Thinking Like a Human

NASA Technical Reports Server (NTRS)

1999-01-01

Accurate Automation Corporation (AAC) of Chattanooga, TN, developed a neural network processor (NNP) for use onboard the NASA- and Air Force-sponsored LoFLYTE aircraft. The processor is modeled after connections in the brain.

CPU architecture for a fast and energy-saving calculation of convolution neural networks

NASA Astrophysics Data System (ADS)

Knoll, Florian J.; Grelcke, Michael; Czymmek, Vitali; Holtorf, Tim; Hussmann, Stephan

2017-06-01

One of the most difficult problem in the use of artificial neural networks is the computational capacity. Although large search engine companies own specially developed hardware to provide the necessary computing power, for the conventional user only remains the state of the art method, which is the use of a graphic processing unit (GPU) as a computational basis. Although these processors are well suited for large matrix computations, they need massive energy. Therefore a new processor on the basis of a field programmable gate array (FPGA) has been developed and is optimized for the application of deep learning. This processor is presented in this paper. The processor can be adapted for a particular application (in this paper to an organic farming application). The power consumption is only a fraction of a GPU application and should therefore be well suited for energy-saving applications.

Neural network post-processing of grayscale optical correlator

NASA Technical Reports Server (NTRS)

Lu, Thomas T; Hughlett, Casey L.; Zhoua, Hanying; Chao, Tien-Hsin; Hanan, Jay C.

2005-01-01

In this paper we present the use of a radial basis function neural network (RBFNN) as a post-processor to assist the optical correlator to identify the objects and to reject false alarms. Image plane features near the correlation peaks are extracted and fed to the neural network for analysis. The approach is capable of handling large number of object variations and filter sets. Preliminary experimental results are presented and the performance is analyzed.

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

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin

1991-01-01

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

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.

Implementation of pulse-coupled neural networks in a CNAPS environment.

PubMed

Kinser, J M; Lindblad, T

1999-01-01

Pulse coupled neural networks (PCNN's) are biologically inspired algorithms very well suited for image/signal preprocessing. While several analog implementations are proposed we suggest a digital implementation in an existing environment, the connected network of adapted processors system (CNAPS). The reason for this is two fold. First, CNAPS is a commercially available chip which has been used for several neural-network implementations. Second, the PCNN is, in almost all applications, a very efficient component of a system requiring subsequent and additional processing. This may include gating, Fourier transforms, neural classifiers, data mining, etc, with or without feedback to the PCNN.

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

PubMed

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

2008-08-01

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

Neural networks for calibration tomography

NASA Technical Reports Server (NTRS)

Decker, Arthur

1993-01-01

Artificial neural networks are suitable for performing pattern-to-pattern calibrations. These calibrations are potentially useful for facilities operations in aeronautics, the control of optical alignment, and the like. Computed tomography is compared with neural net calibration tomography for estimating density from its x-ray transform. X-ray transforms are measured, for example, in diffuse-illumination, holographic interferometry of fluids. Computed tomography and neural net calibration tomography are shown to have comparable performance for a 10 degree viewing cone and 29 interferograms within that cone. The system of tomography discussed is proposed as a relevant test of neural networks and other parallel processors intended for using flow visualization data.

Neural nets on the MPP

NASA Technical Reports Server (NTRS)

Hastings, Harold M.; Waner, Stefan

1987-01-01

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

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.

Spiking neural networks on high performance computer clusters

NASA Astrophysics Data System (ADS)

Chen, Chong; Taha, Tarek M.

2011-09-01

In this paper we examine the acceleration of two spiking neural network models on three clusters of multicore processors representing three categories of processors: x86, STI Cell, and NVIDIA GPGPUs. The x86 cluster utilized consists of 352 dualcore AMD Opterons, the Cell cluster consists of 320 Sony Playstation 3s, while the GPGPU cluster contains 32 NVIDIA Tesla S1070 systems. The results indicate that the GPGPU platform can dominate in performance compared to the Cell and x86 platforms examined. From a cost perspective, the GPGPU is more expensive in terms of neuron/s throughput. If the cost of GPGPUs go down in the future, this platform will become very cost effective for these models.

USC orthogonal multiprocessor for image processing with neural networks

NASA Astrophysics Data System (ADS)

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

1990-07-01

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

Neural network with dynamically adaptable neurons

NASA Technical Reports Server (NTRS)

Tawel, Raoul (Inventor)

1994-01-01

This invention is an adaptive neuron for use in neural network processors. The adaptive neuron participates in the supervised learning phase of operation on a co-equal basis with the synapse matrix elements by adaptively changing its gain in a similar manner to the change of weights in the synapse IO elements. In this manner, training time is decreased by as much as three orders of magnitude.

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).

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.

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.

Hot Chips and Hot Interconnects for High End Computing Systems

NASA Technical Reports Server (NTRS)

Saini, Subhash

2005-01-01

I will discuss several processors: 1. The Cray proprietary processor used in the Cray X1; 2. The IBM Power 3 and Power 4 used in an IBM SP 3 and IBM SP 4 systems; 3. The Intel Itanium and Xeon, used in the SGI Altix systems and clusters respectively; 4. IBM System-on-a-Chip used in IBM BlueGene/L; 5. HP Alpha EV68 processor used in DOE ASCI Q cluster; 6. SPARC64 V processor, which is used in the Fujitsu PRIMEPOWER HPC2500; 7. An NEC proprietary processor, which is used in NEC SX-6/7; 8. Power 4+ processor, which is used in Hitachi SR11000; 9. NEC proprietary processor, which is used in Earth Simulator. The IBM POWER5 and Red Storm Computing Systems will also be discussed. The architectures of these processors will first be presented, followed by interconnection networks and a description of high-end computer systems based on these processors and networks. The performance of various hardware/programming model combinations will then be compared, based on latest NAS Parallel Benchmark results (MPI, OpenMP/HPF and hybrid (MPI + OpenMP). The tutorial will conclude with a discussion of general trends in the field of high performance computing, (quantum computing, DNA computing, cellular engineering, and neural networks).

Using Neural Networks in Decision Making for a Reconfigurable Electro Mechanical Actuator (EMA)

NASA Technical Reports Server (NTRS)

Latino, Carl D.

2001-01-01

The objectives of this project were to demonstrate applicability and advantages of a neural network approach for evaluating the performance of an electro-mechanical actuator (EMA). The EMA in question was intended for the X-37 Advanced Technology Vehicle. It will have redundant components for safety and reliability. The neural networks for this application are to monitor the operation of the redundant electronics that control the actuator in real time and decide on the operating configuration. The system we proposed consists of the actuator, sensors, control circuitry and dedicated (embedded) processors. The main purpose of the study was to develop suitable hardware and neural network capable of allowing real time reconfiguration decisions to be made. This approach was to be compared to other methods such as fuzzy logic and knowledge based systems considered for the same application. Over the course of the project a more general objective was the identification of the other neural network applications and the education of interested NASA personnel on the topic of Neural Networks.

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

Multiprocessor Neural Network in Healthcare.

PubMed

Godó, Zoltán Attila; Kiss, Gábor; Kocsis, Dénes

2015-01-01

A possible way of creating a multiprocessor artificial neural network is by the use of microcontrollers. The RISC processors' high performance and the large number of I/O ports mean they are greatly suitable for creating such a system. During our research, we wanted to see if it is possible to efficiently create interaction between the artifical neural network and the natural nervous system. To achieve as much analogy to the living nervous system as possible, we created a frequency-modulated analog connection between the units. Our system is connected to the living nervous system through 128 microelectrodes. Two-way communication is provided through A/D transformation, which is even capable of testing psychopharmacons. The microcontroller-based analog artificial neural network can play a great role in medical singal processing, such as ECG, EEG etc.

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)

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

NASA Astrophysics Data System (ADS)

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

1997-04-01

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

Real-time support for high performance aircraft operation

NASA Technical Reports Server (NTRS)

Vidal, Jacques J.

1989-01-01

The feasibility of real-time processing schemes using artificial neural networks (ANNs) is investigated. A rationale for digital neural nets is presented and a general processor architecture for control applications is illustrated. Research results on ANN structures for real-time applications are given. Research results on ANN algorithms for real-time control are also shown.

A Scalable Multicore Architecture With Heterogeneous Memory Structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs).

PubMed

Moradi, Saber; Qiao, Ning; Stefanini, Fabio; Indiveri, Giacomo

2018-02-01

Neuromorphic computing systems comprise networks of neurons that use asynchronous events for both computation and communication. This type of representation offers several advantages in terms of bandwidth and power consumption in neuromorphic electronic systems. However, managing the traffic of asynchronous events in large scale systems is a daunting task, both in terms of circuit complexity and memory requirements. Here, we present a novel routing methodology that employs both hierarchical and mesh routing strategies and combines heterogeneous memory structures for minimizing both memory requirements and latency, while maximizing programming flexibility to support a wide range of event-based neural network architectures, through parameter configuration. We validated the proposed scheme in a prototype multicore neuromorphic processor chip that employs hybrid analog/digital circuits for emulating synapse and neuron dynamics together with asynchronous digital circuits for managing the address-event traffic. We present a theoretical analysis of the proposed connectivity scheme, describe the methods and circuits used to implement such scheme, and characterize the prototype chip. Finally, we demonstrate the use of the neuromorphic processor with a convolutional neural network for the real-time classification of visual symbols being flashed to a dynamic vision sensor (DVS) at high speed.

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

Development and Flight Testing of a Neural Network Based Flight Control System on the NF-15B Aircraft

NASA Technical Reports Server (NTRS)

Bomben, Craig R.; Smolka, James W.; Bosworth, John T.; Silliams-Hayes, Peggy S.; Burken, John J.; Larson, Richard R.; Buschbacher, Mark J.; Maliska, Heather A.

2006-01-01

The Intelligent Flight Control System (IFCS) project at the NASA Dryden Flight Research Center, Edwards AFB, CA, has been investigating the use of neural network based adaptive control on a unique NF-15B test aircraft. The IFCS neural network is a software processor that stores measured aircraft response information to dynamically alter flight control gains. In 2006, the neural network was engaged and allowed to learn in real time to dynamically alter the aircraft handling qualities characteristics in the presence of actual aerodynamic failure conditions injected into the aircraft through the flight control system. The use of neural network and similar adaptive technologies in the design of highly fault and damage tolerant flight control systems shows promise in making future aircraft far more survivable than current technology allows. This paper will present the results of the IFCS flight test program conducted at the NASA Dryden Flight Research Center in 2006, with emphasis on challenges encountered and lessons learned.

APRON: A Cellular Processor Array Simulation and Hardware Design Tool

NASA Astrophysics Data System (ADS)

Barr, David R. W.; Dudek, Piotr

2009-12-01

We present a software environment for the efficient simulation of cellular processor arrays (CPAs). This software (APRON) is used to explore algorithms that are designed for massively parallel fine-grained processor arrays, topographic multilayer neural networks, vision chips with SIMD processor arrays, and related architectures. The software uses a highly optimised core combined with a flexible compiler to provide the user with tools for the design of new processor array hardware architectures and the emulation of existing devices. We present performance benchmarks for the software processor array implemented on standard commodity microprocessors. APRON can be configured to use additional processing hardware if necessary and can be used as a complete graphical user interface and development environment for new or existing CPA systems, allowing more users to develop algorithms for CPA systems.

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.

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.

Neural-network dedicated processor for solving competitive assignment problems

NASA Technical Reports Server (NTRS)

Eberhardt, Silvio P. (Inventor)

1993-01-01

A neural-network processor for solving first-order competitive assignment problems consists of a matrix of N x M processing units, each of which corresponds to the pairing of a first number of elements of (R sub i) with a second number of elements (C sub j), wherein limits of the first number are programmed in row control superneurons, and limits of the second number are programmed in column superneurons as MIN and MAX values. The cost (weight) W sub ij of the pairings is programmed separately into each PU. For each row and column of PU's, a dedicated constraint superneuron insures that the number of active neurons within the associated row or column fall within a specified range. Annealing is provided by gradually increasing the PU gain for each row and column or increasing positive feedback to each PU, the latter being effective to increase hysteresis of each PU or by combining both of these techniques.

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.

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.

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.

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

NASA Astrophysics Data System (ADS)

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

1996-10-01

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

Color sensor and neural processor on one chip

NASA Astrophysics Data System (ADS)

Fiesler, Emile; Campbell, Shannon R.; Kempem, Lother; Duong, Tuan A.

1998-10-01

Low-cost, compact, and robust color sensor that can operate in real-time under various environmental conditions can benefit many applications, including quality control, chemical sensing, food production, medical diagnostics, energy conservation, monitoring of hazardous waste, and recycling. Unfortunately, existing color sensor are either bulky and expensive or do not provide the required speed and accuracy. In this publication we describe the design of an accurate real-time color classification sensor, together with preprocessing and a subsequent neural network processor integrated on a single complementary metal oxide semiconductor (CMOS) integrated circuit. This one-chip sensor and information processor will be low in cost, robust, and mass-producible using standard commercial CMOS processes. The performance of the chip and the feasibility of its manufacturing is proven through computer simulations based on CMOS hardware parameters. Comparisons with competing methodologies show a significantly higher performance for our device.

The 2nd Symposium on the Frontiers of Massively Parallel Computations

NASA Technical Reports Server (NTRS)

Mills, Ronnie (Editor)

1988-01-01

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

Data systems and computer science programs: Overview

NASA Technical Reports Server (NTRS)

Smith, Paul H.; Hunter, Paul

1991-01-01

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

The cognitive structural approach for image restoration

NASA Astrophysics Data System (ADS)

Mardare, Igor; Perju, Veacheslav; Casasent, David

2008-03-01

It is analyzed the important and actual problem of the defective images of scenes restoration. The proposed approach provides restoration of scenes by a system on the basis of human intelligence phenomena reproduction used for restoration-recognition of images. The cognitive models of the restoration process are elaborated. The models are realized by the intellectual processors constructed on the base of neural networks and associative memory using neural network simulator NNToolbox from MATLAB 7.0. The models provides restoration and semantic designing of images of scenes under defective images of the separate objects.

Design and simulation of programmable relational optoelectronic time-pulse coded processors as base elements for sorting neural networks

NASA Astrophysics Data System (ADS)

Krasilenko, Vladimir G.; Nikolsky, Alexander I.; Lazarev, Alexander A.; Lazareva, Maria V.

2010-05-01

In the paper we show that the biologically motivated conception of time-pulse encoding usage gives a set of advantages (single methodological basis, universality, tuning simplicity, learning and programming et al) at creation and design of sensor systems with parallel input-output and processing for 2D structures hybrid and next generations neuro-fuzzy neurocomputers. We show design principles of programmable relational optoelectronic time-pulse encoded processors on the base of continuous logic, order logic and temporal waves processes. We consider a structure that execute analog signal extraction, analog and time-pulse coded variables sorting. We offer optoelectronic realization of such base relational order logic element, that consists of time-pulse coded photoconverters (pulse-width and pulse-phase modulators) with direct and complementary outputs, sorting network on logical elements and programmable commutation blocks. We make technical parameters estimations of devices and processors on such base elements by simulation and experimental research: optical input signals power 0.2 - 20 uW, processing time 1 - 10 us, supply voltage 1 - 3 V, consumption power 10 - 100 uW, extended functional possibilities, learning possibilities. We discuss some aspects of possible rules and principles of learning and programmable tuning on required function, relational operation and realization of hardware blocks for modifications of such processors. We show that it is possible to create sorting machines, neural networks and hybrid data-processing systems with untraditional numerical systems and pictures operands on the basis of such quasiuniversal hardware simple blocks with flexible programmable tuning.

Artificial and Bayesian Neural Networks

PubMed

Korhani Kangi, Azam; Bahrampour, Abbas

2018-02-26

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

DeepX: Deep Learning Accelerator for Restricted Boltzmann Machine Artificial Neural Networks.

PubMed

Kim, Lok-Won

2018-05-01

Although there have been many decades of research and commercial presence on high performance general purpose processors, there are still many applications that require fully customized hardware architectures for further computational acceleration. Recently, deep learning has been successfully used to learn in a wide variety of applications, but their heavy computation demand has considerably limited their practical applications. This paper proposes a fully pipelined acceleration architecture to alleviate high computational demand of an artificial neural network (ANN) which is restricted Boltzmann machine (RBM) ANNs. The implemented RBM ANN accelerator (integrating network size, using 128 input cases per batch, and running at a 303-MHz clock frequency) integrated in a state-of-the art field-programmable gate array (FPGA) (Xilinx Virtex 7 XC7V-2000T) provides a computational performance of 301-billion connection-updates-per-second and about 193 times higher performance than a software solution running on general purpose processors. Most importantly, the architecture enables over 4 times (12 times in batch learning) higher performance compared with a previous work when both are implemented in an FPGA device (XC2VP70).

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

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

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

1992-10-01

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

Parsing recursive sentences with a connectionist model including a neural stack and synaptic gating.

PubMed

Fedor, Anna; Ittzés, Péter; Szathmáry, Eörs

2011-02-21

It is supposed that humans are genetically predisposed to be able to recognize sequences of context-free grammars with centre-embedded recursion while other primates are restricted to the recognition of finite state grammars with tail-recursion. Our aim was to construct a minimalist neural network that is able to parse artificial sentences of both grammars in an efficient way without using the biologically unrealistic backpropagation algorithm. The core of this network is a neural stack-like memory where the push and pop operations are regulated by synaptic gating on the connections between the layers of the stack. The network correctly categorizes novel sentences of both grammars after training. We suggest that the introduction of the neural stack memory will turn out to be substantial for any biological 'hierarchical processor' and the minimalist design of the model suggests a quest for similar, realistic neural architectures. Copyright © 2010 Elsevier Ltd. All rights reserved.

Extended Logic Intelligent Processing System for a Sensor Fusion Processor Hardware

NASA Technical Reports Server (NTRS)

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

2000-01-01

The paper presents the hardware implementation and initial tests from a low-power, highspeed reconfigurable sensor fusion processor. The Extended Logic Intelligent Processing System (ELIPS) is described, which combines rule-based systems, fuzzy logic, and neural networks to achieve parallel fusion of sensor signals in compact low power VLSI. The development of the ELIPS concept is being done to demonstrate the interceptor functionality which particularly underlines the high speed and low power requirements. The hardware programmability allows the processor to reconfigure into different machines, taking the most efficient hardware implementation during each phase of information processing. Processing speeds of microseconds have been demonstrated using our test hardware.

Vigilante: Ultrafast Smart Sensor for Target Recognition and Precision Tracking in a Simulated CMD Scenario

NASA Technical Reports Server (NTRS)

Uldomkesmalee, Suraphol; Suddarth, Steven C.

1997-01-01

VIGILANTE is an ultrafast smart sensor testbed for generic Automatic Target Recognition (ATR) applications with a series of capability demonstration focussed on cruise missile defense (CMD). VIGILANTE's sensor/processor architecture is based on next-generation UV/visible/IR sensors and a tera-operations per second sugar-cube processor, as well as supporting airborne vehicle. Excellent results of efficient ATR methodologies that use an eigenvectors/neural network combination and feature-based precision tracking have been demonstrated in the laboratory environment.

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.

Programmed optoelectronic time-pulse coded relational processor as base element for sorting neural networks

NASA Astrophysics Data System (ADS)

Krasilenko, Vladimir G.; Bardachenko, Vitaliy F.; Nikolsky, Alexander I.; Lazarev, Alexander A.

2007-04-01

In the paper we show that the biologically motivated conception of the use of time-pulse encoding gives the row of advantages (single methodological basis, universality, simplicity of tuning, training and programming et al) at creation and designing of sensor systems with parallel input-output and processing, 2D-structures of hybrid and neuro-fuzzy neurocomputers of next generations. We show principles of construction of programmable relational optoelectronic time-pulse coded processors, continuous logic, order logic and temporal waves processes, that lie in basis of the creation. We consider structure that executes extraction of analog signal of the set grade (order), sorting of analog and time-pulse coded variables. We offer optoelectronic realization of such base relational elements of order logic, which consists of time-pulse coded phototransformers (pulse-width and pulse-phase modulators) with direct and complementary outputs, sorting network on logical elements and programmable commutations blocks. We make estimations of basic technical parameters of such base devices and processors on their basis by simulation and experimental research: power of optical input signals - 0.200-20 μW, processing time - microseconds, supply voltage - 1.5-10 V, consumption power - hundreds of microwatts per element, extended functional possibilities, training possibilities. We discuss some aspects of possible rules and principles of training and programmable tuning on the required function, relational operation and realization of hardware blocks for modifications of such processors. We show as on the basis of such quasiuniversal hardware simple block and flexible programmable tuning it is possible to create sorting machines, neural networks and hybrid data-processing systems with the untraditional numerical systems and pictures operands.

Neurovision processor for designing intelligent sensors

NASA Astrophysics Data System (ADS)

Gupta, Madan M.; Knopf, George K.

1992-03-01

A programmable multi-task neuro-vision processor, called the Positive-Negative (PN) neural processor, is proposed as a plausible hardware mechanism for constructing robust multi-task vision sensors. The computational operations performed by the PN neural processor are loosely based on the neural activity fields exhibited by certain nervous tissue layers situated in the brain. The neuro-vision processor can be programmed to generate diverse dynamic behavior that may be used for spatio-temporal stabilization (STS), short-term visual memory (STVM), spatio-temporal filtering (STF) and pulse frequency modulation (PFM). A multi- functional vision sensor that performs a variety of information processing operations on time- varying two-dimensional sensory images can be constructed from a parallel and hierarchical structure of numerous individually programmed PN neural processors.

Performance and Power Optimization for Cognitive Processor Design Using Deep-Submicron Very Large Scale Integration (VLSI) Technology

DTIC Science & Technology

2010-03-01

DATES COVERED (From - To) October 2008 – October 2009 4 . TITLE AND SUBTITLE PERFORMANCE AND POWER OPTIMIZATION FOR COGNITIVE PROCESSOR DESIGN USING...Computations 2  2.2  Cognitive Models and Algorithms for Intelligent Text Recognition 4   2.2.1 Brain-State-in-a-Box Neural Network Model. 4   2.2.2...The ASIC-style design and synthesis flow for FPU 8  Figure 4 : Screen shots of the final layouts 10  Figure 5: Projected performance and power roadmap

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.

(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.

JPRS Report, Science & Technology, Europe.

DTIC Science & Technology

1991-04-30

processor in collaboration with Intel . The processor , christened Touchstone, will be used as the core of a parallel computer with 2,000 processors . One of...ELECTRONIQUE HEBDO in French 24 Jan 91 pp 14-15 [Article by Claire Remy: "Everything Set for Neural Signal Processors " first paragraph is ELECTRONIQUE...paving the way for neural signal processors in so doing. The principal advantage of this specific circuit over a neuromimetic software program is

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.

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

NASA Astrophysics Data System (ADS)

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

2016-03-01

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

Application of Neural Networks to Predict UH-60L Electrical Generator Condition using (IMD-HUMS) Data

DTIC Science & Technology

2006-12-01

Data transfer unit ( DTU ) • Remote data concentrator (RDC) • Main processor unit (MPU) • 2 junction boxes (JB1/JB2) • 20 drive train and...NETWORKS TO PREDICT UH-60L ELECTRICAL GENERATOR CONDITION USING (IMD-HUMS) DATA by Evangelos Tourvalis December 2006 Thesis Advisor...including the time for reviewing instruction, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the

A fully integrated mixed-signal neural processor for implantable multichannel cortical recording.

PubMed

Sodagar, Amir M; Wise, Kensall D; Najafi, Khalil

2007-06-01

A 64-channel neural processor has been developed for use in an implantable neural recording microsystem. In the Scan Mode, the processor is capable of detecting neural spikes by programmable positive, negative, or window thresholding. Spikes are tagged with their associated channel addresses and formed into 18-bit data words that are sent serially to the external host. In the Monitor Mode, two channels can be selected and viewed at high resolution for studies where the entire signal is of interest. The processor runs from a 3-V supply and a 2-MHz clock, with a channel scan rate of 64 kS/s and an output bit rate of 2 Mbps.

Low power signal processing research at Stanford

NASA Technical Reports Server (NTRS)

Burr, J.; Williamson, P. R.; Peterson, A.

1991-01-01

This paper gives an overview of the research being conducted at Stanford University's Space, Telecommunications, and Radioscience Laboratory in the area of low energy computation. It discusses the work we are doing in large scale digital VLSI neural networks, interleaved processor and pipelined memory architectures, energy estimation and optimization, multichip module packaging, and low voltage digital logic.

Neural network face recognition using wavelets

NASA Astrophysics Data System (ADS)

Karunaratne, Passant V.; Jouny, Ismail I.

1997-04-01

The recognition of human faces is a phenomenon that has been mastered by the human visual system and that has been researched extensively in the domain of computer neural networks and image processing. This research is involved in the study of neural networks and wavelet image processing techniques in the application of human face recognition. The objective of the system is to acquire a digitized still image of a human face, carry out pre-processing on the image as required, an then, given a prior database of images of possible individuals, be able to recognize the individual in the image. The pre-processing segment of the system includes several procedures, namely image compression, denoising, and feature extraction. The image processing is carried out using Daubechies wavelets. Once the images have been passed through the wavelet-based image processor they can be efficiently analyzed by means of a neural network. A back- propagation neural network is used for the recognition segment of the system. The main constraints of the system is with regard to the characteristics of the images being processed. The system should be able to carry out effective recognition of the human faces irrespective of the individual's facial-expression, presence of extraneous objects such as head-gear or spectacles, and face/head orientation. A potential application of this face recognition system would be as a secondary verification method in an automated teller machine.

