ADS)

Suleimenov, Ibragim; Mun, Grigoriy; Panchenko, Sergey; Pak, Ivan

2016-11-01

There were implemented samples of asymmetric Hopfield neural networks which have finite time of transition from one state to another. It was shown that in such systems, various oscillation modes could occur. It was revealed that the oscillation of the output signal of certain neuron could be treated as extra logical variable, which describes the state of the neuron. Asymmetric Hopfield neural networks are described in terms of ternary logic. Such logic may be employed in image recognition procedure.

Neural network based short-term load forecasting using weather compensation

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

Chow, T.W.S.; Leung, C.T.

This paper presents a novel technique for electric load forecasting based on neural weather compensation. The proposed method is a nonlinear generalization of Box and Jenkins approach for nonstationary time-series prediction. A weather compensation neural network is implemented for one-day ahead electric load forecasting. The weather compensation neural network can accurately predict the change of actual electric load consumption from the previous day. The results, based on Hong Kong Island historical load demand, indicate that this methodology is capable of providing a more accurate load forecast with a 0.9% reduction in forecast error.

Neural networks to classify speaker independent isolated words recorded in radio car environments

NASA Astrophysics Data System (ADS)

Alippi, C.; Simeoni, M.; Torri, V.

1993-02-01

Many applications, in particular the ones requiring nonlinear signal processing, have proved Artificial Neural Networks (ANN's) to be invaluable tools for model free estimation. The classifying abilities of ANN's are addressed by testing their performance in a speaker independent word recognition application. A real world case requiring implementation of compact integrated devices is taken into account: the classification of isolated words in radio car environment. A multispeaker database of isolated words was recorded in different environments. Data were first processed to determinate the boundaries of each word and then to extract speech features, the latter accomplished by using cepstral coefficient representation, log area ratios and filters bank techniques. Multilayered perceptron and adaptive vector quantization neural paradigms were tested to find a reasonable compromise between performances and network simplicity, fundamental requirement for the implementation of compact real time running neural devices.

pth moment exponential stability of stochastic memristor-based bidirectional associative memory (BAM) neural networks with time delays.

PubMed

Wang, Fen; Chen, Yuanlong; Liu, Meichun

2018-02-01

Stochastic memristor-based bidirectional associative memory (BAM) neural networks with time delays play an increasingly important role in the design and implementation of neural network systems. Under the framework of Filippov solutions, the issues of the pth moment exponential stability of stochastic memristor-based BAM neural networks are investigated. By using the stochastic stability theory, Itô's differential formula and Young inequality, the criteria are derived. Meanwhile, with Lyapunov approach and Cauchy-Schwarz inequality, we derive some sufficient conditions for the mean square exponential stability of the above systems. The obtained results improve and extend previous works on memristor-based or usual neural networks dynamical systems. Four numerical examples are provided to illustrate the effectiveness of the proposed results. Copyright © 2017 Elsevier Ltd. All rights reserved.

Quantum generalisation of feedforward neural networks

NASA Astrophysics Data System (ADS)

Wan, Kwok Ho; Dahlsten, Oscar; Kristjánsson, Hlér; Gardner, Robert; Kim, M. S.

2017-09-01

We propose a quantum generalisation of a classical neural network. The classical neurons are firstly rendered reversible by adding ancillary bits. Then they are generalised to being quantum reversible, i.e., unitary (the classical networks we generalise are called feedforward, and have step-function activation functions). The quantum network can be trained efficiently using gradient descent on a cost function to perform quantum generalisations of classical tasks. We demonstrate numerically that it can: (i) compress quantum states onto a minimal number of qubits, creating a quantum autoencoder, and (ii) discover quantum communication protocols such as teleportation. Our general recipe is theoretical and implementation-independent. The quantum neuron module can naturally be implemented photonically.

Neural coordination can be enhanced by occasional interruption of normal firing patterns: a self-optimizing spiking neural network model.

PubMed

Woodward, Alexander; Froese, Tom; Ikegami, Takashi

2015-02-01

The state space of a conventional Hopfield network typically exhibits many different attractors of which only a small subset satisfies constraints between neurons in a globally optimal fashion. It has recently been demonstrated that combining Hebbian learning with occasional alterations of normal neural states avoids this problem by means of self-organized enlargement of the best basins of attraction. However, so far it is not clear to what extent this process of self-optimization is also operative in real brains. Here we demonstrate that it can be transferred to more biologically plausible neural networks by implementing a self-optimizing spiking neural network model. In addition, by using this spiking neural network to emulate a Hopfield network with Hebbian learning, we attempt to make a connection between rate-based and temporal coding based neural systems. Although further work is required to make this model more realistic, it already suggests that the efficacy of the self-optimizing process is independent from the simplifying assumptions of a conventional Hopfield network. We also discuss natural and cultural processes that could be responsible for occasional alteration of neural firing patterns in actual brains. Copyright © 2014 Elsevier Ltd. All rights reserved.

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

PubMed

Sokoloski, Sacha

2017-09-01

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

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

PubMed

Matsubara, Takashi; Torikai, Hiroyuki

2016-04-01

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

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

NASA Astrophysics Data System (ADS)

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

2017-06-01

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

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

Open quantum generalisation of Hopfield neural networks

NASA Astrophysics Data System (ADS)

Rotondo, P.; Marcuzzi, M.; Garrahan, J. P.; Lesanovsky, I.; Müller, M.

2018-03-01

We propose a new framework to understand how quantum effects may impact on the dynamics of neural networks. We implement the dynamics of neural networks in terms of Markovian open quantum systems, which allows us to treat thermal and quantum coherent effects on the same footing. In particular, we propose an open quantum generalisation of the Hopfield neural network, the simplest toy model of associative memory. We determine its phase diagram and show that quantum fluctuations give rise to a qualitatively new non-equilibrium phase. This novel phase is characterised by limit cycles corresponding to high-dimensional stationary manifolds that may be regarded as a generalisation of storage patterns to the quantum domain.

Identification of Correlated GRACE Monthly Harmonic Coefficients Using Pattern Recognition and Neural Networks

NASA Astrophysics Data System (ADS)

Piretzidis, D.; Sra, G.; Sideris, M. G.

2016-12-01

This study explores new methods for identifying correlation errors in harmonic coefficients derived from monthly solutions of the Gravity Recovery and Climate Experiment (GRACE) satellite mission using pattern recognition and neural network algorithms. These correlation errors are evidenced in the differences between monthly solutions and can be suppressed using a de-correlation filter. In all studies so far, the implementation of the de-correlation filter starts from a specific minimum order (i.e., 11 for RL04 and 38 for RL05) until the maximum order of the monthly solution examined. This implementation method has two disadvantages, namely, the omission of filtering correlated coefficients of order less than the minimum order and the filtering of uncorrelated coefficients of order higher than the minimum order. In the first case, the filtered solution is not completely free of correlated errors, whereas the second case results in a monthly solution that suffers from loss of geophysical signal. In the present study, a new method of implementing the de-correlation filter is suggested, by identifying and filtering only the coefficients that show indications of high correlation. Several numerical and geometric properties of the harmonic coefficient series of all orders are examined. Extreme cases of both correlated and uncorrelated coefficients are selected, and their corresponding properties are used to train a two-layer feed-forward neural network. The objective of the neural network is to identify and quantify the correlation by providing the probability of an order of coefficients to be correlated. Results show good performance of the neural network, both in the validation stage of the training procedure and in the subsequent use of the trained network to classify independent coefficients. The neural network is also capable of identifying correlated coefficients even when a small number of training samples and neurons are used (e.g.,100 and 10, respectively).

Sign Language Recognition System using Neural Network for Digital Hardware Implementation

NASA Astrophysics Data System (ADS)

Vargas, Lorena P.; Barba, Leiner; Torres, C. O.; Mattos, L.

2011-01-01

This work presents an image pattern recognition system using neural network for the identification of sign language to deaf people. The system has several stored image that show the specific symbol in this kind of language, which is employed to teach a multilayer neural network using a back propagation algorithm. Initially, the images are processed to adapt them and to improve the performance of discriminating of the network, including in this process of filtering, reduction and elimination noise algorithms as well as edge detection. The system is evaluated using the signs without including movement in their representation.

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).

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

PubMed

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

2017-01-01

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

A neural network controller for automated composite manufacturing

NASA Technical Reports Server (NTRS)

Lichtenwalner, Peter F.

1994-01-01

At McDonnell Douglas Aerospace (MDA), an artificial neural network based control system has been developed and implemented to control laser heating for the fiber placement composite manufacturing process. This neurocontroller learns an approximate inverse model of the process on-line to provide performance that improves with experience and exceeds that of conventional feedback control techniques. When untrained, the control system behaves as a proportional plus integral (PI) controller. However after learning from experience, the neural network feedforward control module provides control signals that greatly improve temperature tracking performance. Faster convergence to new temperature set points and reduced temperature deviation due to changing feed rate have been demonstrated on the machine. A Cerebellar Model Articulation Controller (CMAC) network is used for inverse modeling because of its rapid learning performance. This control system is implemented in an IBM compatible 386 PC with an A/D board interface to the machine.

Models of Innate Neural Attractors and Their Applications for Neural Information Processing

PubMed Central

Solovyeva, Ksenia P.; Karandashev, Iakov M.; Zhavoronkov, Alex; Dunin-Barkowski, Witali L.

2016-01-01

In this work we reveal and explore a new class of attractor neural networks, based on inborn connections provided by model molecular markers, the molecular marker based attractor neural networks (MMBANN). Each set of markers has a metric, which is used to make connections between neurons containing the markers. We have explored conditions for the existence of attractor states, critical relations between their parameters and the spectrum of single neuron models, which can implement the MMBANN. Besides, we describe functional models (perceptron and SOM), which obtain significant advantages over the traditional implementation of these models, while using MMBANN. In particular, a perceptron, based on MMBANN, gets specificity gain in orders of error probabilities values, MMBANN SOM obtains real neurophysiological meaning, the number of possible grandma cells increases 1000-fold with MMBANN. MMBANN have sets of attractor states, which can serve as finite grids for representation of variables in computations. These grids may show dimensions of d = 0, 1, 2,…. We work with static and dynamic attractor neural networks of the dimensions d = 0 and 1. We also argue that the number of dimensions which can be represented by attractors of activities of neural networks with the number of elements N = 104 does not exceed 8. PMID:26778977

Classification and pose estimation of objects using nonlinear features

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-03-01

A new nonlinear feature extraction method called the maximum representation and discrimination feature (MRDF) method is presented for extraction of features from input image data. It implements transformations similar to the Sigma-Pi neural network. However, the weights of the MRDF are obtained in closed form, and offer advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We show its use in estimating the class and pose of images of real objects and rendered solid CAD models of machine parts from single views using a feature-space trajectory (FST) neural network classifier. We show more accurate classification and pose estimation results than are achieved by standard principal component analysis (PCA) and Fukunaga-Koontz (FK) feature extraction methods.

Computational models of location-invariant orthographic processing

NASA Astrophysics Data System (ADS)

Dandurand, Frédéric; Hannagan, Thomas; Grainger, Jonathan

2013-03-01

We trained three topologies of backpropagation neural networks to discriminate 2000 words (lexical representations) presented at different positions of a horizontal letter array. The first topology (zero-deck) contains no hidden layer, the second (one-deck) has a single hidden layer, and for the last topology (two-deck), the task is divided in two subtasks implemented as two stacked neural networks, with explicit word-centred letters as intermediate representations. All topologies successfully simulated two key benchmark phenomena observed in skilled human reading: transposed-letter priming and relative-position priming. However, the two-deck topology most accurately simulated the ability to discriminate words from nonwords, while containing the fewest connection weights. We analysed the internal representations after training. Zero-deck networks implement a letter-based scheme with a position bias to differentiate anagrams. One-deck networks implement a holographic overlap coding in which representations are essentially letter-based and words are linear combinations of letters. Two-deck networks also implement holographic-coding.

Smart Sensing and Recognition Based on Models of Neural Networks

DTIC Science & Technology

1990-11-15

9P-o ,yY𔄃-’. AD-A230 701 University of Pensylvania Philadelphia, PA 19104-6390 SMART SENSING AND RECOGNITION BASED ON MODELS OF NEURAL NETWORKS ... networks , photonic 1 implementations, nonlinear dynamical signal processing 9 ABSTRACT (Continue on reverse if necessary and identify by block number...not develop in isolation but in synergism with sensory organs and their feature forming networks . This means that development of artificial pattern

Real-Time Adaptive Color Segmentation by Neural Networks

NASA Technical Reports Server (NTRS)

Duong, Tuan A.

2004-01-01

Artificial neural networks that would utilize the cascade error projection (CEP) algorithm have been proposed as means of autonomous, real-time, adaptive color segmentation of images that change with time. In the original intended application, such a neural network would be used to analyze digitized color video images of terrain on a remote planet as viewed from an uninhabited spacecraft approaching the planet. During descent toward the surface of the planet, information on the segmentation of the images into differently colored areas would be updated adaptively in real time to capture changes in contrast, brightness, and resolution, all in an effort to identify a safe and scientifically productive landing site and provide control feedback to steer the spacecraft toward that site. Potential terrestrial applications include monitoring images of crops to detect insect invasions and monitoring of buildings and other facilities to detect intruders. The CEP algorithm is reliable and is well suited to implementation in very-large-scale integrated (VLSI) circuitry. It was chosen over other neural-network learning algorithms because it is better suited to realtime learning: It provides a self-evolving neural-network structure, requires fewer iterations to converge and is more tolerant to low resolution (that is, fewer bits) in the quantization of neural-network synaptic weights. Consequently, a CEP neural network learns relatively quickly, and the circuitry needed to implement it is relatively simple. Like other neural networks, a CEP neural network includes an input layer, hidden units, and output units (see figure). As in other neural networks, a CEP network is presented with a succession of input training patterns, giving rise to a set of outputs that are compared with the desired outputs. Also as in other neural networks, the synaptic weights are updated iteratively in an effort to bring the outputs closer to target values. A distinctive feature of the CEP neural network and algorithm is that each update of synaptic weights takes place in conjunction with the addition of another hidden unit, which then remains in place as still other hidden units are added on subsequent iterations. For a given training pattern, the synaptic weight between (1) the inputs and the previously added hidden units and (2) the newly added hidden unit is updated by an amount proportional to the partial derivative of a quadratic error function with respect to the synaptic weight. The synaptic weight between the newly added hidden unit and each output unit is given by a more complex function that involves the errors between the outputs and their target values, the transfer functions (hyperbolic tangents) of the neural units, and the derivatives of the transfer functions.

Applications of self-organizing neural networks in virtual screening and diversity selection.

PubMed

Selzer, Paul; Ertl, Peter

2006-01-01

Artificial neural networks provide a powerful technique for the analysis and modeling of nonlinear relationships between molecular structures and pharmacological activity. Many network types, including Kohonen and counterpropagation, also provide an intuitive method for the visual assessment of correspondence between the input and output data. This work shows how a combination of neural networks and radial distribution function molecular descriptors can be applied in various areas of industrial pharmaceutical research. These applications include the prediction of biological activity, the selection of screening candidates (cherry picking), and the extraction of representative subsets from large compound collections such as combinatorial libraries. The methods described have also been implemented as an easy-to-use Web tool, allowing chemists to perform interactive neural network experiments on the Novartis intranet.

An extended abstract: A heuristic repair method for constraint-satisfaction and scheduling problems

NASA Technical Reports Server (NTRS)

Minton, Steven; Johnston, Mark D.; Philips, Andrew B.; Laird, Philip

1992-01-01

The work described in this paper was inspired by a surprisingly effective neural network developed for scheduling astronomical observations on the Hubble Space Telescope. Our heuristic constraint satisfaction problem (CSP) method was distilled from an analysis of the network. In the process of carrying out the analysis, we discovered that the effectiveness of the network has little to do with its connectionist implementation. Furthermore, the ideas employed in the network can be implemented very efficiently within a symbolic CSP framework. The symbolic implementation is extremely simple. It also has the advantage that several different search strategies can be employed, although we have found that hill-climbing methods are particularly well-suited for the applications that we have investigated. We begin the paper with a brief review of the neural network. Following this, we describe our symbolic method for heuristic repair.

Devices and circuits for nanoelectronic implementation of artificial neural networks

NASA Astrophysics Data System (ADS)

Turel, Ozgur

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

Optical implementation of a feature-based neural network with application to automatic target recognition

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Stoner, William W.

1993-01-01

An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.

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

PubMed

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

2014-02-01

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

The architecture of adaptive neural network based on a fuzzy inference system for implementing intelligent control in photovoltaic systems

NASA Astrophysics Data System (ADS)

Gimazov, R.; Shidlovskiy, S.

2018-05-01

In this paper, we consider the architecture of the algorithm for extreme regulation in the photovoltaic system. An algorithm based on an adaptive neural network with fuzzy inference is proposed. The implementation of such an algorithm not only allows solving a number of problems in existing algorithms for extreme power regulation of photovoltaic systems, but also creates a reserve for the creation of a universal control system for a photovoltaic system.

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

NASA Astrophysics Data System (ADS)

Barreiro, Andrea K.; Ly, Cheng

2017-08-01

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

Artificial Intelligence in Prediction of Secondary Protein Structure Using CB513 Database

PubMed Central

Avdagic, Zikrija; Purisevic, Elvir; Omanovic, Samir; Coralic, Zlatan

2009-01-01

In this paper we describe CB513 a non-redundant dataset, suitable for development of algorithms for prediction of secondary protein structure. A program was made in Borland Delphi for transforming data from our dataset to make it suitable for learning of neural network for prediction of secondary protein structure implemented in MATLAB Neural-Network Toolbox. Learning (training and testing) of neural network is researched with different sizes of windows, different number of neurons in the hidden layer and different number of training epochs, while using dataset CB513. PMID:21347158

Neural network-based run-to-run controller using exposure and resist thickness adjustment

NASA Astrophysics Data System (ADS)

Geary, Shane; Barry, Ronan

2003-06-01

This paper describes the development of a run-to-run control algorithm using a feedforward neural network, trained using the backpropagation training method. The algorithm is used to predict the critical dimension of the next lot using previous lot information. It is compared to a common prediction algorithm - the exponentially weighted moving average (EWMA) and is shown to give superior prediction performance in simulations. The manufacturing implementation of the final neural network showed significantly improved process capability when compared to the case where no run-to-run control was utilised.

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.

A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network

NASA Astrophysics Data System (ADS)

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

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

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

NASA Technical Reports Server (NTRS)

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

1994-01-01

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

Implementation of neuromorphic systems: from discrete components to analog VLSI chips (testing and communication issues).

PubMed

Dante, V; Del Giudice, P; Mattia, M

2001-01-01

We review a series of implementations of electronic devices aiming at imitating to some extent structure and function of simple neural systems, with particular emphasis on communication issues. We first provide a short overview of general features of such "neuromorphic" devices and the implications of setting up "tests" for them. We then review the developments directly related to our work at the Istituto Superiore di Sanità (ISS): a pilot electronic neural network implementing a simple classifier, autonomously developing internal representations of incoming stimuli; an output network, collecting information from the previous classifier and extracting the relevant part to be forwarded to the observer; an analog, VLSI (very large scale integration) neural chip implementing a recurrent network of spiking neurons and plastic synapses, and the test setup for it; a board designed to interface the standard PCI (peripheral component interconnect) bus of a PC with a special purpose, asynchronous bus for communication among neuromorphic chips; a short and preliminary account of an application-oriented device, taking advantage of the above communication infrastructure.

Photonic Technology for Implementation of Generalizable Neural Networks: A Synthetic Approach

DTIC Science & Technology

1993-10-28

holographic medium, thus permitting duplication of a pretrainedI neural network in a manufacturing environment. Iamnfatrn I n • n wrnrm •mrmTv...usual heavy hole (hh) to first confined o. electron (le) excitonic transitions at - ljrm Co 05 wavelength, but even the light hole (1h) to leand

Evolving neural networks with genetic algorithms to study the string landscape

NASA Astrophysics Data System (ADS)

Ruehle, Fabian

2017-08-01

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

Forecasting PM10 in metropolitan areas: Efficacy of neural networks.

PubMed

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

2012-04-01

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

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.

Neural network-based sliding mode control for atmospheric-actuated spacecraft formation using switching strategy

NASA Astrophysics Data System (ADS)

Sun, Ran; Wang, Jihe; Zhang, Dexin; Shao, Xiaowei

2018-02-01

This paper presents an adaptive neural networks-based control method for spacecraft formation with coupled translational and rotational dynamics using only aerodynamic forces. It is assumed that each spacecraft is equipped with several large flat plates. A coupled orbit-attitude dynamic model is considered based on the specific configuration of atmospheric-based actuators. For this model, a neural network-based adaptive sliding mode controller is implemented, accounting for system uncertainties and external perturbations. To avoid invalidation of the neural networks destroying stability of the system, a switching control strategy is proposed which combines an adaptive neural networks controller dominating in its active region and an adaptive sliding mode controller outside the neural active region. An optimal process is developed to determine the control commands for the plates system. The stability of the closed-loop system is proved by a Lyapunov-based method. Comparative results through numerical simulations illustrate the effectiveness of executing attitude control while maintaining the relative motion, and higher control accuracy can be achieved by using the proposed neural-based switching control scheme than using only adaptive sliding mode controller.

A hypercube compact neural network

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

Rostykus, P.L.; Somani, A.K.

1988-09-01

A major problem facing implementation of neural networks is the connection problem. One popular tradeoff is to remove connections. Random disconnection severely degrades the capabilities. The hypercube based Compact Neural Network (CNN) has structured architecture combined with a rearrangement of the memory vectors gives a larger input space and better degradation than a cost equivalent network with more connections. The CNNs are based on a Hopfield network. The changes from the Hopfield net include states of -1 and +1 and when a node was evaluated to 0, it was not biased either positive or negative, instead it resumed its previousmore » state. L = PEs, N = memories and t/sub ij/s is the weights between i and j.« less

Neural Networks

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

Smith, Patrick I.

2003-09-23

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

Classification capacity of a modular neural network implementing neurally inspired architecture and training rules.

PubMed

Poirazi, Panayiota; Neocleous, Costas; Pattichis, Costantinos S; Schizas, Christos N

2004-05-01

A three-layer neural network (NN) with novel adaptive architecture has been developed. The hidden layer of the network consists of slabs of single neuron models, where neurons within a slab--but not between slabs--have the same type of activation function. The network activation functions in all three layers have adaptable parameters. The network was trained using a biologically inspired, guided-annealing learning rule on a variety of medical data. Good training/testing classification performance was obtained on all data sets tested. The performance achieved was comparable to that of SVM classifiers. It was shown that the adaptive network architecture, inspired from the modular organization often encountered in the mammalian cerebral cortex, can benefit classification performance.

Electronic device aspects of neural network memories

NASA Technical Reports Server (NTRS)

Lambe, J.; Moopenn, A.; Thakoor, A. P.

1985-01-01

The basic issues related to the electronic implementation of the neural network model (NNM) for content addressable memories are examined. A brief introduction to the principles of the NNM is followed by an analysis of the information storage of the neural network in the form of a binary connection matrix and the recall capability of such matrix memories based on a hardware simulation study. In addition, materials and device architecture issues involved in the future realization of such networks in VLSI-compatible ultrahigh-density memories are considered. A possible space application of such devices would be in the area of large-scale information storage without mechanical devices.

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

NASA Astrophysics Data System (ADS)

Madan, Alok

2005-11-01

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

Flight control with adaptive critic neural network

NASA Astrophysics Data System (ADS)

Han, Dongchen

2001-10-01

In this dissertation, the adaptive critic neural network technique is applied to solve complex nonlinear system control problems. Based on dynamic programming, the adaptive critic neural network can embed the optimal solution into a neural network. Though trained off-line, the neural network forms a real-time feedback controller. Because of its general interpolation properties, the neurocontroller has inherit robustness. The problems solved here are an agile missile control for U.S. Air Force and a midcourse guidance law for U.S. Navy. In the first three papers, the neural network was used to control an air-to-air agile missile to implement a minimum-time heading-reverse in a vertical plane corresponding to following conditions: a system without constraint, a system with control inequality constraint, and a system with state inequality constraint. While the agile missile is a one-dimensional problem, the midcourse guidance law is the first test-bed for multiple-dimensional problem. In the fourth paper, the neurocontroller is synthesized to guide a surface-to-air missile to a fixed final condition, and to a flexible final condition from a variable initial condition. In order to evaluate the adaptive critic neural network approach, the numerical solutions for these cases are also obtained by solving two-point boundary value problem with a shooting method. All of the results showed that the adaptive critic neural network could solve complex nonlinear system control problems.

Hybrid information privacy system: integration of chaotic neural network and RSA coding

NASA Astrophysics Data System (ADS)

Hsu, Ming-Kai; Willey, Jeff; Lee, Ting N.; Szu, Harold H.

2005-03-01

Electronic mails are adopted worldwide; most are easily hacked by hackers. In this paper, we purposed a free, fast and convenient hybrid privacy system to protect email communication. The privacy system is implemented by combining private security RSA algorithm with specific chaos neural network encryption process. The receiver can decrypt received email as long as it can reproduce the specified chaos neural network series, so called spatial-temporal keys. The chaotic typing and initial seed value of chaos neural network series, encrypted by the RSA algorithm, can reproduce spatial-temporal keys. The encrypted chaotic typing and initial seed value are hidden in watermark mixed nonlinearly with message media, wrapped with convolution error correction codes for wireless 3rd generation cellular phones. The message media can be an arbitrary image. The pattern noise has to be considered during transmission and it could affect/change the spatial-temporal keys. Since any change/modification on chaotic typing or initial seed value of chaos neural network series is not acceptable, the RSA codec system must be robust and fault-tolerant via wireless channel. The robust and fault-tolerant properties of chaos neural networks (CNN) were proved by a field theory of Associative Memory by Szu in 1997. The 1-D chaos generating nodes from the logistic map having arbitrarily negative slope a = p/q generating the N-shaped sigmoid was given first by Szu in 1992. In this paper, we simulated the robust and fault-tolerance properties of CNN under additive noise and pattern noise. We also implement a private version of RSA coding and chaos encryption process on messages.

Rare Neural Correlations Implement Robotic Conditioning with Delayed Rewards and Disturbances

PubMed Central

Soltoggio, Andrea; Lemme, Andre; Reinhart, Felix; Steil, Jochen J.

2013-01-01

Neural conditioning associates cues and actions with following rewards. The environments in which robots operate, however, are pervaded by a variety of disturbing stimuli and uncertain timing. In particular, variable reward delays make it difficult to reconstruct which previous actions are responsible for following rewards. Such an uncertainty is handled by biological neural networks, but represents a challenge for computational models, suggesting the lack of a satisfactory theory for robotic neural conditioning. The present study demonstrates the use of rare neural correlations in making correct associations between rewards and previous cues or actions. Rare correlations are functional in selecting sparse synapses to be eligible for later weight updates if a reward occurs. The repetition of this process singles out the associating and reward-triggering pathways, and thereby copes with distal rewards. The neural network displays macro-level classical and operant conditioning, which is demonstrated in an interactive real-life human-robot interaction. The proposed mechanism models realistic conditioning in humans and animals and implements similar behaviors in neuro-robotic platforms. PMID:23565092

Prototype-Incorporated Emotional Neural Network.

PubMed

Oyedotun, Oyebade K; Khashman, Adnan

2017-08-15

Artificial neural networks (ANNs) aim to simulate the biological neural activities. Interestingly, many ''engineering'' prospects in ANN have relied on motivations from cognition and psychology studies. So far, two important learning theories that have been subject of active research are the prototype and adaptive learning theories. The learning rules employed for ANNs can be related to adaptive learning theory, where several examples of the different classes in a task are supplied to the network for adjusting internal parameters. Conversely, the prototype-learning theory uses prototypes (representative examples); usually, one prototype per class of the different classes contained in the task. These prototypes are supplied for systematic matching with new examples so that class association can be achieved. In this paper, we propose and implement a novel neural network algorithm based on modifying the emotional neural network (EmNN) model to unify the prototype- and adaptive-learning theories. We refer to our new model as ``prototype-incorporated EmNN''. Furthermore, we apply the proposed model to two real-life challenging tasks, namely, static hand-gesture recognition and face recognition, and compare the result to those obtained using the popular back-propagation neural network (BPNN), emotional BPNN (EmNN), deep networks, an exemplar classification model, and k-nearest neighbor.

Electronic neuroprocessors

NASA Technical Reports Server (NTRS)

Thakoor, Anil

1991-01-01

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

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.

Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture

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

Disney, Adam; Reynolds, John

2015-01-01

Dynamic Adaptive Neural Network Array (DANNA) is a neuromorphic hardware implementation. It differs from most other neuromorphic projects in that it allows for programmability of structure, and it is trained or designed using evolutionary optimization. This paper describes the DANNA structure, how DANNA is trained using evolutionary optimization, and an application of DANNA to a very simple classification task.

I See What You Mean: Theta Power Increases Are Involved in the Retrieval of Lexical Semantic Information

ERIC Educational Resources Information Center

Bastiaansen, Marcel C. M.; Oostenveld, Robert; Jensen, Ole; Hagoort, Peter

2008-01-01

An influential hypothesis regarding the neural basis of the mental lexicon is that semantic representations are neurally implemented as distributed networks carrying sensory, motor and/or more abstract functional information. This work investigates whether the semantic properties of words partly determine the topography of such networks. Subjects…

A Brain-Machine Interface Operating with a Real-Time Spiking Neural Network Control Algorithm.

PubMed

Dethier, Julie; Nuyujukian, Paul; Eliasmith, Chris; Stewart, Terry; Elassaad, Shauki A; Shenoy, Krishna V; Boahen, Kwabena

2011-01-01

Motor prostheses aim to restore function to disabled patients. Despite compelling proof of concept systems, barriers to clinical translation remain. One challenge is to develop a low-power, fully-implantable system that dissipates only minimal power so as not to damage tissue. To this end, we implemented a Kalman-filter based decoder via a spiking neural network (SNN) and tested it in brain-machine interface (BMI) experiments with a rhesus monkey. The Kalman filter was trained to predict the arm's velocity and mapped on to the SNN using the Neural Engineering Framework (NEF). A 2,000-neuron embedded Matlab SNN implementation runs in real-time and its closed-loop performance is quite comparable to that of the standard Kalman filter. The success of this closed-loop decoder holds promise for hardware SNN implementations of statistical signal processing algorithms on neuromorphic chips, which may offer power savings necessary to overcome a major obstacle to the successful clinical translation of neural motor prostheses.

Superconducting Optoelectronic Circuits for Neuromorphic Computing

NASA Astrophysics Data System (ADS)

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

2017-03-01

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

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.

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.

Polarity-specific high-level information propagation in neural networks.

PubMed

Lin, Yen-Nan; Chang, Po-Yen; Hsiao, Pao-Yueh; Lo, Chung-Chuan

2014-01-01

Analyzing the connectome of a nervous system provides valuable information about the functions of its subsystems. Although much has been learned about the architectures of neural networks in various organisms by applying analytical tools developed for general networks, two distinct and functionally important properties of neural networks are often overlooked. First, neural networks are endowed with polarity at the circuit level: Information enters a neural network at input neurons, propagates through interneurons, and leaves via output neurons. Second, many functions of nervous systems are implemented by signal propagation through high-level pathways involving multiple and often recurrent connections rather than by the shortest paths between nodes. In the present study, we analyzed two neural networks: the somatic nervous system of Caenorhabditis elegans (C. elegans) and the partial central complex network of Drosophila, in light of these properties. Specifically, we quantified high-level propagation in the vertical and horizontal directions: the former characterizes how signals propagate from specific input nodes to specific output nodes and the latter characterizes how a signal from a specific input node is shared by all output nodes. We found that the two neural networks are characterized by very efficient vertical and horizontal propagation. In comparison, classic small-world networks show a trade-off between vertical and horizontal propagation; increasing the rewiring probability improves the efficiency of horizontal propagation but worsens the efficiency of vertical propagation. Our result provides insights into how the complex functions of natural neural networks may arise from a design that allows them to efficiently transform and combine input signals.

Polarity-specific high-level information propagation in neural networks

PubMed Central

Lin, Yen-Nan; Chang, Po-Yen; Hsiao, Pao-Yueh; Lo, Chung-Chuan

2014-01-01

Analyzing the connectome of a nervous system provides valuable information about the functions of its subsystems. Although much has been learned about the architectures of neural networks in various organisms by applying analytical tools developed for general networks, two distinct and functionally important properties of neural networks are often overlooked. First, neural networks are endowed with polarity at the circuit level: Information enters a neural network at input neurons, propagates through interneurons, and leaves via output neurons. Second, many functions of nervous systems are implemented by signal propagation through high-level pathways involving multiple and often recurrent connections rather than by the shortest paths between nodes. In the present study, we analyzed two neural networks: the somatic nervous system of Caenorhabditis elegans (C. elegans) and the partial central complex network of Drosophila, in light of these properties. Specifically, we quantified high-level propagation in the vertical and horizontal directions: the former characterizes how signals propagate from specific input nodes to specific output nodes and the latter characterizes how a signal from a specific input node is shared by all output nodes. We found that the two neural networks are characterized by very efficient vertical and horizontal propagation. In comparison, classic small-world networks show a trade-off between vertical and horizontal propagation; increasing the rewiring probability improves the efficiency of horizontal propagation but worsens the efficiency of vertical propagation. Our result provides insights into how the complex functions of natural neural networks may arise from a design that allows them to efficiently transform and combine input signals. PMID:24672472

tf_unet: Generic convolutional neural network U-Net implementation in Tensorflow

NASA Astrophysics Data System (ADS)

Akeret, Joel; Chang, Chihway; Lucchi, Aurelien; Refregier, Alexandre

2016-11-01

tf_unet mitigates radio frequency interference (RFI) signals in radio data using a special type of Convolutional Neural Network, the U-Net, that enables the classification of clean signal and RFI signatures in 2D time-ordered data acquired from a radio telescope. The code is not tied to a specific segmentation and can be used, for example, to detect radio frequency interference (RFI) in radio astronomy or galaxies and stars in widefield imaging data. This U-Net implementation can outperform classical RFI mitigation algorithms.