Advances in optical information processing IV; Proceedings of the Meeting, Orlando, FL, Apr. 18-20, 1990

NASA Astrophysics Data System (ADS)

Pape, Dennis R.

1990-09-01

The present conference discusses topics in optical image processing, optical signal processing, acoustooptic spectrum analyzer systems and components, and optical computing. Attention is given to tradeoffs in nonlinearly recorded matched filters, miniature spatial light modulators, detection and classification using higher-order statistics of optical matched filters, rapid traversal of an image data base using binary synthetic discriminant filters, wideband signal processing for emitter location, an acoustooptic processor for autonomous SAR guidance, and sampling of Fresnel transforms. Also discussed are an acoustooptic RF signal-acquisition system, scanning acoustooptic spectrum analyzers, the effects of aberrations on acoustooptic systems, fast optical digital arithmetic processors, information utilization in analog and digital processing, optical processors for smart structures, and a self-organizing neural network for unsupervised learning.

Optical Neural Classification Of Binary Patterns

NASA Astrophysics Data System (ADS)

Gustafson, Steven C.; Little, Gordon R.

1988-05-01

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

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

NASA Astrophysics Data System (ADS)

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

2018-03-01

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

A universal concept based on cellular neural networks for ultrafast and flexible solving of differential equations.

PubMed

Chedjou, Jean Chamberlain; Kyamakya, Kyandoghere

2015-04-01

This paper develops and validates a comprehensive and universally applicable computational concept for solving nonlinear differential equations (NDEs) through a neurocomputing concept based on cellular neural networks (CNNs). High-precision, stability, convergence, and lowest-possible memory requirements are ensured by the CNN processor architecture. A significant challenge solved in this paper is that all these cited computing features are ensured in all system-states (regular or chaotic ones) and in all bifurcation conditions that may be experienced by NDEs.One particular quintessence of this paper is to develop and demonstrate a solver concept that shows and ensures that CNN processors (realized either in hardware or in software) are universal solvers of NDE models. The solving logic or algorithm of given NDEs (possible examples are: Duffing, Mathieu, Van der Pol, Jerk, Chua, Rössler, Lorenz, Burgers, and the transport equations) through a CNN processor system is provided by a set of templates that are computed by our comprehensive templates calculation technique that we call nonlinear adaptive optimization. This paper is therefore a significant contribution and represents a cutting-edge real-time computational engineering approach, especially while considering the various scientific and engineering applications of this ultrafast, energy-and-memory-efficient, and high-precise NDE solver concept. For illustration purposes, three NDE models are demonstratively solved, and related CNN templates are derived and used: the periodically excited Duffing equation, the Mathieu equation, and the transport equation.

Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses

NASA Astrophysics Data System (ADS)

Serb, Alexander; Bill, Johannes; Khiat, Ali; Berdan, Radu; Legenstein, Robert; Prodromakis, Themis

2016-09-01

In an increasingly data-rich world the need for developing computing systems that cannot only process, but ideally also interpret big data is becoming continuously more pressing. Brain-inspired concepts have shown great promise towards addressing this need. Here we demonstrate unsupervised learning in a probabilistic neural network that utilizes metal-oxide memristive devices as multi-state synapses. Our approach can be exploited for processing unlabelled data and can adapt to time-varying clusters that underlie incoming data by supporting the capability of reversible unsupervised learning. The potential of this work is showcased through the demonstration of successful learning in the presence of corrupted input data and probabilistic neurons, thus paving the way towards robust big-data processors.

Analog hardware for delta-backpropagation neural networks

NASA Technical Reports Server (NTRS)

Eberhardt, Silvio P. (Inventor)

1992-01-01

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

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

Simulation of an array-based neural net model

NASA Technical Reports Server (NTRS)

Barnden, John A.

1987-01-01

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

VLSI neuroprocessors

NASA Technical Reports Server (NTRS)

Kemeny, Sabrina E.

1994-01-01

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

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.

Vision-Based Navigation and Parallel Computing

DTIC Science & Technology

1990-08-01

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

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

DTIC Science & Technology

2012-11-01

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

Satellite communications for the next generation telecommunication services and networks

NASA Technical Reports Server (NTRS)

Chitre, D. M.

1991-01-01

Satellite communications can play an important role in provisioning the next-generation telecommunication services and networks, provided the protocols specifying these services and networks are satellite-compatible and the satellite subnetworks, consisting of earth stations interconnected by the processor and the switch on board the satellite, interwork effectively with the terrestrial networks. The specific parameters and procedures of frame relay and broadband integrated services digital network (B-ISDN) protocols which are impacted by a satellite delay. Congestion and resource management functions for frame relay and B-ISDN are discussed in detail, describing the division of these functions between earth stations and on board the satellite. Specific onboard and ground functions are identified as potential candidates for their implementation via neural network technology.

Simple Algorithms for Distributed Leader Election in Anonymous Synchronous Rings and Complete Networks Inspired by Neural Development in Fruit Flies.

PubMed

Xu, Lei; Jeavons, Peter

2015-11-01

Leader election in anonymous rings and complete networks is a very practical problem in distributed computing. Previous algorithms for this problem are generally designed for a classical message passing model where complex messages are exchanged. However, the need to send and receive complex messages makes such algorithms less practical for some real applications. We present some simple synchronous algorithms for distributed leader election in anonymous rings and complete networks that are inspired by the development of the neural system of the fruit fly. Our leader election algorithms all assume that only one-bit messages are broadcast by nodes in the network and processors are only able to distinguish between silence and the arrival of one or more messages. These restrictions allow implementations to use a simpler message-passing architecture. Even with these harsh restrictions our algorithms are shown to achieve good time and message complexity both analytically and experimentally.

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.

Comparison of neuronal spike exchange methods on a Blue Gene/P supercomputer.

PubMed

Hines, Michael; Kumar, Sameer; Schürmann, Felix

2011-01-01

For neural network simulations on parallel machines, interprocessor spike communication can be a significant portion of the total simulation time. The performance of several spike exchange methods using a Blue Gene/P (BG/P) supercomputer has been tested with 8-128 K cores using randomly connected networks of up to 32 M cells with 1 k connections per cell and 4 M cells with 10 k connections per cell, i.e., on the order of 4·10(10) connections (K is 1024, M is 1024(2), and k is 1000). The spike exchange methods used are the standard Message Passing Interface (MPI) collective, MPI_Allgather, and several variants of the non-blocking Multisend method either implemented via non-blocking MPI_Isend, or exploiting the possibility of very low overhead direct memory access (DMA) communication available on the BG/P. In all cases, the worst performing method was that using MPI_Isend due to the high overhead of initiating a spike communication. The two best performing methods-the persistent Multisend method using the Record-Replay feature of the Deep Computing Messaging Framework DCMF_Multicast; and a two-phase multisend in which a DCMF_Multicast is used to first send to a subset of phase one destination cores, which then pass it on to their subset of phase two destination cores-had similar performance with very low overhead for the initiation of spike communication. Departure from ideal scaling for the Multisend methods is almost completely due to load imbalance caused by the large variation in number of cells that fire on each processor in the interval between synchronization. Spike exchange time itself is negligible since transmission overlaps with computation and is handled by a DMA controller. We conclude that ideal performance scaling will be ultimately limited by imbalance between incoming processor spikes between synchronization intervals. Thus, counterintuitively, maximization of load balance requires that the distribution of cells on processors should not reflect neural net architecture but be randomly distributed so that sets of cells which are burst firing together should be on different processors with their targets on as large a set of processors as possible.

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

Refractory pulse counting processes in stochastic neural computers.

PubMed

McNeill, Dean K; Card, Howard C

2005-03-01

This letter quantitiatively investigates the effect of a temporary refractory period or dead time in the ability of a stochastic Bernoulli processor to record subsequent pulse events, following the arrival of a pulse. These effects can arise in either the input detectors of a stochastic neural network or in subsequent processing. A transient period is observed, which increases with both the dead time and the Bernoulli probability of the dead-time free system, during which the system reaches equilibrium. Unless the Bernoulli probability is small compared to the inverse of the dead time, the mean and variance of the pulse count distributions are both appreciably reduced.

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

Real-time phase correlation based integrated system for seizure detection

NASA Astrophysics Data System (ADS)

Romaine, James B.; Delgado-Restituto, Manuel; Leñero-Bardallo, Juan A.; Rodríguez-Vázquez, Ángel

2017-05-01

This paper reports a low area, low power, integer-based digital processor for the calculation of phase synchronization between two neural signals. The processor calculates the phase-frequency content of a signal by identifying the specific time periods associated with two consecutive minima. The simplicity of this phase-frequency content identifier allows for the digital processor to utilize only basic digital blocks, such as registers, counters, adders and subtractors, without incorporating any complex multiplication and or division algorithms. In fact, the processor, fabricated in a 0.18μm CMOS process, only occupies an area of 0.0625μm2 and consumes 12.5nW from a 1.2V supply voltage when operated at 128kHz. These low-area, low-power features make the proposed processor a valuable computing element in closed loop neural prosthesis for the treatment of neural diseases, such as epilepsy, or for extracting functional connectivity maps between different recording sites in the brain.

A DSP-based neural network non-uniformity correction algorithm for IRFPA

NASA Astrophysics Data System (ADS)

Liu, Chong-liang; Jin, Wei-qi; Cao, Yang; Liu, Xiu

2009-07-01

An effective neural network non-uniformity correction (NUC) algorithm based on DSP is proposed in this paper. The non-uniform response in infrared focal plane array (IRFPA) detectors produces corrupted images with a fixed-pattern noise(FPN).We introduced and analyzed the artificial neural network scene-based non-uniformity correction (SBNUC) algorithm. A design of DSP-based NUC development platform for IRFPA is described. The DSP hardware platform designed is of low power consumption, with 32-bit fixed point DSP TMS320DM643 as the kernel processor. The dependability and expansibility of the software have been improved by DSP/BIOS real-time operating system and Reference Framework 5. In order to realize real-time performance, the calibration parameters update is set at a lower task priority then video input and output in DSP/BIOS. In this way, calibration parameters updating will not affect video streams. The work flow of the system and the strategy of real-time realization are introduced. Experiments on real infrared imaging sequences demonstrate that this algorithm requires only a few frames to obtain high quality corrections. It is computationally efficient and suitable for all kinds of non-uniformity.

Implementation of an Adaptive Controller System from Concept to Flight Test

NASA Technical Reports Server (NTRS)

Larson, Richard R.; Burken, John J.; Butler, Bradley S.; Yokum, Steve

2009-01-01

The National Aeronautics and Space Administration Dryden Flight Research Center (Edwards, California) is conducting ongoing flight research using adaptive controller algorithms. A highly modified McDonnell-Douglas NF-15B airplane called the F-15 Intelligent Flight Control System (IFCS) is used to test and develop these algorithms. Modifications to this airplane include adding canards and changing the flight control systems to interface a single-string research controller processor for neural network algorithms. Research goals include demonstration of revolutionary control approaches that can efficiently optimize aircraft performance in both normal and failure conditions and advancement of neural-network-based flight control technology for new aerospace system designs. This report presents an overview of the processes utilized to develop adaptive controller algorithms during a flight-test program, including a description of initial adaptive controller concepts and a discussion of modeling formulation and performance testing. Design finalization led to integration with the system interfaces, verification of the software, validation of the hardware to the requirements, design of failure detection, development of safety limiters to minimize the effect of erroneous neural network commands, and creation of flight test control room displays to maximize human situational awareness; these are also discussed.

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

PubMed

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

2010-09-01

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

Hierarchical Address Event Routing for Reconfigurable Large-Scale Neuromorphic Systems.

PubMed

Park, Jongkil; Yu, Theodore; Joshi, Siddharth; Maier, Christoph; Cauwenberghs, Gert

2017-10-01

We present a hierarchical address-event routing (HiAER) architecture for scalable communication of neural and synaptic spike events between neuromorphic processors, implemented with five Xilinx Spartan-6 field-programmable gate arrays and four custom analog neuromophic integrated circuits serving 262k neurons and 262M synapses. The architecture extends the single-bus address-event representation protocol to a hierarchy of multiple nested buses, routing events across increasing scales of spatial distance. The HiAER protocol provides individually programmable axonal delay in addition to strength for each synapse, lending itself toward biologically plausible neural network architectures, and scales across a range of hierarchies suitable for multichip and multiboard systems in reconfigurable large-scale neuromorphic systems. We show approximately linear scaling of net global synaptic event throughput with number of routing nodes in the network, at 3.6×10 7 synaptic events per second per 16k-neuron node in the hierarchy.

Holography and optical information processing; Proceedings of the Soviet-Chinese Joint Seminar, Bishkek, Kyrgyzstan, Sept. 21-26, 1991

NASA Astrophysics Data System (ADS)

Mikaelian, Andrei L.

Attention is given to data storage, devices, architectures, and implementations of optical memory and neural networks; holographic optical elements and computer-generated holograms; holographic display and materials; systems, pattern recognition, interferometry, and applications in optical information processing; and special measurements and devices. Topics discussed include optical immersion as a new way to increase information recording density, systems for data reading from optical disks on the basis of diffractive lenses, a new real-time optical associative memory system, an optical pattern recognition system based on a WTA model of neural networks, phase diffraction grating for the integral transforms of coherent light fields, holographic recording with operated sensitivity and stability in chalcogenide glass layers, a compact optical logic processor, a hybrid optical system for computing invariant moments of images, optical fiber holographic inteferometry, and image transmission through random media in single pass via optical phase conjugation.

Enhancing Communication in Noisy Environments

DTIC Science & Technology

2009-10-01

derived from the ITD and ILD cues, which are binaural . ITD depends on the azimuthal position of the source. Similarly, ILD refers to the fact...4.4 dB No Perceptual Binaural Speech Enhancement [42] 4.5 dB Yes Fuzzy Cocktail Party Processor [25] 7.5 dB Yes Binaural segregation [43] 8.9 dB No...modulation. IEEE Transactions on Neural Networks. 15 (2004): 1135-50. [42] Dong R. Perceptual Binaural Speech Enhancement in Noisy Environments. M.A.Sc

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

NASA Astrophysics Data System (ADS)

Bandyopadhyay, Anirban; Miki, Kazushi

2007-06-01

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

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

NASA Astrophysics Data System (ADS)

Javidi, Bahram

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

Decentralized Multisensory Information Integration in Neural Systems.

PubMed

Zhang, Wen-Hao; Chen, Aihua; Rasch, Malte J; Wu, Si

2016-01-13

How multiple sensory cues are integrated in neural circuitry remains a challenge. The common hypothesis is that information integration might be accomplished in a dedicated multisensory integration area receiving feedforward inputs from the modalities. However, recent experimental evidence suggests that it is not a single multisensory brain area, but rather many multisensory brain areas that are simultaneously involved in the integration of information. Why many mutually connected areas should be needed for information integration is puzzling. Here, we investigated theoretically how information integration could be achieved in a distributed fashion within a network of interconnected multisensory areas. Using biologically realistic neural network models, we developed a decentralized information integration system that comprises multiple interconnected integration areas. Studying an example of combining visual and vestibular cues to infer heading direction, we show that such a decentralized system is in good agreement with anatomical evidence and experimental observations. In particular, we show that this decentralized system can integrate information optimally. The decentralized system predicts that optimally integrated information should emerge locally from the dynamics of the communication between brain areas and sheds new light on the interpretation of the connectivity between multisensory brain areas. To extract information reliably from ambiguous environments, the brain integrates multiple sensory cues, which provide different aspects of information about the same entity of interest. Here, we propose a decentralized architecture for multisensory integration. In such a system, no processor is in the center of the network topology and information integration is achieved in a distributed manner through reciprocally connected local processors. Through studying the inference of heading direction with visual and vestibular cues, we show that the decentralized system can integrate information optimally, with the reciprocal connections between processers determining the extent of cue integration. Our model reproduces known multisensory integration behaviors observed in experiments and sheds new light on our understanding of how information is integrated in the brain. Copyright © 2016 Zhang et al.

Decentralized Multisensory Information Integration in Neural Systems

PubMed Central

Zhang, Wen-hao; Chen, Aihua

2016-01-01

How multiple sensory cues are integrated in neural circuitry remains a challenge. The common hypothesis is that information integration might be accomplished in a dedicated multisensory integration area receiving feedforward inputs from the modalities. However, recent experimental evidence suggests that it is not a single multisensory brain area, but rather many multisensory brain areas that are simultaneously involved in the integration of information. Why many mutually connected areas should be needed for information integration is puzzling. Here, we investigated theoretically how information integration could be achieved in a distributed fashion within a network of interconnected multisensory areas. Using biologically realistic neural network models, we developed a decentralized information integration system that comprises multiple interconnected integration areas. Studying an example of combining visual and vestibular cues to infer heading direction, we show that such a decentralized system is in good agreement with anatomical evidence and experimental observations. In particular, we show that this decentralized system can integrate information optimally. The decentralized system predicts that optimally integrated information should emerge locally from the dynamics of the communication between brain areas and sheds new light on the interpretation of the connectivity between multisensory brain areas. SIGNIFICANCE STATEMENT To extract information reliably from ambiguous environments, the brain integrates multiple sensory cues, which provide different aspects of information about the same entity of interest. Here, we propose a decentralized architecture for multisensory integration. In such a system, no processor is in the center of the network topology and information integration is achieved in a distributed manner through reciprocally connected local processors. Through studying the inference of heading direction with visual and vestibular cues, we show that the decentralized system can integrate information optimally, with the reciprocal connections between processers determining the extent of cue integration. Our model reproduces known multisensory integration behaviors observed in experiments and sheds new light on our understanding of how information is integrated in the brain. PMID:26758843

Hazard detection and avoidance sensor for NASA's planetary landers

NASA Technical Reports Server (NTRS)

Lau, Brian; Chao, Tien-Hsin

1992-01-01

An optical terrain analysis based sensor system specifically designed for landing hazard detection as required for NASA's autonomous planetary landers is introduced. This optical hazard detection and avoidance (HDA) sensor utilizes an optoelectronic wedge-and-ting (WRD) filter for Fourier transformed feature extraction and an electronic neural network processor for pattern classification. A fully implemented optical HDA sensor would assure safe landing of the planetary landers. Computer simulation results of a successful feasibility study is reported. Future research for hardware system implementation is also provided.

Image understanding and the man-machine interface II; Proceedings of the Meeting, Los Angeles, CA, Jan. 17, 18, 1989

NASA Technical Reports Server (NTRS)

Barrett, Eamon B. (Editor); Pearson, James J. (Editor)

1989-01-01

Image understanding concepts and models, image understanding systems and applications, advanced digital processors and software tools, and advanced man-machine interfaces are among the topics discussed. Particular papers are presented on such topics as neural networks for computer vision, object-based segmentation and color recognition in multispectral images, the application of image algebra to image measurement and feature extraction, and the integration of modeling and graphics to create an infrared signal processing test bed.

Microlaser-based compact optical neuro-processors (Invited Paper)

NASA Astrophysics Data System (ADS)

Paek, Eung Gi; Chan, Winston K.; Zah, Chung-En; Cheung, Kwok-wai; Curtis, L.; Chang-Hasnain, Constance J.

1992-10-01

This paper reviews the recent progress in the development of holographic neural networks using surface-emitting laser diode arrays (SELDAs). Since the previous work on ultrafast holographic memory readout system and a robust incoherent correlator, progress has been made in several areas: the use of an array of monolithic `neurons' to reconstruct holographic memories; two-dimensional (2-D) wavelength-division multiplexing (WDM) for image transmission through a single-mode fiber; and finally, an associative memory using time- division multiplexing (TDM). Experimental demonstrations on these are presented.

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

NASA Astrophysics Data System (ADS)

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

2017-08-01

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

Toward Real Time Neural Net Flight Controllers

NASA Technical Reports Server (NTRS)

Jorgensen, C. C.; Mah, R. W.; Ross, J.; Lu, Henry, Jr. (Technical Monitor)

1994-01-01

NASA Ames Research Center has an ongoing program in neural network control technology targeted toward real time flight demonstrations using a modified F-15 which permits direct inner loop control of actuators, rapid switching between alternative control designs, and substitutable processors. An important part of this program is the ACTIVE flight project which is examining the feasibility of using neural networks in the design, control, and system identification of new aircraft prototypes. This paper discusses two research applications initiated with this objective in mind: utilization of neural networks for wind tunnel aircraft model identification and rapid learning algorithms for on line reconfiguration and control. The first application involves the identification of aerodynamic flight characteristics from analysis of wind tunnel test data. This identification is important in the early stages of aircraft design because complete specification of control architecture's may not be possible even though concept models at varying scales are available for aerodynamic wind tunnel testing. Testing of this type is often a long and expensive process involving measurement of aircraft lift, drag, and moment of inertia at varying angles of attack and control surface configurations. This information in turn can be used in the design of the flight control systems by applying the derived lookup tables to generate piece wise linearized controllers. Thus, reduced costs in tunnel test times and the rapid transfer of wind tunnel insights into prototype controllers becomes an important factor in more efficient generation and testing of new flight systems. NASA Ames Research Center is successfully applying modular neural networks as one way of anticipating small scale aircraft model performances prior to testing, thus reducing the number of in tunnel test hours and potentially, the number of intermediate scaled models required for estimation of surface flow effects.

Parallel processing data network of master and slave transputers controlled by a serial control network

DOEpatents

Crosetto, D.B.

1996-12-31

The present device provides for a dynamically configurable communication network having a multi-processor parallel processing system having a serial communication network and a high speed parallel communication network. The serial communication network is used to disseminate commands from a master processor to a plurality of slave processors to effect communication protocol, to control transmission of high density data among nodes and to monitor each slave processor`s status. The high speed parallel processing network is used to effect the transmission of high density data among nodes in the parallel processing system. Each node comprises a transputer, a digital signal processor, a parallel transfer controller, and two three-port memory devices. A communication switch within each node connects it to a fast parallel hardware channel through which all high density data arrives or leaves the node. 6 figs.

Implementation of an Adaptive Controller System from Concept to Flight Test

NASA Technical Reports Server (NTRS)

Larson, Richard R.; Burken, John J.; Butler, Bradley S.

2009-01-01

The National Aeronautics and Space Administration Dryden Flight Research Center (Edwards, California) is conducting ongoing flight research using adaptive controller algorithms. A highly modified McDonnell-Douglas NF-15B airplane called the F-15 Intelligent Flight Control System (IFCS) was used for these algorithms. This airplane has been modified by the addition of canards and by changing the flight control systems to interface a single-string research controller processor for neural network algorithms. Research goals included demonstration of revolutionary control approaches that can efficiently optimize aircraft performance for both normal and failure conditions, and to advance neural-network-based flight control technology for new aerospace systems designs. Before the NF-15B IFCS airplane was certified for flight test, however, certain processes needed to be completed. This paper presents an overview of these processes, including a description of the initial adaptive controller concepts followed by a discussion of modeling formulation and performance testing. Upon design finalization, the next steps are: integration with the system interfaces, verification of the software, validation of the hardware to the requirements, design of failure detection, development of safety limiters to minimize the effect of erroneous neural network commands, and creation of flight test control room displays to maximize human situational awareness.

Recognition of handwritten similar Chinese characters by self-growing probabilistic decision-based neural network.

PubMed

Fu, H C; Xu, Y Y; Chang, H Y

1999-12-01

Recognition of similar (confusion) characters is a difficult problem in optical character recognition (OCR). In this paper, we introduce a neural network solution that is capable of modeling minor differences among similar characters, and is robust to various personal handwriting styles. The Self-growing Probabilistic Decision-based Neural Network (SPDNN) is a probabilistic type neural network, which adopts a hierarchical network structure with nonlinear basis functions and a competitive credit-assignment scheme. Based on the SPDNN model, we have constructed a three-stage recognition system. First, a coarse classifier determines a character to be input to one of the pre-defined subclasses partitioned from a large character set, such as Chinese mixed with alphanumerics. Then a character recognizer determines the input image which best matches the reference character in the subclass. Lastly, the third module is a similar character recognizer, which can further enhance the recognition accuracy among similar or confusing characters. The prototype system has demonstrated a successful application of SPDNN to similar handwritten Chinese recognition for the public database CCL/HCCR1 (5401 characters x200 samples). Regarding performance, experiments on the CCL/HCCR1 database produced 90.12% recognition accuracy with no rejection, and 94.11% accuracy with 6.7% rejection, respectively. This recognition accuracy represents about 4% improvement on the previously announced performance. As to processing speed, processing before recognition (including image preprocessing, segmentation, and feature extraction) requires about one second for an A4 size character image, and recognition consumes approximately 0.27 second per character on a Pentium-100 based personal computer, without use of any hardware accelerator or co-processor.

A method for compression of intra-cortically-recorded neural signals dedicated to implantable brain-machine interfaces.

PubMed

Shaeri, Mohammad Ali; Sodagar, Amir M

2015-05-01

This paper proposes an efficient data compression technique dedicated to implantable intra-cortical neural recording devices. The proposed technique benefits from processing neural signals in the Discrete Haar Wavelet Transform space, a new spike extraction approach, and a novel data framing scheme to telemeter the recorded neural information to the outside world. Based on the proposed technique, a 64-channel neural signal processor was designed and prototyped as a part of a wireless implantable extra-cellular neural recording microsystem. Designed in a 0.13- μ m standard CMOS process, the 64-channel neural signal processor reported in this paper occupies ∼ 0.206 mm(2) of silicon area, and consumes 94.18 μW when operating under a 1.2-V supply voltage at a master clock frequency of 1.28 MHz.

Locating faces in color photographs using neural networks

NASA Astrophysics Data System (ADS)

Brown, Joe R.; Talley, Jim

1994-03-01

This paper summarizes a research effort in finding the locations and sizes of faces in color images (photographs, video stills, etc.) if, in fact, faces are presented. Scenarios for using such a system include serving as the means of localizing skin for automatic color balancing during photo processing or it could be used as a front-end in a customs port of energy context for a system which identified persona non grata given a database of known faces. The approach presented here is a hybrid system including: a neural pre-processor, some conventional image processing steps, and a neural classifier as the final face/non-face discriminator. Neither the training (containing 17,655 faces) nor the test (containing 1829 faces) imagery databases were constrained in their content or quality. The results for the pilot system are reported along with a discussion for improving the current system.

Class network routing

DOEpatents

Bhanot, Gyan [Princeton, NJ; Blumrich, Matthias A [Ridgefield, CT; Chen, Dong [Croton On Hudson, NY; Coteus, Paul W [Yorktown Heights, NY; Gara, Alan G [Mount Kisco, NY; Giampapa, Mark E [Irvington, NY; Heidelberger, Philip [Cortlandt Manor, NY; Steinmacher-Burow, Burkhard D [Mount Kisco, NY; Takken, Todd E [Mount Kisco, NY; Vranas, Pavlos M [Bedford Hills, NY

2009-09-08

Class network routing is implemented in a network such as a computer network comprising a plurality of parallel compute processors at nodes thereof. Class network routing allows a compute processor to broadcast a message to a range (one or more) of other compute processors in the computer network, such as processors in a column or a row. Normally this type of operation requires a separate message to be sent to each processor. With class network routing pursuant to the invention, a single message is sufficient, which generally reduces the total number of messages in the network as well as the latency to do a broadcast. Class network routing is also applied to dense matrix inversion algorithms on distributed memory parallel supercomputers with hardware class function (multicast) capability. This is achieved by exploiting the fact that the communication patterns of dense matrix inversion can be served by hardware class functions, which results in faster execution times.

Switch for serial or parallel communication networks

DOEpatents

Crosette, D.B.

1994-07-19

A communication switch apparatus and a method for use in a geographically extensive serial, parallel or hybrid communication network linking a multi-processor or parallel processing system has a very low software processing overhead in order to accommodate random burst of high density data. Associated with each processor is a communication switch. A data source and a data destination, a sensor suite or robot for example, may also be associated with a switch. The configuration of the switches in the network are coordinated through a master processor node and depends on the operational phase of the multi-processor network: data acquisition, data processing, and data exchange. The master processor node passes information on the state to be assumed by each switch to the processor node associated with the switch. The processor node then operates a series of multi-state switches internal to each communication switch. The communication switch does not parse and interpret communication protocol and message routing information. During a data acquisition phase, the communication switch couples sensors producing data to the processor node associated with the switch, to a downlink destination on the communications network, or to both. It also may couple an uplink data source to its processor node. During the data exchange phase, the switch couples its processor node or an uplink data source to a downlink destination (which may include a processor node or a robot), or couples an uplink source to its processor node and its processor node to a downlink destination. 9 figs.

Switch for serial or parallel communication networks

DOEpatents

Crosette, Dario B.

1994-01-01

A communication switch apparatus and a method for use in a geographically extensive serial, parallel or hybrid communication network linking a multi-processor or parallel processing system has a very low software processing overhead in order to accommodate random burst of high density data. Associated with each processor is a communication switch. A data source and a data destination, a sensor suite or robot for example, may also be associated with a switch. The configuration of the switches in the network are coordinated through a master processor node and depends on the operational phase of the multi-processor network: data acquisition, data processing, and data exchange. The master processor node passes information on the state to be assumed by each switch to the processor node associated with the switch. The processor node then operates a series of multi-state switches internal to each communication switch. The communication switch does not parse and interpret communication protocol and message routing information. During a data acquisition phase, the communication switch couples sensors producing data to the processor node associated with the switch, to a downlink destination on the communications network, or to both. It also may couple an uplink data source to its processor node. During the data exchange phase, the switch couples its processor node or an uplink data source to a downlink destination (which may include a processor node or a robot), or couples an uplink source to its processor node and its processor node to a downlink destination.

Shift-, rotation-, and scale-invariant shape recognition system using an optical Hough transform

NASA Astrophysics Data System (ADS)

Schmid, Volker R.; Bader, Gerhard; Lueder, Ernst H.

1998-02-01

We present a hybrid shape recognition system with an optical Hough transform processor. The features of the Hough space offer a separate cancellation of distortions caused by translations and rotations. Scale invariance is also provided by suitable normalization. The proposed system extends the capabilities of Hough transform based detection from only straight lines to areas bounded by edges. A very compact optical design is achieved by a microlens array processor accepting incoherent light as direct optical input and realizing the computationally expensive connections massively parallel. Our newly developed algorithm extracts rotation and translation invariant normalized patterns of bright spots on a 2D grid. A neural network classifier maps the 2D features via a nonlinear hidden layer onto the classification output vector. We propose initialization of the connection weights according to regions of activity specifically assigned to each neuron in the hidden layer using a competitive network. The presented system is designed for industry inspection applications. Presently we have demonstrated detection of six different machined parts in real-time. Our method yields very promising detection results of more than 96% correctly classified parts.

A High Performance VLSI Computer Architecture For Computer Graphics

NASA Astrophysics Data System (ADS)

Chin, Chi-Yuan; Lin, Wen-Tai

1988-10-01

A VLSI computer architecture, consisting of multiple processors, is presented in this paper to satisfy the modern computer graphics demands, e.g. high resolution, realistic animation, real-time display etc.. All processors share a global memory which are partitioned into multiple banks. Through a crossbar network, data from one memory bank can be broadcasted to many processors. Processors are physically interconnected through a hyper-crossbar network (a crossbar-like network). By programming the network, the topology of communication links among processors can be reconfigurated to satisfy specific dataflows of different applications. Each processor consists of a controller, arithmetic operators, local memory, a local crossbar network, and I/O ports to communicate with other processors, memory banks, and a system controller. Operations in each processor are characterized into two modes, i.e. object domain and space domain, to fully utilize the data-independency characteristics of graphics processing. Special graphics features such as 3D-to-2D conversion, shadow generation, texturing, and reflection, can be easily handled. With the current high density interconnection (MI) technology, it is feasible to implement a 64-processor system to achieve 2.5 billion operations per second, a performance needed in most advanced graphics applications.

Performance Modeling of the ADA Rendezvous

DTIC Science & Technology

1991-10-01

queueing network of figure 2, SERVERTASK can complete only one rendezvous at a time. Thus, the rate that the rendezvous requests are processed at the... Network 1, SERVERTASK competes with the traffic tasks of Server Processor. Each time SERVERTASK gains access to the processor, SERVERTASK completes...Client Processor Server Processor Software Server Nek Netork2 Figure 10. A conceptualization of the algorithm. The SERVERTASK software server of Network 2

Parallel processing data network of master and slave transputers controlled by a serial control network

DOEpatents

Crosetto, Dario B.

1996-01-01

The present device provides for a dynamically configurable communication network having a multi-processor parallel processing system having a serial communication network and a high speed parallel communication network. The serial communication network is used to disseminate commands from a master processor (100) to a plurality of slave processors (200) to effect communication protocol, to control transmission of high density data among nodes and to monitor each slave processor's status. The high speed parallel processing network is used to effect the transmission of high density data among nodes in the parallel processing system. Each node comprises a transputer (104), a digital signal processor (114), a parallel transfer controller (106), and two three-port memory devices. A communication switch (108) within each node (100) connects it to a fast parallel hardware channel (70) through which all high density data arrives or leaves the node.

Optical information processing for NASA's space exploration

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Ochoa, Ellen; Juday, Richard

1990-01-01

The development status of optical processing techniques under development at NASA-JPL, NASA-Ames, and NASA-Johnson, is evaluated with a view to their potential applications in future NASA planetary exploration missions. It is projected that such optical processing systems can yield major reductions in mass, volume, and power requirements relative to exclusively electronic systems of comparable processing capabilities. Attention is given to high-order neural networks for distortion-invariant classification and pattern recognition, multispectral imaging using an acoustooptic tunable filter, and an optical matrix processor for control problems.

Microwave vision for robots

NASA Technical Reports Server (NTRS)

Lewandowski, Leon; Struckman, Keith

1994-01-01

Microwave Vision (MV), a concept originally developed in 1985, could play a significant role in the solution to robotic vision problems. Originally our Microwave Vision concept was based on a pattern matching approach employing computer based stored replica correlation processing. Artificial Neural Network (ANN) processor technology offers an attractive alternative to the correlation processing approach, namely the ability to learn and to adapt to changing environments. This paper describes the Microwave Vision concept, some initial ANN-MV experiments, and the design of an ANN-MV system that has led to a second patent disclosure in the robotic vision field.

REGIONAL-SCALE (1000 KM) MODEL OF PHOTOCHEMICAL AIR POLLUTION. PART 2. INPUT PROCESSOR NETWORK DESIGN

EPA Science Inventory

Detailed specifications are given for a network of data processors and submodels that can generate the parameter fields required by the regional oxidant model formulated in Part 1 of this report. Operations performed by the processor network include simulation of the motion and d...

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.

Implementing direct, spatially isolated problems on transputer networks

NASA Technical Reports Server (NTRS)

Ellis, Graham K.

1988-01-01

Parametric studies were performed on transputer networks of up to 40 processors to determine how to implement and maximize the performance of the solution of problems where no processor-to-processor data transfer is required for the problem solution (spatially isolated). Two types of problems are investigated a computationally intensive problem where the solution required the transmission of 160 bytes of data through the parallel network, and a communication intensive example that required the transmission of 3 Mbytes of data through the network. This data consists of solutions being sent back to the host processor and not intermediate results for another processor to work on. Studies were performed on both integer and floating-point transputers. The latter features an on-chip floating-point math unit and offers approximately an order of magnitude performance increase over the integer transputer on real valued computations. The results indicate that a minimum amount of work is required on each node per communication to achieve high network speedups (efficiencies). The floating-point processor requires approximately an order of magnitude more work per communication than the integer processor because of the floating-point unit's increased computing capacity.

DynaSim: A MATLAB Toolbox for Neural Modeling and Simulation

PubMed Central

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

2018-01-01

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

DynaSim: A MATLAB Toolbox for Neural Modeling and Simulation.

PubMed

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

2018-01-01

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

Array processor architecture connection network

NASA Technical Reports Server (NTRS)

Barnes, George H. (Inventor); Lundstrom, Stephen F. (Inventor); Shafer, Philip E. (Inventor)

1982-01-01

A connection network is disclosed for use between a parallel array of processors and a parallel array of memory modules for establishing non-conflicting data communications paths between requested memory modules and requesting processors. The connection network includes a plurality of switching elements interposed between the processor array and the memory modules array in an Omega networking architecture. Each switching element includes a first and a second processor side port, a first and a second memory module side port, and control logic circuitry for providing data connections between the first and second processor ports and the first and second memory module ports. The control logic circuitry includes strobe logic for examining data arriving at the first and the second processor ports to indicate when the data arriving is requesting data from a requesting processor to a requested memory module. Further, connection circuitry is associated with the strobe logic for examining requesting data arriving at the first and the second processor ports for providing a data connection therefrom to the first and the second memory module ports in response thereto when the data connection so provided does not conflict with a pre-established data connection currently in use.

Toward Petascale Biologically Plausible Neural Networks

NASA Astrophysics Data System (ADS)

Long, Lyle

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

Shuttle orbiter S-band payload communications equipment design evaluation

NASA Technical Reports Server (NTRS)

Springett, J. C.; Maronde, R. G.

1979-01-01

The analysis of the design, and the performance assessment of the Orbiter S-band communication equipment are reported. The equipment considered include: network transponder, network signal processor, FM transmitter, FM signal processor, payload interrogator, and payload signal processor.

A nanostructure based on metasurfaces for optical interconnects

NASA Astrophysics Data System (ADS)

Lin, Shulang; Gu, Huarong

2017-08-01

Optical-electronic Integrated Neural Co-processor takes vital part in optical neural network, which is mainly realized by optical interconnects. Because of the accuracy requirement and long-term goal of integration, optical interconnects should be effective and pint-size. In traditional solutions of optical interconnects, holography built on crystalloid or law of Fresnel diffraction exploited on zone plate was used. However, holographic method cannot meet the efficiency requirement and zone plate is too bulk to make the optical neural unit miniaturization. Thus, this paper aims to find a way to replace holographic method or zone plate with enough diffraction efficiency and smaller size. Metasurfaces are composed of subwavelength-spaced phase shifters at an interface of medium. Metasurfaces allow for unprecedented control of light properties. They also have advanced optical technology of enabling versatile functionalities in a planar structure. In this paper, a nanostructure is presented for optical interconnects. The comparisons of light splitting ability and simulated crosstalk between nanostructure and zone plate are also made.

Accelerating Pseudo-Random Number Generator for MCNP on GPU

NASA Astrophysics Data System (ADS)

Gong, Chunye; Liu, Jie; Chi, Lihua; Hu, Qingfeng; Deng, Li; Gong, Zhenghu

2010-09-01

Pseudo-random number generators (PRNG) are intensively used in many stochastic algorithms in particle simulations, artificial neural networks and other scientific computation. The PRNG in Monte Carlo N-Particle Transport Code (MCNP) requires long period, high quality, flexible jump and fast enough. In this paper, we implement such a PRNG for MCNP on NVIDIA's GTX200 Graphics Processor Units (GPU) using CUDA programming model. Results shows that 3.80 to 8.10 times speedup are achieved compared with 4 to 6 cores CPUs and more than 679.18 million double precision random numbers can be generated per second on GPU.

Optimization of the computational load of a hypercube supercomputer onboard a mobile robot.

PubMed

Barhen, J; Toomarian, N; Protopopescu, V

1987-12-01

A combinatorial optimization methodology is developed, which enables the efficient use of hypercube multiprocessors onboard mobile intelligent robots dedicated to time-critical missions. The methodology is implemented in terms of large-scale concurrent algorithms based either on fast simulated annealing, or on nonlinear asynchronous neural networks. In particular, analytic expressions are given for the effect of singleneuron perturbations on the systems' configuration energy. Compact neuromorphic data structures are used to model effects such as prec xdence constraints, processor idling times, and task-schedule overlaps. Results for a typical robot-dynamics benchmark are presented.

Optimization of the computational load of a hypercube supercomputer onboard a mobile robot

NASA Technical Reports Server (NTRS)

Barhen, Jacob; Toomarian, N.; Protopopescu, V.

1987-01-01

A combinatorial optimization methodology is developed, which enables the efficient use of hypercube multiprocessors onboard mobile intelligent robots dedicated to time-critical missions. The methodology is implemented in terms of large-scale concurrent algorithms based either on fast simulated annealing, or on nonlinear asynchronous neural networks. In particular, analytic expressions are given for the effect of single-neuron perturbations on the systems' configuration energy. Compact neuromorphic data structures are used to model effects such as precedence constraints, processor idling times, and task-schedule overlaps. Results for a typical robot-dynamics benchmark are presented.

Embedded neural recording with TinyOS-based wireless-enabled processor modules.

PubMed

Farshchi, Shahin; Pesterev, Aleksey; Nuyujukian, Paul; Guenterberg, Eric; Mody, Istvan; Judy, Jack W

2010-04-01

To create a wireless neural recording system that can benefit from the continuous advancements being made in embedded microcontroller and communications technologies, an embedded-system-based architecture for wireless neural recording has been designed, fabricated, and tested. The system consists of commercial-off-the-shelf wireless-enabled processor modules (motes) for communicating the neural signals, and a back-end database server and client application for archiving and browsing the neural signals. A neural-signal-acquisition application has been developed to enable the mote to either acquire neural signals at a rate of 4000 12-bit samples per second, or detect and transmit spike heights and widths sampled at a rate of 16670 12-bit samples per second on a single channel. The motes acquire neural signals via a custom low-noise neural-signal amplifier with adjustable gain and high-pass corner frequency that has been designed, and fabricated in a 1.5-microm CMOS process. In addition to browsing acquired neural data, the client application enables the user to remotely toggle modes of operation (real-time or spike-only), as well as amplifier gain and high-pass corner frequency.

A New Experiment on Bengali Character Recognition

NASA Astrophysics Data System (ADS)

Barman, Sumana; Bhattacharyya, Debnath; Jeon, Seung-Whan; Kim, Tai-Hoon; Kim, Haeng-Kon

This paper presents a method to use View based approach in Bangla Optical Character Recognition (OCR) system providing reduced data set to the ANN classification engine rather than the traditional OCR methods. It describes how Bangla characters are processed, trained and then recognized with the use of a Backpropagation Artificial neural network. This is the first published account of using a segmentation-free optical character recognition system for Bangla using a view based approach. The methodology presented here assumes that the OCR pre-processor has presented the input images to the classification engine described here. The size and the font face used to render the characters are also significant in both training and classification. The images are first converted into greyscale and then to binary images; these images are then scaled to a fit a pre-determined area with a fixed but significant number of pixels. The feature vectors are then formed extracting the characteristics points, which in this case is simply a series of 0s and 1s of fixed length. Finally, an artificial neural network is chosen for the training and classification process.

Implementation of an RBF neural network on embedded systems: real-time face tracking and identity verification.

PubMed

Yang, Fan; Paindavoine, M

2003-01-01

This paper describes a real time vision system that allows us to localize faces in video sequences and verify their identity. These processes are image processing techniques based on the radial basis function (RBF) neural network approach. The robustness of this system has been evaluated quantitatively on eight video sequences. We have adapted our model for an application of face recognition using the Olivetti Research Laboratory (ORL), Cambridge, UK, database so as to compare the performance against other systems. We also describe three hardware implementations of our model on embedded systems based on the field programmable gate array (FPGA), zero instruction set computer (ZISC) chips, and digital signal processor (DSP) TMS320C62, respectively. We analyze the algorithm complexity and present results of hardware implementations in terms of the resources used and processing speed. The success rates of face tracking and identity verification are 92% (FPGA), 85% (ZISC), and 98.2% (DSP), respectively. For the three embedded systems, the processing speeds for images size of 288 /spl times/ 352 are 14 images/s, 25 images/s, and 4.8 images/s, respectively.

Buffered coscheduling for parallel programming and enhanced fault tolerance

DOEpatents

Petrini, Fabrizio [Los Alamos, NM; Feng, Wu-chun [Los Alamos, NM

2006-01-31

A computer implemented method schedules processor jobs on a network of parallel machine processors or distributed system processors. Control information communications generated by each process performed by each processor during a defined time interval is accumulated in buffers, where adjacent time intervals are separated by strobe intervals for a global exchange of control information. A global exchange of the control information communications at the end of each defined time interval is performed during an intervening strobe interval so that each processor is informed by all of the other processors of the number of incoming jobs to be received by each processor in a subsequent time interval. The buffered coscheduling method of this invention also enhances the fault tolerance of a network of parallel machine processors or distributed system processors

Next Generation Space Telescope Integrated Science Module Data System

NASA Technical Reports Server (NTRS)

Schnurr, Richard G.; Greenhouse, Matthew A.; Jurotich, Matthew M.; Whitley, Raymond; Kalinowski, Keith J.; Love, Bruce W.; Travis, Jeffrey W.; Long, Knox S.

1999-01-01

The Data system for the Next Generation Space Telescope (NGST) Integrated Science Module (ISIM) is the primary data interface between the spacecraft, telescope, and science instrument systems. This poster includes block diagrams of the ISIM data system and its components derived during the pre-phase A Yardstick feasibility study. The poster details the hardware and software components used to acquire and process science data for the Yardstick instrument compliment, and depicts the baseline external interfaces to science instruments and other systems. This baseline data system is a fully redundant, high performance computing system. Each redundant computer contains three 150 MHz power PC processors. All processors execute a commercially available real time multi-tasking operating system supporting, preemptive multi-tasking, file management and network interfaces. These six processors in the system are networked together. The spacecraft interface baseline is an extension of the network, which links the six processors. The final selection for Processor busses, processor chips, network interfaces, and high-speed data interfaces will be made during mid 2002.

Network Coding on Heterogeneous Multi-Core Processors for Wireless Sensor Networks

PubMed Central

Kim, Deokho; Park, Karam; Ro, Won W.

2011-01-01

While network coding is well known for its efficiency and usefulness in wireless sensor networks, the excessive costs associated with decoding computation and complexity still hinder its adoption into practical use. On the other hand, high-performance microprocessors with heterogeneous multi-cores would be used as processing nodes of the wireless sensor networks in the near future. To this end, this paper introduces an efficient network coding algorithm developed for the heterogenous multi-core processors. The proposed idea is fully tested on one of the currently available heterogeneous multi-core processors referred to as the Cell Broadband Engine. PMID:22164053

Evaluation of the traffic parameters in a metropolitan area by fusing visual perceptions and CNN processing of webcam images.

PubMed

Faro, Alberto; Giordano, Daniela; Spampinato, Concetto

2008-06-01

This paper proposes a traffic monitoring architecture based on a high-speed communication network whose nodes are equipped with fuzzy processors and cellular neural network (CNN) embedded systems. It implements a real-time mobility information system where visual human perceptions sent by people working on the territory and video-sequences of traffic taken from webcams are jointly processed to evaluate the fundamental traffic parameters for every street of a metropolitan area. This paper presents the whole methodology for data collection and analysis and compares the accuracy and the processing time of the proposed soft computing techniques with other existing algorithms. Moreover, this paper discusses when and why it is recommended to fuse the visual perceptions of the traffic with the automated measurements taken from the webcams to compute the maximum traveling time that is likely needed to reach any destination in the traffic network.

NCC Simulation Model: Simulating the operations of the network control center, phase 2

NASA Technical Reports Server (NTRS)

Benjamin, Norman M.; Paul, Arthur S.; Gill, Tepper L.

1992-01-01

The simulation of the network control center (NCC) is in the second phase of development. This phase seeks to further develop the work performed in phase one. Phase one concentrated on the computer systems and interconnecting network. The focus of phase two will be the implementation of the network message dialogues and the resources controlled by the NCC. These resources are requested, initiated, monitored and analyzed via network messages. In the NCC network messages are presented in the form of packets that are routed across the network. These packets are generated, encoded, decoded and processed by the network host processors that generate and service the message traffic on the network that connects these hosts. As a result, the message traffic is used to characterize the work done by the NCC and the connected network. Phase one of the model development represented the NCC as a network of bi-directional single server queues and message generating sources. The generators represented the external segment processors. The served based queues represented the host processors. The NCC model consists of the internal and external processors which generate message traffic on the network that links these hosts. To fully realize the objective of phase two it is necessary to identify and model the processes in each internal processor. These processes live in the operating system of the internal host computers and handle tasks such as high speed message exchanging, ISN and NFE interface, event monitoring, network monitoring, and message logging. Inter process communication is achieved through the operating system facilities. The overall performance of the host is determined by its ability to service messages generated by both internal and external processors.

Multilayer perceptron architecture optimization using parallel computing techniques.

PubMed

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

2017-01-01

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

Multilayer perceptron architecture optimization using parallel computing techniques

PubMed Central

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

2017-01-01

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

FPGA-based distributed computing microarchitecture for complex physical dynamics investigation.

PubMed

Borgese, Gianluca; Pace, Calogero; Pantano, Pietro; Bilotta, Eleonora

2013-09-01

In this paper, we present a distributed computing system, called DCMARK, aimed at solving partial differential equations at the basis of many investigation fields, such as solid state physics, nuclear physics, and plasma physics. This distributed architecture is based on the cellular neural network paradigm, which allows us to divide the differential equation system solving into many parallel integration operations to be executed by a custom multiprocessor system. We push the number of processors to the limit of one processor for each equation. In order to test the present idea, we choose to implement DCMARK on a single FPGA, designing the single processor in order to minimize its hardware requirements and to obtain a large number of easily interconnected processors. This approach is particularly suited to study the properties of 1-, 2- and 3-D locally interconnected dynamical systems. In order to test the computing platform, we implement a 200 cells, Korteweg-de Vries (KdV) equation solver and perform a comparison between simulations conducted on a high performance PC and on our system. Since our distributed architecture takes a constant computing time to solve the equation system, independently of the number of dynamical elements (cells) of the CNN array, it allows us to reduce the elaboration time more than other similar systems in the literature. To ensure a high level of reconfigurability, we design a compact system on programmable chip managed by a softcore processor, which controls the fast data/control communication between our system and a PC Host. An intuitively graphical user interface allows us to change the calculation parameters and plot the results.

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

Fiber-Optic Sensor And Smart Structures Research At Florida Institute Of Technology

NASA Astrophysics Data System (ADS)

Grossman, Barry G.; Alavie, A. Tino; Ham, Fredric M.; Franke, Jorge E.; Thursby, Michael H.

1990-02-01

This paper discusses the fundamental issues being investigated by Florida Institute of Technology (F.I.T.) to implement the technology of smart structural systems for DoD, NASA, and commercial applications. Embedded sensors and actuators controlled by processors can provide a modification of the mechanical characteristics of composite structures to produce smart structures1-3. Recent advances in material science have spurred the development and use of composite materials in a wide range of applications from rotocraft blades and advanced tactical fighter aircraft to undersea and aerospace structures. Along with the advantages of an increased strength-to-weight ratio, the use of these materials has raised a number of questions related to understanding their failure mechanisms. Also, being able to predict structural failures far enough in advance to prevent them and to provide real-time structural health and damage monitoring has become a realistic possibility. Unfortunately, conventional sensors, actuators, and digital processors, although highly developed and well proven for other systems, may not be best suited for most smart structure applications. Our research has concentrated on few-mode and polarimetric single-fiber strain sensors4-7 and optically activated shape memory alloy (SMA) actuators controlled by artificial neural processors. We have constructed and characterized both few-mode and polarimetric sensors for a variety of fiber types, including standard single-mode, high-birefringence polarization preserving, and low-birefringence polarization insensitive fibers. We have investigated signal processing techniques for these sensors and have demonstrated active phase tracking for the high- and low-birefringence polarimetric sensors through the incorporation into the system of an electrooptic modulator designed and fabricated at F.I.T.. We have also started the design and testing of neural network architectures for processing the sensor signal outputs to calculate strain magnitude and actuator control signals for simple structures.