Application of hierarchical dissociated neural network in closed-loop hybrid system integrating biological and mechanical intelligence.

PubMed

Li, Yongcheng; Sun, Rong; Zhang, Bin; Wang, Yuechao; Li, Hongyi

2015-01-01

Neural networks are considered the origin of intelligence in organisms. In this paper, a new design of an intelligent system merging biological intelligence with artificial intelligence was created. It was based on a neural controller bidirectionally connected to an actual mobile robot to implement a novel vehicle. Two types of experimental preparations were utilized as the neural controller including 'random' and '4Q' (cultured neurons artificially divided into four interconnected parts) neural network. Compared to the random cultures, the '4Q' cultures presented absolutely different activities, and the robot controlled by the '4Q' network presented better capabilities in search tasks. Our results showed that neural cultures could be successfully employed to control an artificial agent; the robot performed better and better with the stimulus because of the short-term plasticity. A new framework is provided to investigate the bidirectional biological-artificial interface and develop new strategies for a future intelligent system using these simplified model systems.

Application of Hierarchical Dissociated Neural Network in Closed-Loop Hybrid System Integrating Biological and Mechanical Intelligence

PubMed Central

Zhang, Bin; Wang, Yuechao; Li, Hongyi

2015-01-01

Neural networks are considered the origin of intelligence in organisms. In this paper, a new design of an intelligent system merging biological intelligence with artificial intelligence was created. It was based on a neural controller bidirectionally connected to an actual mobile robot to implement a novel vehicle. Two types of experimental preparations were utilized as the neural controller including ‘random’ and ‘4Q’ (cultured neurons artificially divided into four interconnected parts) neural network. Compared to the random cultures, the ‘4Q’ cultures presented absolutely different activities, and the robot controlled by the ‘4Q’ network presented better capabilities in search tasks. Our results showed that neural cultures could be successfully employed to control an artificial agent; the robot performed better and better with the stimulus because of the short-term plasticity. A new framework is provided to investigate the bidirectional biological-artificial interface and develop new strategies for a future intelligent system using these simplified model systems. PMID:25992579

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

PubMed Central

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

2015-01-01

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

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

PubMed Central

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

2017-01-01

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

A neural network for the identification of measured helicopter noise

NASA Technical Reports Server (NTRS)

Cabell, R. H.; Fuller, C. R.; O'Brien, W. F.

1991-01-01

The results of a preliminary study of the components of a novel acoustic helicopter identification system are described. The identification system uses the relationship between the amplitudes of the first eight harmonics in the main rotor noise spectrum to distinguish between helicopter types. Two classification algorithms are tested; a statistically optimal Bayes classifier, and a neural network adaptive classifier. The performance of these classifiers is tested using measured noise of three helicopters. The statistical classifier can correctly identify the helicopter an average of 67 percent of the time, while the neural network is correct an average of 65 percent of the time. These results indicate the need for additional study of the envelope of harmonic amplitudes as a component of a helicopter identification system. Issues concerning the implementation of the neural network classifier, such as training time and structure of the network, are discussed.

Vein matching using artificial neural network in vein authentication systems

NASA Astrophysics Data System (ADS)

Noori Hoshyar, Azadeh; Sulaiman, Riza

2011-10-01

Personal identification technology as security systems is developing rapidly. Traditional authentication modes like key; password; card are not safe enough because they could be stolen or easily forgotten. Biometric as developed technology has been applied to a wide range of systems. According to different researchers, vein biometric is a good candidate among other biometric traits such as fingerprint, hand geometry, voice, DNA and etc for authentication systems. Vein authentication systems can be designed by different methodologies. All the methodologies consist of matching stage which is too important for final verification of the system. Neural Network is an effective methodology for matching and recognizing individuals in authentication systems. Therefore, this paper explains and implements the Neural Network methodology for finger vein authentication system. Neural Network is trained in Matlab to match the vein features of authentication system. The Network simulation shows the quality of matching as 95% which is a good performance for authentication system matching.

Anisotropic connectivity implements motion-based prediction in a spiking neural network.

PubMed

Kaplan, Bernhard A; Lansner, Anders; Masson, Guillaume S; Perrinet, Laurent U

2013-01-01

Predictive coding hypothesizes that the brain explicitly infers upcoming sensory input to establish a coherent representation of the world. Although it is becoming generally accepted, it is not clear on which level spiking neural networks may implement predictive coding and what function their connectivity may have. We present a network model of conductance-based integrate-and-fire neurons inspired by the architecture of retinotopic cortical areas that assumes predictive coding is implemented through network connectivity, namely in the connection delays and in selectiveness for the tuning properties of source and target cells. We show that the applied connection pattern leads to motion-based prediction in an experiment tracking a moving dot. In contrast to our proposed model, a network with random or isotropic connectivity fails to predict the path when the moving dot disappears. Furthermore, we show that a simple linear decoding approach is sufficient to transform neuronal spiking activity into a probabilistic estimate for reading out the target trajectory.

Binary Associative Memories as a Benchmark for Spiking Neuromorphic Hardware

PubMed Central

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

2017-01-01

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

Two Unipolar Terminal-Attractor-Based Associative Memories

NASA Technical Reports Server (NTRS)

Liu, Hua-Kuang; Wu, Chwan-Hwa

1995-01-01

Two unipolar mathematical models of electronic neural network functioning as terminal-attractor-based associative memory (TABAM) developed. Models comprise sets of equations describing interactions between time-varying inputs and outputs of neural-network memory, regarded as dynamical system. Simplifies design and operation of optoelectronic processor to implement TABAM performing associative recall of images. TABAM concept described in "Optoelectronic Terminal-Attractor-Based Associative Memory" (NPO-18790). Experimental optoelectronic apparatus that performed associative recall of binary images described in "Optoelectronic Inner-Product Neural Associative Memory" (NPO-18491).

Gait Recognition Based on Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Sokolova, A.; Konushin, A.

2017-05-01

In this work we investigate the problem of people recognition by their gait. For this task, we implement deep learning approach using the optical flow as the main source of motion information and combine neural feature extraction with the additional embedding of descriptors for representation improvement. In order to find the best heuristics, we compare several deep neural network architectures, learning and classification strategies. The experiments were made on two popular datasets for gait recognition, so we investigate their advantages and disadvantages and the transferability of considered methods.

Experiments in Neural-Network Control of a Free-Flying Space Robot

NASA Technical Reports Server (NTRS)

Wilson, Edward

1995-01-01

Four important generic issues are identified and addressed in some depth in this thesis as part of the development of an adaptive neural network based control system for an experimental free flying space robot prototype. The first issue concerns the importance of true system level design of the control system. A new hybrid strategy is developed here, in depth, for the beneficial integration of neural networks into the total control system. A second important issue in neural network control concerns incorporating a priori knowledge into the neural network. In many applications, it is possible to get a reasonably accurate controller using conventional means. If this prior information is used purposefully to provide a starting point for the optimizing capabilities of the neural network, it can provide much faster initial learning. In a step towards addressing this issue, a new generic Fully Connected Architecture (FCA) is developed for use with backpropagation. A third issue is that neural networks are commonly trained using a gradient based optimization method such as backpropagation; but many real world systems have Discrete Valued Functions (DVFs) that do not permit gradient based optimization. One example is the on-off thrusters that are common on spacecraft. A new technique is developed here that now extends backpropagation learning for use with DVFs. The fourth issue is that the speed of adaptation is often a limiting factor in the implementation of a neural network control system. This issue has been strongly resolved in the research by drawing on the above new contributions.

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.

Using neural networks for prediction of air pollution index in industrial city

NASA Astrophysics Data System (ADS)

Rahman, P. A.; Panchenko, A. A.; Safarov, A. M.

2017-10-01

This scientific paper is dedicated to the use of artificial neural networks for the ecological prediction of state of the atmospheric air of an industrial city for capability of the operative environmental decisions. In the paper, there is also the described development of two types of prediction models for determining of the air pollution index on the basis of neural networks: a temporal (short-term forecast of the pollutants content in the air for the nearest days) and a spatial (forecast of atmospheric pollution index in any point of city). The stages of development of the neural network models are briefly overviewed and description of their parameters is also given. The assessment of the adequacy of the prediction models, based on the calculation of the correlation coefficient between the output and reference data, is also provided. Moreover, due to the complexity of perception of the «neural network code» of the offered models by the ordinary users, the software implementations allowing practical usage of neural network models are also offered. It is established that the obtained neural network models provide sufficient reliable forecast, which means that they are an effective tool for analyzing and predicting the behavior of dynamics of the air pollution in an industrial city. Thus, this scientific work successfully develops the urgent matter of forecasting of the atmospheric air pollution index in industrial cities based on the use of neural network models.

CLIPS on the NeXT computer

NASA Technical Reports Server (NTRS)

Charnock, Elizabeth; Eng, Norman

1990-01-01

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

Adaptive enhanced sampling by force-biasing using neural networks

NASA Astrophysics Data System (ADS)

Guo, Ashley Z.; Sevgen, Emre; Sidky, Hythem; Whitmer, Jonathan K.; Hubbell, Jeffrey A.; de Pablo, Juan J.

2018-04-01

A machine learning assisted method is presented for molecular simulation of systems with rugged free energy landscapes. The method is general and can be combined with other advanced sampling techniques. In the particular implementation proposed here, it is illustrated in the context of an adaptive biasing force approach where, rather than relying on discrete force estimates, one can resort to a self-regularizing artificial neural network to generate continuous, estimated generalized forces. By doing so, the proposed approach addresses several shortcomings common to adaptive biasing force and other algorithms. Specifically, the neural network enables (1) smooth estimates of generalized forces in sparsely sampled regions, (2) force estimates in previously unexplored regions, and (3) continuous force estimates with which to bias the simulation, as opposed to biases generated at specific points of a discrete grid. The usefulness of the method is illustrated with three different examples, chosen to highlight the wide range of applicability of the underlying concepts. In all three cases, the new method is found to enhance considerably the underlying traditional adaptive biasing force approach. The method is also found to provide improvements over previous implementations of neural network assisted algorithms.

Artificial neural networks as a useful tool to predict the risk level of Betula pollen in the air

NASA Astrophysics Data System (ADS)

Castellano-Méndez, M.; Aira, M. J.; Iglesias, I.; Jato, V.; González-Manteiga, W.

2005-05-01

An increasing percentage of the European population suffers from allergies to pollen. The study of the evolution of air pollen concentration supplies prior knowledge of the levels of pollen in the air, which can be useful for the prevention and treatment of allergic symptoms, and the management of medical resources. The symptoms of Betula pollinosis can be associated with certain levels of pollen in the air. The aim of this study was to predict the risk of the concentration of pollen exceeding a given level, using previous pollen and meteorological information, by applying neural network techniques. Neural networks are a widespread statistical tool useful for the study of problems associated with complex or poorly understood phenomena. The binary response variable associated with each level requires a careful selection of the neural network and the error function associated with the learning algorithm used during the training phase. The performance of the neural network with the validation set showed that the risk of the pollen level exceeding a certain threshold can be successfully forecasted using artificial neural networks. This prediction tool may be implemented to create an automatic system that forecasts the risk of suffering allergic symptoms.

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

NASA Astrophysics Data System (ADS)

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

2017-11-01

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

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

NASA Technical Reports Server (NTRS)

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

1990-01-01

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

Artificial neural networks for control of a grid-connected rectifier/inverter under disturbance, dynamic and power converter switching conditions.

PubMed

Li, Shuhui; Fairbank, Michael; Johnson, Cameron; Wunsch, Donald C; Alonso, Eduardo; Proaño, Julio L

2014-04-01

Three-phase grid-connected converters are widely used in renewable and electric power system applications. Traditionally, grid-connected converters are controlled with standard decoupled d-q vector control mechanisms. However, recent studies indicate that such mechanisms show limitations in their applicability to dynamic systems. This paper investigates how to mitigate such restrictions using a neural network to control a grid-connected rectifier/inverter. The neural network implements a dynamic programming algorithm and is trained by using back-propagation through time. To enhance performance and stability under disturbance, additional strategies are adopted, including the use of integrals of error signals to the network inputs and the introduction of grid disturbance voltage to the outputs of a well-trained network. The performance of the neural-network controller is studied under typical vector control conditions and compared against conventional vector control methods, which demonstrates that the neural vector control strategy proposed in this paper is effective. Even in dynamic and power converter switching environments, the neural vector controller shows strong ability to trace rapidly changing reference commands, tolerate system disturbances, and satisfy control requirements for a faulted power system.

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.

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

SpikingLab: modelling agents controlled by Spiking Neural Networks in Netlogo.

PubMed

Jimenez-Romero, Cristian; Johnson, Jeffrey

2017-01-01

The scientific interest attracted by Spiking Neural Networks (SNN) has lead to the development of tools for the simulation and study of neuronal dynamics ranging from phenomenological models to the more sophisticated and biologically accurate Hodgkin-and-Huxley-based and multi-compartmental models. However, despite the multiple features offered by neural modelling tools, their integration with environments for the simulation of robots and agents can be challenging and time consuming. The implementation of artificial neural circuits to control robots generally involves the following tasks: (1) understanding the simulation tools, (2) creating the neural circuit in the neural simulator, (3) linking the simulated neural circuit with the environment of the agent and (4) programming the appropriate interface in the robot or agent to use the neural controller. The accomplishment of the above-mentioned tasks can be challenging, especially for undergraduate students or novice researchers. This paper presents an alternative tool which facilitates the simulation of simple SNN circuits using the multi-agent simulation and the programming environment Netlogo (educational software that simplifies the study and experimentation of complex systems). The engine proposed and implemented in Netlogo for the simulation of a functional model of SNN is a simplification of integrate and fire (I&F) models. The characteristics of the engine (including neuronal dynamics, STDP learning and synaptic delay) are demonstrated through the implementation of an agent representing an artificial insect controlled by a simple neural circuit. The setup of the experiment and its outcomes are described in this work.

Analysis and Modeling of DIII-D Experiments With OMFIT and Neural Networks

NASA Astrophysics Data System (ADS)

Meneghini, O.; Luna, C.; Smith, S. P.; Lao, L. L.; GA Theory Team

2013-10-01

The OMFIT integrated modeling framework is designed to facilitate experimental data analysis and enable integrated simulations. This talk introduces this framework and presents a selection of its applications to the DIII-D experiment. Examples include kinetic equilibrium reconstruction analysis; evaluation of MHD stability in the core and in the edge; and self-consistent predictive steady-state transport modeling. The OMFIT framework also provides the platform for an innovative approach based on neural networks to predict electron and ion energy fluxes. In our study a multi-layer feed-forward back-propagation neural network is built and trained over a database of DIII-D data. It is found that given the same parameters that the highest fidelity models use, the neural network model is able to predict to a large degree the heat transport profiles observed in the DIII-D experiments. Once the network is built, the numerical cost of evaluating the transport coefficients is virtually nonexistent, thus making the neural network model particularly well suited for plasma control and quick exploration of operational scenarios. The implementation of the neural network model and benchmark with experimental results and gyro-kinetic models will be discussed. Work supported in part by the US DOE under DE-FG02-95ER54309.

A neuromorphic network for generic multivariate data classification

PubMed Central

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

2014-01-01

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

An intelligent control system for failure detection and controller reconfiguration

NASA Technical Reports Server (NTRS)

Biswas, Saroj K.

1994-01-01

We present an architecture of an intelligent restructurable control system to automatically detect failure of system components, assess its impact on system performance and safety, and reconfigure the controller for performance recovery. Fault detection is based on neural network associative memories and pattern classifiers, and is implemented using a multilayer feedforward network. Details of the fault detection network along with simulation results on health monitoring of a dc motor have been presented. Conceptual developments for fault assessment using an expert system and controller reconfiguration using a neural network are outlined.

Electronic implementation of associative memory based on neural network models

NASA Technical Reports Server (NTRS)

Moopenn, A.; Lambe, John; Thakoor, A. P.

1987-01-01

An electronic embodiment of a neural network based associative memory in the form of a binary connection matrix is described. The nature of false memory errors, their effect on the information storage capacity of binary connection matrix memories, and a novel technique to eliminate such errors with the help of asymmetrical extra connections are discussed. The stability of the matrix memory system incorporating a unique local inhibition scheme is analyzed in terms of local minimization of an energy function. The memory's stability, dynamic behavior, and recall capability are investigated using a 32-'neuron' electronic neural network memory with a 1024-programmable binary connection matrix.

Multilingual vocal emotion recognition and classification using back propagation neural network

NASA Astrophysics Data System (ADS)

Kayal, Apoorva J.; Nirmal, Jagannath

2016-03-01

This work implements classification of different emotions in different languages using Artificial Neural Networks (ANN). Mel Frequency Cepstral Coefficients (MFCC) and Short Term Energy (STE) have been considered for creation of feature set. An emotional speech corpus consisting of 30 acted utterances per emotion has been developed. The emotions portrayed in this work are Anger, Joy and Neutral in each of English, Marathi and Hindi languages. Different configurations of Artificial Neural Networks have been employed for classification purposes. The performance of the classifiers has been evaluated by False Negative Rate (FNR), False Positive Rate (FPR), True Positive Rate (TPR) and True Negative Rate (TNR).

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.

Conic section function neural network circuitry for offline signature recognition.

PubMed

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

2010-04-01

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

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

NASA Astrophysics Data System (ADS)

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

2017-12-01

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

The probabilistic neural network architecture for high speed classification of remotely sensed imagery

NASA Technical Reports Server (NTRS)

Chettri, Samir R.; Cromp, Robert F.

1993-01-01

In this paper we discuss a neural network architecture (the Probabilistic Neural Net or the PNN) that, to the best of our knowledge, has not previously been applied to remotely sensed data. The PNN is a supervised non-parametric classification algorithm as opposed to the Gaussian maximum likelihood classifier (GMLC). The PNN works by fitting a Gaussian kernel to each training point. The width of the Gaussian is controlled by a tuning parameter called the window width. If very small widths are used, the method is equivalent to the nearest neighbor method. For large windows, the PNN behaves like the GMLC. The basic implementation of the PNN requires no training time at all. In this respect it is far better than the commonly used backpropagation neural network which can be shown to take O(N6) time for training where N is the dimensionality of the input vector. In addition the PNN can be implemented in a feed forward mode in hardware. The disadvantage of the PNN is that it requires all the training data to be stored. Some solutions to this problem are discussed in the paper. Finally, we discuss the accuracy of the PNN with respect to the GMLC and the backpropagation neural network (BPNN). The PNN is shown to be better than GMLC and not as good as the BPNN with regards to classification accuracy.

A space-time neural network

NASA Technical Reports Server (NTRS)

Villarreal, James A.; Shelton, Robert O.

1991-01-01

Introduced here is a novel technique which adds the dimension of time to the well known back propagation neural network algorithm. Cited here are several reasons why the inclusion of automated spatial and temporal associations are crucial to effective systems modeling. An overview of other works which also model spatiotemporal dynamics is furnished. A detailed description is given of the processes necessary to implement the space-time network algorithm. Several demonstrations that illustrate the capabilities and performance of this new architecture are given.

Neural network technologies

NASA Technical Reports Server (NTRS)

Villarreal, James A.

1991-01-01

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

Genetic learning in rule-based and neural systems

NASA Technical Reports Server (NTRS)

Smith, Robert E.

1993-01-01

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

Compact holographic optical neural network system for real-time pattern recognition

NASA Astrophysics Data System (ADS)

Lu, Taiwei; Mintzer, David T.; Kostrzewski, Andrew A.; Lin, Freddie S.

1996-08-01

One of the important characteristics of artificial neural networks is their capability for massive interconnection and parallel processing. Recently, specialized electronic neural network processors and VLSI neural chips have been introduced in the commercial market. The number of parallel channels they can handle is limited because of the limited parallel interconnections that can be implemented with 1D electronic wires. High-resolution pattern recognition problems can require a large number of neurons for parallel processing of an image. This paper describes a holographic optical neural network (HONN) that is based on high- resolution volume holographic materials and is capable of performing massive 3D parallel interconnection of tens of thousands of neurons. A HONN with more than 16,000 neurons packaged in an attache case has been developed. Rotation- shift-scale-invariant pattern recognition operations have been demonstrated with this system. System parameters such as the signal-to-noise ratio, dynamic range, and processing speed are discussed.

Hopf bifurcation of an (n + 1) -neuron bidirectional associative memory neural network model with delays.

PubMed

Xiao, Min; Zheng, Wei Xing; Cao, Jinde

2013-01-01

Recent studies on Hopf bifurcations of neural networks with delays are confined to simplified neural network models consisting of only two, three, four, five, or six neurons. It is well known that neural networks are complex and large-scale nonlinear dynamical systems, so the dynamics of the delayed neural networks are very rich and complicated. Although discussing the dynamics of networks with a few neurons may help us to understand large-scale networks, there are inevitably some complicated problems that may be overlooked if simplified networks are carried over to large-scale networks. In this paper, a general delayed bidirectional associative memory neural network model with n + 1 neurons is considered. By analyzing the associated characteristic equation, the local stability of the trivial steady state is examined, and then the existence of the Hopf bifurcation at the trivial steady state is established. By applying the normal form theory and the center manifold reduction, explicit formulae are derived to determine the direction and stability of the bifurcating periodic solution. Furthermore, the paper highlights situations where the Hopf bifurcations are particularly critical, in the sense that the amplitude and the period of oscillations are very sensitive to errors due to tolerances in the implementation of neuron interconnections. It is shown that the sensitivity is crucially dependent on the delay and also significantly influenced by the feature of the number of neurons. Numerical simulations are carried out to illustrate the main results.

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.

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

NASA Astrophysics Data System (ADS)

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

2017-12-01

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

The graph neural network model.

PubMed

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

2009-01-01

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

(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.

Noise reduction and image enhancement using a hardware implementation of artificial neural networks

NASA Astrophysics Data System (ADS)

David, Robert; Williams, Erin; de Tremiolles, Ghislain; Tannhof, Pascal

1999-03-01

In this paper, we present a neural based solution developed for noise reduction and image enhancement using the ZISC, an IBM hardware processor which implements the Restricted Coulomb Energy algorithm and the K-Nearest Neighbor algorithm. Artificial neural networks present the advantages of processing time reduction in comparison with classical models, adaptability, and the weighted property of pattern learning. The goal of the developed application is image enhancement in order to restore old movies (noise reduction, focus correction, etc.), to improve digital television images, or to treat images which require adaptive processing (medical images, spatial images, special effects, etc.). Image results show a quantitative improvement over the noisy image as well as the efficiency of this system. Further enhancements are being examined to improve the output of the system.

An artificial neural network model for periodic trajectory generation

NASA Astrophysics Data System (ADS)

Shankar, S.; Gander, R. E.; Wood, H. C.

A neural network model based on biological systems was developed for potential robotic application. The model consists of three interconnected layers of artificial neurons or units: an input layer subdivided into state and plan units, an output layer, and a hidden layer between the two outer layers which serves to implement nonlinear mappings between the input and output activation vectors. Weighted connections are created between the three layers, and learning is effected by modifying these weights. Feedback connections between the output and the input state serve to make the network operate as a finite state machine. The activation vector of the plan units of the input layer emulates the supraspinal commands in biological central pattern generators in that different plan activation vectors correspond to different sequences or trajectories being recalled, even with different frequencies. Three trajectories were chosen for implementation, and learning was accomplished in 10,000 trials. The fault tolerant behavior, adaptiveness, and phase maintenance of the implemented network are discussed.

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment.

PubMed

Li, Yongcheng; Sun, Rong; Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

2016-01-01

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot's performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks.

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment

PubMed Central

Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

2016-01-01

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot’s performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks. PMID:27806074

Potential implementation of reservoir computing models based on magnetic skyrmions

NASA Astrophysics Data System (ADS)

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

2018-05-01

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

NEVESIM: event-driven neural simulation framework with a Python interface.

PubMed

Pecevski, Dejan; Kappel, David; Jonke, Zeno

2014-01-01

NEVESIM is a software package for event-driven simulation of networks of spiking neurons with a fast simulation core in C++, and a scripting user interface in the Python programming language. It supports simulation of heterogeneous networks with different types of neurons and synapses, and can be easily extended by the user with new neuron and synapse types. To enable heterogeneous networks and extensibility, NEVESIM is designed to decouple the simulation logic of communicating events (spikes) between the neurons at a network level from the implementation of the internal dynamics of individual neurons. In this paper we will present the simulation framework of NEVESIM, its concepts and features, as well as some aspects of the object-oriented design approaches and simulation strategies that were utilized to efficiently implement the concepts and functionalities of the framework. We will also give an overview of the Python user interface, its basic commands and constructs, and also discuss the benefits of integrating NEVESIM with Python. One of the valuable capabilities of the simulator is to simulate exactly and efficiently networks of stochastic spiking neurons from the recently developed theoretical framework of neural sampling. This functionality was implemented as an extension on top of the basic NEVESIM framework. Altogether, the intended purpose of the NEVESIM framework is to provide a basis for further extensions that support simulation of various neural network models incorporating different neuron and synapse types that can potentially also use different simulation strategies.

NEVESIM: event-driven neural simulation framework with a Python interface

PubMed Central

Pecevski, Dejan; Kappel, David; Jonke, Zeno

2014-01-01

NEVESIM is a software package for event-driven simulation of networks of spiking neurons with a fast simulation core in C++, and a scripting user interface in the Python programming language. It supports simulation of heterogeneous networks with different types of neurons and synapses, and can be easily extended by the user with new neuron and synapse types. To enable heterogeneous networks and extensibility, NEVESIM is designed to decouple the simulation logic of communicating events (spikes) between the neurons at a network level from the implementation of the internal dynamics of individual neurons. In this paper we will present the simulation framework of NEVESIM, its concepts and features, as well as some aspects of the object-oriented design approaches and simulation strategies that were utilized to efficiently implement the concepts and functionalities of the framework. We will also give an overview of the Python user interface, its basic commands and constructs, and also discuss the benefits of integrating NEVESIM with Python. One of the valuable capabilities of the simulator is to simulate exactly and efficiently networks of stochastic spiking neurons from the recently developed theoretical framework of neural sampling. This functionality was implemented as an extension on top of the basic NEVESIM framework. Altogether, the intended purpose of the NEVESIM framework is to provide a basis for further extensions that support simulation of various neural network models incorporating different neuron and synapse types that can potentially also use different simulation strategies. PMID:25177291

Fast Neural Solution Of A Nonlinear Wave Equation

NASA Technical Reports Server (NTRS)

Barhen, Jacob; Toomarian, Nikzad

1996-01-01

Neural algorithm for simulation of class of nonlinear wave phenomena devised. Numerically solves special one-dimensional case of Korteweg-deVries equation. Intended to be executed rapidly by neural network implemented as charge-coupled-device/charge-injection device, very-large-scale integrated-circuit analog data processor of type described in "CCD/CID Processors Would Offer Greater Precision" (NPO-18972).

Resonator memories and optical novelty filters

NASA Astrophysics Data System (ADS)

Anderson, Dana Z.; Erle, Marie C.

Optical resonators having holographic elements are potential candidates for storing information that can be accessed through content addressable or associative recall. Closely related to the resonator memory is the optical novelty filter, which can detect the differences between a test object and a set of reference objects. We discuss implementations of these devices using continuous optical media such as photorefractive materials. The discussion is framed in the context of neural network models. There are both formal and qualitative similarities between the resonator memory and optical novelty filter and network models. Mode competition arises in the theory of the resonator memory, much as it does in some network models. We show that the role of the phenomena of "daydreaming" in the real-time programmable optical resonator is very much akin to the role of "unlearning" in neural network memories. The theory of programming the real-time memory for a single mode is given in detail. This leads to a discussion of the optical novelty filter. Experimental results for the resonator memory, the real-time programmable memory, and the optical tracking novelty filter are reviewed. We also point to several issues that need to be addressed in order to implement more formal models of neural networks.

Resonator Memories And Optical Novelty Filters

NASA Astrophysics Data System (ADS)

Anderson, Dana Z.; Erie, Marie C.

1987-05-01

Optical resonators having holographic elements are potential candidates for storing information that can be accessed through content-addressable or associative recall. Closely related to the resonator memory is the optical novelty filter, which can detect the differences between a test object and a set of reference objects. We discuss implementations of these devices using continuous optical media such as photorefractive ma-terials. The discussion is framed in the context of neural network models. There are both formal and qualitative similarities between the resonator memory and optical novelty filter and network models. Mode competition arises in the theory of the resonator memory, much as it does in some network models. We show that the role of the phenomena of "daydream-ing" in the real-time programmable optical resonator is very much akin to the role of "unlearning" in neural network memories. The theory of programming the real-time memory for a single mode is given in detail. This leads to a discussion of the optical novelty filter. Experimental results for the resonator memory, the real-time programmable memory, and the optical tracking novelty filter are reviewed. We also point to several issues that need to be addressed in order to implement more formal models of neural networks.

The application of neural networks to myoelectric signal analysis: a preliminary study.

PubMed

Kelly, M F; Parker, P A; Scott, R N

1990-03-01

Two neural network implementations are applied to myoelectric signal (MES) analysis tasks. The motivation behind this research is to explore more reliable methods of deriving control for multidegree of freedom arm prostheses. A discrete Hopfield network is used to calculate the time series parameters for a moving average MES model. It is demonstrated that the Hopfield network is capable of generating the same time series parameters as those produced by the conventional sequential least squares (SLS) algorithm. Furthermore, it can be extended to applications utilizing larger amounts of data, and possibly to higher order time series models, without significant degradation in computational efficiency. The second neural network implementation involves using a two-layer perceptron for classifying a single site MES based on two features, specifically the first time series parameter, and the signal power. Using these features, the perceptron is trained to distinguish between four separate arm functions. The two-dimensional decision boundaries used by the perceptron classifier are delineated. It is also demonstrated that the perceptron is able to rapidly compensate for variations when new data are incorporated into the training set. This adaptive quality suggests that perceptrons may provide a useful tool for future MES analysis.

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.

Driving profile modeling and recognition based on soft computing approach.

PubMed

Wahab, Abdul; Quek, Chai; Tan, Chin Keong; Takeda, Kazuya

2009-04-01

Advancements in biometrics-based authentication have led to its increasing prominence and are being incorporated into everyday tasks. Existing vehicle security systems rely only on alarms or smart card as forms of protection. A biometric driver recognition system utilizing driving behaviors is a highly novel and personalized approach and could be incorporated into existing vehicle security system to form a multimodal identification system and offer a greater degree of multilevel protection. In this paper, detailed studies have been conducted to model individual driving behavior in order to identify features that may be efficiently and effectively used to profile each driver. Feature extraction techniques based on Gaussian mixture models (GMMs) are proposed and implemented. Features extracted from the accelerator and brake pedal pressure were then used as inputs to a fuzzy neural network (FNN) system to ascertain the identity of the driver. Two fuzzy neural networks, namely, the evolving fuzzy neural network (EFuNN) and the adaptive network-based fuzzy inference system (ANFIS), are used to demonstrate the viability of the two proposed feature extraction techniques. The performances were compared against an artificial neural network (NN) implementation using the multilayer perceptron (MLP) network and a statistical method based on the GMM. Extensive testing was conducted and the results show great potential in the use of the FNN for real-time driver identification and verification. In addition, the profiling of driver behaviors has numerous other potential applications for use by law enforcement and companies dealing with buses and truck drivers.

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.

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

PubMed Central

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

2012-01-01

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

Bankruptcy prediction based on financial ratios using Jordan Recurrent Neural Networks: a case study in Polish companies

NASA Astrophysics Data System (ADS)

Hardinata, Lingga; Warsito, Budi; Suparti

2018-05-01

Complexity of bankruptcy causes the accurate models of bankruptcy prediction difficult to be achieved. Various prediction models have been developed to improve the accuracy of bankruptcy predictions. Machine learning has been widely used to predict because of its adaptive capabilities. Artificial Neural Networks (ANN) is one of machine learning which proved able to complete inference tasks such as prediction and classification especially in data mining. In this paper, we propose the implementation of Jordan Recurrent Neural Networks (JRNN) to classify and predict corporate bankruptcy based on financial ratios. Feedback interconnection in JRNN enable to make the network keep important information well allowing the network to work more effectively. The result analysis showed that JRNN works very well in bankruptcy prediction with average success rate of 81.3785%.

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

PubMed

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

2012-01-01

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

From neural-based object recognition toward microelectronic eyes

NASA Technical Reports Server (NTRS)

Sheu, Bing J.; Bang, Sa Hyun

1994-01-01

Engineering neural network systems are best known for their abilities to adapt to the changing characteristics of the surrounding environment by adjusting system parameter values during the learning process. Rapid advances in analog current-mode design techniques have made possible the implementation of major neural network functions in custom VLSI chips. An electrically programmable analog synapse cell with large dynamic range can be realized in a compact silicon area. New designs of the synapse cells, neurons, and analog processor are presented. A synapse cell based on Gilbert multiplier structure can perform the linear multiplication for back-propagation networks. A double differential-pair synapse cell can perform the Gaussian function for radial-basis network. The synapse cells can be biased in the strong inversion region for high-speed operation or biased in the subthreshold region for low-power operation. The voltage gain of the sigmoid-function neurons is externally adjustable which greatly facilitates the search of optimal solutions in certain networks. Various building blocks can be intelligently connected to form useful industrial applications. Efficient data communication is a key system-level design issue for large-scale networks. We also present analog neural processors based on perceptron architecture and Hopfield network for communication applications. Biologically inspired neural networks have played an important role towards the creation of powerful intelligent machines. Accuracy, limitations, and prospects of analog current-mode design of the biologically inspired vision processing chips and cellular neural network chips are key design issues.

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.

Verification and Validation of Adaptive and Intelligent Systems with Flight Test Results

NASA Technical Reports Server (NTRS)

Burken, John J.; Larson, Richard R.

2009-01-01

F-15 IFCS project goals are: a) Demonstrate Control Approaches that can Efficiently Optimize Aircraft Performance in both Normal and Failure Conditions [A] & [B] failures. b) Advance Neural Network-Based Flight Control Technology for New Aerospace Systems Designs with a Pilot in the Loop. Gen II objectives include; a) Implement and Fly a Direct Adaptive Neural Network Based Flight Controller; b) Demonstrate the Ability of the System to Adapt to Simulated System Failures: 1) Suppress Transients Associated with Failure; 2) Re-Establish Sufficient Control and Handling of Vehicle for Safe Recovery. c) Provide Flight Experience for Development of Verification and Validation Processes for Flight Critical Neural Network Software.

Soft sensor based composition estimation and controller design for an ideal reactive distillation column.

PubMed

Vijaya Raghavan, S R; Radhakrishnan, T K; Srinivasan, K

2011-01-01

In this research work, the authors have presented the design and implementation of a recurrent neural network (RNN) based inferential state estimation scheme for an ideal reactive distillation column. Decentralized PI controllers are designed and implemented. The reactive distillation process is controlled by controlling the composition which has been estimated from the available temperature measurements using a type of RNN called Time Delayed Neural Network (TDNN). The performance of the RNN based state estimation scheme under both open loop and closed loop have been compared with a standard Extended Kalman filter (EKF) and a Feed forward Neural Network (FNN). The online training/correction has been done for both RNN and FNN schemes for every ten minutes whenever new un-trained measurements are available from a conventional composition analyzer. The performance of RNN shows better state estimation capability as compared to other state estimation schemes in terms of qualitative and quantitative performance indices. Copyright © 2010 ISA. Published by Elsevier Ltd. All rights reserved.

Synchronization of heteroclinic circuits through learning in coupled neural networks

NASA Astrophysics Data System (ADS)

Selskii, Anton; Makarov, Valeri A.

2016-01-01

The synchronization of oscillatory activity in neural networks is usually implemented by coupling the state variables describing neuronal dynamics. Here we study another, but complementary mechanism based on a learning process with memory. A driver network, acting as a teacher, exhibits winner-less competition (WLC) dynamics, while a driven network, a learner, tunes its internal couplings according to the oscillations observed in the teacher. We show that under appropriate training the learner can "copy" the coupling structure and thus synchronize oscillations with the teacher. The replication of the WLC dynamics occurs for intermediate memory lengths only, consequently, the learner network exhibits a phenomenon of learning resonance.

Effects of measurement unobservability on neural extended Kalman filter tracking

NASA Astrophysics Data System (ADS)

Stubberud, Stephen C.; Kramer, Kathleen A.

2009-05-01

An important component of tracking fusion systems is the ability to fuse various sensors into a coherent picture of the scene. When multiple sensor systems are being used in an operational setting, the types of data vary. A significant but often overlooked concern of multiple sensors is the incorporation of measurements that are unobservable. An unobservable measurement is one that may provide information about the state, but cannot recreate a full target state. A line of bearing measurement, for example, cannot provide complete position information. Often, such measurements come from passive sensors such as a passive sonar array or an electronic surveillance measure (ESM) system. Unobservable measurements will, over time, result in the measurement uncertainty to grow without bound. While some tracking implementations have triggers to protect against the detrimental effects, many maneuver tracking algorithms avoid discussing this implementation issue. One maneuver tracking technique is the neural extended Kalman filter (NEKF). The NEKF is an adaptive estimation algorithm that estimates the target track as it trains a neural network on line to reduce the error between the a priori target motion model and the actual target dynamics. The weights of neural network are trained in a similar method to the state estimation/parameter estimation Kalman filter techniques. The NEKF has been shown to improve target tracking accuracy through maneuvers and has been use to predict target behavior using the new model that consists of the a priori model and the neural network. The key to the on-line adaptation of the NEKF is the fact that the neural network is trained using the same residuals as the Kalman filter for the tracker. The neural network weights are treated as augmented states to the target track. Through the state-coupling function, the weights are coupled to the target states. Thus, if the measurements cause the states of the target track to be unobservable, then the weights of the neural network have unobservable modes as well. In recent analysis, the NEKF was shown to have a significantly larger growth in the eigenvalues of the error covariance matrix than the standard EKF tracker when the measurements were purely bearings-only. This caused detrimental effects to the ability of the NEKF to model the target dynamics. In this work, the analysis is expanded to determine the detrimental effects of bearings-only measurements of various uncertainties on the performance of the NEKF when these unobservable measurements are interlaced with completely observable measurements. This analysis provides the ability to put implementation limitations on the NEKF when bearings-only sensors are present.

A model for integrating elementary neural functions into delayed-response behavior.

PubMed

Gisiger, Thomas; Kerszberg, Michel

2006-04-01

It is well established that various cortical regions can implement a wide array of neural processes, yet the mechanisms which integrate these processes into behavior-producing, brain-scale activity remain elusive. We propose that an important role in this respect might be played by executive structures controlling the traffic of information between the cortical regions involved. To illustrate this hypothesis, we present a neural network model comprising a set of interconnected structures harboring stimulus-related activity (visual representation, working memory, and planning), and a group of executive units with task-related activity patterns that manage the information flowing between them. The resulting dynamics allows the network to perform the dual task of either retaining an image during a delay (delayed-matching to sample task), or recalling from this image another one that has been associated with it during training (delayed-pair association task). The model reproduces behavioral and electrophysiological data gathered on the inferior temporal and prefrontal cortices of primates performing these same tasks. It also makes predictions on how neural activity coding for the recall of the image associated with the sample emerges and becomes prospective during the training phase. The network dynamics proves to be very stable against perturbations, and it exhibits signs of scale-invariant organization and cooperativity. The present network represents a possible neural implementation for active, top-down, prospective memory retrieval in primates. The model suggests that brain activity leading to performance of cognitive tasks might be organized in modular fashion, simple neural functions becoming integrated into more complex behavior by executive structures harbored in prefrontal cortex and/or basal ganglia.

Hardware Prototyping of Neural Network based Fetal Electrocardiogram Extraction

NASA Astrophysics Data System (ADS)

Hasan, M. A.; Reaz, M. B. I.

2012-01-01

The aim of this paper is to model the algorithm for Fetal ECG (FECG) extraction from composite abdominal ECG (AECG) using VHDL (Very High Speed Integrated Circuit Hardware Description Language) for FPGA (Field Programmable Gate Array) implementation. Artificial Neural Network that provides efficient and effective ways of separating FECG signal from composite AECG signal has been designed. The proposed method gives an accuracy of 93.7% for R-peak detection in FHR monitoring. The designed VHDL model is synthesized and fitted into Altera's Stratix II EP2S15F484C3 using the Quartus II version 8.0 Web Edition for FPGA implementation.

Implementation study of an analog spiking neural network for assisting cardiac delay prediction in a cardiac resynchronization therapy device.

PubMed

Sun, Qing; Schwartz, François; Michel, Jacques; Herve, Yannick; Dalmolin, Renzo

2011-06-01

In this paper, we aim at developing an analog spiking neural network (SNN) for reinforcing the performance of conventional cardiac resynchronization therapy (CRT) devices (also called biventricular pacemakers). Targeting an alternative analog solution in 0.13- μm CMOS technology, this paper proposes an approach to improve cardiac delay predictions in every cardiac period in order to assist the CRT device to provide real-time optimal heartbeats. The primary analog SNN architecture is proposed and its implementation is studied to fulfill the requirement of very low energy consumption. By using the Hebbian learning and reinforcement learning algorithms, the intended adaptive CRT device works with different functional modes. The simulations of both learning algorithms have been carried out, and they were shown to demonstrate the global functionalities. To improve the realism of the system, we introduce various heart behavior models (with constant/variable heart rates) that allow pathologic simulations with/without noise on the signals of the input sensors. The simulations of the global system (pacemaker models coupled with heart models) have been investigated and used to validate the analog spiking neural network implementation.

Neural Computations in a Dynamical System with Multiple Time Scales.

PubMed

Mi, Yuanyuan; Lin, Xiaohan; Wu, Si

2016-01-01

Neural systems display rich short-term dynamics at various levels, e.g., spike-frequency adaptation (SFA) at the single-neuron level, and short-term facilitation (STF) and depression (STD) at the synapse level. These dynamical features typically cover a broad range of time scales and exhibit large diversity in different brain regions. It remains unclear what is the computational benefit for the brain to have such variability in short-term dynamics. In this study, we propose that the brain can exploit such dynamical features to implement multiple seemingly contradictory computations in a single neural circuit. To demonstrate this idea, we use continuous attractor neural network (CANN) as a working model and include STF, SFA and STD with increasing time constants in its dynamics. Three computational tasks are considered, which are persistent activity, adaptation, and anticipative tracking. These tasks require conflicting neural mechanisms, and hence cannot be implemented by a single dynamical feature or any combination with similar time constants. However, with properly coordinated STF, SFA and STD, we show that the network is able to implement the three computational tasks concurrently. We hope this study will shed light on the understanding of how the brain orchestrates its rich dynamics at various levels to realize diverse cognitive functions.

An overview on development of neural network technology

NASA Technical Reports Server (NTRS)

Lin, Chun-Shin

1993-01-01

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

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.

Neural network fusion capabilities for efficient implementation of tracking algorithms

NASA Astrophysics Data System (ADS)

Sundareshan, Malur K.; Amoozegar, Farid

1997-03-01

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

Improving subjective pattern recognition in chemical senses through reduction of nonlinear effects in evaluation of sparse data

NASA Astrophysics Data System (ADS)

Assadi, Amir H.; Rasouli, Firooz; Wrenn, Susan E.; Subbiah, M.

2002-11-01

Artificial neural network models are typically useful in pattern recognition and extraction of important features in large data sets. These models are implemented in a wide variety of contexts and with diverse type of input-output data. The underlying mathematics of supervised training of neural networks is ultimately tied to the ability to approximate the nonlinearities that are inherent in network"s generalization ability. The quality and availability of sufficient data points for training and validation play a key role in the generalization ability of the network. A potential domain of applications of neural networks is in analysis of subjective data, such as in consumer science, affective neuroscience and perception of chemical senses. In applications of ANN to subjective data, it is common to rely on knowledge of the science and context for data acquisition, for instance as a priori probabilities in the Bayesian framework. In this paper, we discuss the circumstances that create challenges for success of neural network models for subjective data analysis, such as sparseness of data and cost of acquisition of additional samples. In particular, in the case of affect and perception of chemical senses, we suggest that inherent ambiguity of subjective responses could be offset by a combination of human-machine expert. We propose a method of pre- and post-processing for blind analysis of data that that relies on heuristics from human performance in interpretation of data. In particular, we offer an information-theoretic smoothing (ITS) algorithm that optimizes that geometric visualization of multi-dimensional data and improves human interpretation of the input-output view of neural network implementations. The pre- and post-processing algorithms and ITS are unsupervised. Finally, we discuss the details of an example of blind data analysis from actual taste-smell subjective data, and demonstrate the usefulness of PCA in reduction of dimensionality, as well as ITS.

Analysis of Acoustic Depth Sounder Signals with Artificial Neural Networks

DTIC Science & Technology

1991-04-01

battery pack, processor, and mode switches and (2) a stainless steel shaft 1 meter long and 27 millimeters in diameter, containing 8 milliCurie of...returned signal which is not used in conventional depth sounders due to lack of real-time tools for interpreting the 36 information. The shape and...develop some software tools for conducting the research. Commercial programs for neural network implementation were available, but were "black box" in

Radio frequency interference mitigation using deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Akeret, J.; Chang, C.; Lucchi, A.; Refregier, A.

2017-01-01

We propose a novel approach for mitigating radio frequency interference (RFI) signals in radio data using the latest advances in deep learning. We employ a special type of Convolutional Neural Network, the U-Net, that enables the classification of clean signal and RFI signatures in 2D time-ordered data acquired from a radio telescope. We train and assess the performance of this network using the HIDE &SEEK radio data simulation and processing packages, as well as early Science Verification data acquired with the 7m single-dish telescope at the Bleien Observatory. We find that our U-Net implementation is showing competitive accuracy to classical RFI mitigation algorithms such as SEEK's SUMTHRESHOLD implementation. We publish our U-Net software package on GitHub under GPLv3 license.

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

PubMed

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

2016-01-01

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

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

PubMed Central

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

2016-01-01

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

Numbers And Gains Of Neurons In Winner-Take-All Networks

NASA Technical Reports Server (NTRS)

Brown, Timothy X.

1993-01-01

Report presents theoretical study of gains required in neurons to implement winner-take-all electronic neural network of given size and related question of maximum size of winner-take-all network in which neurons have specified sigmoid transfer or response function with specified gain.

Neural networks for structural design - An integrated system implementation

NASA Technical Reports Server (NTRS)

Berke, Laszlo; Hafez, Wassim; Pao, Yoh-Han

1992-01-01

The development of powerful automated procedures to aid the creative designer is becoming increasingly critical for complex design tasks. In the work described here Artificial Neural Nets are applied to acquire structural analysis and optimization domain expertise. Based on initial instructions from the user an automated procedure generates random instances of structural analysis and/or optimization 'experiences' that cover a desired domain. It extracts training patterns from the created instances, constructs and trains an appropriate network architecture and checks the accuracy of net predictions. The final product is a trained neural net that can estimate analysis and/or optimization results instantaneously.

Design and validation of a real-time spiking-neural-network decoder for brain-machine interfaces.

PubMed

Dethier, Julie; Nuyujukian, Paul; Ryu, Stephen I; Shenoy, Krishna V; Boahen, Kwabena

2013-06-01

Cortically-controlled motor prostheses aim to restore functions lost to neurological disease and injury. Several proof of concept demonstrations have shown encouraging results, but barriers to clinical translation still remain. In particular, intracortical prostheses must satisfy stringent power dissipation constraints so as not to damage cortex. One possible solution is to use ultra-low power neuromorphic chips to decode neural signals for these intracortical implants. The first step is to explore in simulation the feasibility of translating decoding algorithms for brain-machine interface (BMI) applications into spiking neural networks (SNNs). Here we demonstrate the validity of the approach by implementing an existing Kalman-filter-based decoder in a simulated SNN using the Neural Engineering Framework (NEF), a general method for mapping control algorithms onto SNNs. To measure this system's robustness and generalization, we tested it online in closed-loop BMI experiments with two rhesus monkeys. Across both monkeys, a Kalman filter implemented using a 2000-neuron SNN has comparable performance to that of a Kalman filter implemented using standard floating point techniques. These results demonstrate the tractability of SNN implementations of statistical signal processing algorithms on different monkeys and for several tasks, suggesting that a SNN decoder, implemented on a neuromorphic chip, may be a feasible computational platform for low-power fully-implanted prostheses. The validation of this closed-loop decoder system and the demonstration of its robustness and generalization hold promise for SNN implementations on an ultra-low power neuromorphic chip using the NEF.

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.

Integration of Continuous-Time Dynamics in a Spiking Neural Network Simulator.

PubMed

Hahne, Jan; Dahmen, David; Schuecker, Jannis; Frommer, Andreas; Bolten, Matthias; Helias, Moritz; Diesmann, Markus

2017-01-01

Contemporary modeling approaches to the dynamics of neural networks include two important classes of models: biologically grounded spiking neuron models and functionally inspired rate-based units. We present a unified simulation framework that supports the combination of the two for multi-scale modeling, enables the quantitative validation of mean-field approaches by spiking network simulations, and provides an increase in reliability by usage of the same simulation code and the same network model specifications for both model classes. While most spiking simulations rely on the communication of discrete events, rate models require time-continuous interactions between neurons. Exploiting the conceptual similarity to the inclusion of gap junctions in spiking network simulations, we arrive at a reference implementation of instantaneous and delayed interactions between rate-based models in a spiking network simulator. The separation of rate dynamics from the general connection and communication infrastructure ensures flexibility of the framework. In addition to the standard implementation we present an iterative approach based on waveform-relaxation techniques to reduce communication and increase performance for large-scale simulations of rate-based models with instantaneous interactions. Finally we demonstrate the broad applicability of the framework by considering various examples from the literature, ranging from random networks to neural-field models. The study provides the prerequisite for interactions between rate-based and spiking models in a joint simulation.

Integration of Continuous-Time Dynamics in a Spiking Neural Network Simulator

PubMed Central

Hahne, Jan; Dahmen, David; Schuecker, Jannis; Frommer, Andreas; Bolten, Matthias; Helias, Moritz; Diesmann, Markus

2017-01-01

Contemporary modeling approaches to the dynamics of neural networks include two important classes of models: biologically grounded spiking neuron models and functionally inspired rate-based units. We present a unified simulation framework that supports the combination of the two for multi-scale modeling, enables the quantitative validation of mean-field approaches by spiking network simulations, and provides an increase in reliability by usage of the same simulation code and the same network model specifications for both model classes. While most spiking simulations rely on the communication of discrete events, rate models require time-continuous interactions between neurons. Exploiting the conceptual similarity to the inclusion of gap junctions in spiking network simulations, we arrive at a reference implementation of instantaneous and delayed interactions between rate-based models in a spiking network simulator. The separation of rate dynamics from the general connection and communication infrastructure ensures flexibility of the framework. In addition to the standard implementation we present an iterative approach based on waveform-relaxation techniques to reduce communication and increase performance for large-scale simulations of rate-based models with instantaneous interactions. Finally we demonstrate the broad applicability of the framework by considering various examples from the literature, ranging from random networks to neural-field models. The study provides the prerequisite for interactions between rate-based and spiking models in a joint simulation. PMID:28596730

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

Homeostatic Scaling of Excitability in Recurrent Neural Networks

PubMed Central

Remme, Michiel W. H.; Wadman, Wytse J.

2012-01-01

Neurons adjust their intrinsic excitability when experiencing a persistent change in synaptic drive. This process can prevent neural activity from moving into either a quiescent state or a saturated state in the face of ongoing plasticity, and is thought to promote stability of the network in which neurons reside. However, most neurons are embedded in recurrent networks, which require a delicate balance between excitation and inhibition to maintain network stability. This balance could be disrupted when neurons independently adjust their intrinsic excitability. Here, we study the functioning of activity-dependent homeostatic scaling of intrinsic excitability (HSE) in a recurrent neural network. Using both simulations of a recurrent network consisting of excitatory and inhibitory neurons that implement HSE, and a mean-field description of adapting excitatory and inhibitory populations, we show that the stability of such adapting networks critically depends on the relationship between the adaptation time scales of both neuron populations. In a stable adapting network, HSE can keep all neurons functioning within their dynamic range, while the network is undergoing several (patho)physiologically relevant types of plasticity, such as persistent changes in external drive, changes in connection strengths, or the loss of inhibitory cells from the network. However, HSE cannot prevent the unstable network dynamics that result when, due to such plasticity, recurrent excitation in the network becomes too strong compared to feedback inhibition. This suggests that keeping a neural network in a stable and functional state requires the coordination of distinct homeostatic mechanisms that operate not only by adjusting neural excitability, but also by controlling network connectivity. PMID:22570604

Evaluation and prediction of solar radiation for energy management based on neural networks

NASA Astrophysics Data System (ADS)

Aldoshina, O. V.; Van Tai, Dinh

2017-08-01

Currently, there is a high rate of distribution of renewable energy sources and distributed power generation based on intelligent networks; therefore, meteorological forecasts are particularly useful for planning and managing the energy system in order to increase its overall efficiency and productivity. The application of artificial neural networks (ANN) in the field of photovoltaic energy is presented in this article. Implemented in this study, two periodically repeating dynamic ANS, that are the concentration of the time delay of a neural network (CTDNN) and the non-linear autoregression of a network with exogenous inputs of the NAEI, are used in the development of a model for estimating and daily forecasting of solar radiation. ANN show good productivity, as reliable and accurate models of daily solar radiation are obtained. This allows to successfully predict the photovoltaic output power for this installation. The potential of the proposed method for controlling the energy of the electrical network is shown using the example of the application of the NAEI network for predicting the electric load.

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

PubMed Central

Testolin, Alberto; Zorzi, Marco

2016-01-01

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

The image recognition based on neural network and Bayesian decision

NASA Astrophysics Data System (ADS)

Wang, Chugege

2018-04-01

The artificial neural network began in 1940, which is an important part of artificial intelligence. At present, it has become a hot topic in the fields of neuroscience, computer science, brain science, mathematics, and psychology. Thomas Bayes firstly reported the Bayesian theory in 1763. After the development in the twentieth century, it has been widespread in all areas of statistics. In recent years, due to the solution of the problem of high-dimensional integral calculation, Bayesian Statistics has been improved theoretically, which solved many problems that cannot be solved by classical statistics and is also applied to the interdisciplinary fields. In this paper, the related concepts and principles of the artificial neural network are introduced. It also summarizes the basic content and principle of Bayesian Statistics, and combines the artificial neural network technology and Bayesian decision theory and implement them in all aspects of image recognition, such as enhanced face detection method based on neural network and Bayesian decision, as well as the image classification based on the Bayesian decision. It can be seen that the combination of artificial intelligence and statistical algorithms has always been the hot research topic.

A neural network approach to job-shop scheduling.

PubMed

Zhou, D N; Cherkassky, V; Baldwin, T R; Olson, D E

1991-01-01

A novel analog computational network is presented for solving NP-complete constraint satisfaction problems, i.e. job-shop scheduling. In contrast to most neural approaches to combinatorial optimization based on quadratic energy cost function, the authors propose to use linear cost functions. As a result, the network complexity (number of neurons and the number of resistive interconnections) grows only linearly with problem size, and large-scale implementations become possible. The proposed approach is related to the linear programming network described by D.W. Tank and J.J. Hopfield (1985), which also uses a linear cost function for a simple optimization problem. It is shown how to map a difficult constraint-satisfaction problem onto a simple neural net in which the number of neural processors equals the number of subjobs (operations) and the number of interconnections grows linearly with the total number of operations. Simulations show that the authors' approach produces better solutions than existing neural approaches to job-shop scheduling, i.e. the traveling salesman problem-type Hopfield approach and integer linear programming approach of J.P.S. Foo and Y. Takefuji (1988), in terms of the quality of the solution and the network complexity.

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

PubMed

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

2017-07-18

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

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

PubMed

Testolin, Alberto; Zorzi, Marco

2016-01-01

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

Exploring the Combination of Dempster-Shafer Theory and Neural Network for Predicting Trust and Distrust

PubMed Central

Wang, Xin; Wang, Ying; Sun, Hongbin

2016-01-01

In social media, trust and distrust among users are important factors in helping users make decisions, dissect information, and receive recommendations. However, the sparsity and imbalance of social relations bring great difficulties and challenges in predicting trust and distrust. Meanwhile, there are numerous inducing factors to determine trust and distrust relations. The relationship among inducing factors may be dependency, independence, and conflicting. Dempster-Shafer theory and neural network are effective and efficient strategies to deal with these difficulties and challenges. In this paper, we study trust and distrust prediction based on the combination of Dempster-Shafer theory and neural network. We firstly analyze the inducing factors about trust and distrust, namely, homophily, status theory, and emotion tendency. Then, we quantify inducing factors of trust and distrust, take these features as evidences, and construct evidence prototype as input nodes of multilayer neural network. Finally, we propose a framework of predicting trust and distrust which uses multilayer neural network to model the implementing process of Dempster-Shafer theory in different hidden layers, aiming to overcome the disadvantage of Dempster-Shafer theory without optimization method. Experimental results on a real-world dataset demonstrate the effectiveness of the proposed framework. PMID:27034651

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.

Center for Neural Engineering: applications of pulse-coupled neural networks

NASA Astrophysics Data System (ADS)

Malkani, Mohan; Bodruzzaman, Mohammad; Johnson, John L.; Davis, Joel

1999-03-01

Pulsed-Coupled Neural Network (PCNN) is an oscillatory model neural network where grouping of cells and grouping among the groups that form the output time series (number of cells that fires in each input presentation also called `icon'). This is based on the synchronicity of oscillations. Recent work by Johnson and others demonstrated the functional capabilities of networks containing such elements for invariant feature extraction using intensity maps. PCNN thus presents itself as a more biologically plausible model with solid functional potential. This paper will present the summary of several projects and their results where we successfully applied PCNN. In project one, the PCNN was applied for object recognition and classification through a robotic vision system. The features (icons) generated by the PCNN were then fed into a feedforward neural network for classification. In project two, we developed techniques for sensory data fusion. The PCNN algorithm was implemented and tested on a B14 mobile robot. The PCNN-based features were extracted from the images taken from the robot vision system and used in conjunction with the map generated by data fusion of the sonar and wheel encoder data for the navigation of the mobile robot. In our third project, we applied the PCNN for speaker recognition. The spectrogram image of speech signals are fed into the PCNN to produce invariant feature icons which are then fed into a feedforward neural network for speaker identification.

A modular neural network scheme applied to fault diagnosis in electric power systems.

PubMed

Flores, Agustín; Quiles, Eduardo; García, Emilio; Morant, Francisco; Correcher, Antonio

2014-01-01

This work proposes a new method for fault diagnosis in electric power systems based on neural modules. With this method the diagnosis is performed by assigning a neural module for each type of component comprising the electric power system, whether it is a transmission line, bus or transformer. The neural modules for buses and transformers comprise two diagnostic levels which take into consideration the logic states of switches and relays, both internal and back-up, with the exception of the neural module for transmission lines which also has a third diagnostic level which takes into account the oscillograms of fault voltages and currents as well as the frequency spectrums of these oscillograms, in order to verify if the transmission line had in fact been subjected to a fault. One important advantage of the diagnostic system proposed is that its implementation does not require the use of a network configurator for the system; it does not depend on the size of the power network nor does it require retraining of the neural modules if the power network increases in size, making its application possible to only one component, a specific area, or the whole context of the power system.

A Modular Neural Network Scheme Applied to Fault Diagnosis in Electric Power Systems

PubMed Central

Flores, Agustín; Morant, Francisco

2014-01-01

This work proposes a new method for fault diagnosis in electric power systems based on neural modules. With this method the diagnosis is performed by assigning a neural module for each type of component comprising the electric power system, whether it is a transmission line, bus or transformer. The neural modules for buses and transformers comprise two diagnostic levels which take into consideration the logic states of switches and relays, both internal and back-up, with the exception of the neural module for transmission lines which also has a third diagnostic level which takes into account the oscillograms of fault voltages and currents as well as the frequency spectrums of these oscillograms, in order to verify if the transmission line had in fact been subjected to a fault. One important advantage of the diagnostic system proposed is that its implementation does not require the use of a network configurator for the system; it does not depend on the size of the power network nor does it require retraining of the neural modules if the power network increases in size, making its application possible to only one component, a specific area, or the whole context of the power system. PMID:25610897

Object recognition with hierarchical discriminant saliency networks.

PubMed

Han, Sunhyoung; Vasconcelos, Nuno

2014-01-01

The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as a pre-processor for recognition, we investigate the hypothesis that attention is an intrinsic component of recognition and vice-versa. This hypothesis is tested with a recognition model, the hierarchical discriminant saliency network (HDSN), whose layers are top-down saliency detectors, tuned for a visual class according to the principles of discriminant saliency. As a model of neural computation, the HDSN has two possible implementations. In a biologically plausible implementation, all layers comply with the standard neurophysiological model of visual cortex, with sub-layers of simple and complex units that implement a combination of filtering, divisive normalization, pooling, and non-linearities. In a convolutional neural network implementation, all layers are convolutional and implement a combination of filtering, rectification, and pooling. The rectification is performed with a parametric extension of the now popular rectified linear units (ReLUs), whose parameters can be tuned for the detection of target object classes. This enables a number of functional enhancements over neural network models that lack a connection to saliency, including optimal feature denoising mechanisms for recognition, modulation of saliency responses by the discriminant power of the underlying features, and the ability to detect both feature presence and absence. In either implementation, each layer has a precise statistical interpretation, and all parameters are tuned by statistical learning. Each saliency detection layer learns more discriminant saliency templates than its predecessors and higher layers have larger pooling fields. This enables the HDSN to simultaneously achieve high selectivity to target object classes and invariance. The performance of the network in saliency and object recognition tasks is compared to those of models from the biological and computer vision literatures. This demonstrates benefits for all the functional enhancements of the HDSN, the class tuning inherent to discriminant saliency, and saliency layers based on templates of increasing target selectivity and invariance. Altogether, these experiments suggest that there are non-trivial benefits in integrating attention and recognition.

Investigation of /tt¯ in the full hadronic final state at CDF with a neural network approach

NASA Astrophysics Data System (ADS)

Sidoti, A.; Azzi, P.; Busetto, G.; Castro, A.; Dusini, S.; Lazzizzera, I.; Wyss, J. L.

2001-07-01

In this work we present the results of a neural network (NN) approach to the measurement of the t t¯ production cross-section and top mass in the all-hadronic channel, analyzing data collected at the Collider Detector at Fermilab (CDF) experiment. We have used a hardware implementation of a feed forward neural network, TOTEM, the product of a collaboration of INFN (Istituto Nazionale Fisica Nucleare)—IRST (Istituto per la Ricerca Scientifica e Tecnologica)—University of Trento, Italy. Particular attention has been payed to the evaluation of the systematics specifically related to the NN approach. The results are consistent with those obtained at CDF by conventional data selection techniques.

Global exponential periodicity and stability of discrete-time complex-valued recurrent neural networks with time-delays.

PubMed

Hu, Jin; Wang, Jun

2015-06-01

In recent years, complex-valued recurrent neural networks have been developed and analysed in-depth in view of that they have good modelling performance for some applications involving complex-valued elements. In implementing continuous-time dynamical systems for simulation or computational purposes, it is quite necessary to utilize a discrete-time model which is an analogue of the continuous-time system. In this paper, we analyse a discrete-time complex-valued recurrent neural network model and obtain the sufficient conditions on its global exponential periodicity and exponential stability. Simulation results of several numerical examples are delineated to illustrate the theoretical results and an application on associative memory is also given. Copyright © 2015 Elsevier Ltd. All rights reserved.

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.

A method for optical imaging and monitoring of the excretion of fluorescent nanocomposites from the body using artificial neural networks.

PubMed

Sarmanova, Olga E; Burikov, Sergey A; Dolenko, Sergey A; Isaev, Igor V; Laptinskiy, Kirill A; Prabhakar, Neeraj; Karaman, Didem Şen; Rosenholm, Jessica M; Shenderova, Olga A; Dolenko, Tatiana A

2018-04-12

In this study, a new approach to the implementation of optical imaging of fluorescent nanoparticles in a biological medium using artificial neural networks is proposed. The studies were carried out using new synthesized nanocomposites - nanometer graphene oxides, covered by the poly(ethylene imine)-poly(ethylene glycol) copolymer and by the folic acid. We present an example of a successful solution of the problem of monitoring the removal of nanocomposites based on nGO and their components with urine using fluorescent spectroscopy and artificial neural networks. However, the proposed method is applicable for optical imaging of any fluorescent nanoparticles used as theranostic agents in biological tissue. Copyright © 2018. Published by Elsevier Inc.

Method for star identification using neural networks

NASA Astrophysics Data System (ADS)

Lindsey, Clark S.; Lindblad, Thomas; Eide, Age J.

1997-04-01

Identification of star constellations with an onboard star tracker provides the highest precision of all attitude determination techniques for spacecraft. A method for identification of star constellations inspired by neural network (NNW) techniques is presented. It compares feature vectors derived from histograms of distances to multiple stars around the unknown star. The NNW method appears most robust with respect to position noise and would require a smaller database than conventional methods, especially for small fields of view. The neural network method is quite slow when performed on a sequential (serial) processor, but would provide very high speed if implemented in special hardware. Such hardware solutions could also yield lower low weight and low power consumption, both important features for small satellites.