SAPIENS: Spreading Activation Processor for Information Encoded in Network Structures. Technical Report No. 296.

ERIC Educational Resources Information Center

Ortony, Andrew; Radin, Dean I.

The product of researchers' efforts to develop a computer processor which distinguishes between relevant and irrelevant information in the database, Spreading Activation Processor for Information Encoded in Network Structures (SAPIENS) exhibits (1) context sensitivity, (2) efficiency, (3) decreasing activation over time, (4) summation of…

Real-time estimation of lesion depth and control of radiofrequency ablation within ex vivo animal tissues using a neural network.

PubMed

Wang, Yearnchee Curtis; Chan, Terence Chee-Hung; Sahakian, Alan Varteres

2018-01-04

Radiofrequency ablation (RFA), a method of inducing thermal ablation (cell death), is often used to destroy tumours or potentially cancerous tissue. Current techniques for RFA estimation (electrical impedance tomography, Nakagami ultrasound, etc.) require long compute times (≥ 2 s) and measurement devices other than the RFA device. This study aims to determine if a neural network (NN) can estimate ablation lesion depth for control of bipolar RFA using complex electrical impedance - since tissue electrical conductivity varies as a function of tissue temperature - in real time using only the RFA therapy device's electrodes. Three-dimensional, cubic models comprised of beef liver, pork loin or pork belly represented target tissue. Temperature and complex electrical impedance from 72 data generation ablations in pork loin and belly were used for training the NN (403 s on Xeon processor). NN inputs were inquiry depth, starting complex impedance and current complex impedance. Training-validation-test splits were 70%-0%-30% and 80%-10%-10% (overfit test). Once the NN-estimated lesion depth for a margin reached the target lesion depth, RFA was stopped for that margin of tissue. The NN trained to 93% accuracy and an NN-integrated control ablated tissue to within 1.0 mm of the target lesion depth on average. Full 15-mm depth maps were calculated in 0.2 s on a single-core ARMv7 processor. The results show that a NN could make lesion depth estimations in real-time using less in situ devices than current techniques. With the NN-based technique, physicians could deliver quicker and more precise ablation therapy.

Broadcasting collective operation contributions throughout a parallel computer

DOEpatents

Faraj, Ahmad [Rochester, MN

2012-02-21

Methods, systems, and products are disclosed for broadcasting collective operation contributions throughout a parallel computer. The parallel computer includes a plurality of compute nodes connected together through a data communications network. Each compute node has a plurality of processors for use in collective parallel operations on the parallel computer. Broadcasting collective operation contributions throughout a parallel computer according to embodiments of the present invention includes: transmitting, by each processor on each compute node, that processor's collective operation contribution to the other processors on that compute node using intra-node communications; and transmitting on a designated network link, by each processor on each compute node according to a serial processor transmission sequence, that processor's collective operation contribution to the other processors on the other compute nodes using inter-node communications.

Parallel discrete event simulation: A shared memory approach

NASA Technical Reports Server (NTRS)

Reed, Daniel A.; Malony, Allen D.; Mccredie, Bradley D.

1987-01-01

With traditional event list techniques, evaluating a detailed discrete event simulation model can often require hours or even days of computation time. Parallel simulation mimics the interacting servers and queues of a real system by assigning each simulated entity to a processor. By eliminating the event list and maintaining only sufficient synchronization to insure causality, parallel simulation can potentially provide speedups that are linear in the number of processors. A set of shared memory experiments is presented using the Chandy-Misra distributed simulation algorithm to simulate networks of queues. Parameters include queueing network topology and routing probabilities, number of processors, and assignment of network nodes to processors. These experiments show that Chandy-Misra distributed simulation is a questionable alternative to sequential simulation of most queueing network models.

Smart Sensor Network for Aircraft Corrosion Monitoring

DTIC Science & Technology

2010-02-01

Network Elements – Hub, Network capable application processor ( NCAP ) – Node, Smart transducer interface module (STIM)  Corrosion Sensing and...software Transducer software Network Protocol 1451.2 1451.3 1451.5 1451.6 1451.7 I/O Node -processor Power TEDS Smart Sensor Hub ( NCAP ) IEEE 1451.0 and

Parallel processor-based raster graphics system architecture

DOEpatents

Littlefield, Richard J.

1990-01-01

An apparatus for generating raster graphics images from the graphics command stream includes a plurality of graphics processors connected in parallel, each adapted to receive any part of the graphics command stream for processing the command stream part into pixel data. The apparatus also includes a frame buffer for mapping the pixel data to pixel locations and an interconnection network for interconnecting the graphics processors to the frame buffer. Through the interconnection network, each graphics processor may access any part of the frame buffer concurrently with another graphics processor accessing any other part of the frame buffer. The plurality of graphics processors can thereby transmit concurrently pixel data to pixel locations in the frame buffer.

Efficient Interconnection Schemes for VLSI and Parallel Computation

DTIC Science & Technology

1989-08-01

Definition: Let R be a routing network. A set S of wires in R is a (directed) cut if it partitions the network into two sets of processors A and B ...such that every path from a processor in A to a processor in B contains a wire in S. The capacity cap(S) is the number of wires in the cut. For a set of...messages M, define the load load(M, S) of M on a cut S to be the number of messages in M from a processor in A to a processor in B . The load factor

A novel speech-processing strategy incorporating tonal information for cochlear implants.

PubMed

Lan, N; Nie, K B; Gao, S K; Zeng, F G

2004-05-01

Good performance in cochlear implant users depends in large part on the ability of a speech processor to effectively decompose speech signals into multiple channels of narrow-band electrical pulses for stimulation of the auditory nerve. Speech processors that extract only envelopes of the narrow-band signals (e.g., the continuous interleaved sampling (CIS) processor) may not provide sufficient information to encode the tonal cues in languages such as Chinese. To improve the performance in cochlear implant users who speak tonal language, we proposed and developed a novel speech-processing strategy, which extracted both the envelopes of the narrow-band signals and the fundamental frequency (F0) of the speech signal, and used them to modulate both the amplitude and the frequency of the electrical pulses delivered to stimulation electrodes. We developed an algorithm to extract the fundatmental frequency and identified the general patterns of pitch variations of four typical tones in Chinese speech. The effectiveness of the extraction algorithm was verified with an artificial neural network that recognized the tonal patterns from the extracted F0 information. We then compared the novel strategy with the envelope-extraction CIS strategy in human subjects with normal hearing. The novel strategy produced significant improvement in perception of Chinese tones, phrases, and sentences. This novel processor with dynamic modulation of both frequency and amplitude is encouraging for the design of a cochlear implant device for sensorineurally deaf patients who speak tonal languages.

Vehicle-borne IED detection using the ULTOR correlation processor

NASA Astrophysics Data System (ADS)

Burcham, Joel D.; Vachon, Joyce E.

2006-05-01

Advanced Optical Systems, Inc. developed the ULTOR(r) system, a real-time correlation processor that looks for improvised explosive devices (IED) by examining imagery of vehicles. The system determines the level of threat an approaching vehicle may represent. The system works on incoming video collected at different wavelengths, including visible, infrared, and synthetic aperture radar. Sensors that attach to ULTOR can be located wherever necessary to improve the safety around a checkpoint. When a suspect vehicle is detected, ULTOR can track the vehicle, alert personnel, check for previous instances of the vehicle, and update other networked systems with the threat information. The ULTOR processing engine focuses on the spatial frequency information available in the image. It correlates the imagery with templates that specify the criteria defining a suspect vehicle. It can perform full field correlations at a rate of 180 Hz or better. Additionally, the spatial frequency information is applied to a trained neural network to identify suspect vehicles. We have performed various laboratory and field experiments to verify the performance of the ULTOR system in a counter IED environment. The experiments cover tracking specific targets in video clips to demonstrating real-time ULTOR system performance. The selected targets in the experiments include various automobiles in both visible and infrared video.

Mechanically verified hardware implementing an 8-bit parallel IO Byzantine agreement processor

NASA Technical Reports Server (NTRS)

Moore, J. Strother

1992-01-01

Consider a network of four processors that use the Oral Messages (Byzantine Generals) Algorithm of Pease, Shostak, and Lamport to achieve agreement in the presence of faults. Bevier and Young have published a functional description of a single processor that, when interconnected appropriately with three identical others, implements this network under the assumption that the four processors step in synchrony. By formalizing the original Pease, et al work, Bevier and Young mechanically proved that such a network achieves fault tolerance. We develop, formalize, and discuss a hardware design that has been mechanically proven to implement their processor. In particular, we formally define mapping functions from the abstract state space of the Bevier-Young processor to a concrete state space of a hardware module and state a theorem that expresses the claim that the hardware correctly implements the processor. We briefly discuss the Brock-Hunt Formal Hardware Description Language which permits designs both to be proved correct with the Boyer-Moore theorem prover and to be expressed in a commercially supported hardware description language for additional electrical analysis and layout. We briefly describe our implementation.

An executable specification for the message processor in a simple combining network

NASA Technical Reports Server (NTRS)

Middleton, David

1995-01-01

While the primary function of the network in a parallel computer is to communicate data between processors, it is often useful if the network can also perform rudimentary calculations. That is, some simple processing ability in the network itself, particularly for performing parallel prefix computations, can reduce both the volume of data being communicated and the computational load on the processors proper. Unfortunately, typical implementations of such networks require a large fraction of the hardware budget, and so combining networks are viewed as being impractical. The FFP Machine has such a combining network, and various characteristics of the machine allow a good deal of simplification in the network design. Despite being simple in construction however, the network relies on many subtle details to work correctly. This paper describes an executable model of the network which will serve several purposes. It provides a complete and detailed description of the network which can substantiate its ability to support necessary functions. It provides an environment in which algorithms to be run on the network can be designed and debugged more easily than they would on physical hardware. Finally, it provides the foundation for exploring the design of the message receiving facility which connects the network to the individual processors.

A Software Implementation of a Satellite Interface Message Processor.

ERIC Educational Resources Information Center

Eastwood, Margaret A.; Eastwood, Lester F., Jr.

A design for network control software for a computer network is described in which some nodes are linked by a communications satellite channel. It is assumed that the network has an ARPANET-like configuration; that is, that specialized processors at each node are responsible for message switching and network control. The purpose of the control…

Sentient networks

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

Chapline, G.

1998-03-01

The engineering problems of constructing autonomous networks of sensors and data processors that can provide alerts for dangerous situations provide a new context for debating the question whether man-made systems can emulate the cognitive capabilities of the mammalian brain. In this paper we consider the question whether a distributed network of sensors and data processors can form ``perceptions`` based on sensory data. Because sensory data can have exponentially many explanations, the use of a central data processor to analyze the outputs from a large ensemble of sensors will in general introduce unacceptable latencies for responding to dangerous situations. A bettermore » idea is to use a distributed ``Helmholtz machine`` architecture in which the sensors are connected to a network of simple processors, and the collective state of the network as a whole provides an explanation for the sensory data. In general communication within such a network will require time division multiplexing, which opens the door to the possibility that with certain refinements to the Helmholtz machine architecture it may be possible to build sensor networks that exhibit a form of artificial consciousness.« less

Solving Constraint Satisfaction Problems with Networks of Spiking Neurons

PubMed Central

Jonke, Zeno; Habenschuss, Stefan; Maass, Wolfgang

2016-01-01

Network of neurons in the brain apply—unlike processors in our current generation of computer hardware—an event-based processing strategy, where short pulses (spikes) are emitted sparsely by neurons to signal the occurrence of an event at a particular point in time. Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes. However, it turns out to be surprisingly difficult to design networks of spiking neurons that can solve difficult computational problems on the level of single spikes, rather than rates of spikes. We present here a new method for designing networks of spiking neurons via an energy function. Furthermore, we show how the energy function of a network of stochastically firing neurons can be shaped in a transparent manner by composing the networks of simple stereotypical network motifs. We show that this design approach enables networks of spiking neurons to produce approximate solutions to difficult (NP-hard) constraint satisfaction problems from the domains of planning/optimization and verification/logical inference. The resulting networks employ noise as a computational resource. Nevertheless, the timing of spikes plays an essential role in their computations. Furthermore, networks of spiking neurons carry out for the Traveling Salesman Problem a more efficient stochastic search for good solutions compared with stochastic artificial neural networks (Boltzmann machines) and Gibbs sampling. PMID:27065785

Hyperswitch Communication Network Computer

NASA Technical Reports Server (NTRS)

Peterson, John C.; Chow, Edward T.; Priel, Moshe; Upchurch, Edwin T.

1993-01-01

Hyperswitch Communications Network (HCN) computer is prototype multiple-processor computer being developed. Incorporates improved version of hyperswitch communication network described in "Hyperswitch Network For Hypercube Computer" (NPO-16905). Designed to support high-level software and expansion of itself. HCN computer is message-passing, multiple-instruction/multiple-data computer offering significant advantages over older single-processor and bus-based multiple-processor computers, with respect to price/performance ratio, reliability, availability, and manufacturing. Design of HCN operating-system software provides flexible computing environment accommodating both parallel and distributed processing. Also achieves balance among following competing factors; performance in processing and communications, ease of use, and tolerance of (and recovery from) faults.

Parallel discrete event simulation using shared memory

NASA Technical Reports Server (NTRS)

Reed, Daniel A.; Malony, Allen D.; Mccredie, Bradley D.

1988-01-01

With traditional event-list techniques, evaluating a detailed discrete-event simulation-model can often require hours or even days of computation time. By eliminating the event list and maintaining only sufficient synchronization to ensure causality, parallel simulation can potentially provide speedups that are linear in the numbers of processors. A set of shared-memory experiments, using the Chandy-Misra distributed-simulation algorithm, to simulate networks of queues is presented. Parameters of the study include queueing network topology and routing probabilities, number of processors, and assignment of network nodes to processors. These experiments show that Chandy-Misra distributed simulation is a questionable alternative to sequential-simulation of most queueing network models.

Set processing in a network environment. [data bases and magnetic disks and tapes

NASA Technical Reports Server (NTRS)

Hardgrave, W. T.

1975-01-01

A combination of a local network, a mass storage system, and an autonomous set processor serving as a data/storage management machine is described. Its characteristics include: content-accessible data bases usable from all connected devices; efficient storage/access of large data bases; simple and direct programming with data manipulation and storage management handled by the set processor; simple data base design and entry from source representation to set processor representation with no predefinition necessary; capability available for user sort/order specification; significant reduction in tape/disk pack storage and mounts; flexible environment that allows upgrading hardware/software configuration without causing major interruptions in service; minimal traffic on data communications network; and improved central memory usage on large processors.

Mobility timing for agent communities, a cue for advanced connectionist systems.

PubMed

Apolloni, Bruno; Bassis, Simone; Pagani, Elena; Rossi, Gian Paolo; Valerio, Lorenzo

2011-12-01

We introduce a wait-and-chase scheme that models the contact times between moving agents within a connectionist construct. The idea that elementary processors move within a network to get a proper position is borne out both by biological neurons in the brain morphogenesis and by agents within social networks. From the former, we take inspiration to devise a medium-term project for new artificial neural network training procedures where mobile neurons exchange data only when they are close to one another in a proper space (are in contact). From the latter, we accumulate mobility tracks experience. We focus on the preliminary step of characterizing the elapsed time between neuron contacts, which results from a spatial process fitting in the family of random processes with memory, where chasing neurons are stochastically driven by the goal of hitting target neurons. Thus, we add an unprecedented mobility model to the literature in the field, introducing a distribution law of the intercontact times that merges features of both negative exponential and Pareto distribution laws. We give a constructive description and implementation of our model, as well as a short analytical form whose parameters are suitably estimated in terms of confidence intervals from experimental data. Numerical experiments show the model and related inference tools to be sufficiently robust to cope with two main requisites for its exploitation in a neural network: the nonindependence of the observed intercontact times and the feasibility of the model inversion problem to infer suitable mobility parameters.

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.

An incentive-based distributed mechanism for scheduling divisible loads in tree networks

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

Carroll, T. E.; Grosu, D.

The underlying assumption of Divisible Load Scheduling (DLS) theory is that the pro-cessors composing the network are obedient, i.e., they do not “cheat” the scheduling algorithm. This assumption is unrealistic if the processors are owned by autonomous, self-interested organizations that have no a priori motivation for cooperation and they will manipulate the algorithm if it is beneficial to do so. In this paper, we address this issue by designing a distributed mechanism for scheduling divisible loads in tree net-works, called DLS-T, which provides incentives to processors for reporting their true processing capacity and executing their assigned load at full processingmore » capacity. We prove that the DLS-T mechanism computes the optimal allocation in an ex post Nash equilibrium. Finally, we simulate and study the mechanism under various network structures and processor parameters.« less

Interconnect Performance Evaluation of SGI Altix 3700 BX2, Cray X1, Cray Opteron Cluster, and Dell PowerEdge

NASA Technical Reports Server (NTRS)

Fatoohi, Rod; Saini, Subbash; Ciotti, Robert

2006-01-01

We study the performance of inter-process communication on four high-speed multiprocessor systems using a set of communication benchmarks. The goal is to identify certain limiting factors and bottlenecks with the interconnect of these systems as well as to compare these interconnects. We measured network bandwidth using different number of communicating processors and communication patterns, such as point-to-point communication, collective communication, and dense communication patterns. The four platforms are: a 512-processor SGI Altix 3700 BX2 shared-memory machine with 3.2 GB/s links; a 64-processor (single-streaming) Cray XI shared-memory machine with 32 1.6 GB/s links; a 128-processor Cray Opteron cluster using a Myrinet network; and a 1280-node Dell PowerEdge cluster with an InfiniBand network. Our, results show the impact of the network bandwidth and topology on the overall performance of each interconnect.

Fast neural net simulation with a DSP processor array.

PubMed

Muller, U A; Gunzinger, A; Guggenbuhl, W

1995-01-01

This paper describes the implementation of a fast neural net simulator on a novel parallel distributed-memory computer. A 60-processor system, named MUSIC (multiprocessor system with intelligent communication), is operational and runs the backpropagation algorithm at a speed of 330 million connection updates per second (continuous weight update) using 32-b floating-point precision. This is equal to 1.4 Gflops sustained performance. The complete system with 3.8 Gflops peak performance consumes less than 800 W of electrical power and fits into a 19-in rack. While reaching the speed of modern supercomputers, MUSIC still can be used as a personal desktop computer at a researcher's own disposal. In neural net simulation, this gives a computing performance to a single user which was unthinkable before. The system's real-time interfaces make it especially useful for embedded applications.

Introduction to Parallel Computing

DTIC Science & Technology

1992-05-01

Instruction Stream, Multiple Data Stream Machines .................... 19 2.4 Networks of M achines...independent memory units and connecting them to the processors by an interconnection network . Many different interconnection schemes have been considered, and...connected to the same processor at the same time. Crossbar switching networks are still too expensive to be practical for connecting large numbers of

GPU: the biggest key processor for AI and parallel processing

NASA Astrophysics Data System (ADS)

Baji, Toru

2017-07-01

Two types of processors exist in the market. One is the conventional CPU and the other is Graphic Processor Unit (GPU). Typical CPU is composed of 1 to 8 cores while GPU has thousands of cores. CPU is good for sequential processing, while GPU is good to accelerate software with heavy parallel executions. GPU was initially dedicated for 3D graphics. However from 2006, when GPU started to apply general-purpose cores, it was noticed that this architecture can be used as a general purpose massive-parallel processor. NVIDIA developed a software framework Compute Unified Device Architecture (CUDA) that make it possible to easily program the GPU for these application. With CUDA, GPU started to be used in workstations and supercomputers widely. Recently two key technologies are highlighted in the industry. The Artificial Intelligence (AI) and Autonomous Driving Cars. AI requires a massive parallel operation to train many-layers of neural networks. With CPU alone, it was impossible to finish the training in a practical time. The latest multi-GPU system with P100 makes it possible to finish the training in a few hours. For the autonomous driving cars, TOPS class of performance is required to implement perception, localization, path planning processing and again SoC with integrated GPU will play a key role there. In this paper, the evolution of the GPU which is one of the biggest commercial devices requiring state-of-the-art fabrication technology will be introduced. Also overview of the GPU demanding key application like the ones described above will be introduced.

Report from the MPP Working Group to the NASA Associate Administrator for Space Science and Applications

NASA Technical Reports Server (NTRS)

Fischer, James R.; Grosch, Chester; Mcanulty, Michael; Odonnell, John; Storey, Owen

1987-01-01

NASA's Office of Space Science and Applications (OSSA) gave a select group of scientists the opportunity to test and implement their computational algorithms on the Massively Parallel Processor (MPP) located at Goddard Space Flight Center, beginning in late 1985. One year later, the Working Group presented its report, which addressed the following: algorithms, programming languages, architecture, programming environments, the way theory relates, and performance measured. The findings point to a number of demonstrated computational techniques for which the MPP architecture is ideally suited. For example, besides executing much faster on the MPP than on conventional computers, systolic VLSI simulation (where distances are short), lattice simulation, neural network simulation, and image problems were found to be easier to program on the MPP's architecture than on a CYBER 205 or even a VAX. The report also makes technical recommendations covering all aspects of MPP use, and recommendations concerning the future of the MPP and machines based on similar architectures, expansion of the Working Group, and study of the role of future parallel processors for space station, EOS, and the Great Observatories era.

Optimization of Applications with Non-blocking Neighborhood Collectives via Multisends on the Blue Gene/P Supercomputer.

PubMed

Kumar, Sameer; Heidelberger, Philip; Chen, Dong; Hines, Michael

2010-04-19

We explore the multisend interface as a data mover interface to optimize applications with neighborhood collective communication operations. One of the limitations of the current MPI 2.1 standard is that the vector collective calls require counts and displacements (zero and nonzero bytes) to be specified for all the processors in the communicator. Further, all the collective calls in MPI 2.1 are blocking and do not permit overlap of communication with computation. We present the record replay persistent optimization to the multisend interface that minimizes the processor overhead of initiating the collective. We present four different case studies with the multisend API on Blue Gene/P (i) 3D-FFT, (ii) 4D nearest neighbor exchange as used in Quantum Chromodynamics, (iii) NAMD and (iv) neural network simulator NEURON. Performance results show 1.9× speedup with 32(3) 3D-FFTs, 1.9× speedup for 4D nearest neighbor exchange with the 2(4) problem, 1.6× speedup in NAMD and almost 3× speedup in NEURON with 256K cells and 1k connections/cell.

Software reconfigurable processor technologies: the key to long-life infrastructure for future space missions

NASA Technical Reports Server (NTRS)

Srinivasan, J.; Farrington, A.; Gray, A.

2001-01-01

They present an overview of long-life reconfigurable processor technologies and of a specific architecture for implementing a software reconfigurable (software-defined) network processor for space applications.

Applications considerations in the system design of highly concurrent multiprocessors

NASA Technical Reports Server (NTRS)

Lundstrom, Stephen F.

1987-01-01

A flow model processor approach to parallel processing is described, using very-high-performance individual processors, high-speed circuit switched interconnection networks, and a high-speed synchronization capability to minimize the effect of the inherently serial portions of applications on performance. Design studies related to the determination of the number of processors, the memory organization, and the structure of the networks used to interconnect the processor and memory resources are discussed. Simulations indicate that applications centered on the large shared data memory should be able to sustain over 500 million floating point operations per second.

Metamodeling and the Critic-based approach to multi-level optimization.

PubMed

Werbos, Ludmilla; Kozma, Robert; Silva-Lugo, Rodrigo; Pazienza, Giovanni E; Werbos, Paul J

2012-08-01

Large-scale networks with hundreds of thousands of variables and constraints are becoming more and more common in logistics, communications, and distribution domains. Traditionally, the utility functions defined on such networks are optimized using some variation of Linear Programming, such as Mixed Integer Programming (MIP). Despite enormous progress both in hardware (multiprocessor systems and specialized processors) and software (Gurobi) we are reaching the limits of what these tools can handle in real time. Modern logistic problems, for example, call for expanding the problem both vertically (from one day up to several days) and horizontally (combining separate solution stages into an integrated model). The complexity of such integrated models calls for alternative methods of solution, such as Approximate Dynamic Programming (ADP), which provide a further increase in the performance necessary for the daily operation. In this paper, we present the theoretical basis and related experiments for solving the multistage decision problems based on the results obtained for shorter periods, as building blocks for the models and the solution, via Critic-Model-Action cycles, where various types of neural networks are combined with traditional MIP models in a unified optimization system. In this system architecture, fast and simple feed-forward networks are trained to reasonably initialize more complicated recurrent networks, which serve as approximators of the value function (Critic). The combination of interrelated neural networks and optimization modules allows for multiple queries for the same system, providing flexibility and optimizing performance for large-scale real-life problems. A MATLAB implementation of our solution procedure for a realistic set of data and constraints shows promising results, compared to the iterative MIP approach. Copyright © 2012 Elsevier Ltd. All rights reserved.

Asynchronous Communication Scheme For Hypercube Computer

NASA Technical Reports Server (NTRS)

Madan, Herb S.