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.

Neural Network Assisted Inverse Dynamic Guidance for Terminally Constrained Entry Flight

PubMed Central

Chen, Wanchun

2014-01-01

This paper presents a neural network assisted entry guidance law that is designed by applying Bézier approximation. It is shown that a fully constrained approximation of a reference trajectory can be made by using the Bézier curve. Applying this approximation, an inverse dynamic system for an entry flight is solved to generate guidance command. The guidance solution thus gotten ensures terminal constraints for position, flight path, and azimuth angle. In order to ensure terminal velocity constraint, a prediction of the terminal velocity is required, based on which, the approximated Bézier curve is adjusted. An artificial neural network is used for this prediction of the terminal velocity. The method enables faster implementation in achieving fully constrained entry flight. Results from simulations indicate improved performance of the neural network assisted method. The scheme is expected to have prospect for further research on automated onboard control of terminal velocity for both reentry and terminal guidance laws. PMID:24723821

Adaptive critic learning techniques for engine torque and air-fuel ratio control.

PubMed

Liu, Derong; Javaherian, Hossein; Kovalenko, Olesia; Huang, Ting

2008-08-01

A new approach for engine calibration and control is proposed. In this paper, we present our research results on the implementation of adaptive critic designs for self-learning control of automotive engines. A class of adaptive critic designs that can be classified as (model-free) action-dependent heuristic dynamic programming is used in this research project. The goals of the present learning control design for automotive engines include improved performance, reduced emissions, and maintained optimum performance under various operating conditions. Using the data from a test vehicle with a V8 engine, we developed a neural network model of the engine and neural network controllers based on the idea of approximate dynamic programming to achieve optimal control. We have developed and simulated self-learning neural network controllers for both engine torque (TRQ) and exhaust air-fuel ratio (AFR) control. The goal of TRQ control and AFR control is to track the commanded values. For both control problems, excellent neural network controller transient performance has been achieved.

Toward a More Robust Pruning Procedure for MLP Networks

NASA Technical Reports Server (NTRS)

Stepniewski, Slawomir W.; Jorgensen, Charles C.

1998-01-01

Choosing a proper neural network architecture is a problem of great practical importance. Smaller models mean not only simpler designs but also lower variance for parameter estimation and network prediction. The widespread utilization of neural networks in modeling highlights an issue in human factors. The procedure of building neural models should find an appropriate level of model complexity in a more or less automatic fashion to make it less prone to human subjectivity. In this paper we present a Singular Value Decomposition based node elimination technique and enhanced implementation of the Optimal Brain Surgeon algorithm. Combining both methods creates a powerful pruning engine that can be used for tuning feedforward connectionist models. The performance of the proposed method is demonstrated by adjusting the structure of a multi-input multi-output model used to calibrate a six-component wind tunnel strain gage.

Cosmic-ray discrimination capabilities of /ΔE-/E silicon nuclear telescopes using neural networks

NASA Astrophysics Data System (ADS)

Ambriola, M.; Bellotti, R.; Cafagna, F.; Castellano, M.; Ciacio, F.; Circella, M.; Marzo, C. N. D.; Montaruli, T.

2000-02-01

An isotope classifier of cosmic-ray events collected by space detectors has been implemented using a multi-layer perceptron neural architecture. In order to handle a great number of different isotopes a modular architecture of the ``mixture of experts'' type is proposed. The performance of this classifier has been tested on simulated data and has been compared with a ``classical'' classifying procedure. The quantitative comparison with traditional techniques shows that the neural approach has classification performances comparable - within /1% - with that of the classical one, with efficiency of the order of /98%. A possible hardware implementation of such a kind of neural architecture in future space missions is considered.

Design of a neural network simulator on a transputer array

NASA Technical Reports Server (NTRS)

Mcintire, Gary; Villarreal, James; Baffes, Paul; Rua, Monica

1987-01-01

A brief summary of neural networks is presented which concentrates on the design constraints imposed. Major design issues are discussed together with analysis methods and the chosen solutions. Although the system will be capable of running on most transputer architectures, it currently is being implemented on a 40-transputer system connected to a toroidal architecture. Predictions show a performance level equivalent to that of a highly optimized simulator running on the SX-2 supercomputer.

Neural Network Classifies Teleoperation Data

NASA Technical Reports Server (NTRS)

Fiorini, Paolo; Giancaspro, Antonio; Losito, Sergio; Pasquariello, Guido

1994-01-01

Prototype artificial neural network, implemented in software, identifies phases of telemanipulator tasks in real time by analyzing feedback signals from force sensors on manipulator hand. Prototype is early, subsystem-level product of continuing effort to develop automated system that assists in training and supervising human control operator: provides symbolic feedback (e.g., warnings of impending collisions or evaluations of performance) to operator in real time during successive executions of same task. Also simplifies transition between teleoperation and autonomous modes of telerobotic system.

Spiking neuron network Helmholtz machine.

PubMed

Sountsov, Pavel; Miller, Paul

2015-01-01

An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule.

Spiking neuron network Helmholtz machine

PubMed Central

Sountsov, Pavel; Miller, Paul

2015-01-01

An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule. PMID:25954191

Fault-tolerant nonlinear adaptive flight control using sliding mode online learning.

PubMed

Krüger, Thomas; Schnetter, Philipp; Placzek, Robin; Vörsmann, Peter

2012-08-01

An expanded nonlinear model inversion flight control strategy using sliding mode online learning for neural networks is presented. The proposed control strategy is implemented for a small unmanned aircraft system (UAS). This class of aircraft is very susceptible towards nonlinearities like atmospheric turbulence, model uncertainties and of course system failures. Therefore, these systems mark a sensible testbed to evaluate fault-tolerant, adaptive flight control strategies. Within this work the concept of feedback linearization is combined with feed forward neural networks to compensate for inversion errors and other nonlinear effects. Backpropagation-based adaption laws of the network weights are used for online training. Within these adaption laws the standard gradient descent backpropagation algorithm is augmented with the concept of sliding mode control (SMC). Implemented as a learning algorithm, this nonlinear control strategy treats the neural network as a controlled system and allows a stable, dynamic calculation of the learning rates. While considering the system's stability, this robust online learning method therefore offers a higher speed of convergence, especially in the presence of external disturbances. The SMC-based flight controller is tested and compared with the standard gradient descent backpropagation algorithm in the presence of system failures. Copyright © 2012 Elsevier Ltd. All rights reserved.

Control Reallocation Strategies for Damage Adaptation in Transport Class Aircraft

NASA Technical Reports Server (NTRS)

Gundy-Burlet, Karen; Krishnakumar, K.; Limes, Greg; Bryant, Don

2003-01-01

This paper examines the feasibility, potential benefits and implementation issues associated with retrofitting a neural-adaptive flight control system (NFCS) to existing transport aircraft, including both cable/hydraulic and fly-by-wire configurations. NFCS uses a neural network based direct adaptive control approach for applying alternate sources of control authority in the presence of damage or failures in order to achieve desired flight control performance. Neural networks are used to provide consistent handling qualities across flight conditions, adapt to changes in aircraft dynamics and to make the controller easy to apply when implemented on different aircraft. Full-motion piloted simulation studies were performed on two different transport models: the Boeing 747-400 and the Boeing C-17. Subjects included NASA, Air Force and commercial airline pilots. Results demonstrate the potential for improving handing qualities and significantly increased survivability rates under various simulated failure conditions.

Hardware implementation of CMAC neural network with reduced storage requirement.

PubMed

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

1997-01-01

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

Efficiently passing messages in distributed spiking neural network simulation.

PubMed

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

2013-01-01

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

Neural network fusion capabilities for efficient implementation of tracking algorithms

NASA Astrophysics Data System (ADS)

Sundareshan, Malur K.; Amoozegar, Farid

1996-05-01

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

A neural network based implementation of an MPC algorithm applied in the control systems of electromechanical plants

NASA Astrophysics Data System (ADS)

Marusak, Piotr M.; Kuntanapreeda, Suwat

2018-01-01

The paper considers application of a neural network based implementation of a model predictive control (MPC) control algorithm to electromechanical plants. Properties of such control plants implicate that a relatively short sampling time should be used. However, in such a case, finding the control value numerically may be too time-consuming. Therefore, the current paper tests the solution based on transforming the MPC optimization problem into a set of differential equations whose solution is the same as that of the original optimization problem. This set of differential equations can be interpreted as a dynamic neural network. In such an approach, the constraints can be introduced into the optimization problem with relative ease. Moreover, the solution of the optimization problem can be obtained faster than when the standard numerical quadratic programming routine is used. However, a very careful tuning of the algorithm is needed to achieve this. A DC motor and an electrohydraulic actuator are taken as illustrative examples. The feasibility and effectiveness of the proposed approach are demonstrated through numerical simulations.

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.

An ultra-low-voltage electronic implementation of inertial neuron model with nonmonotonous Liao's activation function.

PubMed

Kant, Nasir Ali; Dar, Mohamad Rafiq; Khanday, Farooq Ahmad

2015-01-01

The output of every neuron in neural network is specified by the employed activation function (AF) and therefore forms the heart of neural networks. As far as the design of artificial neural networks (ANNs) is concerned, hardware approach is preferred over software one because it promises the full utilization of the application potential of ANNs. Therefore, besides some arithmetic blocks, designing AF in hardware is the most important for designing ANN. While attempting to design the AF in hardware, the designs should be compatible with the modern Very Large Scale Integration (VLSI) design techniques. In this regard, the implemented designs should: only be in Metal Oxide Semiconductor (MOS) technology in order to be compatible with the digital designs, provide electronic tunability feature, and be able to operate at ultra-low voltage. Companding is one of the promising circuit design techniques for achieving these goals. In this paper, 0.5 V design of Liao's AF using sinh-domain technique is introduced. Furthermore, the function is tested by implementing inertial neuron model. The performance of the AF and inertial neuron model have been evaluated through simulation results, using the PSPICE software with the MOS transistor models provided by the 0.18-μm Taiwan Semiconductor Manufacturer Complementary Metal Oxide Semiconductor (TSM CMOS) process.

A program for the Bayesian Neural Network in the ROOT framework

NASA Astrophysics Data System (ADS)

Zhong, Jiahang; Huang, Run-Sheng; Lee, Shih-Chang

2011-12-01

We present a Bayesian Neural Network algorithm implemented in the TMVA package (Hoecker et al., 2007 [1]), within the ROOT framework (Brun and Rademakers, 1997 [2]). Comparing to the conventional utilization of Neural Network as discriminator, this new implementation has more advantages as a non-parametric regression tool, particularly for fitting probabilities. It provides functionalities including cost function selection, complexity control and uncertainty estimation. An example of such application in High Energy Physics is shown. The algorithm is available with ROOT release later than 5.29. Program summaryProgram title: TMVA-BNN Catalogue identifier: AEJX_v1_0 Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AEJX_v1_0.html Program obtainable from: CPC Program Library, Queen's University, Belfast, N. Ireland Licensing provisions: BSD license No. of lines in distributed program, including test data, etc.: 5094 No. of bytes in distributed program, including test data, etc.: 1,320,987 Distribution format: tar.gz Programming language: C++ Computer: Any computer system or cluster with C++ compiler and UNIX-like operating system Operating system: Most UNIX/Linux systems. The application programs were thoroughly tested under Fedora and Scientific Linux CERN. Classification: 11.9 External routines: ROOT package version 5.29 or higher ( http://root.cern.ch) Nature of problem: Non-parametric fitting of multivariate distributions Solution method: An implementation of Neural Network following the Bayesian statistical interpretation. Uses Laplace approximation for the Bayesian marginalizations. Provides the functionalities of automatic complexity control and uncertainty estimation. Running time: Time consumption for the training depends substantially on the size of input sample, the NN topology, the number of training iterations, etc. For the example in this manuscript, about 7 min was used on a PC/Linux with 2.0 GHz processors.

$$\\mu / \\pi$$ Separation using Convolutional Neural Networks for the MicroBooNE Charged Current Inclusive Cross Section Measurement

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

Esquivel, Jessica Nicole

The purpose of this thesis was to use Convolutional Neural Networks (CNN) to separatemore » $$\\mu^{\\prime}$$s and $$\\pi^{\\prime}$$s for use in increasing the acceptance rate of $$\\mu^{\\prime}$$s below the implemented 75cm track length cut in the Charged Current Inclusive (CC-Inclusive) event selection for the CC-Inclusive Cross-Section Measurement. In doing this, we increase acceptance rate for CC-Inclusive events below a specific momentum range.« less

Hetero-association for pattern translation

NASA Astrophysics Data System (ADS)

Yu, Francis T. S.; Lu, Thomas T.; Yang, Xiangyang

1991-09-01

A hetero-association neural network using an interpattern association algorithm is presented. By using simple logical rules, hetero-association memory can be constructed based on the association between the input-output reference patterns. For optical implementation, a compact size liquid crystal television neural network is used. Translations between the English letters and the Chinese characters as well as Arabic and Chinese numerics are demonstrated. The authors have shown that the hetero-association model can perform more effectively in comparison to the Hopfield model in retrieving large numbers of similar patterns.

Vector neural network signal integration for radar application

NASA Astrophysics Data System (ADS)

Bierman, Gregory S.

1994-07-01

The Litton Data Systems Vector Neural Network (VNN) is a unique multi-scan integration algorithm currently in development. The target of interest is a low-flying cruise missile. Current tactical radar cannot detect and track the missile in ground clutter at tactically useful ranges. The VNN solves this problem by integrating the energy from multiple frames to effectively increase the target's signal-to-noise ratio. The implementation plan is addressing the APG-63 radar. Real-time results will be available by March 1994.

Design and validation of a real-time spiking-neural-network decoder for brain-machine interfaces

NASA Astrophysics Data System (ADS)

Dethier, Julie; Nuyujukian, Paul; Ryu, Stephen I.; Shenoy, Krishna V.; Boahen, Kwabena

2013-06-01

Objective. Cortically-controlled motor prostheses aim to restore functions lost to neurological disease and injury. Several proof of concept demonstrations have shown encouraging results, but barriers to clinical translation still remain. In particular, intracortical prostheses must satisfy stringent power dissipation constraints so as not to damage cortex. Approach. One possible solution is to use ultra-low power neuromorphic chips to decode neural signals for these intracortical implants. The first step is to explore in simulation the feasibility of translating decoding algorithms for brain-machine interface (BMI) applications into spiking neural networks (SNNs). Main results. Here we demonstrate the validity of the approach by implementing an existing Kalman-filter-based decoder in a simulated SNN using the Neural Engineering Framework (NEF), a general method for mapping control algorithms onto SNNs. To measure this system’s robustness and generalization, we tested it online in closed-loop BMI experiments with two rhesus monkeys. Across both monkeys, a Kalman filter implemented using a 2000-neuron SNN has comparable performance to that of a Kalman filter implemented using standard floating point techniques. Significance. These results demonstrate the tractability of SNN implementations of statistical signal processing algorithms on different monkeys and for several tasks, suggesting that a SNN decoder, implemented on a neuromorphic chip, may be a feasible computational platform for low-power fully-implanted prostheses. The validation of this closed-loop decoder system and the demonstration of its robustness and generalization hold promise for SNN implementations on an ultra-low power neuromorphic chip using the NEF.

Optical neural net for classifying imaging spectrometer data

NASA Technical Reports Server (NTRS)

Barnard, Etienne; Casasent, David P.

1989-01-01

The problem of determining the composition of an unknown input mixture from its measured spectrum, given the spectra of a number of elements, is studied. The Hopfield minimization procedure was used to express the determination of the compositions as a problem suitable for solution by neural nets. A mathematical description of the problem was developed and used as a basis for a neural network solution and an optical implementation.

Spiking Neural Networks Based on OxRAM Synapses for Real-Time Unsupervised Spike Sorting.

PubMed

Werner, Thilo; Vianello, Elisa; Bichler, Olivier; Garbin, Daniele; Cattaert, Daniel; Yvert, Blaise; De Salvo, Barbara; Perniola, Luca

2016-01-01

In this paper, we present an alternative approach to perform spike sorting of complex brain signals based on spiking neural networks (SNN). The proposed architecture is suitable for hardware implementation by using resistive random access memory (RRAM) technology for the implementation of synapses whose low latency (<1μs) enables real-time spike sorting. This offers promising advantages to conventional spike sorting techniques for brain-computer interfaces (BCI) and neural prosthesis applications. Moreover, the ultra-low power consumption of the RRAM synapses of the spiking neural network (nW range) may enable the design of autonomous implantable devices for rehabilitation purposes. We demonstrate an original methodology to use Oxide based RRAM (OxRAM) as easy to program and low energy (<75 pJ) synapses. Synaptic weights are modulated through the application of an online learning strategy inspired by biological Spike Timing Dependent Plasticity. Real spiking data have been recorded both intra- and extracellularly from an in-vitro preparation of the Crayfish sensory-motor system and used for validation of the proposed OxRAM based SNN. This artificial SNN is able to identify, learn, recognize and distinguish between different spike shapes in the input signal with a recognition rate about 90% without any supervision.

Dense Matching Comparison Between Census and a Convolutional Neural Network Algorithm for Plant Reconstruction

NASA Astrophysics Data System (ADS)

Xia, Y.; Tian, J.; d'Angelo, P.; Reinartz, P.

2018-05-01

3D reconstruction of plants is hard to implement, as the complex leaf distribution highly increases the difficulty level in dense matching. Semi-Global Matching has been successfully applied to recover the depth information of a scene, but may perform variably when different matching cost algorithms are used. In this paper two matching cost computation algorithms, Census transform and an algorithm using a convolutional neural network, are tested for plant reconstruction based on Semi-Global Matching. High resolution close-range photogrammetric images from a handheld camera are used for the experiment. The disparity maps generated based on the two selected matching cost methods are comparable with acceptable quality, which shows the good performance of Census and the potential of neural networks to improve the dense matching.

Incidents Prediction in Road Junctions Using Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Hajji, Tarik; Alami Hassani, Aicha; Ouazzani Jamil, Mohammed

2018-05-01

The implementation of an incident detection system (IDS) is an indispensable operation in the analysis of the road traffics. However the IDS may, in no case, represent an alternative to the classical monitoring system controlled by the human eye. The aim of this work is to increase detection and prediction probability of incidents in camera-monitored areas. Knowing that, these areas are monitored by multiple cameras and few supervisors. Our solution is to use Artificial Neural Networks (ANN) to analyze moving objects trajectories on captured images. We first propose a modelling of the trajectories and their characteristics, after we develop a learning database for valid and invalid trajectories, and then we carry out a comparative study to find the artificial neural network architecture that maximizes the rate of valid and invalid trajectories recognition.

Different propagation speeds of recalled sequences in plastic spiking neural networks

NASA Astrophysics Data System (ADS)

Huang, Xuhui; Zheng, Zhigang; Hu, Gang; Wu, Si; Rasch, Malte J.

2015-03-01

Neural networks can generate spatiotemporal patterns of spike activity. Sequential activity learning and retrieval have been observed in many brain areas, and e.g. is crucial for coding of episodic memory in the hippocampus or generating temporal patterns during song production in birds. In a recent study, a sequential activity pattern was directly entrained onto the neural activity of the primary visual cortex (V1) of rats and subsequently successfully recalled by a local and transient trigger. It was observed that the speed of activity propagation in coordinates of the retinotopically organized neural tissue was constant during retrieval regardless how the speed of light stimulation sweeping across the visual field during training was varied. It is well known that spike-timing dependent plasticity (STDP) is a potential mechanism for embedding temporal sequences into neural network activity. How training and retrieval speeds relate to each other and how network and learning parameters influence retrieval speeds, however, is not well described. We here theoretically analyze sequential activity learning and retrieval in a recurrent neural network with realistic synaptic short-term dynamics and STDP. Testing multiple STDP rules, we confirm that sequence learning can be achieved by STDP. However, we found that a multiplicative nearest-neighbor (NN) weight update rule generated weight distributions and recall activities that best matched the experiments in V1. Using network simulations and mean-field analysis, we further investigated the learning mechanisms and the influence of network parameters on recall speeds. Our analysis suggests that a multiplicative STDP rule with dominant NN spike interaction might be implemented in V1 since recall speed was almost constant in an NMDA-dominant regime. Interestingly, in an AMPA-dominant regime, neural circuits might exhibit recall speeds that instead follow the change in stimulus speeds. This prediction could be tested in experiments.

Reducing weight precision of convolutional neural networks towards large-scale on-chip image recognition

NASA Astrophysics Data System (ADS)

Ji, Zhengping; Ovsiannikov, Ilia; Wang, Yibing; Shi, Lilong; Zhang, Qiang

2015-05-01

In this paper, we develop a server-client quantization scheme to reduce bit resolution of deep learning architecture, i.e., Convolutional Neural Networks, for image recognition tasks. Low bit resolution is an important factor in bringing the deep learning neural network into hardware implementation, which directly determines the cost and power consumption. We aim to reduce the bit resolution of the network without sacrificing its performance. To this end, we design a new quantization algorithm called supervised iterative quantization to reduce the bit resolution of learned network weights. In the training stage, the supervised iterative quantization is conducted via two steps on server - apply k-means based adaptive quantization on learned network weights and retrain the network based on quantized weights. These two steps are alternated until the convergence criterion is met. In this testing stage, the network configuration and low-bit weights are loaded to the client hardware device to recognize coming input in real time, where optimized but expensive quantization becomes infeasible. Considering this, we adopt a uniform quantization for the inputs and internal network responses (called feature maps) to maintain low on-chip expenses. The Convolutional Neural Network with reduced weight and input/response precision is demonstrated in recognizing two types of images: one is hand-written digit images and the other is real-life images in office scenarios. Both results show that the new network is able to achieve the performance of the neural network with full bit resolution, even though in the new network the bit resolution of both weight and input are significantly reduced, e.g., from 64 bits to 4-5 bits.

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.

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

PubMed

Kriegeskorte, Nikolaus

2015-11-24

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

A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms

PubMed Central

Yang, Changju; Kim, Hyongsuk; Adhikari, Shyam Prasad; Chua, Leon O.

2016-01-01

A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems. PMID:28025566

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

A forecast-based STDP rule suitable for neuromorphic implementation.

PubMed

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

2012-08-01

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

Intelligent neural network and fuzzy logic control of industrial and power systems

NASA Astrophysics Data System (ADS)

Kuljaca, Ognjen

The main role played by neural network and fuzzy logic intelligent control algorithms today is to identify and compensate unknown nonlinear system dynamics. There are a number of methods developed, but often the stability analysis of neural network and fuzzy control systems was not provided. This work will meet those problems for the several algorithms. Some more complicated control algorithms included backstepping and adaptive critics will be designed. Nonlinear fuzzy control with nonadaptive fuzzy controllers is also analyzed. An experimental method for determining describing function of SISO fuzzy controller is given. The adaptive neural network tracking controller for an autonomous underwater vehicle is analyzed. A novel stability proof is provided. The implementation of the backstepping neural network controller for the coupled motor drives is described. Analysis and synthesis of adaptive critic neural network control is also provided in the work. Novel tuning laws for the system with action generating neural network and adaptive fuzzy critic are given. Stability proofs are derived for all those control methods. It is shown how these control algorithms and approaches can be used in practical engineering control. Stability proofs are given. Adaptive fuzzy logic control is analyzed. Simulation study is conducted to analyze the behavior of the adaptive fuzzy system on the different environment changes. A novel stability proof for adaptive fuzzy logic systems is given. Also, adaptive elastic fuzzy logic control architecture is described and analyzed. A novel membership function is used for elastic fuzzy logic system. The stability proof is proffered. Adaptive elastic fuzzy logic control is compared with the adaptive nonelastic fuzzy logic control. The work described in this dissertation serves as foundation on which analysis of particular representative industrial systems will be conducted. Also, it gives a good starting point for analysis of learning abilities of adaptive and neural network control systems, as well as for the analysis of the different algorithms such as elastic fuzzy systems.

Abnormal neural activities of directional brain networks in patients with long-term bilateral hearing loss.

PubMed

Xu, Long-Chun; Zhang, Gang; Zou, Yue; Zhang, Min-Feng; Zhang, Dong-Sheng; Ma, Hua; Zhao, Wen-Bo; Zhang, Guang-Yu

2017-10-13

The objective of the study is to provide some implications for rehabilitation of hearing impairment by investigating changes of neural activities of directional brain networks in patients with long-term bilateral hearing loss. Firstly, we implemented neuropsychological tests of 21 subjects (11 patients with long-term bilateral hearing loss, and 10 subjects with normal hearing), and these tests revealed significant differences between the deaf group and the controls. Then we constructed the individual specific virtual brain based on functional magnetic resonance data of participants by utilizing effective connectivity and multivariate regression methods. We exerted the stimulating signal to the primary auditory cortices of the virtual brain and observed the brain region activations. We found that patients with long-term bilateral hearing loss presented weaker brain region activations in the auditory and language networks, but enhanced neural activities in the default mode network as compared with normally hearing subjects. Especially, the right cerebral hemisphere presented more changes than the left. Additionally, weaker neural activities in the primary auditor cortices were also strongly associated with poorer cognitive performance. Finally, causal analysis revealed several interactional circuits among activated brain regions, and these interregional causal interactions implied that abnormal neural activities of the directional brain networks in the deaf patients impacted cognitive function.

A convolutional neural network to filter artifacts in spectroscopic MRI.

PubMed

Gurbani, Saumya S; Schreibmann, Eduard; Maudsley, Andrew A; Cordova, James Scott; Soher, Brian J; Poptani, Harish; Verma, Gaurav; Barker, Peter B; Shim, Hyunsuk; Cooper, Lee A D

2018-03-09

Proton MRSI is a noninvasive modality capable of generating volumetric maps of in vivo tissue metabolism without the need for ionizing radiation or injected contrast agent. Magnetic resonance spectroscopic imaging has been shown to be a viable imaging modality for studying several neuropathologies. However, a key hurdle in the routine clinical adoption of MRSI is the presence of spectral artifacts that can arise from a number of sources, possibly leading to false information. A deep learning model was developed that was capable of identifying and filtering out poor quality spectra. The core of the model used a tiled convolutional neural network that analyzed frequency-domain spectra to detect artifacts. When compared with a panel of MRS experts, our convolutional neural network achieved high sensitivity and specificity with an area under the curve of 0.95. A visualization scheme was implemented to better understand how the convolutional neural network made its judgement on single-voxel or multivoxel MRSI, and the convolutional neural network was embedded into a pipeline capable of producing whole-brain spectroscopic MRI volumes in real time. The fully automated method for assessment of spectral quality provides a valuable tool to support clinical MRSI or spectroscopic MRI studies for use in fields such as adaptive radiation therapy planning. © 2018 International Society for Magnetic Resonance in Medicine.

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.

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.

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

PubMed

Sengupta, Abhronil; Shim, Yong; Roy, Kaushik

2016-12-01

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

Global cluster synchronization in nonlinearly coupled community networks with heterogeneous coupling delays.

PubMed

Tseng, Jui-Pin

2017-02-01

This investigation establishes the global cluster synchronization of complex networks with a community structure based on an iterative approach. The units comprising the network are described by differential equations, and can be non-autonomous and involve time delays. In addition, units in the different communities can be governed by different equations. The coupling configuration of the network is rather general. The coupling terms can be non-diffusive, nonlinear, asymmetric, and with heterogeneous coupling delays. Based on this approach, both delay-dependent and delay-independent criteria for global cluster synchronization are derived. We implement the present approach for a nonlinearly coupled neural network with heterogeneous coupling delays. Two numerical examples are given to show that neural networks can behave in a variety of new collective ways under the synchronization criteria. These examples also demonstrate that neural networks remain synchronized in spite of coupling delays between neurons across different communities; however, they may lose synchrony if the coupling delays between the neurons within the same community are too large, such that the synchronization criteria are violated. Copyright © 2016 Elsevier Ltd. All rights reserved.

F77NNS - A FORTRAN-77 NEURAL NETWORK SIMULATOR

NASA Technical Reports Server (NTRS)

Mitchell, P. H.

1994-01-01

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

Arbitrary nonlinearity is sufficient to represent all functions by neural networks - A theorem

NASA Technical Reports Server (NTRS)

Kreinovich, Vladik YA.

1991-01-01

It is proved that if we have neurons implementing arbitrary linear functions and a neuron implementing one (arbitrary but smooth) nonlinear function g(x), then for every continuous function f(x sub 1,..., x sub m) of arbitrarily many variables, and for arbitrary e above 0, we can construct a network that consists of g-neurons and linear neurons, and computes f with precision e.

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.

Neural adaptation accounts for the dynamic resizing of peripersonal space: evidence from a psychophysical-computational approach.

PubMed

Noel, Jean-Paul; Blanke, Olaf; Magosso, Elisa; Serino, Andrea

2018-06-01

Interactions between the body and the environment occur within the peripersonal space (PPS), the space immediately surrounding the body. The PPS is encoded by multisensory (audio-tactile, visual-tactile) neurons that possess receptive fields (RFs) anchored on the body and restricted in depth. The extension in depth of PPS neurons' RFs has been documented to change dynamically as a function of the velocity of incoming stimuli, but the underlying neural mechanisms are still unknown. Here, by integrating a psychophysical approach with neural network modeling, we propose a mechanistic explanation behind this inherent dynamic property of PPS. We psychophysically mapped the size of participant's peri-face and peri-trunk space as a function of the velocity of task-irrelevant approaching auditory stimuli. Findings indicated that the peri-trunk space was larger than the peri-face space, and, importantly, as for the neurophysiological delineation of RFs, both of these representations enlarged as the velocity of incoming sound increased. We propose a neural network model to mechanistically interpret these findings: the network includes reciprocal connections between unisensory areas and higher order multisensory neurons, and it implements neural adaptation to persistent stimulation as a mechanism sensitive to stimulus velocity. The network was capable of replicating the behavioral observations of PPS size remapping and relates behavioral proxies of PPS size to neurophysiological measures of multisensory neurons' RF size. We propose that a biologically plausible neural adaptation mechanism embedded within the network encoding for PPS can be responsible for the dynamic alterations in PPS size as a function of the velocity of incoming stimuli. NEW & NOTEWORTHY Interactions between body and environment occur within the peripersonal space (PPS). PPS neurons are highly dynamic, adapting online as a function of body-object interactions. The mechanistic underpinning PPS dynamic properties are unexplained. We demonstrate with a psychophysical approach that PPS enlarges as incoming stimulus velocity increases, efficiently preventing contacts with faster approaching objects. We present a neurocomputational model of multisensory PPS implementing neural adaptation to persistent stimulation to propose a neurophysiological mechanism underlying this effect.

Supervised Learning Using Spike-Timing-Dependent Plasticity of Memristive Synapses.

PubMed

Nishitani, Yu; Kaneko, Yukihiro; Ueda, Michihito

2015-12-01

We propose a supervised learning model that enables error backpropagation for spiking neural network hardware. The method is modeled by modifying an existing model to suit the hardware implementation. An example of a network circuit for the model is also presented. In this circuit, a three-terminal ferroelectric memristor (3T-FeMEM), which is a field-effect transistor with a gate insulator composed of ferroelectric materials, is used as an electric synapse device to store the analog synaptic weight. Our model can be implemented by reflecting the network error to the write voltage of the 3T-FeMEMs and introducing a spike-timing-dependent learning function to the device. An XOR problem was successfully demonstrated as a benchmark learning by numerical simulations using the circuit properties to estimate the learning performance. In principle, the learning time per step of this supervised learning model and the circuit is independent of the number of neurons in each layer, promising a high-speed and low-power calculation in large-scale neural networks.

Multispectral embedding-based deep neural network for three-dimensional human pose recovery

NASA Astrophysics Data System (ADS)

Yu, Jialin; Sun, Jifeng

2018-01-01

Monocular image-based three-dimensional (3-D) human pose recovery aims to retrieve 3-D poses using the corresponding two-dimensional image features. Therefore, the pose recovery performance highly depends on the image representations. We propose a multispectral embedding-based deep neural network (MSEDNN) to automatically obtain the most discriminative features from multiple deep convolutional neural networks and then embed their penultimate fully connected layers into a low-dimensional manifold. This compact manifold can explore not only the optimum output from multiple deep networks but also the complementary properties of them. Furthermore, the distribution of each hierarchy discriminative manifold is sufficiently smooth so that the training process of our MSEDNN can be effectively implemented only using few labeled data. Our proposed network contains a body joint detector and a human pose regressor that are jointly trained. Extensive experiments conducted on four databases show that our proposed MSEDNN can achieve the best recovery performance compared with the state-of-the-art methods.

Multireference adaptive noise canceling applied to the EEG.

PubMed

James, C J; Hagan, M T; Jones, R D; Bones, P J; Carroll, G J

1997-08-01

The technique of multireference adaptive noise canceling (MRANC) is applied to enhance transient nonstationarities in the electroeancephalogram (EEG), with the adaptation implemented by means of a multilayer-perception artificial neural network (ANN). The method was applied to recorded EEG segments and the performance on documented nonstationarities recorded. The results show that the neural network (nonlinear) gives an improvement in performance (i.e., signal-to-noise ratio (SNR) of the nonstationarities) compared to a linear implementation of MRANC. In both cases an improvement in the SNR was obtained. The advantage of the spatial filtering aspect of MRANC is highlighted when the performance of MRANC is compared to that of the inverse auto-regressive filtering of the EEG, a purely temporal filter.

A neuro-fuzzy architecture for real-time applications

NASA Technical Reports Server (NTRS)

Ramamoorthy, P. A.; Huang, Song

1992-01-01

Neural networks and fuzzy expert systems perform the same task of functional mapping using entirely different approaches. Each approach has certain unique features. The ability to learn specific input-output mappings from large input/output data possibly corrupted by noise and the ability to adapt or continue learning are some important features of neural networks. Fuzzy expert systems are known for their ability to deal with fuzzy information and incomplete/imprecise data in a structured, logical way. Since both of these techniques implement the same task (that of functional mapping--we regard 'inferencing' as one specific category under this class), a fusion of the two concepts that retains their unique features while overcoming their individual drawbacks will have excellent applications in the real world. In this paper, we arrive at a new architecture by fusing the two concepts. The architecture has the trainability/adaptibility (based on input/output observations) property of the neural networks and the architectural features that are unique to fuzzy expert systems. It also does not require specific information such as fuzzy rules, defuzzification procedure used, etc., though any such information can be integrated into the architecture. We show that this architecture can provide better performance than is possible from a single two or three layer feedforward neural network. Further, we show that this new architecture can be used as an efficient vehicle for hardware implementation of complex fuzzy expert systems for real-time applications. A numerical example is provided to show the potential of this approach.

Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence.

PubMed

Khan, Abhinandan; Mandal, Sudip; Pal, Rajat Kumar; Saha, Goutam

2016-01-01

We have proposed a methodology for the reverse engineering of biologically plausible gene regulatory networks from temporal genetic expression data. We have used established information and the fundamental mathematical theory for this purpose. We have employed the Recurrent Neural Network formalism to extract the underlying dynamics present in the time series expression data accurately. We have introduced a new hybrid swarm intelligence framework for the accurate training of the model parameters. The proposed methodology has been first applied to a small artificial network, and the results obtained suggest that it can produce the best results available in the contemporary literature, to the best of our knowledge. Subsequently, we have implemented our proposed framework on experimental (in vivo) datasets. Finally, we have investigated two medium sized genetic networks (in silico) extracted from GeneNetWeaver, to understand how the proposed algorithm scales up with network size. Additionally, we have implemented our proposed algorithm with half the number of time points. The results indicate that a reduction of 50% in the number of time points does not have an effect on the accuracy of the proposed methodology significantly, with a maximum of just over 15% deterioration in the worst case.

A memory efficient implementation scheme of Gauss error function in a Laguerre-Volterra network for neuroprosthetic devices

NASA Astrophysics Data System (ADS)

Li, Will X. Y.; Cui, Ke; Zhang, Wei

2017-04-01

Cognitive neural prosthesis is a manmade device which can be used to restore or compensate for lost human cognitive modalities. The generalized Laguerre-Volterra (GLV) network serves as a robust mathematical underpinning for the development of such prosthetic instrument. In this paper, a hardware implementation scheme of Gauss error function for the GLV network targeting reconfigurable platforms is reported. Numerical approximations are formulated which transform the computation of nonelementary function into combinational operations of elementary functions, and memory-intensive look-up table (LUT) based approaches can therefore be circumvented. The computational precision can be made adjustable with the utilization of an error compensation scheme, which is proposed based on the experimental observation of the mathematical characteristics of the error trajectory. The precision can be further customizable by exploiting the run-time characteristics of the reconfigurable system. Compared to the polynomial expansion based implementation scheme, the utilization of slice LUTs, occupied slices, and DSP48E1s on a Xilinx XC6VLX240T field-programmable gate array has decreased by 94.2%, 94.1%, and 90.0%, respectively. While compared to the look-up table based scheme, 1.0 ×1017 bits of storage can be spared under the maximum allowable error of 1.0 ×10-3 . The proposed implementation scheme can be employed in the study of large-scale neural ensemble activity and in the design and development of neural prosthetic device.

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

PubMed

Bernal, Javier; Torres-Jimenez, Jose

2015-01-01

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

Artificial Neural Network for Total Laboratory Automation to Improve the Management of Sample Dilution.

PubMed

Ialongo, Cristiano; Pieri, Massimo; Bernardini, Sergio

2017-02-01

Diluting a sample to obtain a measure within the analytical range is a common task in clinical laboratories. However, for urgent samples, it can cause delays in test reporting, which can put patients' safety at risk. The aim of this work is to show a simple artificial neural network that can be used to make it unnecessary to predilute a sample using the information available through the laboratory information system. Particularly, the Multilayer Perceptron neural network built on a data set of 16,106 cardiac troponin I test records produced a correct inference rate of 100% for samples not requiring predilution and 86.2% for those requiring predilution. With respect to the inference reliability, the most relevant inputs were the presence of a cardiac event or surgery and the result of the previous assay. Therefore, such an artificial neural network can be easily implemented into a total automation framework to sensibly reduce the turnaround time of critical orders delayed by the operation required to retrieve, dilute, and retest the sample.

Short-term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs

DOE PAGES

Buitrago, Jaime; Asfour, Shihab

2017-01-01

Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable input (NARX). The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input.more » Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. Finally, the New England electrical load data are used to train and validate the forecast prediction.« less

Short-term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs

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

Buitrago, Jaime; Asfour, Shihab

Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable input (NARX). The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input.more » Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. Finally, the New England electrical load data are used to train and validate the forecast prediction.« less

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.

A neural networks-based hybrid routing protocol for wireless mesh networks.

PubMed

Kojić, Nenad; Reljin, Irini; Reljin, Branimir

2012-01-01

The networking infrastructure of wireless mesh networks (WMNs) is decentralized and relatively simple, but they can display reliable functioning performance while having good redundancy. WMNs provide Internet access for fixed and mobile wireless devices. Both in urban and rural areas they provide users with high-bandwidth networks over a specific coverage area. The main problems affecting these networks are changes in network topology and link quality. In order to provide regular functioning, the routing protocol has the main influence in WMN implementations. In this paper we suggest a new routing protocol for WMN, based on good results of a proactive and reactive routing protocol, and for that reason it can be classified as a hybrid routing protocol. The proposed solution should avoid flooding and creating the new routing metric. We suggest the use of artificial logic-i.e., neural networks (NNs). This protocol is based on mobile agent technologies controlled by a Hopfield neural network. In addition to this, our new routing metric is based on multicriteria optimization in order to minimize delay and blocking probability (rejected packets or their retransmission). The routing protocol observes real network parameters and real network environments. As a result of artificial logic intelligence, the proposed routing protocol should maximize usage of network resources and optimize network performance.

A Neural Networks-Based Hybrid Routing Protocol for Wireless Mesh Networks

PubMed Central

Kojić, Nenad; Reljin, Irini; Reljin, Branimir

2012-01-01

The networking infrastructure of wireless mesh networks (WMNs) is decentralized and relatively simple, but they can display reliable functioning performance while having good redundancy. WMNs provide Internet access for fixed and mobile wireless devices. Both in urban and rural areas they provide users with high-bandwidth networks over a specific coverage area. The main problems affecting these networks are changes in network topology and link quality. In order to provide regular functioning, the routing protocol has the main influence in WMN implementations. In this paper we suggest a new routing protocol for WMN, based on good results of a proactive and reactive routing protocol, and for that reason it can be classified as a hybrid routing protocol. The proposed solution should avoid flooding and creating the new routing metric. We suggest the use of artificial logic—i.e., neural networks (NNs). This protocol is based on mobile agent technologies controlled by a Hopfield neural network. In addition to this, our new routing metric is based on multicriteria optimization in order to minimize delay and blocking probability (rejected packets or their retransmission). The routing protocol observes real network parameters and real network environments. As a result of artificial logic intelligence, the proposed routing protocol should maximize usage of network resources and optimize network performance. PMID:22969360

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.

An introduction to deep learning on biological sequence data: examples and solutions.

PubMed

Jurtz, Vanessa Isabell; Johansen, Alexander Rosenberg; Nielsen, Morten; Almagro Armenteros, Jose Juan; Nielsen, Henrik; Sønderby, Casper Kaae; Winther, Ole; Sønderby, Søren Kaae

2017-11-15

Deep neural network architectures such as convolutional and long short-term memory networks have become increasingly popular as machine learning tools during the recent years. The availability of greater computational resources, more data, new algorithms for training deep models and easy to use libraries for implementation and training of neural networks are the drivers of this development. The use of deep learning has been especially successful in image recognition; and the development of tools, applications and code examples are in most cases centered within this field rather than within biology. Here, we aim to further the development of deep learning methods within biology by providing application examples and ready to apply and adapt code templates. Given such examples, we illustrate how architectures consisting of convolutional and long short-term memory neural networks can relatively easily be designed and trained to state-of-the-art performance on three biological sequence problems: prediction of subcellular localization, protein secondary structure and the binding of peptides to MHC Class II molecules. All implementations and datasets are available online to the scientific community at https://github.com/vanessajurtz/lasagne4bio. skaaesonderby@gmail.com. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Neural networks for continuous online learning and control.

PubMed

Choy, Min Chee; Srinivasan, Dipti; Cheu, Ruey Long

2006-11-01

This paper proposes a new hybrid neural network (NN) model that employs a multistage online learning process to solve the distributed control problem with an infinite horizon. Various techniques such as reinforcement learning and evolutionary algorithm are used to design the multistage online learning process. For this paper, the infinite horizon distributed control problem is implemented in the form of real-time distributed traffic signal control for intersections in a large-scale traffic network. The hybrid neural network model is used to design each of the local traffic signal controllers at the respective intersections. As the state of the traffic network changes due to random fluctuation of traffic volumes, the NN-based local controllers will need to adapt to the changing dynamics in order to provide effective traffic signal control and to prevent the traffic network from becoming overcongested. Such a problem is especially challenging if the local controllers are used for an infinite horizon problem where online learning has to take place continuously once the controllers are implemented into the traffic network. A comprehensive simulation model of a section of the Central Business District (CBD) of Singapore has been developed using PARAMICS microscopic simulation program. As the complexity of the simulation increases, results show that the hybrid NN model provides significant improvement in traffic conditions when evaluated against an existing traffic signal control algorithm as well as a new, continuously updated simultaneous perturbation stochastic approximation-based neural network (SPSA-NN). Using the hybrid NN model, the total mean delay of each vehicle has been reduced by 78% and the total mean stoppage time of each vehicle has been reduced by 84% compared to the existing traffic signal control algorithm. This shows the efficacy of the hybrid NN model in solving large-scale traffic signal control problem in a distributed manner. Also, it indicates the possibility of using the hybrid NN model for other applications that are similar in nature as the infinite horizon distributed control problem.

Intelligent manipulation technique for multi-branch robotic systems

NASA Technical Reports Server (NTRS)

Chen, Alexander Y. K.; Chen, Eugene Y. S.

1990-01-01

New analytical development in kinematics planning is reported. The INtelligent KInematics Planner (INKIP) consists of the kinematics spline theory and the adaptive logic annealing process. Also, a novel framework of robot learning mechanism is introduced. The FUzzy LOgic Self Organized Neural Networks (FULOSONN) integrates fuzzy logic in commands, control, searching, and reasoning, the embedded expert system for nominal robotics knowledge implementation, and the self organized neural networks for the dynamic knowledge evolutionary process. Progress on the mechanical construction of SRA Advanced Robotic System (SRAARS) and the real time robot vision system is also reported. A decision was made to incorporate the Local Area Network (LAN) technology in the overall communication system.

A feedforward artificial neural network based on quantum effect vector-matrix multipliers.

PubMed

Levy, H J; McGill, T C

1993-01-01

The vector-matrix multiplier is the engine of many artificial neural network implementations because it can simulate the way in which neurons collect weighted input signals from a dendritic arbor. A new technology for building analog weighting elements that is theoretically capable of densities and speeds far beyond anything that conventional VLSI in silicon could ever offer is presented. To illustrate the feasibility of such a technology, a small three-layer feedforward prototype network with five binary neurons and six tri-state synapses was built and used to perform all of the fundamental logic functions: XOR, AND, OR, and NOT.

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

Kolbasin, V. A.; Ivanov, A. I.; Pedash, V. Y.

The two pulse shape discrimination methods were implemented in real-time. The pulse gradient analysis method was implemented programmatically on PC. The method based on artificial neural network was programmatically implemented using CUDA platform. It is shown that both implementations can provide up to 10{sup 6} pulses per second processing performance. The results for pulse shape discrimination using polycrystalline stilbene and LiF detectors were shown. (authors)

Neural Generalized Predictive Control: A Newton-Raphson Implementation

NASA Technical Reports Server (NTRS)

Soloway, Donald; Haley, Pamela J.

1997-01-01

An efficient implementation of Generalized Predictive Control using a multi-layer feedforward neural network as the plant's nonlinear model is presented. In using Newton-Raphson as the optimization algorithm, the number of iterations needed for convergence is significantly reduced from other techniques. The main cost of the Newton-Raphson algorithm is in the calculation of the Hessian, but even with this overhead the low iteration numbers make Newton-Raphson faster than other techniques and a viable algorithm for real-time control. This paper presents a detailed derivation of the Neural Generalized Predictive Control algorithm with Newton-Raphson as the minimization algorithm. Simulation results show convergence to a good solution within two iterations and timing data show that real-time control is possible. Comments about the algorithm's implementation are also included.

Inner and Outer Recursive Neural Networks for Chemoinformatics Applications.

PubMed

Urban, Gregor; Subrahmanya, Niranjan; Baldi, Pierre

2018-02-26

Deep learning methods applied to problems in chemoinformatics often require the use of recursive neural networks to handle data with graphical structure and variable size. We present a useful classification of recursive neural network approaches into two classes, the inner and outer approach. The inner approach uses recursion inside the underlying graph, to essentially "crawl" the edges of the graph, while the outer approach uses recursion outside the underlying graph, to aggregate information over progressively longer distances in an orthogonal direction. We illustrate the inner and outer approaches on several examples. More importantly, we provide open-source implementations [available at www.github.com/Chemoinformatics/InnerOuterRNN and cdb.ics.uci.edu ] for both approaches in Tensorflow which can be used in combination with training data to produce efficient models for predicting the physical, chemical, and biological properties of small molecules.

Adaptive model predictive process control using neural networks

DOEpatents

Buescher, K.L.; Baum, C.C.; Jones, R.D.

1997-08-19

A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data. 46 figs.

Adaptive model predictive process control using neural networks

DOEpatents

Buescher, Kevin L.; Baum, Christopher C.; Jones, Roger D.

1997-01-01

A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data.

Vanishing points detection using combination of fast Hough transform and deep learning

NASA Astrophysics Data System (ADS)

Sheshkus, Alexander; Ingacheva, Anastasia; Nikolaev, Dmitry

2018-04-01

In this paper we propose a novel method for vanishing points detection based on convolutional neural network (CNN) approach and fast Hough transform algorithm. We show how to determine fast Hough transform neural network layer and how to use it in order to increase usability of the neural network approach to the vanishing point detection task. Our algorithm includes CNN with consequence of convolutional and fast Hough transform layers. We are building estimator for distribution of possible vanishing points in the image. This distribution can be used to find candidates of vanishing point. We provide experimental results from tests of suggested method using images collected from videos of road trips. Our approach shows stable result on test images with different projective distortions and noise. Described approach can be effectively implemented for mobile GPU and CPU.

A Pruning Neural Network Model in Credit Classification Analysis

PubMed Central

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

2018-01-01

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

An architectural approach to create self organizing control systems for practical autonomous robots

NASA Technical Reports Server (NTRS)

Greiner, Helen

1991-01-01

For practical industrial applications, the development of trainable robots is an important and immediate objective. Therefore, the developing of flexible intelligence directly applicable to training is emphasized. It is generally agreed upon by the AI community that the fusion of expert systems, neural networks, and conventionally programmed modules (e.g., a trajectory generator) is promising in the quest for autonomous robotic intelligence. Autonomous robot development is hindered by integration and architectural problems. Some obstacles towards the construction of more general robot control systems are as follows: (1) Growth problem; (2) Software generation; (3) Interaction with environment; (4) Reliability; and (5) Resource limitation. Neural networks can be successfully applied to some of these problems. However, current implementations of neural networks are hampered by the resource limitation problem and must be trained extensively to produce computationally accurate output. A generalization of conventional neural nets is proposed, and an architecture is offered in an attempt to address the above problems.

Neural Nets for Generalization and Classification: Comment on Staddon and Reid (1990).

ERIC Educational Resources Information Center

Shepard, Roger N.

1990-01-01

The neural net model of J. E. R. Staddon and A. K. Reid (1990) explains exponential and Gaussian generalization gradients in the same way as the diffusion model of R. N. Shepard (1958). The cognitive generalization theory of Shepard (1987), also implemented as a connectionist network, goes beyond both models in accounting for classification…

A Compact Optical Instrument with Artificial Neural Network for pH Determination

PubMed Central

Capel-Cuevas, Sonia; López-Ruiz, Nuria; Martinez-Olmos, Antonio; Cuéllar, Manuel P.; Pegalajar, Maria del Carmen; Palma, Alberto José; de Orbe-Payá, Ignacio; Capitán-Vallvey, Luis Fermin

2012-01-01

The aim of this work was the determination of pH with a sensor array-based optical portable instrument. This sensor array consists of eleven membranes with selective colour changes at different pH intervals. The method for the pH calculation is based on the implementation of artificial neural networks that use the responses of the membranes to generate a final pH value. A multi-objective algorithm was used to select the minimum number of sensing elements required to achieve an accurate pH determination from the neural network, and also to minimise the network size. This helps to minimise instrument and array development costs and save on microprocessor energy consumption. A set of artificial neural networks that fulfils these requirements is proposed using different combinations of the membranes in the sensor array, and is evaluated in terms of accuracy and reliability. In the end, the network including the response of the eleven membranes in the sensor was selected for validation in the instrument prototype because of its high accuracy. The performance of the instrument was evaluated by measuring the pH of a large set of real samples, showing that high precision can be obtained in the full range. PMID:22778668

VLSI circuits implementing computational models of neocortical circuits.

PubMed

Wijekoon, Jayawan H B; Dudek, Piotr

2012-09-15

This paper overviews the design and implementation of three neuromorphic integrated circuits developed for the COLAMN ("Novel Computing Architecture for Cognitive Systems based on the Laminar Microcircuitry of the Neocortex") project. The circuits are implemented in a standard 0.35 μm CMOS technology and include spiking and bursting neuron models, and synapses with short-term (facilitating/depressing) and long-term (STDP and dopamine-modulated STDP) dynamics. They enable execution of complex nonlinear models in accelerated-time, as compared with biology, and with low power consumption. The neural dynamics are implemented using analogue circuit techniques, with digital asynchronous event-based input and output. The circuits provide configurable hardware blocks that can be used to simulate a variety of neural networks. The paper presents experimental results obtained from the fabricated devices, and discusses the advantages and disadvantages of the analogue circuit approach to computational neural modelling. Copyright © 2012 Elsevier B.V. All rights reserved.

Neural network hardware and software solutions for sorting of waste plastics for recycling

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

Stanton, S.L.; Alam, M.K.; Hebner, G.A.

1992-12-31

While plastic recycling efforts have expanded during the past several years, the cost of recovering plastics is still a major impediment for recyclers. Several factors contribute to the prohibitive cost of recycled resins, including the present low marketability of products made with mixed recycled materials, and costs of collecting, sorting and reprocessing plastic materials. A method for automatic sorting of post-consumer plastics into pure polymer streams is needed to overcome the inaccuracies and low product throughput of the currently used method of hand sorting of waste plastics for recycling. The Society of Plastics has designated seven categories as recyclable: Polyethylenemore » terephthalate (PET); High Density Polyethylene (HDPE); Polyvinyl Chloride (PVC); Low Density Polyethylene (LDPE); Polypropylene (PP); Polystyrene (PS); and Other (mixtures, layered items, etc.). With these categories in mind, a system for sorting of waste plastics using near-infrared reflectance spectra and a backpropagation neural network classifier has been developed. A solution has been demonstrated in the laboratory using a high resolution, and relatively slow instrument. A faster instrument is being developed at this time. Neural network hardware options have been evaluated for use in a real-time industrial system. In the lab, a Fourier transform Near Infrared (FT-NIR) scanning spectrometer was used to gather reflectance data from various locations on samples of actual waste plastics. Neural networks were trained off-line with this data using the NeuralWorks Professional II Plus software package on a SparcStation 2. One of the successfully trained networks was used to compare the neural accelerator hardware options available. The results of running this ``worst case`` network on the neural network hardware will be presented. The AT&T ANNA chip and the Intel 80170NX chip development system were used to determine the ease of implementation and accuracies for this network.« less

Neural network hardware and software solutions for sorting of waste plastics for recycling

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

Stanton, S.L.; Alam, M.K.; Hebner, G.A.

1992-01-01

While plastic recycling efforts have expanded during the past several years, the cost of recovering plastics is still a major impediment for recyclers. Several factors contribute to the prohibitive cost of recycled resins, including the present low marketability of products made with mixed recycled materials, and costs of collecting, sorting and reprocessing plastic materials. A method for automatic sorting of post-consumer plastics into pure polymer streams is needed to overcome the inaccuracies and low product throughput of the currently used method of hand sorting of waste plastics for recycling. The Society of Plastics has designated seven categories as recyclable: Polyethylenemore » terephthalate (PET); High Density Polyethylene (HDPE); Polyvinyl Chloride (PVC); Low Density Polyethylene (LDPE); Polypropylene (PP); Polystyrene (PS); and Other (mixtures, layered items, etc.). With these categories in mind, a system for sorting of waste plastics using near-infrared reflectance spectra and a backpropagation neural network classifier has been developed. A solution has been demonstrated in the laboratory using a high resolution, and relatively slow instrument. A faster instrument is being developed at this time. Neural network hardware options have been evaluated for use in a real-time industrial system. In the lab, a Fourier transform Near Infrared (FT-NIR) scanning spectrometer was used to gather reflectance data from various locations on samples of actual waste plastics. Neural networks were trained off-line with this data using the NeuralWorks Professional II Plus software package on a SparcStation 2. One of the successfully trained networks was used to compare the neural accelerator hardware options available. The results of running this worst case'' network on the neural network hardware will be presented. The AT T ANNA chip and the Intel 80170NX chip development system were used to determine the ease of implementation and accuracies for this network.« less

Application of Artificial Neural Networks and Singular-Spectral Analysis in Forecasting the Daily Traffic in the Moscow Metro

NASA Astrophysics Data System (ADS)

Ivanov, Victor; Osetrov, Evgenii

2018-02-01

In this paper, we investigate the possibility of applying various approaches to solving the problem of medium-term forecasting of daily passenger traffic volumes in the Moscow metro (MM): 1) on the basis of artificial neural networks (ANN); 2) using the singular-spectral analysis implemented in the package "Caterpillar"-SSA; 3) sharing the ANN and the "Caterpillar"-SSA approach. We demonstrate that the developed methods and algorithms allow us to conduct medium-term forecasting of passenger traffic in the MM with reasonable accuracy.

Advanced microprocessor based power protection system using artificial neural network techniques

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

Chen, Z.; Kalam, A.; Zayegh, A.

This paper describes an intelligent embedded microprocessor based system for fault classification in power system protection system using advanced 32-bit microprocessor technology. The paper demonstrates the development of protective relay to provide overcurrent protection schemes for fault detection. It also describes a method for power fault classification in three-phase system based on the use of neural network technology. The proposed design is implemented and tested on a single line three phase power system in power laboratory. Both the hardware and software development are described in detail.

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

NASA Astrophysics Data System (ADS)

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

2018-03-01

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

Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes.

PubMed

Durant, Thomas J S; Olson, Eben M; Schulz, Wade L; Torres, Richard

2017-12-01

Morphologic profiling of the erythrocyte population is a widely used and clinically valuable diagnostic modality, but one that relies on a slow manual process associated with significant labor cost and limited reproducibility. Automated profiling of erythrocytes from digital images by capable machine learning approaches would augment the throughput and value of morphologic analysis. To this end, we sought to evaluate the performance of leading implementation strategies for convolutional neural networks (CNNs) when applied to classification of erythrocytes based on morphology. Erythrocytes were manually classified into 1 of 10 classes using a custom-developed Web application. Using recent literature to guide architectural considerations for neural network design, we implemented a "very deep" CNN, consisting of >150 layers, with dense shortcut connections. The final database comprised 3737 labeled cells. Ensemble model predictions on unseen data demonstrated a harmonic mean of recall and precision metrics of 92.70% and 89.39%, respectively. Of the 748 cells in the test set, 23 misclassification errors were made, with a correct classification frequency of 90.60%, represented as a harmonic mean across the 10 morphologic classes. These findings indicate that erythrocyte morphology profiles could be measured with a high degree of accuracy with "very deep" CNNs. Further, these data support future efforts to expand classes and optimize practical performance in a clinical environment as a prelude to full implementation as a clinical tool. © 2017 American Association for Clinical Chemistry.

Medical image processing using neural networks based on multivalued and universal binary neurons

NASA Astrophysics Data System (ADS)

Aizenberg, Igor N.; Aizenberg, Naum N.; Gotko, Eugen S.; Sochka, Vladimir A.

1998-06-01

Cellular Neural Networks (CNN) has become a very good mean for solution of the different kind of image processing problems. CNN based on multi-valued neurons (CNN-MVN) and CNN based on universal binary neurons (CNN-UBN) are the specific kinds of the CNN. MVN and UBN are neurons with complex-valued weights, and complex internal arithmetic. Their main feature is possibility of implementation of the arbitrary mapping between inputs and output described by the MVN, and arbitrary (not only threshold) Boolean function (UBN). Great advantage of the CNN is possibility of implementation of the any linear and many non-linear filters in spatial domain. Together with noise removing using CNN it is possible to implement filters, which can amplify high and medium frequencies. These filters are a very good mean for solution of the enhancement problem, and problem of details extraction against complex background. So, CNN make it possible to organize all the processing process from filtering until extraction of the important details. Organization of this process for medical image processing is considered in the paper. A major attention will be concentrated on the processing of the x-ray and ultrasound images corresponding to different oncology (or closed to oncology) pathologies. Additionally we will consider new structure of the neural network for solution of the problem of differential diagnostics of breast cancer.

Analyzing large-scale spiking neural data with HRLAnalysis™

PubMed Central

Thibeault, Corey M.; O'Brien, Michael J.; Srinivasa, Narayan

2014-01-01

The additional capabilities provided by high-performance neural simulation environments and modern computing hardware has allowed for the modeling of increasingly larger spiking neural networks. This is important for exploring more anatomically detailed networks but the corresponding accumulation in data can make analyzing the results of these simulations difficult. This is further compounded by the fact that many existing analysis packages were not developed with large spiking data sets in mind. Presented here is a software suite developed to not only process the increased amount of spike-train data in a reasonable amount of time, but also provide a user friendly Python interface. We describe the design considerations, implementation and features of the HRLAnalysis™ suite. In addition, performance benchmarks demonstrating the speedup of this design compared to a published Python implementation are also presented. The result is a high-performance analysis toolkit that is not only usable and readily extensible, but also straightforward to interface with existing Python modules. PMID:24634655

Audio Classification in Speech and Music: A Comparison between a Statistical and a Neural Approach

NASA Astrophysics Data System (ADS)

Bugatti, Alessandro; Flammini, Alessandra; Migliorati, Pierangelo

2002-12-01

We focus the attention on the problem of audio classification in speech and music for multimedia applications. In particular, we present a comparison between two different techniques for speech/music discrimination. The first method is based on Zero crossing rate and Bayesian classification. It is very simple from a computational point of view, and gives good results in case of pure music or speech. The simulation results show that some performance degradation arises when the music segment contains also some speech superimposed on music, or strong rhythmic components. To overcome these problems, we propose a second method, that uses more features, and is based on neural networks (specifically a multi-layer Perceptron). In this case we obtain better performance, at the expense of a limited growth in the computational complexity. In practice, the proposed neural network is simple to be implemented if a suitable polynomial is used as the activation function, and a real-time implementation is possible even if low-cost embedded systems are used.

Wishart Deep Stacking Network for Fast POLSAR Image Classification.

PubMed

Jiao, Licheng; Liu, Fang

2016-05-11

Inspired by the popular deep learning architecture - Deep Stacking Network (DSN), a specific deep model for polarimetric synthetic aperture radar (POLSAR) image classification is proposed in this paper, which is named as Wishart Deep Stacking Network (W-DSN). First of all, a fast implementation of Wishart distance is achieved by a special linear transformation, which speeds up the classification of POLSAR image and makes it possible to use this polarimetric information in the following Neural Network (NN). Then a single-hidden-layer neural network based on the fast Wishart distance is defined for POLSAR image classification, which is named as Wishart Network (WN) and improves the classification accuracy. Finally, a multi-layer neural network is formed by stacking WNs, which is in fact the proposed deep learning architecture W-DSN for POLSAR image classification and improves the classification accuracy further. In addition, the structure of WN can be expanded in a straightforward way by adding hidden units if necessary, as well as the structure of the W-DSN. As a preliminary exploration on formulating specific deep learning architecture for POLSAR image classification, the proposed methods may establish a simple but clever connection between POLSAR image interpretation and deep learning. The experiment results tested on real POLSAR image show that the fast implementation of Wishart distance is very efficient (a POLSAR image with 768000 pixels can be classified in 0.53s), and both the single-hidden-layer architecture WN and the deep learning architecture W-DSN for POLSAR image classification perform well and work efficiently.

Implementing Signature Neural Networks with Spiking Neurons

PubMed Central

Carrillo-Medina, José Luis; Latorre, Roberto

2016-01-01

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

Implementing Signature Neural Networks with Spiking Neurons.

PubMed

Carrillo-Medina, José Luis; Latorre, Roberto

2016-01-01

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

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.

Hadoop neural network for parallel and distributed feature selection.

PubMed

Hodge, Victoria J; O'Keefe, Simon; Austin, Jim

2016-06-01

In this paper, we introduce a theoretical basis for a Hadoop-based neural network for parallel and distributed feature selection in Big Data sets. It is underpinned by an associative memory (binary) neural network which is highly amenable to parallel and distributed processing and fits with the Hadoop paradigm. There are many feature selectors described in the literature which all have various strengths and weaknesses. We present the implementation details of five feature selection algorithms constructed using our artificial neural network framework embedded in Hadoop YARN. Hadoop allows parallel and distributed processing. Each feature selector can be divided into subtasks and the subtasks can then be processed in parallel. Multiple feature selectors can also be processed simultaneously (in parallel) allowing multiple feature selectors to be compared. We identify commonalities among the five features selectors. All can be processed in the framework using a single representation and the overall processing can also be greatly reduced by only processing the common aspects of the feature selectors once and propagating these aspects across all five feature selectors as necessary. This allows the best feature selector and the actual features to select to be identified for large and high dimensional data sets through exploiting the efficiency and flexibility of embedding the binary associative-memory neural network in Hadoop. Copyright © 2015 The Authors. Published by Elsevier Ltd.. All rights reserved.

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.

Neural Architecture of Selective Stopping Strategies: Distinct Brain Activity Patterns Are Associated with Attentional Capture But Not with Outright Stopping.

PubMed

Sebastian, Alexandra; Rössler, Kora; Wibral, Michael; Mobascher, Arian; Lieb, Klaus; Jung, Patrick; Tüscher, Oliver

2017-10-04

In stimulus-selective stop-signal tasks, the salient stop signal needs attentional processing before genuine response inhibition is completed. Differential prefrontal involvement in attentional capture and response inhibition has been linked to the right inferior frontal junction (IFJ) and ventrolateral prefrontal cortex (VLPFC), respectively. Recently, it has been suggested that stimulus-selective stopping may be accomplished by the following different strategies: individuals may selectively inhibit their response only upon detecting a stop signal (independent discriminate then stop strategy) or unselectively whenever detecting a stop or attentional capture signal (stop then discriminate strategy). Alternatively, the discrimination process of the critical signal (stop vs attentional capture signal) may interact with the go process (dependent discriminate then stop strategy). Those different strategies might differentially involve attention- and stopping-related processes that might be implemented by divergent neural networks. This should lead to divergent activation patterns and, if disregarded, interfere with analyses in neuroimaging studies. To clarify this crucial issue, we studied 87 human participants of both sexes during a stimulus-selective stop-signal task and performed strategy-dependent functional magnetic resonance imaging analyses. We found that, regardless of the strategy applied, outright stopping displayed indistinguishable brain activation patterns. However, during attentional capture different strategies resulted in divergent neural activation patterns with variable activation of right IFJ and bilateral VLPFC. In conclusion, the neural network involved in outright stopping is ubiquitous and independent of strategy, while different strategies impact on attention-related processes and underlying neural network usage. Strategic differences should therefore be taken into account particularly when studying attention-related processes in stimulus-selective stopping. SIGNIFICANCE STATEMENT Dissociating inhibition from attention has been a major challenge for the cognitive neuroscience of executive functions. Selective stopping tasks have been instrumental in addressing this question. However, recent theoretical, cognitive and behavioral research suggests that different strategies are applied in successful execution of the task. The underlying strategy-dependent neural networks might differ substantially. Here, we show evidence that, regardless of the strategy used, the neural network involved in outright stopping is ubiquitous. However, significant differences can only be found in the attention-related processes underlying those different strategies. Thus, when studying attentional processing of salient stop signals, strategic differences should be considered. In contrast, the neural networks implementing outright stopping seem less or not at all affected by strategic differences. Copyright © 2017 the authors 0270-6474/17/379786-10$15.00/0.