1988-01-01

Scheme devised for asynchronous-message communication system for Mark III hypercube concurrent-processor network. Network consists of up to 1,024 processing elements connected electrically as though were at corners of 10-dimensional cube. Each node contains two Motorola 68020 processors along with Motorola 68881 floating-point processor utilizing up to 4 megabytes of shared dynamic random-access memory. Scheme intended to support applications requiring passage of both polled or solicited and unsolicited messages.

Mobile high-performance computing (HPC) for synthetic aperture radar signal processing

NASA Astrophysics Data System (ADS)

Misko, Joshua; Kim, Youngsoo; Qi, Chenchen; Sirkeci, Birsen

2018-04-01

The importance of mobile high-performance computing has emerged in numerous battlespace applications at the tactical edge in hostile environments. Energy efficient computing power is a key enabler for diverse areas ranging from real-time big data analytics and atmospheric science to network science. However, the design of tactical mobile data centers is dominated by power, thermal, and physical constraints. Presently, it is very unlikely to achieve required computing processing power by aggregating emerging heterogeneous many-core processing platforms consisting of CPU, Field Programmable Gate Arrays and Graphic Processor cores constrained by power and performance. To address these challenges, we performed a Synthetic Aperture Radar case study for Automatic Target Recognition (ATR) using Deep Neural Networks (DNNs). However, these DNN models are typically trained using GPUs with gigabytes of external memories and massively used 32-bit floating point operations. As a result, DNNs do not run efficiently on hardware appropriate for low power or mobile applications. To address this limitation, we proposed for compressing DNN models for ATR suited to deployment on resource constrained hardware. This proposed compression framework utilizes promising DNN compression techniques including pruning and weight quantization while also focusing on processor features common to modern low-power devices. Following this methodology as a guideline produced a DNN for ATR tuned to maximize classification throughput, minimize power consumption, and minimize memory footprint on a low-power device.

All-memristive neuromorphic computing with level-tuned neurons

NASA Astrophysics Data System (ADS)

Pantazi, Angeliki; Woźniak, Stanisław; Tuma, Tomas; Eleftheriou, Evangelos

2016-09-01

In the new era of cognitive computing, systems will be able to learn and interact with the environment in ways that will drastically enhance the capabilities of current processors, especially in extracting knowledge from vast amount of data obtained from many sources. Brain-inspired neuromorphic computing systems increasingly attract research interest as an alternative to the classical von Neumann processor architecture, mainly because of the coexistence of memory and processing units. In these systems, the basic components are neurons interconnected by synapses. The neurons, based on their nonlinear dynamics, generate spikes that provide the main communication mechanism. The computational tasks are distributed across the neural network, where synapses implement both the memory and the computational units, by means of learning mechanisms such as spike-timing-dependent plasticity. In this work, we present an all-memristive neuromorphic architecture comprising neurons and synapses realized by using the physical properties and state dynamics of phase-change memristors. The architecture employs a novel concept of interconnecting the neurons in the same layer, resulting in level-tuned neuronal characteristics that preferentially process input information. We demonstrate the proposed architecture in the tasks of unsupervised learning and detection of multiple temporal correlations in parallel input streams. The efficiency of the neuromorphic architecture along with the homogenous neuro-synaptic dynamics implemented with nanoscale phase-change memristors represent a significant step towards the development of ultrahigh-density neuromorphic co-processors.

All-memristive neuromorphic computing with level-tuned neurons.

PubMed

Pantazi, Angeliki; Woźniak, Stanisław; Tuma, Tomas; Eleftheriou, Evangelos

2016-09-02

In the new era of cognitive computing, systems will be able to learn and interact with the environment in ways that will drastically enhance the capabilities of current processors, especially in extracting knowledge from vast amount of data obtained from many sources. Brain-inspired neuromorphic computing systems increasingly attract research interest as an alternative to the classical von Neumann processor architecture, mainly because of the coexistence of memory and processing units. In these systems, the basic components are neurons interconnected by synapses. The neurons, based on their nonlinear dynamics, generate spikes that provide the main communication mechanism. The computational tasks are distributed across the neural network, where synapses implement both the memory and the computational units, by means of learning mechanisms such as spike-timing-dependent plasticity. In this work, we present an all-memristive neuromorphic architecture comprising neurons and synapses realized by using the physical properties and state dynamics of phase-change memristors. The architecture employs a novel concept of interconnecting the neurons in the same layer, resulting in level-tuned neuronal characteristics that preferentially process input information. We demonstrate the proposed architecture in the tasks of unsupervised learning and detection of multiple temporal correlations in parallel input streams. The efficiency of the neuromorphic architecture along with the homogenous neuro-synaptic dynamics implemented with nanoscale phase-change memristors represent a significant step towards the development of ultrahigh-density neuromorphic co-processors.

Parallel Algorithms for Switching Edges in Heterogeneous Graphs.

PubMed

Bhuiyan, Hasanuzzaman; Khan, Maleq; Chen, Jiangzhuo; Marathe, Madhav

2017-06-01

An edge switch is an operation on a graph (or network) where two edges are selected randomly and one of their end vertices are swapped with each other. Edge switch operations have important applications in graph theory and network analysis, such as in generating random networks with a given degree sequence, modeling and analyzing dynamic networks, and in studying various dynamic phenomena over a network. The recent growth of real-world networks motivates the need for efficient parallel algorithms. The dependencies among successive edge switch operations and the requirement to keep the graph simple (i.e., no self-loops or parallel edges) as the edges are switched lead to significant challenges in designing a parallel algorithm. Addressing these challenges requires complex synchronization and communication among the processors leading to difficulties in achieving a good speedup by parallelization. In this paper, we present distributed memory parallel algorithms for switching edges in massive networks. These algorithms provide good speedup and scale well to a large number of processors. A harmonic mean speedup of 73.25 is achieved on eight different networks with 1024 processors. One of the steps in our edge switch algorithms requires the computation of multinomial random variables in parallel. This paper presents the first non-trivial parallel algorithm for the problem, achieving a speedup of 925 using 1024 processors.

Parallel Algorithms for Switching Edges in Heterogeneous Graphs☆

PubMed Central

Khan, Maleq; Chen, Jiangzhuo; Marathe, Madhav

2017-01-01

An edge switch is an operation on a graph (or network) where two edges are selected randomly and one of their end vertices are swapped with each other. Edge switch operations have important applications in graph theory and network analysis, such as in generating random networks with a given degree sequence, modeling and analyzing dynamic networks, and in studying various dynamic phenomena over a network. The recent growth of real-world networks motivates the need for efficient parallel algorithms. The dependencies among successive edge switch operations and the requirement to keep the graph simple (i.e., no self-loops or parallel edges) as the edges are switched lead to significant challenges in designing a parallel algorithm. Addressing these challenges requires complex synchronization and communication among the processors leading to difficulties in achieving a good speedup by parallelization. In this paper, we present distributed memory parallel algorithms for switching edges in massive networks. These algorithms provide good speedup and scale well to a large number of processors. A harmonic mean speedup of 73.25 is achieved on eight different networks with 1024 processors. One of the steps in our edge switch algorithms requires the computation of multinomial random variables in parallel. This paper presents the first non-trivial parallel algorithm for the problem, achieving a speedup of 925 using 1024 processors. PMID:28757680

A Bidirectional Brain-Machine Interface Featuring a Neuromorphic Hardware Decoder.

PubMed

Boi, Fabio; Moraitis, Timoleon; De Feo, Vito; Diotalevi, Francesco; Bartolozzi, Chiara; Indiveri, Giacomo; Vato, Alessandro

2016-01-01

Bidirectional brain-machine interfaces (BMIs) establish a two-way direct communication link between the brain and the external world. A decoder translates recorded neural activity into motor commands and an encoder delivers sensory information collected from the environment directly to the brain creating a closed-loop system. These two modules are typically integrated in bulky external devices. However, the clinical support of patients with severe motor and sensory deficits requires compact, low-power, and fully implantable systems that can decode neural signals to control external devices. As a first step toward this goal, we developed a modular bidirectional BMI setup that uses a compact neuromorphic processor as a decoder. On this chip we implemented a network of spiking neurons built using its ultra-low-power mixed-signal analog/digital circuits. On-chip on-line spike-timing-dependent plasticity synapse circuits enabled the network to learn to decode neural signals recorded from the brain into motor outputs controlling the movements of an external device. The modularity of the BMI allowed us to tune the individual components of the setup without modifying the whole system. In this paper, we present the features of this modular BMI and describe how we configured the network of spiking neuron circuits to implement the decoder and to coordinate it with the encoder in an experimental BMI paradigm that connects bidirectionally the brain of an anesthetized rat with an external object. We show that the chip learned the decoding task correctly, allowing the interfaced brain to control the object's trajectories robustly. Based on our demonstration, we propose that neuromorphic technology is mature enough for the development of BMI modules that are sufficiently low-power and compact, while being highly computationally powerful and adaptive.

A Bidirectional Brain-Machine Interface Featuring a Neuromorphic Hardware Decoder

PubMed Central

Boi, Fabio; Moraitis, Timoleon; De Feo, Vito; Diotalevi, Francesco; Bartolozzi, Chiara; Indiveri, Giacomo; Vato, Alessandro

2016-01-01

Bidirectional brain-machine interfaces (BMIs) establish a two-way direct communication link between the brain and the external world. A decoder translates recorded neural activity into motor commands and an encoder delivers sensory information collected from the environment directly to the brain creating a closed-loop system. These two modules are typically integrated in bulky external devices. However, the clinical support of patients with severe motor and sensory deficits requires compact, low-power, and fully implantable systems that can decode neural signals to control external devices. As a first step toward this goal, we developed a modular bidirectional BMI setup that uses a compact neuromorphic processor as a decoder. On this chip we implemented a network of spiking neurons built using its ultra-low-power mixed-signal analog/digital circuits. On-chip on-line spike-timing-dependent plasticity synapse circuits enabled the network to learn to decode neural signals recorded from the brain into motor outputs controlling the movements of an external device. The modularity of the BMI allowed us to tune the individual components of the setup without modifying the whole system. In this paper, we present the features of this modular BMI and describe how we configured the network of spiking neuron circuits to implement the decoder and to coordinate it with the encoder in an experimental BMI paradigm that connects bidirectionally the brain of an anesthetized rat with an external object. We show that the chip learned the decoding task correctly, allowing the interfaced brain to control the object's trajectories robustly. Based on our demonstration, we propose that neuromorphic technology is mature enough for the development of BMI modules that are sufficiently low-power and compact, while being highly computationally powerful and adaptive. PMID:28018162

Array processor architecture

NASA Technical Reports Server (NTRS)

Barnes, George H. (Inventor); Lundstrom, Stephen F. (Inventor); Shafer, Philip E. (Inventor)

1983-01-01

A high speed parallel array data processing architecture fashioned under a computational envelope approach includes a data base memory for secondary storage of programs and data, and a plurality of memory modules interconnected to a plurality of processing modules by a connection network of the Omega gender. Programs and data are fed from the data base memory to the plurality of memory modules and from hence the programs are fed through the connection network to the array of processors (one copy of each program for each processor). Execution of the programs occur with the processors operating normally quite independently of each other in a multiprocessing fashion. For data dependent operations and other suitable operations, all processors are instructed to finish one given task or program branch before all are instructed to proceed in parallel processing fashion on the next instruction. Even when functioning in the parallel processing mode however, the processors are not locked-step but execute their own copy of the program individually unless or until another overall processor array synchronization instruction is issued.

Software-Reconfigurable Processors for Spacecraft

NASA Technical Reports Server (NTRS)

Farrington, Allen; Gray, Andrew; Bell, Bryan; Stanton, Valerie; Chong, Yong; Peters, Kenneth; Lee, Clement; Srinivasan, Jeffrey

2005-01-01

A report presents an overview of an architecture for a software-reconfigurable network data processor for a spacecraft engaged in scientific exploration. When executed on suitable electronic hardware, the software performs the functions of a physical layer (in effect, acts as a software radio in that it performs modulation, demodulation, pulse-shaping, error correction, coding, and decoding), a data-link layer, a network layer, a transport layer, and application-layer processing of scientific data. The software-reconfigurable network processor is undergoing development to enable rapid prototyping and rapid implementation of communication, navigation, and scientific signal-processing functions; to provide a long-lived communication infrastructure; and to provide greatly improved scientific-instrumentation and scientific-data-processing functions by enabling science-driven in-flight reconfiguration of computing resources devoted to these functions. This development is an extension of terrestrial radio and network developments (e.g., in the cellular-telephone industry) implemented in software running on such hardware as field-programmable gate arrays, digital signal processors, traditional digital circuits, and mixed-signal application-specific integrated circuits (ASICs).

System for routing messages in a vertex symmetric network by using addresses formed from permutations of the transmission line indicees

DOEpatents

Faber, Vance; Moore, James W.

1992-01-01

A network of interconnected processors is formed from a vertex symmetric graph selected from graphs .GAMMA..sub.d (k) with degree d, diameter k, and (d+1)!/(d-k+1)! processors for each d.gtoreq.k and .GAMMA..sub.d (k,-1) with degree 3-1, diameter k+1, and (d+1)!/(d-k+1)! processors for each d.gtoreq.k.gtoreq.4. Each processor has an address formed by one of the permutations from a predetermined sequence of letters chosen a selected number of letters at a time, and an extended address formed by appending to the address the remaining ones of the predetermined sequence of letters. A plurality of transmission channels is provided from each of the processors, where each processor has one less channel than the selected number of letters forming the sequence. Where a network .GAMMA..sub.d (k,-1) is provided, no processor has a channel connected to form an edge in a direction .delta..sub.1. Each of the channels has an identification number selected from the sequence of letters and connected from a first processor having a first extended address to a second processor having a second address formed from a second extended address defined by moving to the front of the first extended address the letter found in the position within the first extended address defined by the channel identification number. The second address is then formed by selecting the first elements of the second extended address corresponding to the selected number used to form the address permutations.

Real-time million-synapse simulation of rat barrel cortex.

PubMed

Sharp, Thomas; Petersen, Rasmus; Furber, Steve

2014-01-01

Simulations of neural circuits are bounded in scale and speed by available computing resources, and particularly by the differences in parallelism and communication patterns between the brain and high-performance computers. SpiNNaker is a computer architecture designed to address this problem by emulating the structure and function of neural tissue, using very many low-power processors and an interprocessor communication mechanism inspired by axonal arbors. Here we demonstrate that thousand-processor SpiNNaker prototypes can simulate models of the rodent barrel system comprising 50,000 neurons and 50 million synapses. We use the PyNN library to specify models, and the intrinsic features of Python to control experimental procedures and analysis. The models reproduce known thalamocortical response transformations, exhibit known, balanced dynamics of excitation and inhibition, and show a spatiotemporal spread of activity though the superficial cortical layers. These demonstrations are a significant step toward tractable simulations of entire cortical areas on the million-processor SpiNNaker machines in development.

Real-time million-synapse simulation of rat barrel cortex

PubMed Central

Sharp, Thomas; Petersen, Rasmus; Furber, Steve

2014-01-01

Simulations of neural circuits are bounded in scale and speed by available computing resources, and particularly by the differences in parallelism and communication patterns between the brain and high-performance computers. SpiNNaker is a computer architecture designed to address this problem by emulating the structure and function of neural tissue, using very many low-power processors and an interprocessor communication mechanism inspired by axonal arbors. Here we demonstrate that thousand-processor SpiNNaker prototypes can simulate models of the rodent barrel system comprising 50,000 neurons and 50 million synapses. We use the PyNN library to specify models, and the intrinsic features of Python to control experimental procedures and analysis. The models reproduce known thalamocortical response transformations, exhibit known, balanced dynamics of excitation and inhibition, and show a spatiotemporal spread of activity though the superficial cortical layers. These demonstrations are a significant step toward tractable simulations of entire cortical areas on the million-processor SpiNNaker machines in development. PMID:24910593

Combined Ozone Retrieval From METOP Sensors Using META-Training Of Deep Neural Networks

NASA Astrophysics Data System (ADS)

Felder, Martin; Sehnke, Frank; Kaifel, Anton

2013-12-01

The newest installment of our well-proven Neural Net- work Ozone Retrieval System (NNORSY) combines the METOP sensors GOME-2 and IASI with cloud information from AVHRR. Through the use of advanced meta- learning techniques like automatic feature selection and automatic architecture search applied to a set of deep neural networks, having at least two or three hidden layers, we have been able to avoid many technical issues normally encountered during the construction of such a joint retrieval system. This has been made possible by harnessing the processing power of modern consumer graphics cards with high performance graphic processors (GPU), which decreases training times by about two orders of magnitude. The system was trained on data from 2009 and 2010, including target ozone profiles from ozone sondes, ACE- FTS and MLS-AURA. To make maximum use of tropospheric information in the spectra, the data were partitioned into several sets of different cloud fraction ranges with the GOME-2 FOV, on which specialized retrieval networks are being trained. For the final ozone retrieval processing the different specialized networks are combined. The resulting retrieval system is very stable and does not show any systematic dependence on solar zenith angle, scan angle or sensor degradation. We present several sensitivity studies with regard to cloud fraction and target sensor type, as well as the performance in several latitude bands and with respect to independent validation stations. A visual cross-comparison against high-resolution ozone profiles from the KNMI EUMETSAT Ozone SAF product has also been performed and shows some distinctive features which we will briefly discuss. Overall, we demonstrate that a complex retrieval system can now be constructed with a minimum of ma- chine learning knowledge, using automated algorithms for many design decisions previously requiring expert knowledge. Provided sufficient training data and computation power of GPUs is available, the method can be applied to almost any kind of retrieval or, more generally, regression problem.

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

NASA Technical Reports Server (NTRS)

Rai, Man Mohan

2006-01-01

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

Enabling Functional Neural Circuit Simulations with Distributed Computing of Neuromodulated Plasticity

PubMed Central

Potjans, Wiebke; Morrison, Abigail; Diesmann, Markus

2010-01-01

A major puzzle in the field of computational neuroscience is how to relate system-level learning in higher organisms to synaptic plasticity. Recently, plasticity rules depending not only on pre- and post-synaptic activity but also on a third, non-local neuromodulatory signal have emerged as key candidates to bridge the gap between the macroscopic and the microscopic level of learning. Crucial insights into this topic are expected to be gained from simulations of neural systems, as these allow the simultaneous study of the multiple spatial and temporal scales that are involved in the problem. In particular, synaptic plasticity can be studied during the whole learning process, i.e., on a time scale of minutes to hours and across multiple brain areas. Implementing neuromodulated plasticity in large-scale network simulations where the neuromodulatory signal is dynamically generated by the network itself is challenging, because the network structure is commonly defined purely by the connectivity graph without explicit reference to the embedding of the nodes in physical space. Furthermore, the simulation of networks with realistic connectivity entails the use of distributed computing. A neuromodulated synapse must therefore be informed in an efficient way about the neuromodulatory signal, which is typically generated by a population of neurons located on different machines than either the pre- or post-synaptic neuron. Here, we develop a general framework to solve the problem of implementing neuromodulated plasticity in a time-driven distributed simulation, without reference to a particular implementation language, neuromodulator, or neuromodulated plasticity mechanism. We implement our framework in the simulator NEST and demonstrate excellent scaling up to 1024 processors for simulations of a recurrent network incorporating neuromodulated spike-timing dependent plasticity. PMID:21151370

Optimizing NEURON Simulation Environment Using Remote Memory Access with Recursive Doubling on Distributed Memory Systems.

PubMed

Shehzad, Danish; Bozkuş, Zeki

2016-01-01

Increase in complexity of neuronal network models escalated the efforts to make NEURON simulation environment efficient. The computational neuroscientists divided the equations into subnets amongst multiple processors for achieving better hardware performance. On parallel machines for neuronal networks, interprocessor spikes exchange consumes large section of overall simulation time. In NEURON for communication between processors Message Passing Interface (MPI) is used. MPI_Allgather collective is exercised for spikes exchange after each interval across distributed memory systems. The increase in number of processors though results in achieving concurrency and better performance but it inversely affects MPI_Allgather which increases communication time between processors. This necessitates improving communication methodology to decrease the spikes exchange time over distributed memory systems. This work has improved MPI_Allgather method using Remote Memory Access (RMA) by moving two-sided communication to one-sided communication, and use of recursive doubling mechanism facilitates achieving efficient communication between the processors in precise steps. This approach enhanced communication concurrency and has improved overall runtime making NEURON more efficient for simulation of large neuronal network models.

Optimizing NEURON Simulation Environment Using Remote Memory Access with Recursive Doubling on Distributed Memory Systems

PubMed Central

Bozkuş, Zeki

2016-01-01

Increase in complexity of neuronal network models escalated the efforts to make NEURON simulation environment efficient. The computational neuroscientists divided the equations into subnets amongst multiple processors for achieving better hardware performance. On parallel machines for neuronal networks, interprocessor spikes exchange consumes large section of overall simulation time. In NEURON for communication between processors Message Passing Interface (MPI) is used. MPI_Allgather collective is exercised for spikes exchange after each interval across distributed memory systems. The increase in number of processors though results in achieving concurrency and better performance but it inversely affects MPI_Allgather which increases communication time between processors. This necessitates improving communication methodology to decrease the spikes exchange time over distributed memory systems. This work has improved MPI_Allgather method using Remote Memory Access (RMA) by moving two-sided communication to one-sided communication, and use of recursive doubling mechanism facilitates achieving efficient communication between the processors in precise steps. This approach enhanced communication concurrency and has improved overall runtime making NEURON more efficient for simulation of large neuronal network models. PMID:27413363

On the efficacy of using the transfer-controlled procedure during periods of STP processor overloads in SS7 networks

NASA Astrophysics Data System (ADS)

Rumsewicz, Michael

1994-04-01

In this paper, we examine call completion performance, rather than message throughput, in a Common Channel Signaling network in which the processing resources, and not transmission resources, of a Signaling Transfer Point (STP) are overloaded. Specifically, we perform a transient analysis, via simulation, of a network consisting of a single Central Processor-based STP connecting many local exchanges. We consider the efficacy of using the Transfer Controlled (TFC) procedure when the network call attempt rate exceeds the processing capability of the STP. We find the following: (1) the success of the control depends critically on the rate at which TFC's are sent; (2) use of the TFC procedure in theevent of processor overload can provide reasonable call completion rates.

Interconnection networks

DOEpatents

Faber, V.; Moore, J.W.

1988-06-20

A network of interconnected processors is formed from a vertex symmetric graph selected from graphs GAMMA/sub d/(k) with degree d, diameter k, and (d + 1)exclamation/ (d /minus/ k + 1)exclamation processors for each d greater than or equal to k and GAMMA/sub d/(k, /minus/1) with degree d /minus/ 1, diameter k + 1, and (d + 1)exclamation/(d /minus/ k + 1)exclamation processors for each d greater than or equal to k greater than or equal to 4. Each processor has an address formed by one of the permutations from a predetermined sequence of letters chosen a selected number of letters at a time, and an extended address formed by appending to the address the remaining ones of the predetermined sequence of letters. A plurality of transmission channels is provided from each of the processors, where each processor has one less channel than the selected number of letters forming the sequence. Where a network GAMMA/sub d/(k, /minus/1) is provided, no processor has a channel connected to form an edge in a direction delta/sub 1/. Each of the channels has an identification number selected from the sequence of letters and connected from a first processor having a first extended address to a second processor having a second address formed from a second extended address defined by moving to the front of the first extended address the letter found in the position within the first extended address defined by the channel identification number. The second address is then formed by selecting the first elements of the second extended address corresponding to the selected number used to form the address permutations. 9 figs.

Design and implementation of a high performance network security processor

NASA Astrophysics Data System (ADS)

Wang, Haixin; Bai, Guoqiang; Chen, Hongyi

2010-03-01

The last few years have seen many significant progresses in the field of application-specific processors. One example is network security processors (NSPs) that perform various cryptographic operations specified by network security protocols and help to offload the computation intensive burdens from network processors (NPs). This article presents a high performance NSP system architecture implementation intended for both internet protocol security (IPSec) and secure socket layer (SSL) protocol acceleration, which are widely employed in virtual private network (VPN) and e-commerce applications. The efficient dual one-way pipelined data transfer skeleton and optimised integration scheme of the heterogenous parallel crypto engine arrays lead to a Gbps rate NSP, which is programmable with domain specific descriptor-based instructions. The descriptor-based control flow fragments large data packets and distributes them to the crypto engine arrays, which fully utilises the parallel computation resources and improves the overall system data throughput. A prototyping platform for this NSP design is implemented with a Xilinx XC3S5000 based FPGA chip set. Results show that the design gives a peak throughput for the IPSec ESP tunnel mode of 2.85 Gbps with over 2100 full SSL handshakes per second at a clock rate of 95 MHz.

Fault tolerant, radiation hard, high performance digital signal processor

NASA Technical Reports Server (NTRS)

Holmann, Edgar; Linscott, Ivan R.; Maurer, Michael J.; Tyler, G. L.; Libby, Vibeke

1990-01-01

An architecture has been developed for a high-performance VLSI digital signal processor that is highly reliable, fault-tolerant, and radiation-hard. The signal processor, part of a spacecraft receiver designed to support uplink radio science experiments at the outer planets, organizes the connections between redundant arithmetic resources, register files, and memory through a shuffle exchange communication network. The configuration of the network and the state of the processor resources are all under microprogram control, which both maps the resources according to algorithmic needs and reconfigures the processing should a failure occur. In addition, the microprogram is reloadable through the uplink to accommodate changes in the science objectives throughout the course of the mission. The processor will be implemented with silicon compiler tools, and its design will be verified through silicon compilation simulation at all levels from the resources to full functionality. By blending reconfiguration with redundancy the processor implementation is fault-tolerant and reliable, and possesses the long expected lifetime needed for a spacecraft mission to the outer planets.