Incomplete fuzzy data processing systems using artificial neural network

NASA Technical Reports Server (NTRS)

Patyra, Marek J.

1992-01-01

In this paper, the implementation of a fuzzy data processing system using an artificial neural network (ANN) is discussed. The binary representation of fuzzy data is assumed, where the universe of discourse is decartelized into n equal intervals. The value of a membership function is represented by a binary number. It is proposed that incomplete fuzzy data processing be performed in two stages. The first stage performs the 'retrieval' of incomplete fuzzy data, and the second stage performs the desired operation on the retrieval data. The method of incomplete fuzzy data retrieval is proposed based on the linear approximation of missing values of the membership function. The ANN implementation of the proposed system is presented. The system was computationally verified and showed a relatively small total error.

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation.

PubMed

Camuñas-Mesa, Luis A; Domínguez-Cordero, Yaisel L; Linares-Barranco, Alejandro; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2018-01-01

Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network.

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation

PubMed Central

Camuñas-Mesa, Luis A.; Domínguez-Cordero, Yaisel L.; Linares-Barranco, Alejandro; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2018-01-01

Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network. PMID:29515349

Surface inspection of flat products by means of texture analysis: on-line implementation using neural networks

NASA Astrophysics Data System (ADS)

Fernandez, Carlos; Platero, Carlos; Campoy, Pascual; Aracil, Rafael

1994-11-01

This paper describes some texture-based techniques that can be applied to quality assessment of flat products continuously produced (metal strips, wooden surfaces, cork, textile products, ...). Since the most difficult task is that of inspecting for product appearance, human-like inspection ability is required. A common feature to all these products is the presence of non- deterministic texture on their surfaces. Two main subjects are discussed: statistical techniques for both surface finishing determination and surface defect analysis as well as real-time implementation for on-line inspection in high-speed applications. For surface finishing determination a Gray Level Difference technique is presented to perform over low resolution images, that is, no-zoomed images. Defect analysis is performed by means of statistical texture analysis over defective portions of the surface. On-line implementation is accomplished by means of neural networks. When a defect arises, textural analysis is applied which result in a data-vector, acting as input of a neural net, previously trained in a supervised way. This approach tries to reach on-line performance in automated visual inspection applications when texture is presented in flat product surfaces.

Using neural networks and Dyna algorithm for integrated planning, reacting and learning in systems

NASA Technical Reports Server (NTRS)

Lima, Pedro; Beard, Randal

1992-01-01

The traditional AI answer to the decision making problem for a robot is planning. However, planning is usually CPU-time consuming, depending on the availability and accuracy of a world model. The Dyna system generally described in earlier work, uses trial and error to learn a world model which is simultaneously used to plan reactions resulting in optimal action sequences. It is an attempt to integrate planning, reactive, and learning systems. The architecture of Dyna is presented. The different blocks are described. There are three main components of the system. The first is the world model used by the robot for internal world representation. The input of the world model is the current state and the action taken in the current state. The output is the corresponding reward and resulting state. The second module in the system is the policy. The policy observes the current state and outputs the action to be executed by the robot. At the beginning of program execution, the policy is stochastic and through learning progressively becomes deterministic. The policy decides upon an action according to the output of an evaluation function, which is the third module of the system. The evaluation function takes the following as input: the current state of the system, the action taken in that state, the resulting state, and a reward generated by the world which is proportional to the current distance from the goal state. Originally, the work proposed was as follows: (1) to implement a simple 2-D world where a 'robot' is navigating around obstacles, to learn the path to a goal, by using lookup tables; (2) to substitute the world model and Q estimate function Q by neural networks; and (3) to apply the algorithm to a more complex world where the use of a neural network would be fully justified. In this paper, the system design and achieved results will be described. First we implement the world model with a neural network and leave Q implemented as a look up table. Next, we use a lookup table for the world model and implement the Q function with a neural net. Time limitations prevented the combination of these two approaches. The final section discusses the results and gives clues for future work.

A Squeezed Artificial Neural Network for the Symbolic Network Reliability Functions of Binary-State Networks.

PubMed

Yeh, Wei-Chang

Network reliability is an important index to the provision of useful information for decision support in the modern world. There is always a need to calculate symbolic network reliability functions (SNRFs) due to dynamic and rapid changes in network parameters. In this brief, the proposed squeezed artificial neural network (SqANN) approach uses the Monte Carlo simulation to estimate the corresponding reliability of a given designed matrix from the Box-Behnken design, and then the Taguchi method is implemented to find the appropriate number of neurons and activation functions of the hidden layer and the output layer in ANN to evaluate SNRFs. According to the experimental results of the benchmark networks, the comparison appears to support the superiority of the proposed SqANN method over the traditional ANN-based approach with at least 16.6% improvement in the median absolute deviation in the cost of extra 2 s on average for all experiments.Network reliability is an important index to the provision of useful information for decision support in the modern world. There is always a need to calculate symbolic network reliability functions (SNRFs) due to dynamic and rapid changes in network parameters. In this brief, the proposed squeezed artificial neural network (SqANN) approach uses the Monte Carlo simulation to estimate the corresponding reliability of a given designed matrix from the Box-Behnken design, and then the Taguchi method is implemented to find the appropriate number of neurons and activation functions of the hidden layer and the output layer in ANN to evaluate SNRFs. According to the experimental results of the benchmark networks, the comparison appears to support the superiority of the proposed SqANN method over the traditional ANN-based approach with at least 16.6% improvement in the median absolute deviation in the cost of extra 2 s on average for all experiments.

Digital implementation of a neural network for imaging

NASA Astrophysics Data System (ADS)

Wood, Richard; McGlashan, Alex; Yatulis, Jay; Mascher, Peter; Bruce, Ian

2012-10-01

This paper outlines the design and testing of a digital imaging system that utilizes an artificial neural network with unsupervised and supervised learning to convert streaming input (real time) image space into parameter space. The primary objective of this work is to investigate the effectiveness of using a neural network to significantly reduce the information density of streaming images so that objects can be readily identified by a limited set of primary parameters and act as an enhanced human machine interface (HMI). Many applications are envisioned including use in biomedical imaging, anomaly detection and as an assistive device for the visually impaired. A digital circuit was designed and tested using a Field Programmable Gate Array (FPGA) and an off the shelf digital camera. Our results indicate that the networks can be readily trained when subject to limited sets of objects such as the alphabet. We can also separate limited object sets with rotational and positional invariance. The results also show that limited visual fields form with only local connectivity.

Assessing the Health of LiFePO4 Traction Batteries through Monotonic Echo State Networks

PubMed Central

Anseán, David; Otero, José; Couso, Inés

2017-01-01

A soft sensor is presented that approximates certain health parameters of automotive rechargeable batteries from on-vehicle measurements of current and voltage. The sensor is based on a model of the open circuit voltage curve. This last model is implemented through monotonic neural networks and estimate over-potentials arising from the evolution in time of the Lithium concentration in the electrodes of the battery. The proposed soft sensor is able to exploit the information contained in operational records of the vehicle better than the alternatives, this being particularly true when the charge or discharge currents are between moderate and high. The accuracy of the neural model has been compared to different alternatives, including data-driven statistical models, first principle-based models, fuzzy observers and other recurrent neural networks with different topologies. It is concluded that monotonic echo state networks can outperform well established first-principle models. The algorithms have been validated with automotive Li-FePO4 cells. PMID:29267219

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.

Computer Implementation and Simulation of Some Neural Networks Used in Pattern Recognition and Classification

DTIC Science & Technology

1989-03-01

8,8) REAL ARR(64), X(64), PMAT(8,8), BMAT (8,8), U(10,11) C C C * INITIALIZATION C C PRINT*,’ CARPENTER / GROSSBERG NETWORK IMPLEMENTATION’ PRINT...CONTINUE 38 FORMAT(1X,8I5) 7 DO0441I=1, 8 DO 45 J1I, 8 BMAT (I,J) = REAL(MATRIX(I,J)) 45 CONTINUE 44 CONTINUE CALL MATVEC( BMAT ,X) C C C *COMPUTE MATCHING

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.

Knowledge-Based Aircraft Automation: Managers Guide on the use of Artificial Intelligence for Aircraft Automation and Verification and Validation Approach for a Neural-Based Flight Controller

NASA Technical Reports Server (NTRS)

Broderick, Ron

1997-01-01

The ultimate goal of this report was to integrate the powerful tools of artificial intelligence into the traditional process of software development. To maintain the US aerospace competitive advantage, traditional aerospace and software engineers need to more easily incorporate the technology of artificial intelligence into the advanced aerospace systems being designed today. The future goal was to transition artificial intelligence from an emerging technology to a standard technology that is considered early in the life cycle process to develop state-of-the-art aircraft automation systems. This report addressed the future goal in two ways. First, it provided a matrix that identified typical aircraft automation applications conducive to various artificial intelligence methods. The purpose of this matrix was to provide top-level guidance to managers contemplating the possible use of artificial intelligence in the development of aircraft automation. Second, the report provided a methodology to formally evaluate neural networks as part of the traditional process of software development. The matrix was developed by organizing the discipline of artificial intelligence into the following six methods: logical, object representation-based, distributed, uncertainty management, temporal and neurocomputing. Next, a study of existing aircraft automation applications that have been conducive to artificial intelligence implementation resulted in the following five categories: pilot-vehicle interface, system status and diagnosis, situation assessment, automatic flight planning, and aircraft flight control. The resulting matrix provided management guidance to understand artificial intelligence as it applied to aircraft automation. The approach taken to develop a methodology to formally evaluate neural networks as part of the software engineering life cycle was to start with the existing software quality assurance standards and to change these standards to include neural network development. The changes were to include evaluation tools that can be applied to neural networks at each phase of the software engineering life cycle. The result was a formal evaluation approach to increase the product quality of systems that use neural networks for their implementation.

Analog hardware implementation of neocognitron networks

NASA Astrophysics Data System (ADS)

Inigo, Rafael M.; Bonde, Allen, Jr.; Holcombe, Bradford

1990-08-01

This paper deals with the analog implementation of neocognitron based neural networks. All of Fukushima''s and related work on the neocognitron is based on digital computer simulations. To fully take advantage of the power of this network paradigm an analog electronic approach is proposed. We first implemented a 6-by-6 sensor network with discrete analog components and fixed weights. The network was given weight values to recognize the characters U L and F. These characters are recognized regardless of their location on the sensor and with various levels of distortion and noise. The network performance has also shown an excellent correlation with software simulation results. Next we implemented a variable weight network which can be trained to recognize simple patterns by means of self-organization. The adaptable weights were implemented with PETs configured as voltage-controlled resistors. To implement a variable weight there must be some type of " memory" to store the weight value and hold it while the value is reinforced or incremented. Two methods were evaluated: an analog sample-hold circuit and a digital storage scheme using binary counters. The latter is preferable for VLSI implementation because it uses standard components and does not require the use of capacitors. The analog design and implementation of these small-scale networks demonstrates the feasibility of implementing more complicated ANNs in electronic hardware. The circuits developed can also be designed for VLSI implementation. 1.

Modeling positional effects of regulatory sequences with spline transformations increases prediction accuracy of deep neural networks

PubMed Central

Avsec, Žiga; Cheng, Jun; Gagneur, Julien

2018-01-01

Abstract Motivation Regulatory sequences are not solely defined by their nucleic acid sequence but also by their relative distances to genomic landmarks such as transcription start site, exon boundaries or polyadenylation site. Deep learning has become the approach of choice for modeling regulatory sequences because of its strength to learn complex sequence features. However, modeling relative distances to genomic landmarks in deep neural networks has not been addressed. Results Here we developed spline transformation, a neural network module based on splines to flexibly and robustly model distances. Modeling distances to various genomic landmarks with spline transformations significantly increased state-of-the-art prediction accuracy of in vivo RNA-binding protein binding sites for 120 out of 123 proteins. We also developed a deep neural network for human splice branchpoint based on spline transformations that outperformed the current best, already distance-based, machine learning model. Compared to piecewise linear transformation, as obtained by composition of rectified linear units, spline transformation yields higher prediction accuracy as well as faster and more robust training. As spline transformation can be applied to further quantities beyond distances, such as methylation or conservation, we foresee it as a versatile component in the genomics deep learning toolbox. Availability and implementation Spline transformation is implemented as a Keras layer in the CONCISE python package: https://github.com/gagneurlab/concise. Analysis code is available at https://github.com/gagneurlab/Manuscript_Avsec_Bioinformatics_2017. Contact avsec@in.tum.de or gagneur@in.tum.de Supplementary information Supplementary data are available at Bioinformatics online. PMID:29155928

Proposed health state awareness of helicopter blades using an artificial neural network strategy

NASA Astrophysics Data System (ADS)

Lee, Andrew; Habtour, Ed; Gadsden, S. A.

2016-05-01

Structural health prognostics and diagnosis strategies can be classified as either model or signal-based. Artificial neural network strategies are popular signal-based techniques. This paper proposes the use of helicopter blades in order to study the sensitivity of an artificial neural network to structural fatigue. The experimental setup consists of a scale aluminum helicopter blade exposed to transverse vibratory excitation at the hub using single axis electrodynamic shaker. The intent of this study is to optimize an algorithm for processing high-dimensional data while retaining important information content in an effort to select input features and weights, as well as health parameters, for training a neural network. Data from accelerometers and piezoelectric transducers is collected from a known system designated as healthy. Structural damage will be introduced to different blades, which they will be designated as unhealthy. A variety of different tests will be performed to track the evolution and severity of the damage. A number of damage detection and diagnosis strategies will be implemented. A preliminary experiment was performed on aluminum cantilever beams providing a simpler model for implementation and proof of concept. Future work will look at utilizing the detection information as part of a hierarchical control system in order to mitigate structural damage and fatigue. The proposed approach may eliminate massive data storage on board of an aircraft through retaining relevant information only. The control system can then employ the relevant information to intelligently reconfigure adaptive maneuvers to avoid harmful regimes, thus, extending the life of the aircraft.

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.

Image texture segmentation using a neural network

NASA Astrophysics Data System (ADS)

Sayeh, Mohammed R.; Athinarayanan, Ragu; Dhali, Pushpuak

1992-09-01

In this paper we use a neural network called the Lyapunov associative memory (LYAM) system to segment image texture into different categories or clusters. The LYAM system is constructed by a set of ordinary differential equations which are simulated on a digital computer. The clustering can be achieved by using a single tuning parameter in the simplest model. Pattern classes are represented by the stable equilibrium states of the system. Design of the system is based on synthesizing two local energy functions, namely, the learning and recall energy functions. Before the implementation of the segmentation process, a Gauss-Markov random field (GMRF) model is applied to the raw image. This application suitably reduces the image data and prepares the texture information for the neural network process. We give a simple image example illustrating the capability of the technique. The GMRF-generated features are also used for a clustering, based on the Euclidean distance.

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.

Analog neural network control method proposed for use in a backup satellite control mode

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

Frigo, J.R.; Tilden, M.W.

1998-03-01

The authors propose to use an analog neural network controller implemented in hardware, independent of the active control system, for use in a satellite backup control mode. The controller uses coarse sun sensor inputs. The field of view of the sensors activate the neural controller, creating an analog dead band with respect to the direction of the sun on each axis. This network controls the orientation of the vehicle toward the sunlight to ensure adequate power for the system. The attitude of the spacecraft is stabilized with respect to the ambient magnetic field on orbit. This paper develops a modelmore » of the controller using real-time coarse sun sensor data and a dynamic model of a prototype system based on a satellite system. The simulation results and the feasibility of this control method for use in a satellite backup control mode are discussed.« less

Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems.

PubMed

González-Gutiérrez, Carlos; Santos, Jesús Daniel; Martínez-Zarzuela, Mario; Basden, Alistair G; Osborn, James; Díaz-Pernas, Francisco Javier; De Cos Juez, Francisco Javier

2017-06-02

Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named "CARMEN" are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances.

Enhanced robust finite-time passivity for Markovian jumping discrete-time BAM neural networks with leakage delay.

PubMed

Sowmiya, C; Raja, R; Cao, Jinde; Rajchakit, G; Alsaedi, Ahmed

2017-01-01

This paper is concerned with the problem of enhanced results on robust finite-time passivity for uncertain discrete-time Markovian jumping BAM delayed neural networks with leakage delay. By implementing a proper Lyapunov-Krasovskii functional candidate, the reciprocally convex combination method together with linear matrix inequality technique, several sufficient conditions are derived for varying the passivity of discrete-time BAM neural networks. An important feature presented in our paper is that we utilize the reciprocally convex combination lemma in the main section and the relevance of that lemma arises from the derivation of stability by using Jensen's inequality. Further, the zero inequalities help to propose the sufficient conditions for finite-time boundedness and passivity for uncertainties. Finally, the enhancement of the feasible region of the proposed criteria is shown via numerical examples with simulation to illustrate the applicability and usefulness of the proposed method.

Detection of prostate cancer on multiparametric MRI

NASA Astrophysics Data System (ADS)

Seah, Jarrel C. Y.; Tang, Jennifer S. N.; Kitchen, Andy

2017-03-01

In this manuscript, we describe our approach and methods to the ProstateX challenge, which achieved an overall AUC of 0.84 and the runner-up position. We train a deep convolutional neural network to classify lesions marked on multiparametric MRI of the prostate as clinically significant or not. We implement a novel addition to the standard convolutional architecture described as auto-windowing which is clinically inspired and designed to overcome some of the difficulties faced in MRI interpretation, where high dynamic ranges and low contrast edges may cause difficulty for traditional convolutional neural networks trained on high contrast natural imagery. We demonstrate that this system can be trained end to end and outperforms a similar architecture without such additions. Although a relatively small training set was provided, we use extensive data augmentation to prevent overfitting and transfer learning to improve convergence speed, showing that deep convolutional neural networks can be feasibly trained on small datasets.

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis.

PubMed

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang; Hu, Jianjun

2017-07-28

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster-Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions.

Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals.

PubMed

Acharya, U Rajendra; Oh, Shu Lih; Hagiwara, Yuki; Tan, Jen Hong; Adeli, Hojjat

2017-09-27

An encephalogram (EEG) is a commonly used ancillary test to aide in the diagnosis of epilepsy. The EEG signal contains information about the electrical activity of the brain. Traditionally, neurologists employ direct visual inspection to identify epileptiform abnormalities. This technique can be time-consuming, limited by technical artifact, provides variable results secondary to reader expertise level, and is limited in identifying abnormalities. Therefore, it is essential to develop a computer-aided diagnosis (CAD) system to automatically distinguish the class of these EEG signals using machine learning techniques. This is the first study to employ the convolutional neural network (CNN) for analysis of EEG signals. In this work, a 13-layer deep convolutional neural network (CNN) algorithm is implemented to detect normal, preictal, and seizure classes. The proposed technique achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively. Copyright © 2017 Elsevier Ltd. All rights reserved.

Segmented-memory recurrent neural networks.

PubMed

Chen, Jinmiao; Chaudhari, Narendra S

2009-08-01

Conventional recurrent neural networks (RNNs) have difficulties in learning long-term dependencies. To tackle this problem, we propose an architecture called segmented-memory recurrent neural network (SMRNN). A symbolic sequence is broken into segments and then presented as inputs to the SMRNN one symbol per cycle. The SMRNN uses separate internal states to store symbol-level context, as well as segment-level context. The symbol-level context is updated for each symbol presented for input. The segment-level context is updated after each segment. The SMRNN is trained using an extended real-time recurrent learning algorithm. We test the performance of SMRNN on the information latching problem, the "two-sequence problem" and the problem of protein secondary structure (PSS) prediction. Our implementation results indicate that SMRNN performs better on long-term dependency problems than conventional RNNs. Besides, we also theoretically analyze how the segmented memory of SMRNN helps learning long-term temporal dependencies and study the impact of the segment length.

Review of Medical Image Classification using the Adaptive Neuro-Fuzzy Inference System

PubMed Central

Hosseini, Monireh Sheikh; Zekri, Maryam

2012-01-01

Image classification is an issue that utilizes image processing, pattern recognition and classification methods. Automatic medical image classification is a progressive area in image classification, and it is expected to be more developed in the future. Because of this fact, automatic diagnosis can assist pathologists by providing second opinions and reducing their workload. This paper reviews the application of the adaptive neuro-fuzzy inference system (ANFIS) as a classifier in medical image classification during the past 16 years. ANFIS is a fuzzy inference system (FIS) implemented in the framework of an adaptive fuzzy neural network. It combines the explicit knowledge representation of an FIS with the learning power of artificial neural networks. The objective of ANFIS is to integrate the best features of fuzzy systems and neural networks. A brief comparison with other classifiers, main advantages and drawbacks of this classifier are investigated. PMID:23493054

Relabeling exchange method (REM) for learning in neural networks

NASA Astrophysics Data System (ADS)

Wu, Wen; Mammone, Richard J.

1994-02-01

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

Application of fuzzy neural network technologies in management of transport and logistics processes in Arctic

NASA Astrophysics Data System (ADS)

Levchenko, N. G.; Glushkov, S. V.; Sobolevskaya, E. Yu; Orlov, A. P.

2018-05-01

The method of modeling the transport and logistics process using fuzzy neural network technologies has been considered. The analysis of the implemented fuzzy neural network model of the information management system of transnational multimodal transportation of the process showed the expediency of applying this method to the management of transport and logistics processes in the Arctic and Subarctic conditions. The modular architecture of this model can be expanded by incorporating additional modules, since the working conditions in the Arctic and the subarctic themselves will present more and more realistic tasks. The architecture allows increasing the information management system, without affecting the system or the method itself. The model has a wide range of application possibilities, including: analysis of the situation and behavior of interacting elements; dynamic monitoring and diagnostics of management processes; simulation of real events and processes; prediction and prevention of critical situations.

Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems

PubMed Central

González-Gutiérrez, Carlos; Santos, Jesús Daniel; Martínez-Zarzuela, Mario; Basden, Alistair G.; Osborn, James; Díaz-Pernas, Francisco Javier; De Cos Juez, Francisco Javier

2017-01-01

Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named “CARMEN” are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances. PMID:28574426

Dynamic gesture recognition using neural networks: a fundament for advanced interaction construction

NASA Astrophysics Data System (ADS)

Boehm, Klaus; Broll, Wolfgang; Sokolewicz, Michael A.

1994-04-01

Interaction in virtual reality environments is still a challenging task. Static hand posture recognition is currently the most common and widely used method for interaction using glove input devices. In order to improve the naturalness of interaction, and thereby decrease the user-interface learning time, there is a need to be able to recognize dynamic gestures. In this paper we describe our approach to overcoming the difficulties of dynamic gesture recognition (DGR) using neural networks. Backpropagation neural networks have already proven themselves to be appropriate and efficient for posture recognition. However, the extensive amount of data involved in DGR requires a different approach. Because of features such as topology preservation and automatic-learning, Kohonen Feature Maps are particularly suitable for the reduction of the high dimensional data space that is the result of a dynamic gesture, and are thus implemented for this task.

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis

PubMed Central

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang

2017-01-01

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster–Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions. PMID:28788099

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

Next Day Building Load Predictions based on Limited Input Features Using an On-Line Laterally Primed Adaptive Resonance Theory Artificial Neural Network.

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

Jones, Christian Birk; Robinson, Matt; Yasaei, Yasser

Optimal integration of thermal energy storage within commercial building applications requires accurate load predictions. Several methods exist that provide an estimate of a buildings future needs. Methods include component-based models and data-driven algorithms. This work implemented a previously untested algorithm for this application that is called a Laterally Primed Adaptive Resonance Theory (LAPART) artificial neural network (ANN). The LAPART algorithm provided accurate results over a two month period where minimal historical data and a small amount of input types were available. These results are significant, because common practice has often overlooked the implementation of an ANN. ANN have often beenmore » perceived to be too complex and require large amounts of data to provide accurate results. The LAPART neural network was implemented in an on-line learning manner. On-line learning refers to the continuous updating of training data as time occurs. For this experiment, training began with a singe day and grew to two months of data. This approach provides a platform for immediate implementation that requires minimal time and effort. The results from the LAPART algorithm were compared with statistical regression and a component-based model. The comparison was based on the predictions linear relationship with the measured data, mean squared error, mean bias error, and cost savings achieved by the respective prediction techniques. The results show that the LAPART algorithm provided a reliable and cost effective means to predict the building load for the next day.« less

Loop Mirror Laser Neural Network with a Fast Liquid-Crystal Display

NASA Astrophysics Data System (ADS)

Mos, Evert C.; Schleipen, Jean J. H. B.; de Waardt, Huug; Khoe, Djan G. D.

1999-07-01

In our laser neural network (LNN) all-optical threshold action is obtained by application of controlled optical feedback to a laser diode. Here an extended experimental LNN is presented with as many as 32 neurons and 12 inputs. In the setup we use a fast liquid-crystal display to implement an optical matrix vector multiplier. This display, based on ferroelectric liquid-crystal material, enables us to present 125 training examples s to the LNN. To maximize the optical feedback efficiency of the setup, a loop mirror is introduced. We use a -rule learning algorithm to train the network to perform a number of functions toward the application area of telecommunication data switching.

Adaptive Neuron Model: An architecture for the rapid learning of nonlinear topological transformations

NASA Technical Reports Server (NTRS)

Tawel, Raoul (Inventor)

1994-01-01

A method for the rapid learning of nonlinear mappings and topological transformations using a dynamically reconfigurable artificial neural network is presented. This fully-recurrent Adaptive Neuron Model (ANM) network was applied to the highly degenerate inverse kinematics problem in robotics, and its performance evaluation is bench-marked. Once trained, the resulting neuromorphic architecture was implemented in custom analog neural network hardware and the parameters capturing the functional transformation downloaded onto the system. This neuroprocessor, capable of 10(exp 9) ops/sec, was interfaced directly to a three degree of freedom Heathkit robotic manipulator. Calculation of the hardware feed-forward pass for this mapping was benchmarked at approximately 10 microsec.

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 computing for numeric-to-symbolic conversion in control systems

NASA Technical Reports Server (NTRS)

Passino, Kevin M.; Sartori, Michael A.; Antsaklis, Panos J.

1989-01-01

A type of neural network, the multilayer perceptron, is used to classify numeric data and assign appropriate symbols to various classes. This numeric-to-symbolic conversion results in a type of information extraction, which is similar to what is called data reduction in pattern recognition. The use of the neural network as a numeric-to-symbolic converter is introduced, its application in autonomous control is discussed, and several applications are studied. The perceptron is used as a numeric-to-symbolic converter for a discrete-event system controller supervising a continuous variable dynamic system. It is also shown how the perceptron can implement fault trees, which provide useful information (alarms) in a biological system and information for failure diagnosis and control purposes in an aircraft example.

Cognon Neural Model Software Verification and Hardware Implementation Design

NASA Astrophysics Data System (ADS)

Haro Negre, Pau

Little is known yet about how the brain can recognize arbitrary sensory patterns within milliseconds using neural spikes to communicate information between neurons. In a typical brain there are several layers of neurons, with each neuron axon connecting to ˜104 synapses of neurons in an adjacent layer. The information necessary for cognition is contained in theses synapses, which strengthen during the learning phase in response to newly presented spike patterns. Continuing on the model proposed in "Models for Neural Spike Computation and Cognition" by David H. Staelin and Carl H. Staelin, this study seeks to understand cognition from an information theoretic perspective and develop potential models for artificial implementation of cognition based on neuronal models. To do so we focus on the mathematical properties and limitations of spike-based cognition consistent with existing neurological observations. We validate the cognon model through software simulation and develop concepts for an optical hardware implementation of a network of artificial neural cognons.

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

PubMed

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

2011-01-01

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

Feasibility study of robotic neural controllers

NASA Technical Reports Server (NTRS)

Magana, Mario E.

1990-01-01

The results are given of a feasibility study performed to establish if an artificial neural controller could be used to achieve joint space trajectory tracking of a two-link robot manipulator. The study is based on the results obtained by Hecht-Nielsen, who claims that a functional map can be implemented to a desired degree of accuracy with a three layer feedforward artificial neural network. Central to this study is the assumption that the robot model as well as its parameters values are known.

Identification and Control of Aircrafts using Multiple Models and Adaptive Critics

NASA Technical Reports Server (NTRS)

Principe, Jose C.

2007-01-01

We compared two possible implementations of local linear models for control: one approach is based on a self-organizing map (SOM) to cluster the dynamics followed by a set of linear models operating at each cluster. Therefore the gating function is hard (a single local model will represent the regional dynamics). This simplifies the controller design since there is a one to one mapping between controllers and local models. The second approach uses a soft gate using a probabilistic framework based on a Gaussian Mixture Model (also called a dynamic mixture of experts). In this approach several models may be active at a given time, we can expect a smaller number of models, but the controller design is more involved, with potentially better noise rejection characteristics. Our experiments showed that the SOM provides overall best performance in high SNRs, but the performance degrades faster than with the GMM for the same noise conditions. The SOM approach required about an order of magnitude more models than the GMM, so in terms of implementation cost, the GMM is preferable. The design of the SOM is straight forward, while the design of the GMM controllers, although still reasonable, is more involved and needs more care in the selection of the parameters. Either one of these locally linear approaches outperform global nonlinear controllers based on neural networks, such as the time delay neural network (TDNN). Therefore, in essence the local model approach warrants practical implementations. In order to call the attention of the control community for this design methodology we extended successfully the multiple model approach to PID controllers (still today the most widely used control scheme in the industry), and wrote a paper on this subject. The echo state network (ESN) is a recurrent neural network with the special characteristics that only the output parameters are trained. The recurrent connections are preset according to the problem domain and are fixed. In a nutshell, the states of the reservoir of recurrent processing elements implement a projection space, where the desired response is optimally projected. This architecture trades training efficiency by a large increase in the dimension of the recurrent layer. However, the power of the recurrent neural networks can be brought to bear on practical difficult problems. Our goal was to implement an adaptive critic architecture implementing Bellman s approach to optimal control. However, we could only characterize the ESN performance as a critic in value function evaluation, which is just one of the pieces of the overall adaptive critic controller. The results were very convincing, and the simplicity of the implementation was unparalleled.

A Viola-Jones based hybrid face detection framework

NASA Astrophysics Data System (ADS)

Murphy, Thomas M.; Broussard, Randy; Schultz, Robert; Rakvic, Ryan; Ngo, Hau

2013-12-01

Improvements in face detection performance would benefit many applications. The OpenCV library implements a standard solution, the Viola-Jones detector, with a statistically boosted rejection cascade of binary classifiers. Empirical evidence has shown that Viola-Jones underdetects in some instances. This research shows that a truncated cascade augmented by a neural network could recover these undetected faces. A hybrid framework is constructed, with a truncated Viola-Jones cascade followed by an artificial neural network, used to refine the face decision. Optimally, a truncation stage that captured all faces and allowed the neural network to remove the false alarms is selected. A feedforward backpropagation network with one hidden layer is trained to discriminate faces based upon the thresholding (detection) values of intermediate stages of the full rejection cascade. A clustering algorithm is used as a precursor to the neural network, to group significant overlappings. Evaluated on the CMU/VASC Image Database, comparison with an unmodified OpenCV approach shows: (1) a 37% increase in detection rates if constrained by the requirement of no increase in false alarms, (2) a 48% increase in detection rates if some additional false alarms are tolerated, and (3) an 82% reduction in false alarms with no reduction in detection rates. These results demonstrate improved face detection and could address the need for such improvement in various applications.

Spreading Activation in an Attractor Network with Latching Dynamics: Automatic Semantic Priming Revisited

ERIC Educational Resources Information Center

Lerner, Itamar; Bentin, Shlomo; Shriki, Oren

2012-01-01

Localist models of spreading activation (SA) and models assuming distributed representations offer very different takes on semantic priming, a widely investigated paradigm in word recognition and semantic memory research. In this study, we implemented SA in an attractor neural network model with distributed representations and created a unified…

Signal processing and neural network toolbox and its application to failure diagnosis and prognosis

NASA Astrophysics Data System (ADS)

Tu, Fang; Wen, Fang; Willett, Peter K.; Pattipati, Krishna R.; Jordan, Eric H.

2001-07-01

Many systems are comprised of components equipped with self-testing capability; however, if the system is complex involving feedback and the self-testing itself may occasionally be faulty, tracing faults to a single or multiple causes is difficult. Moreover, many sensors are incapable of reliable decision-making on their own. In such cases, a signal processing front-end that can match inference needs will be very helpful. The work is concerned with providing an object-oriented simulation environment for signal processing and neural network-based fault diagnosis and prognosis. In the toolbox, we implemented a wide range of spectral and statistical manipulation methods such as filters, harmonic analyzers, transient detectors, and multi-resolution decomposition to extract features for failure events from data collected by data sensors. Then we evaluated multiple learning paradigms for general classification, diagnosis and prognosis. The network models evaluated include Restricted Coulomb Energy (RCE) Neural Network, Learning Vector Quantization (LVQ), Decision Trees (C4.5), Fuzzy Adaptive Resonance Theory (FuzzyArtmap), Linear Discriminant Rule (LDR), Quadratic Discriminant Rule (QDR), Radial Basis Functions (RBF), Multiple Layer Perceptrons (MLP) and Single Layer Perceptrons (SLP). Validation techniques, such as N-fold cross-validation and bootstrap techniques, are employed for evaluating the robustness of network models. The trained networks are evaluated for their performance using test data on the basis of percent error rates obtained via cross-validation, time efficiency, generalization ability to unseen faults. Finally, the usage of neural networks for the prediction of residual life of turbine blades with thermal barrier coatings is described and the results are shown. The neural network toolbox has also been applied to fault diagnosis in mixed-signal circuits.

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

PubMed

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

2015-01-01

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

A decentralized training algorithm for Echo State Networks in distributed big data applications.

PubMed

Scardapane, Simone; Wang, Dianhui; Panella, Massimo

2016-06-01

The current big data deluge requires innovative solutions for performing efficient inference on large, heterogeneous amounts of information. Apart from the known challenges deriving from high volume and velocity, real-world big data applications may impose additional technological constraints, including the need for a fully decentralized training architecture. While several alternatives exist for training feed-forward neural networks in such a distributed setting, less attention has been devoted to the case of decentralized training of recurrent neural networks (RNNs). In this paper, we propose such an algorithm for a class of RNNs known as Echo State Networks. The algorithm is based on the well-known Alternating Direction Method of Multipliers optimization procedure. It is formulated only in terms of local exchanges between neighboring agents, without reliance on a coordinating node. Additionally, it does not require the communication of training patterns, which is a crucial component in realistic big data implementations. Experimental results on large scale artificial datasets show that it compares favorably with a fully centralized implementation, in terms of speed, efficiency and generalization accuracy. Copyright © 2015 Elsevier Ltd. All rights reserved.

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

PubMed Central

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

2015-01-01

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

Simulation of networks of spiking neurons: A review of tools and strategies

PubMed Central

Brette, Romain; Rudolph, Michelle; Carnevale, Ted; Hines, Michael; Beeman, David; Bower, James M.; Diesmann, Markus; Morrison, Abigail; Goodman, Philip H.; Harris, Frederick C.; Zirpe, Milind; Natschläger, Thomas; Pecevski, Dejan; Ermentrout, Bard; Djurfeldt, Mikael; Lansner, Anders; Rochel, Olivier; Vieville, Thierry; Muller, Eilif; Davison, Andrew P.; El Boustani, Sami

2009-01-01

We review different aspects of the simulation of spiking neural networks. We start by reviewing the different types of simulation strategies and algorithms that are currently implemented. We next review the precision of those simulation strategies, in particular in cases where plasticity depends on the exact timing of the spikes. We overview different simulators and simulation environments presently available (restricted to those freely available, open source and documented). For each simulation tool, its advantages and pitfalls are reviewed, with an aim to allow the reader to identify which simulator is appropriate for a given task. Finally, we provide a series of benchmark simulations of different types of networks of spiking neurons, including Hodgkin–Huxley type, integrate-and-fire models, interacting with current-based or conductance-based synapses, using clock-driven or event-driven integration strategies. The same set of models are implemented on the different simulators, and the codes are made available. The ultimate goal of this review is to provide a resource to facilitate identifying the appropriate integration strategy and simulation tool to use for a given modeling problem related to spiking neural networks. PMID:17629781

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

PubMed Central

Bernal, Javier; Torres-Jimenez, Jose

2015-01-01

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

Neuro-fuzzy controller to navigate an unmanned vehicle.

PubMed

Selma, Boumediene; Chouraqui, Samira

2013-12-01

A Neuro-fuzzy control method for an Unmanned Vehicle (UV) simulation is described. The objective is guiding an autonomous vehicle to a desired destination along a desired path in an environment characterized by a terrain and a set of distinct objects, such as obstacles like donkey traffic lights and cars circulating in the trajectory. The autonomous navigate ability and road following precision are mainly influenced by its control strategy and real-time control performance. Fuzzy Logic Controller can very well describe the desired system behavior with simple "if-then" relations owing the designer to derive "if-then" rules manually by trial and error. On the other hand, Neural Networks perform function approximation of a system but cannot interpret the solution obtained neither check if its solution is plausible. The two approaches are complementary. Combining them, Neural Networks will allow learning capability while Fuzzy-Logic will bring knowledge representation (Neuro-Fuzzy). In this paper, an artificial neural network fuzzy inference system (ANFIS) controller is described and implemented to navigate the autonomous vehicle. Results show several improvements in the control system adjusted by neuro-fuzzy techniques in comparison to the previous methods like Artificial Neural Network (ANN).

A computational framework for the detection of subcortical brain dysmaturation in neonatal MRI using 3D Convolutional Neural Networks.

PubMed

Ceschin, Rafael; Zahner, Alexandria; Reynolds, William; Gaesser, Jenna; Zuccoli, Giulio; Lo, Cecilia W; Gopalakrishnan, Vanathi; Panigrahy, Ashok

2018-05-21

Deep neural networks are increasingly being used in both supervised learning for classification tasks and unsupervised learning to derive complex patterns from the input data. However, the successful implementation of deep neural networks using neuroimaging datasets requires adequate sample size for training and well-defined signal intensity based structural differentiation. There is a lack of effective automated diagnostic tools for the reliable detection of brain dysmaturation in the neonatal period, related to small sample size and complex undifferentiated brain structures, despite both translational research and clinical importance. Volumetric information alone is insufficient for diagnosis. In this study, we developed a computational framework for the automated classification of brain dysmaturation from neonatal MRI, by combining a specific deep neural network implementation with neonatal structural brain segmentation as a method for both clinical pattern recognition and data-driven inference into the underlying structural morphology. We implemented three-dimensional convolution neural networks (3D-CNNs) to specifically classify dysplastic cerebelli, a subset of surface-based subcortical brain dysmaturation, in term infants born with congenital heart disease. We obtained a 0.985 ± 0. 0241-classification accuracy of subtle cerebellar dysplasia in CHD using 10-fold cross-validation. Furthermore, the hidden layer activations and class activation maps depicted regional vulnerability of the superior surface of the cerebellum, (composed of mostly the posterior lobe and the midline vermis), in regards to differentiating the dysplastic process from normal tissue. The posterior lobe and the midline vermis provide regional differentiation that is relevant to not only to the clinical diagnosis of cerebellar dysplasia, but also genetic mechanisms and neurodevelopmental outcome correlates. These findings not only contribute to the detection and classification of a subset of neonatal brain dysmaturation, but also provide insight to the pathogenesis of cerebellar dysplasia in CHD. In addition, this is one of the first examples of the application of deep learning to a neuroimaging dataset, in which the hidden layer activation revealed diagnostically and biologically relevant features about the clinical pathogenesis. The code developed for this project is open source, published under the BSD License, and designed to be generalizable to applications both within and beyond neonatal brain imaging. Copyright © 2018 Elsevier Inc. All rights reserved.

Algebraic and adaptive learning in neural control systems

NASA Astrophysics Data System (ADS)

Ferrari, Silvia

A systematic approach is developed for designing adaptive and reconfigurable nonlinear control systems that are applicable to plants modeled by ordinary differential equations. The nonlinear controller comprising a network of neural networks is taught using a two-phase learning procedure realized through novel techniques for initialization, on-line training, and adaptive critic design. A critical observation is that the gradients of the functions defined by the neural networks must equal corresponding linear gain matrices at chosen operating points. On-line training is based on a dual heuristic adaptive critic architecture that improves control for large, coupled motions by accounting for actual plant dynamics and nonlinear effects. An action network computes the optimal control law; a critic network predicts the derivative of the cost-to-go with respect to the state. Both networks are algebraically initialized based on prior knowledge of satisfactory pointwise linear controllers and continue to adapt on line during full-scale simulations of the plant. On-line training takes place sequentially over discrete periods of time and involves several numerical procedures. A backpropagating algorithm called Resilient Backpropagation is modified and successfully implemented to meet these objectives, without excessive computational expense. This adaptive controller is as conservative as the linear designs and as effective as a global nonlinear controller. The method is successfully implemented for the full-envelope control of a six-degree-of-freedom aircraft simulation. The results show that the on-line adaptation brings about improved performance with respect to the initialization phase during aircraft maneuvers that involve large-angle and coupled dynamics, and parameter variations.

Improved methods in neural network-based adaptive output feedback control, with applications to flight control

NASA Astrophysics Data System (ADS)

Kim, Nakwan

Utilizing the universal approximation property of neural networks, we develop several novel approaches to neural network-based adaptive output feedback control of nonlinear systems, and illustrate these approaches for several flight control applications. In particular, we address the problem of non-affine systems and eliminate the fixed point assumption present in earlier work. All of the stability proofs are carried out in a form that eliminates an algebraic loop in the neural network implementation. An approximate input/output feedback linearizing controller is augmented with a neural network using input/output sequences of the uncertain system. These approaches permit adaptation to both parametric uncertainty and unmodeled dynamics. All physical systems also have control position and rate limits, which may either deteriorate performance or cause instability for a sufficiently high control bandwidth. Here we apply a method for protecting an adaptive process from the effects of input saturation and time delays, known as "pseudo control hedging". This method was originally developed for the state feedback case, and we provide a stability analysis that extends its domain of applicability to the case of output feedback. The approach is illustrated by the design of a pitch-attitude flight control system for a linearized model of an R-50 experimental helicopter, and by the design of a pitch-rate control system for a 58-state model of a flexible aircraft consisting of rigid body dynamics coupled with actuator and flexible modes. A new approach to augmentation of an existing linear controller is introduced. It is especially useful when there is limited information concerning the plant model, and the existing controller. The approach is applied to the design of an adaptive autopilot for a guided munition. Design of a neural network adaptive control that ensures asymptotically stable tracking performance is also addressed.

Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System.

PubMed

Sheik, Sadique; Coath, Martin; Indiveri, Giacomo; Denham, Susan L; Wennekers, Thomas; Chicca, Elisabetta

2012-01-01

Many sounds of ecological importance, such as communication calls, are characterized by time-varying spectra. However, most neuromorphic auditory models to date have focused on distinguishing mainly static patterns, under the assumption that dynamic patterns can be learned as sequences of static ones. In contrast, the emergence of dynamic feature sensitivity through exposure to formative stimuli has been recently modeled in a network of spiking neurons based on the thalamo-cortical architecture. The proposed network models the effect of lateral and recurrent connections between cortical layers, distance-dependent axonal transmission delays, and learning in the form of Spike Timing Dependent Plasticity (STDP), which effects stimulus-driven changes in the pattern of network connectivity. In this paper we demonstrate how these principles can be efficiently implemented in neuromorphic hardware. In doing so we address two principle problems in the design of neuromorphic systems: real-time event-based asynchronous communication in multi-chip systems, and the realization in hybrid analog/digital VLSI technology of neural computational principles that we propose underlie plasticity in neural processing of dynamic stimuli. The result is a hardware neural network that learns in real-time and shows preferential responses, after exposure, to stimuli exhibiting particular spectro-temporal patterns. The availability of hardware on which the model can be implemented, makes this a significant step toward the development of adaptive, neurobiologically plausible, spike-based, artificial sensory systems.

Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System

PubMed Central

Sheik, Sadique; Coath, Martin; Indiveri, Giacomo; Denham, Susan L.; Wennekers, Thomas; Chicca, Elisabetta

2011-01-01

Many sounds of ecological importance, such as communication calls, are characterized by time-varying spectra. However, most neuromorphic auditory models to date have focused on distinguishing mainly static patterns, under the assumption that dynamic patterns can be learned as sequences of static ones. In contrast, the emergence of dynamic feature sensitivity through exposure to formative stimuli has been recently modeled in a network of spiking neurons based on the thalamo-cortical architecture. The proposed network models the effect of lateral and recurrent connections between cortical layers, distance-dependent axonal transmission delays, and learning in the form of Spike Timing Dependent Plasticity (STDP), which effects stimulus-driven changes in the pattern of network connectivity. In this paper we demonstrate how these principles can be efficiently implemented in neuromorphic hardware. In doing so we address two principle problems in the design of neuromorphic systems: real-time event-based asynchronous communication in multi-chip systems, and the realization in hybrid analog/digital VLSI technology of neural computational principles that we propose underlie plasticity in neural processing of dynamic stimuli. The result is a hardware neural network that learns in real-time and shows preferential responses, after exposure, to stimuli exhibiting particular spectro-temporal patterns. The availability of hardware on which the model can be implemented, makes this a significant step toward the development of adaptive, neurobiologically plausible, spike-based, artificial sensory systems. PMID:22347163

Effect of Heterogeneity on Decorrelation Mechanisms in Spiking Neural Networks: A Neuromorphic-Hardware Study

NASA Astrophysics Data System (ADS)

Pfeil, Thomas; Jordan, Jakob; Tetzlaff, Tom; Grübl, Andreas; Schemmel, Johannes; Diesmann, Markus; Meier, Karlheinz

2016-04-01

High-level brain function, such as memory, classification, or reasoning, can be realized by means of recurrent networks of simplified model neurons. Analog neuromorphic hardware constitutes a fast and energy-efficient substrate for the implementation of such neural computing architectures in technical applications and neuroscientific research. The functional performance of neural networks is often critically dependent on the level of correlations in the neural activity. In finite networks, correlations are typically inevitable due to shared presynaptic input. Recent theoretical studies have shown that inhibitory feedback, abundant in biological neural networks, can actively suppress these shared-input correlations and thereby enable neurons to fire nearly independently. For networks of spiking neurons, the decorrelating effect of inhibitory feedback has so far been explicitly demonstrated only for homogeneous networks of neurons with linear subthreshold dynamics. Theory, however, suggests that the effect is a general phenomenon, present in any system with sufficient inhibitory feedback, irrespective of the details of the network structure or the neuronal and synaptic properties. Here, we investigate the effect of network heterogeneity on correlations in sparse, random networks of inhibitory neurons with nonlinear, conductance-based synapses. Emulations of these networks on the analog neuromorphic-hardware system Spikey allow us to test the efficiency of decorrelation by inhibitory feedback in the presence of hardware-specific heterogeneities. The configurability of the hardware substrate enables us to modulate the extent of heterogeneity in a systematic manner. We selectively study the effects of shared input and recurrent connections on correlations in membrane potentials and spike trains. Our results confirm that shared-input correlations are actively suppressed by inhibitory feedback also in highly heterogeneous networks exhibiting broad, heavy-tailed firing-rate distributions. In line with former studies, cell heterogeneities reduce shared-input correlations. Overall, however, correlations in the recurrent system can increase with the level of heterogeneity as a consequence of diminished effective negative feedback.

Smooth function approximation using neural networks.

PubMed

Ferrari, Silvia; Stengel, Robert F

2005-01-01

An algebraic approach for representing multidimensional nonlinear functions by feedforward neural networks is presented. In this paper, the approach is implemented for the approximation of smooth batch data containing the function's input, output, and possibly, gradient information. The training set is associated to the network adjustable parameters by nonlinear weight equations. The cascade structure of these equations reveals that they can be treated as sets of linear systems. Hence, the training process and the network approximation properties can be investigated via linear algebra. Four algorithms are developed to achieve exact or approximate matching of input-output and/or gradient-based training sets. Their application to the design of forward and feedback neurocontrollers shows that algebraic training is characterized by faster execution speeds and better generalization properties than contemporary optimization techniques.

Inference in the brain: Statistics flowing in redundant population codes

PubMed Central

Pitkow, Xaq; Angelaki, Dora E

2017-01-01

It is widely believed that the brain performs approximate probabilistic inference to estimate causal variables in the world from ambiguous sensory data. To understand these computations, we need to analyze how information is represented and transformed by the actions of nonlinear recurrent neural networks. We propose that these probabilistic computations function by a message-passing algorithm operating at the level of redundant neural populations. To explain this framework, we review its underlying concepts, including graphical models, sufficient statistics, and message-passing, and then describe how these concepts could be implemented by recurrently connected probabilistic population codes. The relevant information flow in these networks will be most interpretable at the population level, particularly for redundant neural codes. We therefore outline a general approach to identify the essential features of a neural message-passing algorithm. Finally, we argue that to reveal the most important aspects of these neural computations, we must study large-scale activity patterns during moderately complex, naturalistic behaviors. PMID:28595050

Generating Seismograms with Deep Neural Networks

NASA Astrophysics Data System (ADS)

Krischer, L.; Fichtner, A.

2017-12-01

The recent surge of successful uses of deep neural networks in computer vision, speech recognition, and natural language processing, mainly enabled by the availability of fast GPUs and extremely large data sets, is starting to see many applications across all natural sciences. In seismology these are largely confined to classification and discrimination tasks. In this contribution we explore the use of deep neural networks for another class of problems: so called generative models.Generative modelling is a branch of statistics concerned with generating new observed data samples, usually by drawing from some underlying probability distribution. Samples with specific attributes can be generated by conditioning on input variables. In this work we condition on seismic source (mechanism and location) and receiver (location) parameters to generate multi-component seismograms.The deep neural networks are trained on synthetic data calculated with Instaseis (http://instaseis.net, van Driel et al. (2015)) and waveforms from the global ShakeMovie project (http://global.shakemovie.princeton.edu, Tromp et al. (2010)). The underlying radially symmetric or smoothly three dimensional Earth structures result in comparatively small waveform differences from similar events or at close receivers and the networks learn to interpolate between training data samples.Of particular importance is the chosen misfit functional. Generative adversarial networks (Goodfellow et al. (2014)) implement a system in which two networks compete: the generator network creates samples and the discriminator network distinguishes these from the true training examples. Both are trained in an adversarial fashion until the discriminator can no longer distinguish between generated and real samples. We show how this can be applied to seismograms and in particular how it compares to networks trained with more conventional misfit metrics. Last but not least we attempt to shed some light on the black-box nature of neural networks by estimating the quality and uncertainties of the generated seismograms.

An Adaptive Critic Approach to Reference Model Adaptation

NASA Technical Reports Server (NTRS)

Krishnakumar, K.; Limes, G.; Gundy-Burlet, K.; Bryant, D.

2003-01-01

Neural networks have been successfully used for implementing control architectures for different applications. In this work, we examine a neural network augmented adaptive critic as a Level 2 intelligent controller for a C- 17 aircraft. This intelligent control architecture utilizes an adaptive critic to tune the parameters of a reference model, which is then used to define the angular rate command for a Level 1 intelligent controller. The present architecture is implemented on a high-fidelity non-linear model of a C-17 aircraft. The goal of this research is to improve the performance of the C-17 under degraded conditions such as control failures and battle damage. Pilot ratings using a motion based simulation facility are included in this paper. The benefits of using an adaptive critic are documented using time response comparisons for severe damage situations.

Modeling Behavioral Experiment Interaction and Environmental Stimuli for a Synthetic C. elegans.

PubMed

Mujika, Andoni; Leškovský, Peter; Álvarez, Roberto; Otaduy, Miguel A; Epelde, Gorka

2017-01-01

This paper focusses on the simulation of the neural network of the Caenorhabditis elegans living organism, and more specifically in the modeling of the stimuli applied within behavioral experiments and the stimuli that is generated in the interaction of the C. elegans with the environment. To the best of our knowledge, all efforts regarding stimuli modeling for the C. elegans are focused on a single type of stimulus, which is usually tested with a limited subnetwork of the C. elegans neural system. In this paper, we follow a different approach where we model a wide-range of different stimuli, with more flexible neural network configurations and simulations in mind. Moreover, we focus on the stimuli sensation by different types of sensory organs or various sensory principles of the neurons. As part of this work, most common stimuli involved in behavioral assays have been modeled. It includes models for mechanical, thermal, chemical, electrical and light stimuli, and for proprioception-related self-sensed information exchange with the neural network. The developed models have been implemented and tested with the hardware-based Si elegans simulation platform.

Hybrid neural network for density limit disruption prediction and avoidance on J-TEXT tokamak

NASA Astrophysics Data System (ADS)

Zheng, W.; Hu, F. R.; Zhang, M.; Chen, Z. Y.; Zhao, X. Q.; Wang, X. L.; Shi, P.; Zhang, X. L.; Zhang, X. Q.; Zhou, Y. N.; Wei, Y. N.; Pan, Y.; J-TEXT team

2018-05-01

Increasing the plasma density is one of the key methods in achieving an efficient fusion reaction. High-density operation is one of the hot topics in tokamak plasmas. Density limit disruptions remain an important issue for safe operation. An effective density limit disruption prediction and avoidance system is the key to avoid density limit disruptions for long pulse steady state operations. An artificial neural network has been developed for the prediction of density limit disruptions on the J-TEXT tokamak. The neural network has been improved from a simple multi-layer design to a hybrid two-stage structure. The first stage is a custom network which uses time series diagnostics as inputs to predict plasma density, and the second stage is a three-layer feedforward neural network to predict the probability of density limit disruptions. It is found that hybrid neural network structure, combined with radiation profile information as an input can significantly improve the prediction performance, especially the average warning time ({{T}warn} ). In particular, the {{T}warn} is eight times better than that in previous work (Wang et al 2016 Plasma Phys. Control. Fusion 58 055014) (from 5 ms to 40 ms). The success rate for density limit disruptive shots is above 90%, while, the false alarm rate for other shots is below 10%. Based on the density limit disruption prediction system and the real-time density feedback control system, the on-line density limit disruption avoidance system has been implemented on the J-TEXT tokamak.

Physical Realization of a Supervised Learning System Built with Organic Memristive Synapses

NASA Astrophysics Data System (ADS)

Lin, Yu-Pu; Bennett, Christopher H.; Cabaret, Théo; Vodenicarevic, Damir; Chabi, Djaafar; Querlioz, Damien; Jousselme, Bruno; Derycke, Vincent; Klein, Jacques-Olivier

2016-09-01

Multiple modern applications of electronics call for inexpensive chips that can perform complex operations on natural data with limited energy. A vision for accomplishing this is implementing hardware neural networks, which fuse computation and memory, with low cost organic electronics. A challenge, however, is the implementation of synapses (analog memories) composed of such materials. In this work, we introduce robust, fastly programmable, nonvolatile organic memristive nanodevices based on electrografted redox complexes that implement synapses thanks to a wide range of accessible intermediate conductivity states. We demonstrate experimentally an elementary neural network, capable of learning functions, which combines four pairs of organic memristors as synapses and conventional electronics as neurons. Our architecture is highly resilient to issues caused by imperfect devices. It tolerates inter-device variability and an adaptable learning rule offers immunity against asymmetries in device switching. Highly compliant with conventional fabrication processes, the system can be extended to larger computing systems capable of complex cognitive tasks, as demonstrated in complementary simulations.

Flight Test Implementation of a Second Generation Intelligent Flight Control System

NASA Technical Reports Server (NTRS)

Williams-Hayes, Peggy S.

2005-01-01

The NASA F-15 Intelligent Flight Control System project team has developed a series of flight control concepts designed to demonstrate the benefits of a neural network-based adaptive controller. The objective of the team was to develop and flight-test control systems that use neural network technology, to optimize the performance of the aircraft under nominal conditions, and to stabilize the aircraft under failure conditions. Failure conditions include locked or failed control surfaces as well as unforeseen damage that might occur to the aircraft in flight. The Intelligent Flight Control System team is currently in the process of implementing a second generation control scheme, collectively known as Generation 2 or Gen 2, for flight testing on the NASA F-15 aircraft. This report describes the Gen 2 system as implemented by the team for flight test evaluation. Simulation results are shown which describe the experiment to be performed in flight and highlight the ways in which the Gen 2 system meets the defined objectives.

Development and program implementation of elements for identification of the electromagnet condition for movable element position control

NASA Astrophysics Data System (ADS)

Leukhin, R. I.; Shaykhutdinov, D. V.; Shirokov, K. M.; Narakidze, N. D.; Vlasov, A. S.

2017-02-01

Developing the experimental design of new electromagnetic constructions types in engineering industry enterprises requires solutions of two major problems: regulator’s parameters setup and comprehensive testing of electromagnets. A weber-ampere characteristic as a data source for electromagnet condition identification was selected. Present article focuses on development and implementation of the software for electromagnetic drive control system based on the weber-ampere characteristic measuring. The software for weber-ampere characteristic data processing based on artificial neural network is developed. Results of the design have been integrated into the program code in LabVIEW environment. The license package of LabVIEW graphic programming was used. The hardware is chosen and possibility of its use for control system implementation was proved. The trained artificial neural network defines electromagnetic drive effector position with minimal error. Developed system allows to control the electromagnetic drive powered by the voltage source, the current source and hybrid sources.

Quadrupedal Robot Locomotion: A Biologically Inspired Approach and Its Hardware Implementation

PubMed Central

Espinal, A.; Rostro-Gonzalez, H.; Carpio, M.; Guerra-Hernandez, E. I.; Ornelas-Rodriguez, M.; Puga-Soberanes, H. J.; Sotelo-Figueroa, M. A.; Melin, P.

2016-01-01

A bioinspired locomotion system for a quadruped robot is presented. Locomotion is achieved by a spiking neural network (SNN) that acts as a Central Pattern Generator (CPG) producing different locomotion patterns represented by their raster plots. To generate these patterns, the SNN is configured with specific parameters (synaptic weights and topologies), which were estimated by a metaheuristic method based on Christiansen Grammar Evolution (CGE). The system has been implemented and validated on two robot platforms; firstly, we tested our system on a quadruped robot and, secondly, on a hexapod one. In this last one, we simulated the case where two legs of the hexapod were amputated and its locomotion mechanism has been changed. For the quadruped robot, the control is performed by the spiking neural network implemented on an Arduino board with 35% of resource usage. In the hexapod robot, we used Spartan 6 FPGA board with only 3% of resource usage. Numerical results show the effectiveness of the proposed system in both cases. PMID:27436997

Quadrupedal Robot Locomotion: A Biologically Inspired Approach and Its Hardware Implementation.

PubMed

Espinal, A; Rostro-Gonzalez, H; Carpio, M; Guerra-Hernandez, E I; Ornelas-Rodriguez, M; Puga-Soberanes, H J; Sotelo-Figueroa, M A; Melin, P

2016-01-01

A bioinspired locomotion system for a quadruped robot is presented. Locomotion is achieved by a spiking neural network (SNN) that acts as a Central Pattern Generator (CPG) producing different locomotion patterns represented by their raster plots. To generate these patterns, the SNN is configured with specific parameters (synaptic weights and topologies), which were estimated by a metaheuristic method based on Christiansen Grammar Evolution (CGE). The system has been implemented and validated on two robot platforms; firstly, we tested our system on a quadruped robot and, secondly, on a hexapod one. In this last one, we simulated the case where two legs of the hexapod were amputated and its locomotion mechanism has been changed. For the quadruped robot, the control is performed by the spiking neural network implemented on an Arduino board with 35% of resource usage. In the hexapod robot, we used Spartan 6 FPGA board with only 3% of resource usage. Numerical results show the effectiveness of the proposed system in both cases.

Physical Realization of a Supervised Learning System Built with Organic Memristive Synapses.

PubMed

Lin, Yu-Pu; Bennett, Christopher H; Cabaret, Théo; Vodenicarevic, Damir; Chabi, Djaafar; Querlioz, Damien; Jousselme, Bruno; Derycke, Vincent; Klein, Jacques-Olivier

2016-09-07

Multiple modern applications of electronics call for inexpensive chips that can perform complex operations on natural data with limited energy. A vision for accomplishing this is implementing hardware neural networks, which fuse computation and memory, with low cost organic electronics. A challenge, however, is the implementation of synapses (analog memories) composed of such materials. In this work, we introduce robust, fastly programmable, nonvolatile organic memristive nanodevices based on electrografted redox complexes that implement synapses thanks to a wide range of accessible intermediate conductivity states. We demonstrate experimentally an elementary neural network, capable of learning functions, which combines four pairs of organic memristors as synapses and conventional electronics as neurons. Our architecture is highly resilient to issues caused by imperfect devices. It tolerates inter-device variability and an adaptable learning rule offers immunity against asymmetries in device switching. Highly compliant with conventional fabrication processes, the system can be extended to larger computing systems capable of complex cognitive tasks, as demonstrated in complementary simulations.

Predictive Coding of Dynamical Variables in Balanced Spiking Networks

PubMed Central

Boerlin, Martin; Machens, Christian K.; Denève, Sophie

2013-01-01

Two observations about the cortex have puzzled neuroscientists for a long time. First, neural responses are highly variable. Second, the level of excitation and inhibition received by each neuron is tightly balanced at all times. Here, we demonstrate that both properties are necessary consequences of neural networks that represent information efficiently in their spikes. We illustrate this insight with spiking networks that represent dynamical variables. Our approach is based on two assumptions: We assume that information about dynamical variables can be read out linearly from neural spike trains, and we assume that neurons only fire a spike if that improves the representation of the dynamical variables. Based on these assumptions, we derive a network of leaky integrate-and-fire neurons that is able to implement arbitrary linear dynamical systems. We show that the membrane voltage of the neurons is equivalent to a prediction error about a common population-level signal. Among other things, our approach allows us to construct an integrator network of spiking neurons that is robust against many perturbations. Most importantly, neural variability in our networks cannot be equated to noise. Despite exhibiting the same single unit properties as widely used population code models (e.g. tuning curves, Poisson distributed spike trains), balanced networks are orders of magnitudes more reliable. Our approach suggests that spikes do matter when considering how the brain computes, and that the reliability of cortical representations could have been strongly underestimated. PMID:24244113

Balanced Cortical Microcircuitry for Spatial Working Memory Based on Corrective Feedback Control

PubMed Central

2014-01-01

A hallmark of working memory is the ability to maintain graded representations of both the spatial location and amplitude of a memorized stimulus. Previous work has identified a neural correlate of spatial working memory in the persistent maintenance of spatially specific patterns of neural activity. How such activity is maintained by neocortical circuits remains unknown. Traditional models of working memory maintain analog representations of either the spatial location or the amplitude of a stimulus, but not both. Furthermore, although most previous models require local excitation and lateral inhibition to maintain spatially localized persistent activity stably, the substrate for lateral inhibitory feedback pathways is unclear. Here, we suggest an alternative model for spatial working memory that is capable of maintaining analog representations of both the spatial location and amplitude of a stimulus, and that does not rely on long-range feedback inhibition. The model consists of a functionally columnar network of recurrently connected excitatory and inhibitory neural populations. When excitation and inhibition are balanced in strength but offset in time, drifts in activity trigger spatially specific negative feedback that corrects memory decay. The resulting networks can temporally integrate inputs at any spatial location, are robust against many commonly considered perturbations in network parameters, and, when implemented in a spiking model, generate irregular neural firing characteristic of that observed experimentally during persistent activity. This work suggests balanced excitatory–inhibitory memory circuits implementing corrective negative feedback as a substrate for spatial working memory. PMID:24828633

A hybrid framework for reservoir characterization using fuzzy ranking and an artificial neural network

NASA Astrophysics Data System (ADS)

Wang, Baijie; Wang, Xin; Chen, Zhangxin

2013-08-01

Reservoir characterization refers to the process of quantitatively assigning reservoir properties using all available field data. Artificial neural networks (ANN) have recently been introduced to solve reservoir characterization problems dealing with the complex underlying relationships inherent in well log data. Despite the utility of ANNs, the current limitation is that most existing applications simply focus on directly implementing existing ANN models instead of improving/customizing them to fit the specific reservoir characterization tasks at hand. In this paper, we propose a novel intelligent framework that integrates fuzzy ranking (FR) and multilayer perceptron (MLP) neural networks for reservoir characterization. FR can automatically identify a minimum subset of well log data as neural inputs, and the MLP is trained to learn the complex correlations from the selected well log data to a target reservoir property. FR guarantees the selection of the optimal subset of representative data from the overall well log data set for the characterization of a specific reservoir property; and, this implicitly improves the modeling and predication accuracy of the MLP. In addition, a growing number of industrial agencies are implementing geographic information systems (GIS) in field data management; and, we have designed the GFAR solution (GIS-based FR ANN Reservoir characterization solution) system, which integrates the proposed framework into a GIS system that provides an efficient characterization solution. Three separate petroleum wells from southwestern Alberta, Canada, were used in the presented case study of reservoir porosity characterization. Our experiments demonstrate that our method can generate reliable results.

A neural network - based algorithm for predicting stone -free status after ESWL therapy

PubMed Central

Seckiner, Ilker; Seckiner, Serap; Sen, Haluk; Bayrak, Omer; Dogan, Kazım; Erturhan, Sakip

2017-01-01

ABSTRACT Objective: The prototype artificial neural network (ANN) model was developed using data from patients with renal stone, in order to predict stone-free status and to help in planning treatment with Extracorporeal Shock Wave Lithotripsy (ESWL) for kidney stones. Materials and Methods: Data were collected from the 203 patients including gender, single or multiple nature of the stone, location of the stone, infundibulopelvic angle primary or secondary nature of the stone, status of hydronephrosis, stone size after ESWL, age, size, skin to stone distance, stone density and creatinine, for eleven variables. Regression analysis and the ANN method were applied to predict treatment success using the same series of data. Results: Subsequently, patients were divided into three groups by neural network software, in order to implement the ANN: training group (n=139), validation group (n=32), and the test group (n=32). ANN analysis demonstrated that the prediction accuracy of the stone-free rate was 99.25% in the training group, 85.48% in the validation group, and 88.70% in the test group. Conclusions: Successful results were obtained to predict the stone-free rate, with the help of the ANN model designed by using a series of data collected from real patients in whom ESWL was implemented to help in planning treatment for kidney stones. PMID:28727384

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.