Performance Study of Earth Networks Total Lightning Network using Rocket-Triggered Lightning Data in 2014

NASA Astrophysics Data System (ADS)

Heckman, S.

2015-12-01

Modern lightning locating systems (LLS) provide real-time monitoring and early warning of lightningactivities. In addition, LLS provide valuable data for statistical analysis in lightning research. It isimportant to know the performance of such LLS. In the present study, the performance of the EarthNetworks Total Lightning Network (ENTLN) is studied using rocket-triggered lightning data acquired atthe International Center for Lightning Research and Testing (ICLRT), Camp Blanding, Florida.In the present study, 18 flashes triggered at ICLRT in 2014 were analyzed and they comprise of 78negative cloud-to-ground return strokes. The geometric mean, median, minimum, and maximum for thepeak currents of the 78 return strokes are 13.4 kA, 13.6 kA, 3.7 kA, and 38.4 kA, respectively. The peakcurrents represent typical subsequent return strokes in natural cloud-to-ground lightning.Earth Networks has developed a new data processor to improve the performance of their network. Inthis study, results are presented for the ENTLN data using the old processor (originally reported in 2014)and the ENTLN data simulated using the new processor. The flash detection efficiency, stroke detectionefficiency, percentage of misclassification, median location error, median peak current estimation error,and median absolute peak current estimation error for the originally reported data from old processorare 100%, 94%, 49%, 271 m, 5%, and 13%, respectively, and those for the simulated data using the newprocessor are 100%, 99%, 9%, 280 m, 11%, and 15%, respectively. The use of new processor resulted inhigher stroke detection efficiency and lower percentage of misclassification. It is worth noting that theslight differences in median location error, median peak current estimation error, and median absolutepeak current estimation error for the two processors are due to the fact that the new processordetected more number of return strokes than the old processor.

Intelligent neuroprocessors for in-situ launch vehicle propulsion systems health management

NASA Technical Reports Server (NTRS)

Gulati, S.; Tawel, R.; Thakoor, A. P.

1993-01-01

Efficacy of existing on-board propulsion systems health management systems (HMS) are severely impacted by computational limitations (e.g., low sampling rates); paradigmatic limitations (e.g., low-fidelity logic/parameter redlining only, false alarms due to noisy/corrupted sensor signatures, preprogrammed diagnostics only); and telemetry bandwidth limitations on space/ground interactions. Ultra-compact/light, adaptive neural networks with massively parallel, asynchronous, fast reconfigurable and fault-tolerant information processing properties have already demonstrated significant potential for inflight diagnostic analyses and resource allocation with reduced ground dependence. In particular, they can automatically exploit correlation effects across multiple sensor streams (plume analyzer, flow meters, vibration detectors, etc.) so as to detect anomaly signatures that cannot be determined from the exploitation of single sensor. Furthermore, neural networks have already demonstrated the potential for impacting real-time fault recovery in vehicle subsystems by adaptively regulating combustion mixture/power subsystems and optimizing resource utilization under degraded conditions. A class of high-performance neuroprocessors, developed at JPL, that have demonstrated potential for next-generation HMS for a family of space transportation vehicles envisioned for the next few decades, including HLLV, NLS, and space shuttle is presented. Of fundamental interest are intelligent neuroprocessors for real-time plume analysis, optimizing combustion mixture-ratio, and feedback to hydraulic, pneumatic control systems. This class includes concurrently asynchronous reprogrammable, nonvolatile, analog neural processors with high speed, high bandwidth electronic/optical I/O interfaced, with special emphasis on NASA's unique requirements in terms of performance, reliability, ultra-high density ultra-compactness, ultra-light weight devices, radiation hardened devices, power stringency, and long life terms.

Using algebra for massively parallel processor design and utilization

NASA Technical Reports Server (NTRS)

Campbell, Lowell; Fellows, Michael R.

1990-01-01

This paper summarizes the author's advances in the design of dense processor networks. Within is reported a collection of recent constructions of dense symmetric networks that provide the largest know values for the number of nodes that can be placed in a network of a given degree and diameter. The constructions are in the range of current potential engineering significance and are based on groups of automorphisms of finite-dimensional vector spaces.

Lambda network having 2.sup.m-1 nodes in each of m stages with each node coupled to four other nodes for bidirectional routing of data packets between nodes

DOEpatents

Napolitano, Jr., Leonard M.

1995-01-01

The Lambda network is a single stage, packet-switched interprocessor communication network for a distributed memory, parallel processor computer. Its design arises from the desired network characteristics of minimizing mean and maximum packet transfer time, local routing, expandability, deadlock avoidance, and fault tolerance. The network is based on fixed degree nodes and has mean and maximum packet transfer distances where n is the number of processors. The routing method is detailed, as are methods for expandability, deadlock avoidance, and fault tolerance.

Closing the Gap: Cybersecurity for U.S. Forces and Commands

DTIC Science & Technology

2017-03-30

Dickson, Ph.D. Professor of Military Studies , JAWS Thesis Advisor Kevin Therrien, Col, USAF Committee Member Stephen Rogers, Colonel, USA Director...infrastructures, and includes the Internet, telecommunications networks, computer systems, and embedded processors and controllers in critical industries.”5...of information technology infrastructures, including the Internet, telecommunications networks, computer systems, and embedded processors and

Computer Sciences and Data Systems, volume 2

NASA Technical Reports Server (NTRS)

1987-01-01

Topics addressed include: data storage; information network architecture; VHSIC technology; fiber optics; laser applications; distributed processing; spaceborne optical disk controller; massively parallel processors; and advanced digital SAR processors.

Parallel network simulations with NEURON.

PubMed

Migliore, M; Cannia, C; Lytton, W W; Markram, Henry; Hines, M L

2006-10-01

The NEURON simulation environment has been extended to support parallel network simulations. Each processor integrates the equations for its subnet over an interval equal to the minimum (interprocessor) presynaptic spike generation to postsynaptic spike delivery connection delay. The performance of three published network models with very different spike patterns exhibits superlinear speedup on Beowulf clusters and demonstrates that spike communication overhead is often less than the benefit of an increased fraction of the entire problem fitting into high speed cache. On the EPFL IBM Blue Gene, almost linear speedup was obtained up to 100 processors. Increasing one model from 500 to 40,000 realistic cells exhibited almost linear speedup on 2,000 processors, with an integration time of 9.8 seconds and communication time of 1.3 seconds. The potential for speed-ups of several orders of magnitude makes practical the running of large network simulations that could otherwise not be explored.

Parallel Network Simulations with NEURON

PubMed Central

Migliore, M.; Cannia, C.; Lytton, W.W; Markram, Henry; Hines, M. L.

2009-01-01

The NEURON simulation environment has been extended to support parallel network simulations. Each processor integrates the equations for its subnet over an interval equal to the minimum (interprocessor) presynaptic spike generation to postsynaptic spike delivery connection delay. The performance of three published network models with very different spike patterns exhibits superlinear speedup on Beowulf clusters and demonstrates that spike communication overhead is often less than the benefit of an increased fraction of the entire problem fitting into high speed cache. On the EPFL IBM Blue Gene, almost linear speedup was obtained up to 100 processors. Increasing one model from 500 to 40,000 realistic cells exhibited almost linear speedup on 2000 processors, with an integration time of 9.8 seconds and communication time of 1.3 seconds. The potential for speed-ups of several orders of magnitude makes practical the running of large network simulations that could otherwise not be explored. PMID:16732488

Robust, High-Speed Network Design for Large-Scale Multiprocessing

DTIC Science & Technology

1993-09-01

3.17 Left: Non-expansive Wiring of Processors to First Stage Routing Elements . ... 38 3.18 Right: Expansive Wiring of Processors to First Stage...162 8.2 RNI Micro -architecture ........ .............................. 163 8.3 Packaged RN I IC...169 11.1 MLUNK Message Formats ........ .............................. 173 12.1 Routing Board Arrangement for 64- processor Machine

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

DTIC Science & Technology

1991-12-01

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

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

PubMed

Chen, Liang; Xue, Wei; Tokuda, Naoyuki

2010-08-01

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

Launching applications on compute and service processors running under different operating systems in scalable network of processor boards with routers

DOEpatents

Tomkins, James L [Albuquerque, NM; Camp, William J [Albuquerque, NM

2009-03-17

A multiple processor computing apparatus includes a physical interconnect structure that is flexibly configurable to support selective segregation of classified and unclassified users. The physical interconnect structure also permits easy physical scalability of the computing apparatus. The computing apparatus can include an emulator which permits applications from the same job to be launched on processors that use different operating systems.

An intelligent allocation algorithm for parallel processing

NASA Technical Reports Server (NTRS)

Carroll, Chester C.; Homaifar, Abdollah; Ananthram, Kishan G.

1988-01-01

The problem of allocating nodes of a program graph to processors in a parallel processing architecture is considered. The algorithm is based on critical path analysis, some allocation heuristics, and the execution granularity of nodes in a program graph. These factors, and the structure of interprocessor communication network, influence the allocation. To achieve realistic estimations of the executive durations of allocations, the algorithm considers the fact that nodes in a program graph have to communicate through varying numbers of tokens. Coarse and fine granularities have been implemented, with interprocessor token-communication duration, varying from zero up to values comparable to the execution durations of individual nodes. The effect on allocation of communication network structures is demonstrated by performing allocations for crossbar (non-blocking) and star (blocking) networks. The algorithm assumes the availability of as many processors as it needs for the optimal allocation of any program graph. Hence, the focus of allocation has been on varying token-communication durations rather than varying the number of processors. The algorithm always utilizes as many processors as necessary for the optimal allocation of any program graph, depending upon granularity and characteristics of the interprocessor communication network.

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

DTIC Science & Technology

1995-11-01

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

Communications systems and methods for subsea processors

DOEpatents

Gutierrez, Jose; Pereira, Luis

2016-04-26

A subsea processor may be located near the seabed of a drilling site and used to coordinate operations of underwater drilling components. The subsea processor may be enclosed in a single interchangeable unit that fits a receptor on an underwater drilling component, such as a blow-out preventer (BOP). The subsea processor may issue commands to control the BOP and receive measurements from sensors located throughout the BOP. A shared communications bus may interconnect the subsea processor and underwater components and the subsea processor and a surface or onshore network. The shared communications bus may be operated according to a time division multiple access (TDMA) scheme.

DMA shared byte counters in a parallel computer

DOEpatents

Chen, Dong; Gara, Alan G.; Heidelberger, Philip; Vranas, Pavlos

2010-04-06

A parallel computer system is constructed as a network of interconnected compute nodes. Each of the compute nodes includes at least one processor, a memory and a DMA engine. The DMA engine includes a processor interface for interfacing with the at least one processor, DMA logic, a memory interface for interfacing with the memory, a DMA network interface for interfacing with the network, injection and reception byte counters, injection and reception FIFO metadata, and status registers and control registers. The injection FIFOs maintain memory locations of the injection FIFO metadata memory locations including its current head and tail, and the reception FIFOs maintain the reception FIFO metadata memory locations including its current head and tail. The injection byte counters and reception byte counters may be shared between messages.

Neural networks for aircraft control

NASA Technical Reports Server (NTRS)

Linse, Dennis

1990-01-01

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

Lambda network having 2{sup m{minus}1} nodes in each of m stages with each node coupled to four other nodes for bidirectional routing of data packets between nodes

DOEpatents

Napolitano, L.M. Jr.

1995-11-28

The Lambda network is a single stage, packet-switched interprocessor communication network for a distributed memory, parallel processor computer. Its design arises from the desired network characteristics of minimizing mean and maximum packet transfer time, local routing, expandability, deadlock avoidance, and fault tolerance. The network is based on fixed degree nodes and has mean and maximum packet transfer distances where n is the number of processors. The routing method is detailed, as are methods for expandability, deadlock avoidance, and fault tolerance. 14 figs.

Neural node network and model, and method of teaching same

DOEpatents

Parlos, A.G.; Atiya, A.F.; Fernandez, B.; Tsai, W.K.; Chong, K.T.

1995-12-26

The present invention is a fully connected feed forward network that includes at least one hidden layer. The hidden layer includes nodes in which the output of the node is fed back to that node as an input with a unit delay produced by a delay device occurring in the feedback path (local feedback). Each node within each layer also receives a delayed output (crosstalk) produced by a delay unit from all the other nodes within the same layer. The node performs a transfer function operation based on the inputs from the previous layer and the delayed outputs. The network can be implemented as analog or digital or within a general purpose processor. Two teaching methods can be used: (1) back propagation of weight calculation that includes the local feedback and the crosstalk or (2) more preferably a feed forward gradient decent which immediately follows the output computations and which also includes the local feedback and the crosstalk. Subsequent to the gradient propagation, the weights can be normalized, thereby preventing convergence to a local optimum. Education of the network can be incremental both on and off-line. An educated network is suitable for modeling and controlling dynamic nonlinear systems and time series systems and predicting the outputs as well as hidden states and parameters. The educated network can also be further educated during on-line processing. 21 figs.

Neural node network and model, and method of teaching same

DOEpatents

Parlos, Alexander G.; Atiya, Amir F.; Fernandez, Benito; Tsai, Wei K.; Chong, Kil T.

1995-01-01

The present invention is a fully connected feed forward network that includes at least one hidden layer 16. The hidden layer 16 includes nodes 20 in which the output of the node is fed back to that node as an input with a unit delay produced by a delay device 24 occurring in the feedback path 22 (local feedback). Each node within each layer also receives a delayed output (crosstalk) produced by a delay unit 36 from all the other nodes within the same layer 16. The node performs a transfer function operation based on the inputs from the previous layer and the delayed outputs. The network can be implemented as analog or digital or within a general purpose processor. Two teaching methods can be used: (1) back propagation of weight calculation that includes the local feedback and the crosstalk or (2) more preferably a feed forward gradient decent which immediately follows the output computations and which also includes the local feedback and the crosstalk. Subsequent to the gradient propagation, the weights can be normalized, thereby preventing convergence to a local optimum. Education of the network can be incremental both on and off-line. An educated network is suitable for modeling and controlling dynamic nonlinear systems and time series systems and predicting the outputs as well as hidden states and parameters. The educated network can also be further educated during on-line processing.

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

NASA Astrophysics Data System (ADS)

Tanadi, Theo

2018-03-01

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

Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing

PubMed Central

Farabet, Clément; Paz, Rafael; Pérez-Carrasco, Jose; Zamarreño-Ramos, Carlos; Linares-Barranco, Alejandro; LeCun, Yann; Culurciello, Eugenio; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabe

2012-01-01

Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search, and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can implement general-purpose bio-inspired vision systems. In standard digital computers 2D convolutions are usually expensive in terms of resource consumption and impose severe limitations for efficient real-time applications. Nevertheless, neuro-cortex inspired solutions, like dedicated Frame-Based or Frame-Free Spiking ConvNet Convolution Processors, are advancing real-time visual processing. These two approaches share the neural inspiration, but each of them solves the problem in different ways. Frame-Based ConvNets process frame by frame video information in a very robust and fast way that requires to use and share the available hardware resources (such as: multipliers, adders). Hardware resources are fixed- and time-multiplexed by fetching data in and out. Thus memory bandwidth and size is important for good performance. On the other hand, spike-based convolution processors are a frame-free alternative that is able to perform convolution of a spike-based source of visual information with very low latency, which makes ideal for very high-speed applications. However, hardware resources need to be available all the time and cannot be time-multiplexed. Thus, hardware should be modular, reconfigurable, and expansible. Hardware implementations in both VLSI custom integrated circuits (digital and analog) and FPGA have been already used to demonstrate the performance of these systems. In this paper we present a comparison study of these two neuro-inspired solutions. A brief description of both systems is presented and also discussions about their differences, pros and cons. PMID:22518097

Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing.

PubMed

Farabet, Clément; Paz, Rafael; Pérez-Carrasco, Jose; Zamarreño-Ramos, Carlos; Linares-Barranco, Alejandro; Lecun, Yann; Culurciello, Eugenio; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabe

2012-01-01

Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search, and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can implement general-purpose bio-inspired vision systems. In standard digital computers 2D convolutions are usually expensive in terms of resource consumption and impose severe limitations for efficient real-time applications. Nevertheless, neuro-cortex inspired solutions, like dedicated Frame-Based or Frame-Free Spiking ConvNet Convolution Processors, are advancing real-time visual processing. These two approaches share the neural inspiration, but each of them solves the problem in different ways. Frame-Based ConvNets process frame by frame video information in a very robust and fast way that requires to use and share the available hardware resources (such as: multipliers, adders). Hardware resources are fixed- and time-multiplexed by fetching data in and out. Thus memory bandwidth and size is important for good performance. On the other hand, spike-based convolution processors are a frame-free alternative that is able to perform convolution of a spike-based source of visual information with very low latency, which makes ideal for very high-speed applications. However, hardware resources need to be available all the time and cannot be time-multiplexed. Thus, hardware should be modular, reconfigurable, and expansible. Hardware implementations in both VLSI custom integrated circuits (digital and analog) and FPGA have been already used to demonstrate the performance of these systems. In this paper we present a comparison study of these two neuro-inspired solutions. A brief description of both systems is presented and also discussions about their differences, pros and cons.

Dynamic Sensor Networks

DTIC Science & Technology

2004-03-01

turned off. SLEEP Set the timer for 30 seconds before scheduled transmit time, then sleep the processor. WAKE When timer trips, power up the processor...slots where none of its neighbors are schedule to transmit. This allows the sensor nodes to perform a simple power man- agement scheme that puts the...routing This simple case study highlights the following crucial observation: optimal traffic scheduling in energy constrained networks requires future

A hybrid optic-fiber sensor network with the function of self-diagnosis and self-healing

NASA Astrophysics Data System (ADS)

Xu, Shibo; Liu, Tiegen; Ge, Chunfeng; Chen, Cheng; Zhang, Hongxia

2014-11-01

We develop a hybrid wavelength division multiplexing optical fiber network with distributed fiber-optic sensors and quasi-distributed FBG sensor arrays which detect vibrations, temperatures and strains at the same time. The network has the ability to locate the failure sites automatically designated as self-diagnosis and make protective switching to reestablish sensing service designated as self-healing by cooperative work of software and hardware. The processes above are accomplished by master-slave processors with the help of optical and wireless telemetry signals. All the sensing and optical telemetry signals transmit in the same fiber either working fiber or backup fiber. We take wavelength 1450nm as downstream signal and wavelength 1350nm as upstream signal to control the network in normal circumstances, both signals are sent by a light emitting node of the corresponding processor. There is also a continuous laser wavelength 1310nm sent by each node and received by next node on both working and backup fibers to monitor their healthy states, but it does not carry any message like telemetry signals do. When fibers of two sensor units are completely damaged, the master processor will lose the communication with the node between the damaged ones.However we install RF module in each node to solve the possible problem. Finally, the whole network state is transmitted to host computer by master processor. Operator could know and control the network by human-machine interface if needed.

Hypercluster - Parallel processing for computational mechanics

NASA Technical Reports Server (NTRS)

Blech, Richard A.

1988-01-01

An account is given of the development status, performance capabilities and implications for further development of NASA-Lewis' testbed 'hypercluster' parallel computer network, in which multiple processors communicate through a shared memory. Processors have local as well as shared memory; the hypercluster is expanded in the same manner as the hypercube, with processor clusters replacing the normal single processor node. The NASA-Lewis machine has three nodes with a vector personality and one node with a scalar personality. Each of the vector nodes uses four board-level vector processors, while the scalar node uses four general-purpose microcomputer boards.

Adaptive pattern recognition by mini-max neural networks as a part of an intelligent processor

NASA Technical Reports Server (NTRS)

Szu, Harold H.

1990-01-01

In this decade and progressing into 21st Century, NASA will have missions including Space Station and the Earth related Planet Sciences. To support these missions, a high degree of sophistication in machine automation and an increasing amount of data processing throughput rate are necessary. Meeting these challenges requires intelligent machines, designed to support the necessary automations in a remote space and hazardous environment. There are two approaches to designing these intelligent machines. One of these is the knowledge-based expert system approach, namely AI. The other is a non-rule approach based on parallel and distributed computing for adaptive fault-tolerances, namely Neural or Natural Intelligence (NI). The union of AI and NI is the solution to the problem stated above. The NI segment of this unit extracts features automatically by applying Cauchy simulated annealing to a mini-max cost energy function. The feature discovered by NI can then be passed to the AI system for future processing, and vice versa. This passing increases reliability, for AI can follow the NI formulated algorithm exactly, and can provide the context knowledge base as the constraints of neurocomputing. The mini-max cost function that solves the unknown feature can furthermore give us a top-down architectural design of neural networks by means of Taylor series expansion of the cost function. A typical mini-max cost function consists of the sample variance of each class in the numerator, and separation of the center of each class in the denominator. Thus, when the total cost energy is minimized, the conflicting goals of intraclass clustering and interclass segregation are achieved simultaneously.

Multiple core computer processor with globally-accessible local memories

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

Shalf, John; Donofrio, David; Oliker, Leonid

A multi-core computer processor including a plurality of processor cores interconnected in a Network-on-Chip (NoC) architecture, a plurality of caches, each of the plurality of caches being associated with one and only one of the plurality of processor cores, and a plurality of memories, each of the plurality of memories being associated with a different set of at least one of the plurality of processor cores and each of the plurality of memories being configured to be visible in a global memory address space such that the plurality of memories are visible to two or more of the plurality ofmore » processor cores.« less

Performance evaluation of throughput computing workloads using multi-core processors and graphics processors

NASA Astrophysics Data System (ADS)

Dave, Gaurav P.; Sureshkumar, N.; Blessy Trencia Lincy, S. S.

2017-11-01

Current trend in processor manufacturing focuses on multi-core architectures rather than increasing the clock speed for performance improvement. Graphic processors have become as commodity hardware for providing fast co-processing in computer systems. Developments in IoT, social networking web applications, big data created huge demand for data processing activities and such kind of throughput intensive applications inherently contains data level parallelism which is more suited for SIMD architecture based GPU. This paper reviews the architectural aspects of multi/many core processors and graphics processors. Different case studies are taken to compare performance of throughput computing applications using shared memory programming in OpenMP and CUDA API based programming.

Parallel ALLSPD-3D: Speeding Up Combustor Analysis Via Parallel Processing

NASA Technical Reports Server (NTRS)

Fricker, David M.

1997-01-01

The ALLSPD-3D Computational Fluid Dynamics code for reacting flow simulation was run on a set of benchmark test cases to determine its parallel efficiency. These test cases included non-reacting and reacting flow simulations with varying numbers of processors. Also, the tests explored the effects of scaling the simulation with the number of processors in addition to distributing a constant size problem over an increasing number of processors. The test cases were run on a cluster of IBM RS/6000 Model 590 workstations with ethernet and ATM networking plus a shared memory SGI Power Challenge L workstation. The results indicate that the network capabilities significantly influence the parallel efficiency, i.e., a shared memory machine is fastest and ATM networking provides acceptable performance. The limitations of ethernet greatly hamper the rapid calculation of flows using ALLSPD-3D.

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

NASA Astrophysics Data System (ADS)

Liu, Xing-fa; Cen, Ming

2007-12-01

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

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

PubMed

Liu, Qingshan; Cao, Jinde; Chen, Guanrong

2010-11-01

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

Modular, Hierarchical Learning By Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Baldi, Pierre F.; Toomarian, Nikzad

1996-01-01

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

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

NASA Astrophysics Data System (ADS)

Wu, Wei; Cui, Bao-Tong

2007-07-01

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

Rapid geodesic mapping of brain functional connectivity: implementation of a dedicated co-processor in a field-programmable gate array (FPGA) and application to resting state functional MRI.

PubMed

Minati, Ludovico; Cercignani, Mara; Chan, Dennis

2013-10-01

Graph theory-based analyses of brain network topology can be used to model the spatiotemporal correlations in neural activity detected through fMRI, and such approaches have wide-ranging potential, from detection of alterations in preclinical Alzheimer's disease through to command identification in brain-machine interfaces. However, due to prohibitive computational costs, graph-based analyses to date have principally focused on measuring connection density rather than mapping the topological architecture in full by exhaustive shortest-path determination. This paper outlines a solution to this problem through parallel implementation of Dijkstra's algorithm in programmable logic. The processor design is optimized for large, sparse graphs and provided in full as synthesizable VHDL code. An acceleration factor between 15 and 18 is obtained on a representative resting-state fMRI dataset, and maps of Euclidean path length reveal the anticipated heterogeneous cortical involvement in long-range integrative processing. These results enable high-resolution geodesic connectivity mapping for resting-state fMRI in patient populations and real-time geodesic mapping to support identification of imagined actions for fMRI-based brain-machine interfaces. Copyright © 2013 IPEM. Published by Elsevier Ltd. All rights reserved.

Intelligent systems technology infrastructure for integrated systems

NASA Technical Reports Server (NTRS)

Lum, Henry, Jr.

1991-01-01

Significant advances have occurred during the last decade in intelligent systems technologies (a.k.a. knowledge-based systems, KBS) including research, feasibility demonstrations, and technology implementations in operational environments. Evaluation and simulation data obtained to date in real-time operational environments suggest that cost-effective utilization of intelligent systems technologies can be realized for Automated Rendezvous and Capture applications. The successful implementation of these technologies involve a complex system infrastructure integrating the requirements of transportation, vehicle checkout and health management, and communication systems without compromise to systems reliability and performance. The resources that must be invoked to accomplish these tasks include remote ground operations and control, built-in system fault management and control, and intelligent robotics. To ensure long-term evolution and integration of new validated technologies over the lifetime of the vehicle, system interfaces must also be addressed and integrated into the overall system interface requirements. An approach for defining and evaluating the system infrastructures including the testbed currently being used to support the on-going evaluations for the evolutionary Space Station Freedom Data Management System is presented and discussed. Intelligent system technologies discussed include artificial intelligence (real-time replanning and scheduling), high performance computational elements (parallel processors, photonic processors, and neural networks), real-time fault management and control, and system software development tools for rapid prototyping capabilities.

The neural network to determine the mechanical properties of the steels

NASA Astrophysics Data System (ADS)

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

2018-04-01

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

The role of neuroimaging in the discovery of processing stages. A review.

PubMed

Mulder, G; Wijers, A A; Lange, J J; Buijink, B M; Mulder, L J; Willemsen, A T; Paans, A M

1995-11-01

In this contribution we show how neuroimaging methods can augment behavioural methods to discover processing stages. Event Related Brain Potentials (ERPs), Brain Electrical Source Analysis (BESA) and regional changes in cerebral blood flow (rCBF) do not necessarily require behavioural responses. With the aid of rCBF we are able to discover several cortical and subcortical brain systems (processors) active in selective attention and memory search tasks. BESA describes cortical activity with high temporal resolution in terms of a limited number of neural generators within these brain systems. The combination of behavioural methods and neuroimaging provides a picture of the functional architecture of the brain. The review is organized around three processors: the Visual, Cognitive and Manual Motor Processors.

Accelerating artificial intelligence with reconfigurable computing

NASA Astrophysics Data System (ADS)

Cieszewski, Radoslaw

Reconfigurable computing is emerging as an important area of research in computer architectures and software systems. Many algorithms can be greatly accelerated by placing the computationally intense portions of an algorithm into reconfigurable hardware. Reconfigurable computing combines many benefits of both software and ASIC implementations. Like software, the mapped circuit is flexible, and can be changed over the lifetime of the system. Similar to an ASIC, reconfigurable systems provide a method to map circuits into hardware. Reconfigurable systems therefore have the potential to achieve far greater performance than software as a result of bypassing the fetch-decode-execute operations of traditional processors, and possibly exploiting a greater level of parallelism. Such a field, where there is many different algorithms which can be accelerated, is an artificial intelligence. This paper presents example hardware implementations of Artificial Neural Networks, Genetic Algorithms and Expert Systems.

Communication System and Method

NASA Technical Reports Server (NTRS)

Sanders, Adam M. (Inventor); Strawser, Philip A. (Inventor)

2014-01-01

A communication system for communicating over high-latency, low bandwidth networks includes a communications processor configured to receive a collection of data from a local system, and a transceiver in communication with the communications processor. The transceiver is configured to transmit and receive data over a network according to a plurality of communication parameters. The communications processor is configured to divide the collection of data into a plurality of data streams; assign a priority level to each of the respective data streams, where the priority level reflects the criticality of the respective data stream; and modify a communication parameter of at least one of the plurality of data streams according to the priority of the at least one data stream.

Picoradio: Communication/Computation Piconodes for Sensor Networks

DTIC Science & Technology

2003-01-02

diagram of PicoNode III, or Quark node. It is made from two custom chips, Strange RF and Charm digital processor , and is complemented by a set of...the chipset comprising of Strange (analog OOK transceiver) and Charm (digital processor ) chips. 44 Figure 33: System block diagram of the Quark node...19 2.B PICONODE II - TWO-CHIP PICONODE IMPLEMENTATION ......................................... 21 2.B.1 Baseband processor (BBP

A high performance linear equation solver on the VPP500 parallel supercomputer

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

Nakanishi, Makoto; Ina, Hiroshi; Miura, Kenichi

1994-12-31

This paper describes the implementation of two high performance linear equation solvers developed for the Fujitsu VPP500, a distributed memory parallel supercomputer system. The solvers take advantage of the key architectural features of VPP500--(1) scalability for an arbitrary number of processors up to 222 processors, (2) flexible data transfer among processors provided by a crossbar interconnection network, (3) vector processing capability on each processor, and (4) overlapped computation and transfer. The general linear equation solver based on the blocked LU decomposition method achieves 120.0 GFLOPS performance with 100 processors in the LIN-PACK Highly Parallel Computing benchmark.

Multi-mode sensor processing on a dynamically reconfigurable massively parallel processor array

NASA Astrophysics Data System (ADS)

Chen, Paul; Butts, Mike; Budlong, Brad; Wasson, Paul

2008-04-01

This paper introduces a novel computing architecture that can be reconfigured in real time to adapt on demand to multi-mode sensor platforms' dynamic computational and functional requirements. This 1 teraOPS reconfigurable Massively Parallel Processor Array (MPPA) has 336 32-bit processors. The programmable 32-bit communication fabric provides streamlined inter-processor connections with deterministically high performance. Software programmability, scalability, ease of use, and fast reconfiguration time (ranging from microseconds to milliseconds) are the most significant advantages over FPGAs and DSPs. This paper introduces the MPPA architecture, its programming model, and methods of reconfigurability. An MPPA platform for reconfigurable computing is based on a structural object programming model. Objects are software programs running concurrently on hundreds of 32-bit RISC processors and memories. They exchange data and control through a network of self-synchronizing channels. A common application design pattern on this platform, called a work farm, is a parallel set of worker objects, with one input and one output stream. Statically configured work farms with homogeneous and heterogeneous sets of workers have been used in video compression and decompression, network processing, and graphics applications.

Eliminating livelock by assigning the same priority state to each message that is input into a flushable routing system during N time intervals

DOEpatents

Faber, V.

1994-11-29

Livelock-free message routing is provided in a network of interconnected nodes that is flushable in time T. An input message processor generates sequences of at least N time intervals, each of duration T. An input register provides for receiving and holding each input message, where the message is assigned a priority state p during an nth one of the N time intervals. At each of the network nodes a message processor reads the assigned priority state and awards priority to messages with priority state (p-1) during an nth time interval and to messages with priority state p during an (n+1) th time interval. The messages that are awarded priority are output on an output path toward the addressed output message processor. Thus, no message remains in the network for a time longer than T. 4 figures.

Eliminating livelock by assigning the same priority state to each message that is inputted into a flushable routing system during N time intervals

DOEpatents

Faber, Vance

1994-01-01

Livelock-free message routing is provided in a network of interconnected nodes that is flushable in time T. An input message processor generates sequences of at least N time intervals, each of duration T. An input register provides for receiving and holding each input message, where the message is assigned a priority state p during an nth one of the N time intervals. At each of the network nodes a message processor reads the assigned priority state and awards priority to messages with priority state (p-1) during an nth time interval and to messages with priority state p during an (n+1) th time interval. The messages that are awarded priority are output on an output path toward the addressed output message processor. Thus, no message remains in the network for a time longer than T.

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

PubMed

Bao, Gang; Zeng, Zhigang; Shen, Yanjun

2018-02-01

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

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

PubMed

Liang, X B; Wang, J

2000-01-01

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

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

USGS Publications Warehouse

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

1997-01-01

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

Meeting the memory challenges of brain-scale network simulation.

PubMed

Kunkel, Susanne; Potjans, Tobias C; Eppler, Jochen M; Plesser, Hans Ekkehard; Morrison, Abigail; Diesmann, Markus

2011-01-01

The development of high-performance simulation software is crucial for studying the brain connectome. Using connectome data to generate neurocomputational models requires software capable of coping with models on a variety of scales: from the microscale, investigating plasticity, and dynamics of circuits in local networks, to the macroscale, investigating the interactions between distinct brain regions. Prior to any serious dynamical investigation, the first task of network simulations is to check the consistency of data integrated in the connectome and constrain ranges for yet unknown parameters. Thanks to distributed computing techniques, it is possible today to routinely simulate local cortical networks of around 10(5) neurons with up to 10(9) synapses on clusters and multi-processor shared-memory machines. However, brain-scale networks are orders of magnitude larger than such local networks, in terms of numbers of neurons and synapses as well as in terms of computational load. Such networks have been investigated in individual studies, but the underlying simulation technologies have neither been described in sufficient detail to be reproducible nor made publicly available. Here, we discover that as the network model sizes approach the regime of meso- and macroscale simulations, memory consumption on individual compute nodes becomes a critical bottleneck. This is especially relevant on modern supercomputers such as the Blue Gene/P architecture where the available working memory per CPU core is rather limited. We develop a simple linear model to analyze the memory consumption of the constituent components of neuronal simulators as a function of network size and the number of cores used. This approach has multiple benefits. The model enables identification of key contributing components to memory saturation and prediction of the effects of potential improvements to code before any implementation takes place. As a consequence, development cycles can be shorter and less expensive. Applying the model to our freely available Neural Simulation Tool (NEST), we identify the software components dominant at different scales, and develop general strategies for reducing the memory consumption, in particular by using data structures that exploit the sparseness of the local representation of the network. We show that these adaptations enable our simulation software to scale up to the order of 10,000 processors and beyond. As memory consumption issues are likely to be relevant for any software dealing with complex connectome data on such architectures, our approach and our findings should be useful for researchers developing novel neuroinformatics solutions to the challenges posed by the connectome project.

An Introduction to Neural Networks for Hearing Aid Noise Recognition.

ERIC Educational Resources Information Center

Kim, Jun W.; Tyler, Richard S.

1995-01-01

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

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

PubMed

Wan, Ying; Cao, Jinde; Wen, Guanghui

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

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

NASA Astrophysics Data System (ADS)

Sengupta, A.; Ranjan, P.

2002-07-01

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

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

PubMed

Jeng, J T; Lee, T T

2000-01-01

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

Training Software in Artificial-Intelligence Computing Techniques

NASA Technical Reports Server (NTRS)

Howard, Ayanna; Rogstad, Eric; Chalfant, Eugene

2005-01-01

The Artificial Intelligence (AI) Toolkit is a computer program for training scientists, engineers, and university students in three soft-computing techniques (fuzzy logic, neural networks, and genetic algorithms) used in artificial-intelligence applications. The program promotes an easily understandable tutorial interface, including an interactive graphical component through which the user can gain hands-on experience in soft-computing techniques applied to realistic example problems. The tutorial provides step-by-step instructions on the workings of soft-computing technology, whereas the hands-on examples allow interaction and reinforcement of the techniques explained throughout the tutorial. In the fuzzy-logic example, a user can interact with a robot and an obstacle course to verify how fuzzy logic is used to command a rover traverse from an arbitrary start to the goal location. For the genetic algorithm example, the problem is to determine the minimum-length path for visiting a user-chosen set of planets in the solar system. For the neural-network example, the problem is to decide, on the basis of input data on physical characteristics, whether a person is a man, woman, or child. The AI Toolkit is compatible with the Windows 95,98, ME, NT 4.0, 2000, and XP operating systems. A computer having a processor speed of at least 300 MHz, and random-access memory of at least 56MB is recommended for optimal performance. The program can be run on a slower computer having less memory, but some functions may not be executed properly.

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

PubMed

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

2017-07-20

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

Experimental system for computer network via satellite /CS/. III - Network control processor

NASA Astrophysics Data System (ADS)

Kakinuma, Y.; Ito, A.; Takahashi, H.; Uchida, K.; Matsumoto, K.; Mitsudome, H.

1982-03-01

A network control processor (NCP) has the functions of generating traffics, the control of links and the control of transmitting bursts. The NCP executes protocols, monitors of experiments, gathering and compiling data of measurements, of which programs are loaded on a minicomputer (MELCOM 70/40) with 512KB of memories. The NCP acts as traffic generators, instead of a host computer, in the experiment. For this purpose, 15 fake stations are realized by the software in each user station. This paper describes the configuration of the NCP and the implementation of the protocols for the experimental system.

A network control concept for the 30/20 GHz communication system baseband processor

NASA Technical Reports Server (NTRS)

Sabourin, D. J.; Hay, R. E.

1982-01-01

The architecture and system design for a satellite-switched TDMA communication system employing on-board processing was developed by Motorola for NASA's Lewis Research Center. The system design is based on distributed processing techniques that provide extreme flexibility in the selection of a network control protocol without impacting the satellite or ground terminal hardware. A network control concept that includes system synchronization and allows burst synchronization to occur within the system operational requirement is described. This concept integrates the tracking and control links with the communication links via the baseband processor, resulting in an autonomous system operational approach.

The Event Based Language and Its Multiple Processor Implementations.

DTIC Science & Technology

1980-01-01

10 6.1 "Recursive" Linear Fibonacci ................................................ 105 6.2 The Readers Writers Problem...kinds. Examples of such systems are: C.mmp [Wu-72], Pluribus [He-73], Data Flow [ De -75], the boolean n-cube parallel machine [Su-77], and the MuNet [Wa...concurrency within programs; therefore, we hate concentrated on two types of systems which seem suitable: a processor network, and a data flow processor [ De -77

PyNEST: A Convenient Interface to the NEST Simulator.

PubMed

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

2008-01-01

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

PyNEST: A Convenient Interface to the NEST Simulator

PubMed Central

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

2008-01-01

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

High precision computing with charge domain devices and a pseudo-spectral method therefor

NASA Technical Reports Server (NTRS)

Barhen, Jacob (Inventor); Toomarian, Nikzad (Inventor); Fijany, Amir (Inventor); Zak, Michail (Inventor)

1997-01-01

The present invention enhances the bit resolution of a CCD/CID MVM processor by storing each bit of each matrix element as a separate CCD charge packet. The bits of each input vector are separately multiplied by each bit of each matrix element in massive parallelism and the resulting products are combined appropriately to synthesize the correct product. In another aspect of the invention, such arrays are employed in a pseudo-spectral method of the invention, in which partial differential equations are solved by expressing each derivative analytically as matrices, and the state function is updated at each computation cycle by multiplying it by the matrices. The matrices are treated as synaptic arrays of a neural network and the state function vector elements are treated as neurons. In a further aspect of the invention, moving target detection is performed by driving the soliton equation with a vector of detector outputs. The neural architecture consists of two synaptic arrays corresponding to the two differential terms of the soliton-equation and an adder connected to the output thereof and to the output of the detector array to drive the soliton equation.

Nested Neural Networks

NASA Technical Reports Server (NTRS)

Baram, Yoram

1992-01-01

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

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

PubMed

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

2018-06-19

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

Quantum neural networks: Current status and prospects for development

NASA Astrophysics Data System (ADS)

Altaisky, M. V.; Kaputkina, N. E.; Krylov, V. A.

2014-11-01

The idea of quantum artificial neural networks, first formulated in [34], unites the artificial neural network concept with the quantum computation paradigm. Quantum artificial neural networks were first systematically considered in the PhD thesis by T. Menneer (1998). Based on the works of Menneer and Narayanan [42, 43], Kouda, Matsui, and Nishimura [35, 36], Altaisky [2, 68], Zhou [67], and others, quantum-inspired learning algorithms for neural networks were developed, and are now used in various training programs and computer games [29, 30]. The first practically realizable scaled hardware-implemented model of the quantum artificial neural network is obtained by D-Wave Systems, Inc. [33]. It is a quantum Hopfield network implemented on the basis of superconducting quantum interference devices (SQUIDs). In this work we analyze possibilities and underlying principles of an alternative way to implement quantum neural networks on the basis of quantum dots. A possibility of using quantum neural network algorithms in automated control systems, associative memory devices, and in modeling biological and social networks is examined.

Neural simulations on multi-core architectures.

PubMed

Eichner, Hubert; Klug, Tobias; Borst, Alexander

2009-01-01

Neuroscience is witnessing increasing knowledge about the anatomy and electrophysiological properties of neurons and their connectivity, leading to an ever increasing computational complexity of neural simulations. At the same time, a rather radical change in personal computer technology emerges with the establishment of multi-cores: high-density, explicitly parallel processor architectures for both high performance as well as standard desktop computers. This work introduces strategies for the parallelization of biophysically realistic neural simulations based on the compartmental modeling technique and results of such an implementation, with a strong focus on multi-core architectures and automation, i.e. user-transparent load balancing.

Neural Simulations on Multi-Core Architectures

PubMed Central

Eichner, Hubert; Klug, Tobias; Borst, Alexander

2009-01-01

Neuroscience is witnessing increasing knowledge about the anatomy and electrophysiological properties of neurons and their connectivity, leading to an ever increasing computational complexity of neural simulations. At the same time, a rather radical change in personal computer technology emerges with the establishment of multi-cores: high-density, explicitly parallel processor architectures for both high performance as well as standard desktop computers. This work introduces strategies for the parallelization of biophysically realistic neural simulations based on the compartmental modeling technique and results of such an implementation, with a strong focus on multi-core architectures and automation, i.e. user-transparent load balancing. PMID:19636393

Neural network approaches to capture temporal information

NASA Astrophysics Data System (ADS)

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

2000-05-01

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

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

PubMed

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

2016-11-01

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

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

PubMed

Zhang, Junfeng; Zhao, Xudong; Huang, Jun

2016-11-01

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

The Laplacian spectrum of neural networks

PubMed Central

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

2014-01-01

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

Queueing models for token and slotted ring networks. Thesis

NASA Technical Reports Server (NTRS)

Peden, Jeffery H.

1990-01-01

Currently the end-to-end delay characteristics of very high speed local area networks are not well understood. The transmission speed of computer networks is increasing, and local area networks especially are finding increasing use in real time systems. Ring networks operation is generally well understood for both token rings and slotted rings. There is, however, a severe lack of queueing models for high layer operation. There are several factors which contribute to the processing delay of a packet, as opposed to the transmission delay, e.g., packet priority, its length, the user load, the processor load, the use of priority preemption, the use of preemption at packet reception, the number of processors, the number of protocol processing layers, the speed of each processor, and queue length limitations. Currently existing medium access queueing models are extended by adding modeling techniques which will handle exhaustive limited service both with and without priority traffic, and modeling capabilities are extended into the upper layers of the OSI model. Some of the model are parameterized solution methods, since it is shown that certain models do not exist as parameterized solutions, but rather as solution methods.

Passive IFF: Autonomous Nonintrusive Rapid Identification of Friendly Assets

NASA Technical Reports Server (NTRS)

Moynihan, Philip; Steenburg, Robert Van; Chao, Tien-Hsin

2004-01-01

A proposed optoelectronic instrument would identify targets rapidly, without need to radiate an interrogating signal, apply identifying marks to the targets, or equip the targets with transponders. The instrument was conceived as an identification, friend or foe (IFF) system in a battlefield setting, where it would be part of a targeting system for weapons, by providing rapid identification for aimed weapons to help in deciding whether and when to trigger them. The instrument could also be adapted to law-enforcement and industrial applications in which it is necessary to rapidly identify objects in view. The instrument would comprise mainly an optical correlator and a neural processor (see figure). The inherent parallel-processing speed and capability of the optical correlator would be exploited to obtain rapid identification of a set of probable targets within a scene of interest and to define regions within the scene for the neural processor to analyze. The neural processor would then concentrate on each region selected by the optical correlator in an effort to identify the target. Depending on whether or not a target was recognized by comparison of its image data with data in an internal database on which the neural processor was trained, the processor would generate an identifying signal (typically, friend or foe ). The time taken for this identification process would be less than the time needed by a human or robotic gunner to acquire a view of, and aim at, a target. An optical correlator that has been under development for several years and that has been demonstrated to be capable of tracking a cruise missile might be considered a prototype of the optical correlator in the proposed IFF instrument. This optical correlator features a 512-by-512-pixel input image frame and operates at an input frame rate of 60 Hz. It includes a spatial light modulator (SLM) for video-to-optical image conversion, a pair of precise lenses to effect Fourier transforms, a filter SLM for digital-to-optical correlation-filter data conversion, and a charge-coupled device (CCD) for detection of correlation peaks. In operation, the input scene grabbed by a video sensor is streamed into the input SLM. Precomputed correlation-filter data files representative of known targets are then downloaded and sequenced into the filter SLM at a rate of 1,000 Hz. When there occurs a match between the input target data and one of the known-target data files, the CCD detects a correlation peak at the location of the target. Distortion- invariant correlation filters from a bank of such filters are then sequenced through the optical correlator for each input frame. The net result is the rapid preliminary recognition of one or a few targets.

Introduction to Neural Networks.

DTIC Science & Technology

1992-03-01

parallel processing of information that can greatly reduce the time required to perform operations which are needed in pattern recognition. Neural network, Artificial neural network , Neural net, ANN.

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

NASA Technical Reports Server (NTRS)

Hayashi, Isao; Nomura, Hiroyoshi; Wakami, Noboru

1991-01-01

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

Fault-tolerant battery system employing intra-battery network architecture

DOEpatents

Hagen, Ronald A.; Chen, Kenneth W.; Comte, Christophe; Knudson, Orlin B.; Rouillard, Jean

2000-01-01

A distributed energy storing system employing a communications network is disclosed. A distributed battery system includes a number of energy storing modules, each of which includes a processor and communications interface. In a network mode of operation, a battery computer communicates with each of the module processors over an intra-battery network and cooperates with individual module processors to coordinate module monitoring and control operations. The battery computer monitors a number of battery and module conditions, including the potential and current state of the battery and individual modules, and the conditions of the battery's thermal management system. An over-discharge protection system, equalization adjustment system, and communications system are also controlled by the battery computer. The battery computer logs and reports various status data on battery level conditions which may be reported to a separate system platform computer. A module transitions to a stand-alone mode of operation if the module detects an absence of communication connectivity with the battery computer. A module which operates in a stand-alone mode performs various monitoring and control functions locally within the module to ensure safe and continued operation.

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

PubMed Central

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

2003-01-01

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

Medical image analysis with artificial neural networks.

PubMed

Jiang, J; Trundle, P; Ren, J

2010-12-01

Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing, with the aims of increasing awareness of how neural networks can be applied to these areas and to provide a foundation for further research and practical development. Representative techniques and algorithms are explained in detail to provide inspiring examples illustrating: (i) how a known neural network with fixed structure and training procedure could be applied to resolve a medical imaging problem; (ii) how medical images could be analysed, processed, and characterised by neural networks; and (iii) how neural networks could be expanded further to resolve problems relevant to medical imaging. In the concluding section, a highlight of comparisons among many neural network applications is included to provide a global view on computational intelligence with neural networks in medical imaging. Copyright © 2010 Elsevier Ltd. All rights reserved.

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

NASA Technical Reports Server (NTRS)

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

1993-01-01

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

Tactical Operations Analysis Support Facility.

DTIC Science & Technology

1981-05-01

Punch/Reader 2 DMC-11AR DDCMP Micro Processor 2 DMC-11DA Network Link Line Unit 2 DL-11E Async Serial Line Interface 4 Intel IN-1670 448K Words MOS Memory...86 5.3 VIRTUAL PROCESSORS - VAX-11/750 ........................... 89 5.4 A RELATIONAL DATA MANAGEMENT SYSTEM - ORACLE...Central Processing Unit (CPU) is a 16 bit processor for high-speed, real time applications, and for large multi-user, multi- task, time shared

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

PubMed

Nitta, Tohru

2017-10-01

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

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

PubMed

Gafarov, F M; Gafarova, V R

2016-09-01

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

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

NASA Astrophysics Data System (ADS)

Kapageridis, Ioannis Konstantinou; Triantafyllou, A. G.

2011-04-01

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

Network control processor for a TDMA system

NASA Astrophysics Data System (ADS)

Suryadevara, Omkarmurthy; Debettencourt, Thomas J.; Shulman, R. B.

Two unique aspects of designing a network control processor (NCP) to monitor and control a demand-assigned, time-division multiple-access (TDMA) network are described. The first involves the implementation of redundancy by synchronizing the databases of two geographically remote NCPs. The two sets of databases are kept in synchronization by collecting data on both systems, transferring databases, sending incremental updates, and the parallel updating of databases. A periodic audit compares the checksums of the databases to ensure synchronization. The second aspect involves the use of a tracking algorithm to dynamically reallocate TDMA frame space. This algorithm detects and tracks current and long-term load changes in the network. When some portions of the network are overloaded while others have excess capacity, the algorithm automatically calculates and implements a new burst time plan.

Creative-Dynamics Approach To Neural Intelligence

NASA Technical Reports Server (NTRS)

Zak, Michail A.

1992-01-01

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

Self-powered information measuring wireless networks using the distribution of tasks within multicore processors

NASA Astrophysics Data System (ADS)

Zhuravska, Iryna M.; Koretska, Oleksandra O.; Musiyenko, Maksym P.; Surtel, Wojciech; Assembay, Azat; Kovalev, Vladimir; Tleshova, Akmaral

2017-08-01

The article contains basic approaches to develop the self-powered information measuring wireless networks (SPIM-WN) using the distribution of tasks within multicore processors critical applying based on the interaction of movable components - as in the direction of data transmission as wireless transfer of energy coming from polymetric sensors. Base mathematic model of scheduling tasks within multiprocessor systems was modernized to schedule and allocate tasks between cores of one-crystal computer (SoC) to increase energy efficiency SPIM-WN objects.