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.

Automated information-analytical system for thunderstorm monitoring and early warning alarms using modern physical sensors and information technologies with elements of artificial intelligence

NASA Astrophysics Data System (ADS)

Boldyreff, Anton S.; Bespalov, Dmitry A.; Adzhiev, Anatoly Kh.

2017-05-01

Methods of artificial intelligence are a good solution for weather phenomena forecasting. They allow to process a large amount of diverse data. Recirculation Neural Networks is implemented in the paper for the system of thunderstorm events prediction. Large amounts of experimental data from lightning sensors and electric field mills networks are received and analyzed. The average recognition accuracy of sensor signals is calculated. It is shown that Recirculation Neural Networks is a promising solution in the forecasting of thunderstorms and weather phenomena, characterized by the high efficiency of the recognition elements of the sensor signals, allows to compress images and highlight their characteristic features for subsequent recognition.

A Tool for Verification and Validation of Neural Network Based Adaptive Controllers for High Assurance Systems

NASA Technical Reports Server (NTRS)

Gupta, Pramod; Schumann, Johann

2004-01-01

High reliability of mission- and safety-critical software systems has been identified by NASA as a high-priority technology challenge. We present an approach for the performance analysis of a neural network (NN) in an advanced adaptive control system. This problem is important in the context of safety-critical applications that require certification, such as flight software in aircraft. We have developed a tool to measure the performance of the NN during operation by calculating a confidence interval (error bar) around the NN's output. Our tool can be used during pre-deployment verification as well as monitoring the network performance during operation. The tool has been implemented in Simulink and simulation results on a F-15 aircraft are presented.

LSTM-CRF | Informatics Technology for Cancer Research (ITCR)

Cancer.gov

LSTM-CRF uses Natural Language Processing methods for detecting Adverse Drug Events, Drugname, Indication and other medically relevant information from Electronic Health Records. It implements Recurrent Neural Networks using several CRF based inference methods.

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.

Cloud Classification in Polar and Desert Regions and Smoke Classification from Biomass Burning Using a Hierarchical Neural Network

NASA Technical Reports Server (NTRS)

Alexander, June; Corwin, Edward; Lloyd, David; Logar, Antonette; Welch, Ronald

1996-01-01

This research focuses on a new neural network scene classification technique. The task is to identify scene elements in Advanced Very High Resolution Radiometry (AVHRR) data from three scene types: polar, desert and smoke from biomass burning in South America (smoke). The ultimate goal of this research is to design and implement a computer system which will identify the clouds present on a whole-Earth satellite view as a means of tracking global climate changes. Previous research has reported results for rule-based systems (Tovinkere et at 1992, 1993) for standard back propagation (Watters et at. 1993) and for a hierarchical approach (Corwin et al 1994) for polar data. This research uses a hierarchical neural network with don't care conditions and applies this technique to complex scenes. A hierarchical neural network consists of a switching network and a collection of leaf networks. The idea of the hierarchical neural network is that it is a simpler task to classify a certain pattern from a subset of patterns than it is to classify a pattern from the entire set. Therefore, the first task is to cluster the classes into groups. The switching, or decision network, performs an initial classification by selecting a leaf network. The leaf networks contain a reduced set of similar classes, and it is in the various leaf networks that the actual classification takes place. The grouping of classes in the various leaf networks is determined by applying an iterative clustering algorithm. Several clustering algorithms were investigated, but due to the size of the data sets, the exhaustive search algorithms were eliminated. A heuristic approach using a confusion matrix from a lightly trained neural network provided the basis for the clustering algorithm. Once the clusters have been identified, the hierarchical network can be trained. The approach of using don't care nodes results from the difficulty in generating extremely complex surfaces in order to separate one class from all of the others. This approach finds pairwise separating surfaces and forms the more complex separating surface from combinations of simpler surfaces. This technique both reduces training time and improves accuracy over the previously reported results. Accuracies of 97.47%, 95.70%, and 99.05% were achieved for the polar, desert and smoke data sets.

Real-time cerebellar neuroprosthetic system based on a spiking neural network model of motor learning.

PubMed

Xu, Tao; Xiao, Na; Zhai, Xiaolong; Kwan Chan, Pak; Tin, Chung

2018-02-01

Damage to the brain, as a result of various medical conditions, impacts the everyday life of patients and there is still no complete cure to neurological disorders. Neuroprostheses that can functionally replace the damaged neural circuit have recently emerged as a possible solution to these problems. Here we describe the development of a real-time cerebellar neuroprosthetic system to substitute neural function in cerebellar circuitry for learning delay eyeblink conditioning (DEC). The system was empowered by a biologically realistic spiking neural network (SNN) model of the cerebellar neural circuit, which considers the neuronal population and anatomical connectivity of the network. The model simulated synaptic plasticity critical for learning DEC. This SNN model was carefully implemented on a field programmable gate array (FPGA) platform for real-time simulation. This hardware system was interfaced in in vivo experiments with anesthetized rats and it used neural spikes recorded online from the animal to learn and trigger conditioned eyeblink in the animal during training. This rat-FPGA hybrid system was able to process neuronal spikes in real-time with an embedded cerebellum model of ~10 000 neurons and reproduce learning of DEC with different inter-stimulus intervals. Our results validated that the system performance is physiologically relevant at both the neural (firing pattern) and behavioral (eyeblink pattern) levels. This integrated system provides the sufficient computation power for mimicking the cerebellar circuit in real-time. The system interacts with the biological system naturally at the spike level and can be generalized for including other neural components (neuron types and plasticity) and neural functions for potential neuroprosthetic applications.

[Hardware Implementation of Numerical Simulation Function of Hodgkin-Huxley Model Neurons Action Potential Based on Field Programmable Gate Array].

PubMed

Wang, Jinlong; Lu, Mai; Hu, Yanwen; Chen, Xiaoqiang; Pan, Qiangqiang

2015-12-01

Neuron is the basic unit of the biological neural system. The Hodgkin-Huxley (HH) model is one of the most realistic neuron models on the electrophysiological characteristic description of neuron. Hardware implementation of neuron could provide new research ideas to clinical treatment of spinal cord injury, bionics and artificial intelligence. Based on the HH model neuron and the DSP Builder technology, in the present study, a single HH model neuron hardware implementation was completed in Field Programmable Gate Array (FPGA). The neuron implemented in FPGA was stimulated by different types of current, the action potential response characteristics were analyzed, and the correlation coefficient between numerical simulation result and hardware implementation result were calculated. The results showed that neuronal action potential response of FPGA was highly consistent with numerical simulation result. This work lays the foundation for hardware implementation of neural network.

Neuromorphic device architectures with global connectivity through electrolyte gating

NASA Astrophysics Data System (ADS)

Gkoupidenis, Paschalis; Koutsouras, Dimitrios A.; Malliaras, George G.

2017-05-01

Information processing in the brain takes place in a network of neurons that are connected with each other by an immense number of synapses. At the same time, neurons are immersed in a common electrochemical environment, and global parameters such as concentrations of various hormones regulate the overall network function. This computational paradigm of global regulation, also known as homeoplasticity, has important implications in the overall behaviour of large neural ensembles and is barely addressed in neuromorphic device architectures. Here, we demonstrate the global control of an array of organic devices based on poly(3,4ethylenedioxythiophene):poly(styrene sulf) that are immersed in an electrolyte, a behaviour that resembles homeoplasticity phenomena of the neural environment. We use this effect to produce behaviour that is reminiscent of the coupling between local activity and global oscillations in the biological neural networks. We further show that the electrolyte establishes complex connections between individual devices, and leverage these connections to implement coincidence detection. These results demonstrate that electrolyte gating offers significant advantages for the realization of networks of neuromorphic devices of higher complexity and with minimal hardwired connectivity.

An Intelligent Active Video Surveillance System Based on the Integration of Virtual Neural Sensors and BDI Agents

NASA Astrophysics Data System (ADS)

Gregorio, Massimo De

In this paper we present an intelligent active video surveillance system currently adopted in two different application domains: railway tunnels and outdoor storage areas. The system takes advantages of the integration of Artificial Neural Networks (ANN) and symbolic Artificial Intelligence (AI). This hybrid system is formed by virtual neural sensors (implemented as WiSARD-like systems) and BDI agents. The coupling of virtual neural sensors with symbolic reasoning for interpreting their outputs, makes this approach both very light from a computational and hardware point of view, and rather robust in performances. The system works on different scenarios and in difficult light conditions.

Dense modifiable interconnections utilizing photorefractive volume holograms

NASA Astrophysics Data System (ADS)

Psaltis, Demetri; Qiao, Yong

1990-11-01

This report describes an experimental two-layer optical neural network built at Caltech. The system uses photorefractive volume holograms to implement dense, modifiable synaptic interconnections and liquid crystal light valves (LCVS) to perform nonlinear thresholding operations. Kanerva's Sparse, Distributed Memory was implemented using this network and its ability to recognize handwritten character-alphabet (A-Z) has been demonstrated experimentally. According to Kanerva's model, the first layer has fixed, random weights of interconnections and the second layer is trained by sum-of-outer-products rule. After training, the recognition rates of the network on the training set (104 patterns) and test set (520 patterns) are 100 and 50 percent, respectively.

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

PubMed Central

Ebner, Marc; Hameroff, Stuart

2011-01-01

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

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

PubMed

Ebner, Marc; Hameroff, Stuart

2011-01-01

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

Artificial Neural Network applied to lightning flashes

NASA Astrophysics Data System (ADS)

Gin, R. B.; Guedes, D.; Bianchi, R.

2013-05-01

The development of video cameras enabled cientists to study lightning discharges comportment with more precision. The main goal of this project is to create a system able to detect images of lightning discharges stored in videos and classify them using an Artificial Neural Network (ANN)using C Language and OpenCV libraries. The developed system, can be split in two different modules: detection module and classification module. The detection module uses OpenCV`s computer vision libraries and image processing techniques to detect if there are significant differences between frames in a sequence, indicating that something, still not classified, occurred. Whenever there is a significant difference between two consecutive frames, two main algorithms are used to analyze the frame image: brightness and shape algorithms. These algorithms detect both shape and brightness of the event, removing irrelevant events like birds, as well as detecting the relevant events exact position, allowing the system to track it over time. The classification module uses a neural network to classify the relevant events as horizontal or vertical lightning, save the event`s images and calculates his number of discharges. The Neural Network was implemented using the backpropagation algorithm, and was trained with 42 training images , containing 57 lightning events (one image can have more than one lightning). TheANN was tested with one to five hidden layers, with up to 50 neurons each. The best configuration achieved a success rate of 95%, with one layer containing 20 neurons (33 test images with 42 events were used in this phase). This configuration was implemented in the developed system to analyze 20 video files, containing 63 lightning discharges previously manually detected. Results showed that all the lightning discharges were detected, many irrelevant events were unconsidered, and the event's number of discharges was correctly computed. The neural network used in this project achieved a success rate of 90%. The videos used in this experiment were acquired by seven video cameras installed in São Bernardo do Campo, Brazil, that continuously recorded lightning events during the summer. The cameras were disposed in a 360 loop, recording all data at a time resolution of 33ms. During this period, several convective storms were recorded.

Prediction of protein tertiary structure from sequences using a very large back-propagation neural network

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

Liu, X.; Wilcox, G.L.

1993-12-31

We have implemented large scale back-propagation neural networks on a 544 node Connection Machine, CM-5, using the C language in MIMD mode. The program running on 512 processors performs backpropagation learning at 0.53 Gflops, which provides 76 million connection updates per second. We have applied the network to the prediction of protein tertiary structure from sequence information alone. A neural network with one hidden layer and 40 million connections is trained to learn the relationship between sequence and tertiary structure. The trained network yields predicted structures of some proteins on which it has not been trained given only their sequences.more » Presentation of the Fourier transform of the sequences accentuates periodicity in the sequence and yields good generalization with greatly increased training efficiency. Training simulations with a large, heterologous set of protein structures (111 proteins from CM-5 time) to solutions with under 2% RMS residual error within the training set (random responses give an RMS error of about 20%). Presentation of 15 sequences of related proteins in a testing set of 24 proteins yields predicted structures with less than 8% RMS residual error, indicating good apparent generalization.« less

The next generation of neural network chips

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

Beiu, V.

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

Phylogenetic convolutional neural networks in metagenomics.

PubMed

Fioravanti, Diego; Giarratano, Ylenia; Maggio, Valerio; Agostinelli, Claudio; Chierici, Marco; Jurman, Giuseppe; Furlanello, Cesare

2018-03-08

Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user.

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.

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

Implementation of neural network for color properties of polycarbonates

NASA Astrophysics Data System (ADS)

Saeed, U.; Ahmad, S.; Alsadi, J.; Ross, D.; Rizvi, G.

2014-05-01

In present paper, the applicability of artificial neural networks (ANN) is investigated for color properties of plastics. The neural networks toolbox of Matlab 6.5 is used to develop and test the ANN model on a personal computer. An optimal design is completed for 10, 12, 14,16,18 & 20 hidden neurons on single hidden layer with five different algorithms: batch gradient descent (GD), batch variable learning rate (GDX), resilient back-propagation (RP), scaled conjugate gradient (SCG), levenberg-marquardt (LM) in the feed forward back-propagation neural network model. The training data for ANN is obtained from experimental measurements. There were twenty two inputs including resins, additives & pigments while three tristimulus color values L*, a* and b* were used as output layer. Statistical analysis in terms of Root-Mean-Squared (RMS), absolute fraction of variance (R squared), as well as mean square error is used to investigate the performance of ANN. LM algorithm with fourteen neurons on hidden layer in Feed Forward Back-Propagation of ANN model has shown best result in the present study. The degree of accuracy of the ANN model in reduction of errors is proven acceptable in all statistical analysis and shown in results. However, it was concluded that ANN provides a feasible method in error reduction in specific color tristimulus values.

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.

Optimization Methods for Spiking Neurons and Networks

PubMed Central

Russell, Alexander; Orchard, Garrick; Dong, Yi; Mihalaş, Ştefan; Niebur, Ernst; Tapson, Jonathan; Etienne-Cummings, Ralph

2011-01-01

Spiking neurons and spiking neural circuits are finding uses in a multitude of tasks such as robotic locomotion control, neuroprosthetics, visual sensory processing, and audition. The desired neural output is achieved through the use of complex neuron models, or by combining multiple simple neurons into a network. In either case, a means for configuring the neuron or neural circuit is required. Manual manipulation of parameters is both time consuming and non-intuitive due to the nonlinear relationship between parameters and the neuron’s output. The complexity rises even further as the neurons are networked and the systems often become mathematically intractable. In large circuits, the desired behavior and timing of action potential trains may be known but the timing of the individual action potentials is unknown and unimportant, whereas in single neuron systems the timing of individual action potentials is critical. In this paper, we automate the process of finding parameters. To configure a single neuron we derive a maximum likelihood method for configuring a neuron model, specifically the Mihalas–Niebur Neuron. Similarly, to configure neural circuits, we show how we use genetic algorithms (GAs) to configure parameters for a network of simple integrate and fire with adaptation neurons. The GA approach is demonstrated both in software simulation and hardware implementation on a reconfigurable custom very large scale integration chip. PMID:20959265

A modular architecture for transparent computation in recurrent neural networks.

PubMed

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

2017-01-01

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

Neural analysis of bovine ovaries ultrasound images in the identification process of the corpus luteum

NASA Astrophysics Data System (ADS)

Górna, K.; Jaśkowski, B. M.; Okoń, P.; Czechlowski, M.; Koszela, K.; Zaborowicz, M.; Idziaszek, P.

2017-07-01

The aim of the paper is to shown the neural image analysis as a method useful for identifying the development stage of the domestic bovine corpus luteum on digital USG (UltraSonoGraphy) images. Corpus luteum (CL) is a transient endocrine gland that develops after ovulation from the follicle secretory cells. The aim of CL is the production of progesterone, which regulates many reproductive functions. In the presented studies, identification of the corpus luteum was carried out on the basis of information contained in ultrasound digital images. Development stage of the corpus luteum was considered in two aspects: just before and middle of domination phase and luteolysis and degradation phase. Prior to the classification, the ultrasound images have been processed using a GLCM (Gray Level Co-occurence Matrix). To generate a classification model, a Neural Networks module implemented in the STATISTICA was used. Five representative parameters describing the ultrasound image were used as learner variables. On the output of the artificial neural network was generated information about the development stage of the corpus luteum. Results of this study indicate that neural image analysis combined with GLCM texture analysis may be a useful tool for identifying the bovine corpus luteum in the context of its development phase. Best-generated artificial neural network model was the structure of MLP (Multi Layer Perceptron) 5:5-17-1:1.

Gas Sensors Characterization and Multilayer Perceptron (MLP) Hardware Implementation for Gas Identification Using a Field Programmable Gate Array (FPGA)

PubMed Central

Benrekia, Fayçal; Attari, Mokhtar; Bouhedda, Mounir

2013-01-01

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases. PMID:23529119

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.

Medical image diagnoses by artificial neural networks with image correlation, wavelet transform, simulated annealing

NASA Astrophysics Data System (ADS)

Szu, Harold H.

1993-09-01

Classical artificial neural networks (ANN) and neurocomputing are reviewed for implementing a real time medical image diagnosis. An algorithm known as the self-reference matched filter that emulates the spatio-temporal integration ability of the human visual system might be utilized for multi-frame processing of medical imaging data. A Cauchy machine, implementing a fast simulated annealing schedule, can determine the degree of abnormality by the degree of orthogonality between the patient imagery and the class of features of healthy persons. An automatic inspection process based on multiple modality image sequences is simulated by incorporating the following new developments: (1) 1-D space-filling Peano curves to preserve the 2-D neighborhood pixels' relationship; (2) fast simulated Cauchy annealing for the global optimization of self-feature extraction; and (3) a mini-max energy function for the intra-inter cluster-segregation respectively useful for top-down ANN designs.

A dynamically reconfigurable logic cell: from artificial neural networks to quantum-dot cellular automata

NASA Astrophysics Data System (ADS)

Naqvi, Syed Rameez; Akram, Tallha; Iqbal, Saba; Haider, Sajjad Ali; Kamran, Muhammad; Muhammad, Nazeer

2018-02-01

Considering the lack of optimization support for Quantum-dot Cellular Automata, we propose a dynamically reconfigurable logic cell capable of implementing various logic operations by means of artificial neural networks. The cell can be reconfigured to any 2-input combinational logic gate by altering the strength of connections, called weights and biases. We demonstrate how these cells may appositely be organized to perform multi-bit arithmetic and logic operations. The proposed work is important in that it gives a standard implementation of an 8-bit arithmetic and logic unit for quantum-dot cellular automata with minimal area and latency overhead. We also compare the proposed design with a few existing arithmetic and logic units, and show that it is more area efficient than any equivalent available in literature. Furthermore, the design is adaptable to 16, 32, and 64 bit architectures.

Efficient modeling of vector hysteresis using a novel Hopfield neural network implementation of Stoner–Wohlfarth-like operators

PubMed Central

Adly, Amr A.; Abd-El-Hafiz, Salwa K.

2012-01-01

Incorporation of hysteresis models in electromagnetic analysis approaches is indispensable to accurate field computation in complex magnetic media. Throughout those computations, vector nature and computational efficiency of such models become especially crucial when sophisticated geometries requiring massive sub-region discretization are involved. Recently, an efficient vector Preisach-type hysteresis model constructed from only two scalar models having orthogonally coupled elementary operators has been proposed. This paper presents a novel Hopfield neural network approach for the implementation of Stoner–Wohlfarth-like operators that could lead to a significant enhancement in the computational efficiency of the aforementioned model. Advantages of this approach stem from the non-rectangular nature of these operators that substantially minimizes the number of operators needed to achieve an accurate vector hysteresis model. Details of the proposed approach, its identification and experimental testing are presented in the paper. PMID:25685446

Cascade control of superheated steam temperature with neuro-PID controller.

PubMed

Zhang, Jianhua; Zhang, Fenfang; Ren, Mifeng; Hou, Guolian; Fang, Fang

2012-11-01

In this paper, an improved cascade control methodology for superheated processes is developed, in which the primary PID controller is implemented by neural networks trained by minimizing error entropy criterion. The entropy of the tracking error can be estimated recursively by utilizing receding horizon window technique. The measurable disturbances in superheated processes are input to the neuro-PID controller besides the sequences of tracking error in outer loop control system, hence, feedback control is combined with feedforward control in the proposed neuro-PID controller. The convergent condition of the neural networks is analyzed. The implementation procedures of the proposed cascade control approach are summarized. Compared with the neuro-PID controller using minimizing squared error criterion, the proposed neuro-PID controller using minimizing error entropy criterion may decrease fluctuations of the superheated steam temperature. A simulation example shows the advantages of the proposed method. Copyright © 2012 ISA. Published by Elsevier Ltd. All rights reserved.

A novel spatter detection algorithm based on typical cellular neural network operations for laser beam welding processes

NASA Astrophysics Data System (ADS)

Nicolosi, L.; Abt, F.; Blug, A.; Heider, A.; Tetzlaff, R.; Höfler, H.

2012-01-01

Real-time monitoring of laser beam welding (LBW) has increasingly gained importance in several manufacturing processes ranging from automobile production to precision mechanics. In the latter, a novel algorithm for the real-time detection of spatters was implemented in a camera based on cellular neural networks. The latter can be connected to the optics of commercially available laser machines leading to real-time monitoring of LBW processes at rates up to 15 kHz. Such high monitoring rates allow the integration of other image evaluation tasks such as the detection of the full penetration hole for real-time control of process parameters.

Spintronic characteristics of self-assembled neurotransmitter acetylcholine molecular complexes enable quantum information processing in neural networks and brain

NASA Astrophysics Data System (ADS)

Tamulis, Arvydas; Majauskaite, Kristina; Kairys, Visvaldas; Zborowski, Krzysztof; Adhikari, Kapil; Krisciukaitis, Sarunas

2016-09-01

Implementation of liquid state quantum information processing based on spatially localized electronic spin in the neurotransmitter stable acetylcholine (ACh) neutral molecular radical is discussed. Using DFT quantum calculations we proved that this molecule possesses stable localized electron spin, which may represent a qubit in quantum information processing. The necessary operating conditions for ACh molecule are formulated in self-assembled dimer and more complex systems. The main quantum mechanical research result of this paper is that the neurotransmitter ACh systems, which were proposed, include the use of quantum molecular spintronics arrays to control the neurotransmission in neural networks.

Learning in Stochastic Bit Stream Neural Networks.

PubMed

van Daalen, Max; Shawe-Taylor, John; Zhao, Jieyu

1996-08-01

This paper presents learning techniques for a novel feedforward stochastic neural network. The model uses stochastic weights and the "bit stream" data representation. It has a clean analysable functionality and is very attractive with its great potential to be implemented in hardware using standard digital VLSI technology. The design allows simulation at three different levels and learning techniques are described for each level. The lowest level corresponds to on-chip learning. Simulation results on three benchmark MONK's problems and handwritten digit recognition with a clean set of 500 16 x 16 pixel digits demonstrate that the new model is powerful enough for the real world applications. Copyright 1996 Elsevier Science Ltd

Multilayer neural networks with extensively many hidden units.

PubMed

Rosen-Zvi, M; Engel, A; Kanter, I

2001-08-13

The information processing abilities of a multilayer neural network with a number of hidden units scaling as the input dimension are studied using statistical mechanics methods. The mapping from the input layer to the hidden units is performed by general symmetric Boolean functions, whereas the hidden layer is connected to the output by either discrete or continuous couplings. Introducing an overlap in the space of Boolean functions as order parameter, the storage capacity is found to scale with the logarithm of the number of implementable Boolean functions. The generalization behavior is smooth for continuous couplings and shows a discontinuous transition to perfect generalization for discrete ones.

Nonlinear Recurrent Neural Network Predictive Control for Energy Distribution of a Fuel Cell Powered Robot

PubMed Central

Chen, Qihong; Long, Rong; Quan, Shuhai

2014-01-01

This paper presents a neural network predictive control strategy to optimize power distribution for a fuel cell/ultracapacitor hybrid power system of a robot. We model the nonlinear power system by employing time variant auto-regressive moving average with exogenous (ARMAX), and using recurrent neural network to represent the complicated coefficients of the ARMAX model. Because the dynamic of the system is viewed as operating- state- dependent time varying local linear behavior in this frame, a linear constrained model predictive control algorithm is developed to optimize the power splitting between the fuel cell and ultracapacitor. The proposed algorithm significantly simplifies implementation of the controller and can handle multiple constraints, such as limiting substantial fluctuation of fuel cell current. Experiment and simulation results demonstrate that the control strategy can optimally split power between the fuel cell and ultracapacitor, limit the change rate of the fuel cell current, and so as to extend the lifetime of the fuel cell. PMID:24707206

Analysis of tribological behaviour of zirconia reinforced Al-SiC hybrid composites using statistical and artificial neural network technique

NASA Astrophysics Data System (ADS)

Arif, Sajjad; Tanwir Alam, Md; Ansari, Akhter H.; Bilal Naim Shaikh, Mohd; Arif Siddiqui, M.

2018-05-01

The tribological performance of aluminium hybrid composites reinforced with micro SiC (5 wt%) and nano zirconia (0, 3, 6 and 9 wt%) fabricated through powder metallurgy technique were investigated using statistical and artificial neural network (ANN) approach. The influence of zirconia reinforcement, sliding distance and applied load were analyzed with test based on full factorial design of experiments. Analysis of variance (ANOVA) was used to evaluate the percentage contribution of each process parameters on wear loss. ANOVA approach suggested that wear loss be mainly influenced by sliding distance followed by zirconia reinforcement and applied load. Further, a feed forward back propagation neural network was applied on input/output date for predicting and analyzing the wear behaviour of fabricated composite. A very close correlation between experimental and ANN output were achieved by implementing the model. Finally, ANN model was effectively used to find the influence of various control factors on wear behaviour of hybrid composites.

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

PubMed

Yan, Zheng; Wang, Jun

2014-03-01

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

Intelligent fiber optic sensor for solution concentration examination

NASA Astrophysics Data System (ADS)

Borecki, Michal; Kruszewski, Jerzy

2003-09-01

This paper presents the working principles of intelligent fiber-optic intensity sensor used for solution concentration examination. The sensor head is the ending of the large core polymer optical fiber. The head works on the reflection intensity basis. The reflected signal level depends on Fresnel reflection and reflection on suspended matter when the head is submersed in solution. The sensor head is mounted on a lift. For detection purposes the signal includes head submerging, submersion, emerging and emergence is measured. This way the viscosity turbidity and refraction coefficient has an effect on measured signal. The signal forthcoming from head is processed electrically in opto-electronic interface. Then it is feed to neural network. The novelty of presented sensor is implementation of neural network that works in generalization mode. The sensor resolution depends on opto-electronic signal conversion precision and neural network learning accuracy. Therefore, the number and quality of points used for learning process is very important. The example sensor application for examination of liquid soap concentration in water is presented in the paper.

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

NASA Technical Reports Server (NTRS)

Hopkins, Dale A.; Patnaik, Surya N.

2000-01-01

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

Space time neural networks for tether operations in space

NASA Technical Reports Server (NTRS)

Lea, Robert N.; Villarreal, James A.; Jani, Yashvant; Copeland, Charles

1993-01-01

A space shuttle flight scheduled for 1992 will attempt to prove the feasibility of operating tethered payloads in earth orbit. due to the interaction between the Earth's magnetic field and current pulsing through the tether, the tethered system may exhibit a circular transverse oscillation referred to as the 'skiprope' phenomenon. Effective damping of skiprope motion depends on rapid and accurate detection of skiprope magnitude and phase. Because of non-linear dynamic coupling, the satellite attitude behavior has characteristic oscillations during the skiprope motion. Since the satellite attitude motion has many other perturbations, the relationship between the skiprope parameters and attitude time history is very involved and non-linear. We propose a Space-Time Neural Network implementation for filtering satellite rate gyro data to rapidly detect and predict skiprope magnitude and phase. Training and testing of the skiprope detection system will be performed using a validated Orbital Operations Simulator and Space-Time Neural Network software developed in the Software Technology Branch at NASA's Lyndon B. Johnson Space Center.

Bayesian estimation inherent in a Mexican-hat-type neural network

NASA Astrophysics Data System (ADS)

Takiyama, Ken

2016-05-01

Brain functions, such as perception, motor control and learning, and decision making, have been explained based on a Bayesian framework, i.e., to decrease the effects of noise inherent in the human nervous system or external environment, our brain integrates sensory and a priori information in a Bayesian optimal manner. However, it remains unclear how Bayesian computations are implemented in the brain. Herein, I address this issue by analyzing a Mexican-hat-type neural network, which was used as a model of the visual cortex, motor cortex, and prefrontal cortex. I analytically demonstrate that the dynamics of an order parameter in the model corresponds exactly to a variational inference of a linear Gaussian state-space model, a Bayesian estimation, when the strength of recurrent synaptic connectivity is appropriately stronger than that of an external stimulus, a plausible condition in the brain. This exact correspondence can reveal the relationship between the parameters in the Bayesian estimation and those in the neural network, providing insight for understanding brain functions.

Training feed-forward neural networks with gain constraints

PubMed

Hartman

2000-04-01

Inaccurate input-output gains (partial derivatives of outputs with respect to inputs) are common in neural network models when input variables are correlated or when data are incomplete or inaccurate. Accurate gains are essential for optimization, control, and other purposes. We develop and explore a method for training feedforward neural networks subject to inequality or equality-bound constraints on the gains of the learned mapping. Gain constraints are implemented as penalty terms added to the objective function, and training is done using gradient descent. Adaptive and robust procedures are devised for balancing the relative strengths of the various terms in the objective function, which is essential when the constraints are inconsistent with the data. The approach has the virtue that the model domain of validity can be extended via extrapolation training, which can dramatically improve generalization. The algorithm is demonstrated here on artificial and real-world problems with very good results and has been advantageously applied to dozens of models currently in commercial use.

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.

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

Ciuca, Razvan; Hernández, Oscar F., E-mail: razvan.ciuca@mail.mcgill.ca, E-mail: oscarh@physics.mcgill.ca

There exists various proposals to detect cosmic strings from Cosmic Microwave Background (CMB) or 21 cm temperature maps. Current proposals do not aim to find the location of strings on sky maps, all of these approaches can be thought of as a statistic on a sky map. We propose a Bayesian interpretation of cosmic string detection and within that framework, we derive a connection between estimates of cosmic string locations and cosmic string tension G μ. We use this Bayesian framework to develop a machine learning framework for detecting strings from sky maps and outline how to implement this frameworkmore » with neural networks. The neural network we trained was able to detect and locate cosmic strings on noiseless CMB temperature map down to a string tension of G μ=5 ×10{sup −9} and when analyzing a CMB temperature map that does not contain strings, the neural network gives a 0.95 probability that G μ≤2.3×10{sup −9}.« less

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

PubMed

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

2011-11-01

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

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.

Large-Scale Simulations of Plastic Neural Networks on Neuromorphic Hardware

PubMed Central

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

2016-01-01

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

An application of artificial neural networks to experimental data approximation

NASA Technical Reports Server (NTRS)

Meade, Andrew J., Jr.

1993-01-01

As an initial step in the evaluation of networks, a feedforward architecture is trained to approximate experimental data by the backpropagation algorithm. Several drawbacks were detected and an alternative learning algorithm was then developed to partially address the drawbacks. This noniterative algorithm has a number of advantages over the backpropagation method and is easily implemented on existing hardware.

[Motivation and Emotional States: Structural Systemic, Neurochemical, Molecular and Cellular Mechanisms].

PubMed

Bazyan, A S

2016-01-01

The structural, systemic, neurochemical, molecular and cellular mechanisms of organization and coding motivation and emotional states are describe. The GABA and glutamatergic synaptic systems of basal ganglia form a neural network and participate in the implementation of voluntary behavior. Neuropeptides, neurohormones and paracrine neuromodulators involved in the organization of motivation and emotional states, integrated with synaptic systems, controlled by neural networks and organizing goal-directed behavior. Structural centers for united and integrated of information in voluntary and goal-directed behavior are globus pallidus. Substantia nigra pars reticulata switches the information from corticobasal networks to thalamocortical networks, induces global dopaminergic (DA) signal and organize interaction of mesolimbic and nigostriatnoy DA systems controlled by prefrontal and motor cortex. Together with the motor cortex, substantia nigra displays information in the brainstem and spinal cord to implementation of behavior. Motivation states are formed in the interaction of neurohormonal and neuropeptide systems by monoaminergic systems of brain. Emotional states are formed by monoaminergic systems of the mid-brain, where the leading role belongs to the mesolimbic DA system. The emotional and motivation state of the encoded specific epigenetic molecular and chemical pattern of neuron.