The Brain's Router: A Cortical Network Model of Serial Processing in the Primate Brain

PubMed Central

Zylberberg, Ariel; Fernández Slezak, Diego; Roelfsema, Pieter R.; Dehaene, Stanislas; Sigman, Mariano

2010-01-01

The human brain efficiently solves certain operations such as object recognition and categorization through a massively parallel network of dedicated processors. However, human cognition also relies on the ability to perform an arbitrarily large set of tasks by flexibly recombining different processors into a novel chain. This flexibility comes at the cost of a severe slowing down and a seriality of operations (100–500 ms per step). A limit on parallel processing is demonstrated in experimental setups such as the psychological refractory period (PRP) and the attentional blink (AB) in which the processing of an element either significantly delays (PRP) or impedes conscious access (AB) of a second, rapidly presented element. Here we present a spiking-neuron implementation of a cognitive architecture where a large number of local parallel processors assemble together to produce goal-driven behavior. The precise mapping of incoming sensory stimuli onto motor representations relies on a “router” network capable of flexibly interconnecting processors and rapidly changing its configuration from one task to another. Simulations show that, when presented with dual-task stimuli, the network exhibits parallel processing at peripheral sensory levels, a memory buffer capable of keeping the result of sensory processing on hold, and a slow serial performance at the router stage, resulting in a performance bottleneck. The network captures the detailed dynamics of human behavior during dual-task-performance, including both mean RTs and RT distributions, and establishes concrete predictions on neuronal dynamics during dual-task experiments in humans and non-human primates. PMID:20442869

An Attractor-Based Complexity Measurement for Boolean Recurrent Neural Networks

PubMed Central

Cabessa, Jérémie; Villa, Alessandro E. P.

2014-01-01

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

How Neural Networks Learn from Experience.

ERIC Educational Resources Information Center

Hinton, Geoffrey E.

1992-01-01

Discusses computational studies of learning in artificial neural networks and findings that may provide insights into the learning abilities of the human brain. Describes efforts to test theories about brain information processing, using artificial neural networks. Vignettes include information concerning how a neural network represents…

Neural network to diagnose lining condition

NASA Astrophysics Data System (ADS)

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

2018-03-01

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

[Measurement and performance analysis of functional neural network].

PubMed

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

2018-04-01

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

Far-infrared and 3D imaging for doneness assessment in chicken breast

NASA Astrophysics Data System (ADS)

Tao, Yang; Ibarra, Juan G.

2001-03-01

Sensor fusion of infrared imaging and range imaging was proposed to estimate internal temperature on just cooked chicken breasts. An infrared camera operating at 8-12 microns registered surface temperature of cooked meat samples, while a single line structured light system located the thickest region of the meat target. In this region of interest, a combined time series/neural network method is applied to correlate the internal and external temperatures during the cool-down process. Experimental verification in a pilot plant oven is presented. To ensure food safety, a mandatory regulation requires all poultry processors in the U.S.A to verify that all ready-to-eat products reach a minimum endpoint temperature (71¦C for chicken breast), but no current assay can do a non-invasively inspection of all the samples. The proposed system has the potential for on-line inspection of ready-to-eat meat for food quality and safety.

Advances in image compression and automatic target recognition; Proceedings of the Meeting, Orlando, FL, Mar. 30, 31, 1989

NASA Technical Reports Server (NTRS)

Tescher, Andrew G. (Editor)

1989-01-01

Various papers on image compression and automatic target recognition are presented. Individual topics addressed include: target cluster detection in cluttered SAR imagery, model-based target recognition using laser radar imagery, Smart Sensor front-end processor for feature extraction of images, object attitude estimation and tracking from a single video sensor, symmetry detection in human vision, analysis of high resolution aerial images for object detection, obscured object recognition for an ATR application, neural networks for adaptive shape tracking, statistical mechanics and pattern recognition, detection of cylinders in aerial range images, moving object tracking using local windows, new transform method for image data compression, quad-tree product vector quantization of images, predictive trellis encoding of imagery, reduced generalized chain code for contour description, compact architecture for a real-time vision system, use of human visibility functions in segmentation coding, color texture analysis and synthesis using Gibbs random fields.

Neural network error correction for solving coupled ordinary differential equations

NASA Technical Reports Server (NTRS)

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

1992-01-01

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

Model Of Neural Network With Creative Dynamics

NASA Technical Reports Server (NTRS)

Zak, Michail; Barhen, Jacob

1993-01-01

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

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

PubMed

Xia, Youshen; Wang, Jun

2015-07-01

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

Thermalnet: a Deep Convolutional Network for Synthetic Thermal Image Generation

NASA Astrophysics Data System (ADS)

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

2017-05-01

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

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

NASA Astrophysics Data System (ADS)

Chang, Hsien-Cheng

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

A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses.

PubMed

Qiao, Ning; Mostafa, Hesham; Corradi, Federico; Osswald, Marc; Stefanini, Fabio; Sumislawska, Dora; Indiveri, Giacomo

2015-01-01

Implementing compact, low-power artificial neural processing systems with real-time on-line learning abilities is still an open challenge. In this paper we present a full-custom mixed-signal VLSI device with neuromorphic learning circuits that emulate the biophysics of real spiking neurons and dynamic synapses for exploring the properties of computational neuroscience models and for building brain-inspired computing systems. The proposed architecture allows the on-chip configuration of a wide range of network connectivities, including recurrent and deep networks, with short-term and long-term plasticity. The device comprises 128 K analog synapse and 256 neuron circuits with biologically plausible dynamics and bi-stable spike-based plasticity mechanisms that endow it with on-line learning abilities. In addition to the analog circuits, the device comprises also asynchronous digital logic circuits for setting different synapse and neuron properties as well as different network configurations. This prototype device, fabricated using a 180 nm 1P6M CMOS process, occupies an area of 51.4 mm(2), and consumes approximately 4 mW for typical experiments, for example involving attractor networks. Here we describe the details of the overall architecture and of the individual circuits and present experimental results that showcase its potential. By supporting a wide range of cortical-like computational modules comprising plasticity mechanisms, this device will enable the realization of intelligent autonomous systems with on-line learning capabilities.

Reducing neural network training time with parallel processing

NASA Technical Reports Server (NTRS)

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

1995-01-01

Obtaining optimal solutions for engineering design problems is often expensive because the process typically requires numerous iterations involving analysis and optimization programs. Previous research has shown that a near optimum solution can be obtained in less time by simulating a slow, expensive analysis with a fast, inexpensive neural network. A new approach has been developed to further reduce this time. This approach decomposes a large neural network into many smaller neural networks that can be trained in parallel. Guidelines are developed to avoid some of the pitfalls when training smaller neural networks in parallel. These guidelines allow the engineer: to determine the number of nodes on the hidden layer of the smaller neural networks; to choose the initial training weights; and to select a network configuration that will capture the interactions among the smaller neural networks. This paper presents results describing how these guidelines are developed.

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

PubMed

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

1992-01-01

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

Underwater Threat Source Localization: Processing Sensor Network TDOAs with a Terascale Optical Core Device

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

Barhen, Jacob; Imam, Neena

2007-01-01

Revolutionary computing technologies are defined in terms of technological breakthroughs, which leapfrog over near-term projected advances in conventional hardware and software to produce paradigm shifts in computational science. For underwater threat source localization using information provided by a dynamical sensor network, one of the most promising computational advances builds upon the emergence of digital optical-core devices. In this article, we present initial results of sensor network calculations that focus on the concept of signal wavefront time-difference-of-arrival (TDOA). The corresponding algorithms are implemented on the EnLight processing platform recently introduced by Lenslet Laboratories. This tera-scale digital optical core processor is optimizedmore » for array operations, which it performs in a fixed-point-arithmetic architecture. Our results (i) illustrate the ability to reach the required accuracy in the TDOA computation, and (ii) demonstrate that a considerable speed-up can be achieved when using the EnLight 64a prototype processor as compared to a dual Intel XeonTM processor.« less

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.

Cedar-a large scale multiprocessor

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

Gajski, D.; Kuck, D.; Lawrie, D.

1983-01-01

This paper presents an overview of Cedar, a large scale multiprocessor being designed at the University of Illinois. This machine is designed to accommodate several thousand high performance processors which are capable of working together on a single job, or they can be partitioned into groups of processors where each group of one or more processors can work on separate jobs. Various aspects of the machine are described including the control methodology, communication network, optimizing compiler and plans for construction. 13 references.

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

NASA Technical Reports Server (NTRS)

Yen, John

1991-01-01

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

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

PubMed

Kwak, N K; Lee, C

1997-04-01

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

Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

NASA Astrophysics Data System (ADS)

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

2017-10-01

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

Adaptive Load-Balancing Algorithms Using Symmetric Broadcast Networks

NASA Technical Reports Server (NTRS)

Das, Sajal K.; Biswas, Rupak; Chancellor, Marisa K. (Technical Monitor)

1997-01-01

In a distributed-computing environment, it is important to ensure that the processor workloads are adequately balanced. Among numerous load-balancing algorithms, a unique approach due to Dam and Prasad defines a symmetric broadcast network (SBN) that provides a robust communication pattern among the processors in a topology-independent manner. In this paper, we propose and analyze three novel SBN-based load-balancing algorithms, and implement them on an SP2. A thorough experimental study with Poisson-distributed synthetic loads demonstrates that these algorithms are very effective in balancing system load while minimizing processor idle time. They also compare favorably with several other existing load-balancing techniques. Additional experiments performed with real data demonstrate that the SBN approach is effective in adaptive computational science and engineering applications where dynamic load balancing is extremely crucial.

Improvement of the Hopfield Neural Network by MC-Adaptation Rule

NASA Astrophysics Data System (ADS)

Zhou, Zhen; Zhao, Hong

2006-06-01

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

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

PubMed

Zhu, Zhenyu; Wang, Rubin; Zhu, Fengyun

2018-01-01

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

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

PubMed

Lin, Chuan-Kai; Wang, Sheng-De

2004-11-01

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

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

PubMed

Yang, S; Wang, D

2000-01-01

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

Financial time series prediction using spiking neural networks.

PubMed

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

2014-01-01

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

Non-Intrusive Gaze Tracking Using Artificial Neural Networks

DTIC Science & Technology

1994-01-05

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

Modulated error diffusion CGHs for neural nets

NASA Astrophysics Data System (ADS)

Vermeulen, Pieter J. E.; Casasent, David P.

1990-05-01

New modulated error diffusion CGHs (computer generated holograms) for optical computing are considered. Specific attention is given to their use in optical matrix-vector, associative processor, neural net and optical interconnection architectures. We consider lensless CGH systems (many CGHs use an external Fourier transform (FT) lens), the Fresnel sampling requirements, the effects of finite CGH apertures (sample and hold inputs), dot size correction (for laser recorders), and new applications for this novel encoding method (that devotes attention to quantization noise effects).

Neural dynamics based on the recognition of neural fingerprints

PubMed Central

Carrillo-Medina, José Luis; Latorre, Roberto

2015-01-01

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

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

PubMed

Li, Haibin; He, Yun; Nie, Xiaobo

2018-01-01

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

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

PubMed

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

2017-01-01

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

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

PubMed

Zhang, WenJun

2007-07-01

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

Simulation of continuously logical base cells (CL BC) with advanced functions for analog-to-digital converters and image processors

NASA Astrophysics Data System (ADS)

Krasilenko, Vladimir G.; Lazarev, Alexander A.; Nikitovich, Diana V.

2017-10-01

The paper considers results of design and modeling of continuously logical base cells (CL BC) based on current mirrors (CM) with functions of preliminary analogue and subsequent analogue-digital processing for creating sensor multichannel analog-to-digital converters (SMC ADCs) and image processors (IP). For such with vector or matrix parallel inputs-outputs IP and SMC ADCs it is needed active basic photosensitive cells with an extended electronic circuit, which are considered in paper. Such basic cells and ADCs based on them have a number of advantages: high speed and reliability, simplicity, small power consumption, high integration level for linear and matrix structures. We show design of the CL BC and ADC of photocurrents and their various possible implementations and its simulations. We consider CL BC for methods of selection and rank preprocessing and linear array of ADCs with conversion to binary codes and Gray codes. In contrast to our previous works here we will dwell more on analogue preprocessing schemes for signals of neighboring cells. Let us show how the introduction of simple nodes based on current mirrors extends the range of functions performed by the image processor. Each channel of the structure consists of several digital-analog cells (DC) on 15-35 CMOS. The amount of DC does not exceed the number of digits of the formed code, and for an iteration type, only one cell of DC, complemented by the device of selection and holding (SHD), is required. One channel of ADC with iteration is based on one DC-(G) and SHD, and it has only 35 CMOS transistors. In such ADCs easily parallel code can be realized and also serial-parallel output code. The circuits and simulation results of their design with OrCAD are shown. The supply voltage of the DC is 1.8÷3.3V, the range of an input photocurrent is 0.1÷24μA, the transformation time is 20÷30nS at 6-8 bit binary or Gray codes. The general power consumption of the ADC with iteration is only 50÷100μW, if the maximum input current is 4μA. Such simple structure of linear array of ADCs with low power consumption and supply voltage 3.3V, and at the same time with good dynamic characteristics (frequency of digitization even for 1.5μm CMOS-technologies is 40÷50 MHz, and can be increased up to 10 times) and accuracy characteristics are show. The SMC ADCs based on CL BC and CM opens new prospects for realization of linear and matrix IP and photo-electronic structures with matrix operands, which are necessary for neural networks, digital optoelectronic processors, neural-fuzzy controllers.

Multiprocessor and memory architecture of the neurocomputer SYNAPSE-1.

PubMed

Ramacher, U; Raab, W; Anlauf, J; Hachmann, U; Beichter, J; Brüls, N; Wesseling, M; Sicheneder, E; Männer, R; Glass, J

1993-12-01

A general purpose neurocomputer, SYNAPSE-1, which exhibits a multiprocessor and memory architecture is presented. It offers wide flexibility with respect to neural algorithms and a speed-up factor of several orders of magnitude--including learning. The computational power is provided by a 2-dimensional systolic array of neural signal processors. Since the weights are stored outside these NSPs, memory size and processing power can be adapted individually to the application needs. A neural algorithms programming language, embedded in C(+2) has been defined for the user to cope with the neurocomputer. In a benchmark test, the prototype of SYNAPSE-1 was 8000 times as fast as a standard workstation.

Accelerating Learning By Neural Networks

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad; Barhen, Jacob

1992-01-01

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

The operational cloud retrieval algorithms from TROPOMI on board Sentinel-5 Precursor

NASA Astrophysics Data System (ADS)

Loyola, Diego G.; Gimeno García, Sebastián; Lutz, Ronny; Argyrouli, Athina; Romahn, Fabian; Spurr, Robert J. D.; Pedergnana, Mattia; Doicu, Adrian; Molina García, Víctor; Schüssler, Olena

2018-01-01

This paper presents the operational cloud retrieval algorithms for the TROPOspheric Monitoring Instrument (TROPOMI) on board the European Space Agency Sentinel-5 Precursor (S5P) mission scheduled for launch in 2017. Two algorithms working in tandem are used for retrieving cloud properties: OCRA (Optical Cloud Recognition Algorithm) and ROCINN (Retrieval of Cloud Information using Neural Networks). OCRA retrieves the cloud fraction using TROPOMI measurements in the ultraviolet (UV) and visible (VIS) spectral regions, and ROCINN retrieves the cloud top height (pressure) and optical thickness (albedo) using TROPOMI measurements in and around the oxygen A-band in the near infrared (NIR). Cloud parameters from TROPOMI/S5P will be used not only for enhancing the accuracy of trace gas retrievals but also for extending the satellite data record of cloud information derived from oxygen A-band measurements, a record initiated with the Global Ozone Monitoring Experiment (GOME) on board the second European Remote-Sensing Satellite (ERS-2) over 20 years ago. The OCRA and ROCINN algorithms are integrated in the S5P operational processor UPAS (Universal Processor for UV/VIS/NIR Atmospheric Spectrometers), and we present here UPAS cloud results using the Ozone Monitoring Instrument (OMI) and GOME-2 measurements. In addition, we examine anticipated challenges for the TROPOMI/S5P cloud retrieval algorithms, and we discuss the future validation needs for OCRA and ROCINN.

Parallel asynchronous systems and image processing algorithms

NASA Technical Reports Server (NTRS)

Coon, D. D.; Perera, A. G. U.

1989-01-01

A new hardware approach to implementation of image processing algorithms is described. The approach is based on silicon devices which would permit an independent analog processing channel to be dedicated to evey pixel. A laminar architecture consisting of a stack of planar arrays of the device would form a two-dimensional array processor with a 2-D array of inputs located directly behind a focal plane detector array. A 2-D image data stream would propagate in neuronlike asynchronous pulse coded form through the laminar processor. Such systems would integrate image acquisition and image processing. Acquisition and processing would be performed concurrently as in natural vision systems. The research is aimed at implementation of algorithms, such as the intensity dependent summation algorithm and pyramid processing structures, which are motivated by the operation of natural vision systems. Implementation of natural vision algorithms would benefit from the use of neuronlike information coding and the laminar, 2-D parallel, vision system type architecture. Besides providing a neural network framework for implementation of natural vision algorithms, a 2-D parallel approach could eliminate the serial bottleneck of conventional processing systems. Conversion to serial format would occur only after raw intensity data has been substantially processed. An interesting challenge arises from the fact that the mathematical formulation of natural vision algorithms does not specify the means of implementation, so that hardware implementation poses intriguing questions involving vision science.

Thermoelastic steam turbine rotor control based on neural network

NASA Astrophysics Data System (ADS)

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

2015-12-01

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

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

NASA Technical Reports Server (NTRS)

Meade, Andrew J., Jr.

1991-01-01

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

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

NASA Astrophysics Data System (ADS)

Li, Hong; Ding, Xue

2017-03-01

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

A Low-Power High-Speed Smart Sensor Design for Space Exploration Missions

NASA Technical Reports Server (NTRS)

Fang, Wai-Chi

1997-01-01

A low-power high-speed smart sensor system based on a large format active pixel sensor (APS) integrated with a programmable neural processor for space exploration missions is presented. The concept of building an advanced smart sensing system is demonstrated by a system-level microchip design that is composed with an APS sensor, a programmable neural processor, and an embedded microprocessor in a SOI CMOS technology. This ultra-fast smart sensor system-on-a-chip design mimics what is inherent in biological vision systems. Moreover, it is programmable and capable of performing ultra-fast machine vision processing in all levels such as image acquisition, image fusion, image analysis, scene interpretation, and control functions. The system provides about one tera-operation-per-second computing power which is a two order-of-magnitude increase over that of state-of-the-art microcomputers. Its high performance is due to massively parallel computing structures, high data throughput rates, fast learning capabilities, and advanced VLSI system-on-a-chip implementation.

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

PubMed

Li, Shuai; Li, Yangming; Wang, Zheng

2013-03-01

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

Satellite image analysis using neural networks

NASA Technical Reports Server (NTRS)

Sheldon, Roger A.

1990-01-01

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

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

NASA Astrophysics Data System (ADS)

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

2018-06-01

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

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

PubMed

Liu, Qingshan; Guo, Zhishan; Wang, Jun

2012-02-01

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

System-Level Design of a 64-Channel Low Power Neural Spike Recording Sensor.

PubMed

Delgado-Restituto, Manuel; Rodriguez-Perez, Alberto; Darie, Angela; Soto-Sanchez, Cristina; Fernandez-Jover, Eduardo; Rodriguez-Vazquez, Angel

2017-04-01

This paper reports an integrated 64-channel neural spike recording sensor, together with all the circuitry to process and configure the channels, process the neural data, transmit via a wireless link the information and receive the required instructions. Neural signals are acquired, filtered, digitized and compressed in the channels. Additionally, each channel implements an auto-calibration algorithm which individually configures the transfer characteristics of the recording site. The system has two transmission modes; in one case the information captured by the channels is sent as uncompressed raw data; in the other, feature vectors extracted from the detected neural spikes are released. Data streams coming from the channels are serialized by the embedded digital processor. Experimental results, including in vivo measurements, show that the power consumption of the complete system is lower than 330 μW.

Applications of artificial neural nets in clinical biomechanics.

PubMed

Schöllhorn, W I

2004-11-01

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

Neural Networks for Rapid Design and Analysis

NASA Technical Reports Server (NTRS)

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

1998-01-01

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

Generalized Adaptive Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Tawel, Raoul

1993-01-01

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

Optimal input sizes for neural network de-interlacing

NASA Astrophysics Data System (ADS)

Choi, Hyunsoo; Seo, Guiwon; Lee, Chulhee

2009-02-01

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

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

PubMed

Huang, Chengdai; Cao, Jinde

2018-02-01

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

Coronary Artery Diagnosis Aided by Neural Network

NASA Astrophysics Data System (ADS)

Stefko, Kamil

2007-01-01

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

Predicate calculus for an architecture of multiple neural networks

NASA Astrophysics Data System (ADS)

Consoli, Robert H.

1990-08-01

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

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

NASA Astrophysics Data System (ADS)

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

2018-01-01

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

Altered Synchronizations among Neural Networks in Geriatric Depression

PubMed Central

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

2015-01-01

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

Altered Synchronizations among Neural Networks in Geriatric Depression.

PubMed

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

2015-01-01

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

System-wide power management control via clock distribution network

DOEpatents

Coteus, Paul W.; Gara, Alan; Gooding, Thomas M.; Haring, Rudolf A.; Kopcsay, Gerard V.; Liebsch, Thomas A.; Reed, Don D.

2015-05-19

An apparatus, method and computer program product for automatically controlling power dissipation of a parallel computing system that includes a plurality of processors. A computing device issues a command to the parallel computing system. A clock pulse-width modulator encodes the command in a system clock signal to be distributed to the plurality of processors. The plurality of processors in the parallel computing system receive the system clock signal including the encoded command, and adjusts power dissipation according to the encoded command.

A consensual neural network

NASA Technical Reports Server (NTRS)

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

1991-01-01

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

Neural-Network Simulator

NASA Technical Reports Server (NTRS)

Mitchell, Paul H.

1991-01-01

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

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

PubMed

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

2016-03-22

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

Neural network-based model reference adaptive control system.

PubMed

Patino, H D; Liu, D

2000-01-01

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

Space-Time Neural Networks

NASA Technical Reports Server (NTRS)

Villarreal, James A.; Shelton, Robert O.

1992-01-01

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

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

PubMed

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

2015-11-01

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

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

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

Liu, Hui; Song, Yongduan; Xue, Fangzheng

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

Financial Time Series Prediction Using Spiking Neural Networks

PubMed Central

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

2014-01-01

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

Qualitative analysis of Cohen-Grossberg neural networks with multiple delays

NASA Astrophysics Data System (ADS)

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

1995-03-01

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

Dynamic Neural Networks Supporting Memory Retrieval

PubMed Central

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

2011-01-01

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

Studies of stimulus parameters for seizure disruption using neural network simulations.

PubMed

Anderson, William S; Kudela, Pawel; Cho, Jounhong; Bergey, Gregory K; Franaszczuk, Piotr J

2007-08-01

A large scale neural network simulation with realistic cortical architecture has been undertaken to investigate the effects of external electrical stimulation on the propagation and evolution of ongoing seizure activity. This is an effort to explore the parameter space of stimulation variables to uncover promising avenues of research for this therapeutic modality. The model consists of an approximately 800 mum x 800 mum region of simulated cortex, and includes seven neuron classes organized by cortical layer, inhibitory or excitatory properties, and electrophysiological characteristics. The cell dynamics are governed by a modified version of the Hodgkin-Huxley equations in single compartment format. Axonal connections are patterned after histological data and published models of local cortical wiring. Stimulation induced action potentials take place at the axon initial segments, according to threshold requirements on the applied electric field distribution. Stimulation induced action potentials in horizontal axonal branches are also separately simulated. The calculations are performed on a 16 node distributed 32-bit processor system. Clear differences in seizure evolution are presented for stimulated versus the undisturbed rhythmic activity. Data is provided for frequency dependent stimulation effects demonstrating a plateau effect of stimulation efficacy as the applied frequency is increased from 60 to 200 Hz. Timing of the stimulation with respect to the underlying rhythmic activity demonstrates a phase dependent sensitivity. Electrode height and position effects are also presented. Using a dipole stimulation electrode arrangement, clear orientation effects of the dipole with respect to the model connectivity is also demonstrated. A sensitivity analysis of these results as a function of the stimulation threshold is also provided.

Coherence resonance in bursting neural networks

NASA Astrophysics Data System (ADS)

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

2015-10-01

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

Classification of Respiratory Sounds by Using An Artificial Neural Network

DTIC Science & Technology

2001-10-28

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

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

DTIC Science & Technology

1987-10-01

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

A neural net approach to space vehicle guidance

NASA Technical Reports Server (NTRS)

Caglayan, Alper K.; Allen, Scott M.

1990-01-01

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

Neural network and its application to CT imaging

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

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

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

Electronic neural networks for global optimization

NASA Technical Reports Server (NTRS)

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

1990-01-01

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

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

NASA Technical Reports Server (NTRS)

Harrington, Peter DEB.; Zheng, Peng

1995-01-01

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

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

NASA Astrophysics Data System (ADS)

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

2001-01-01

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

Rule extraction from minimal neural networks for credit card screening.

PubMed

Setiono, Rudy; Baesens, Bart; Mues, Christophe

2011-08-01

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

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

NASA Astrophysics Data System (ADS)

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

2018-05-01

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

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

PubMed

Soltic, Snjezana; Kasabov, Nikola

2010-12-01

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

Energy-efficient STDP-based learning circuits with memristor synapses

NASA Astrophysics Data System (ADS)

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

2014-05-01

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

Adaptive neural network motion control of manipulators with experimental evaluations.

PubMed

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

2014-01-01

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

Adaptive Neural Network Motion Control of Manipulators with Experimental Evaluations

PubMed Central

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

2014-01-01

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

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

NASA Astrophysics Data System (ADS)

QingJie, Wei; WenBin, Wang

2017-06-01

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

Assignment Of Finite Elements To Parallel Processors

NASA Technical Reports Server (NTRS)

Salama, Moktar A.; Flower, Jon W.; Otto, Steve W.

1990-01-01

Elements assigned approximately optimally to subdomains. Mapping algorithm based on simulated-annealing concept used to minimize approximate time required to perform finite-element computation on hypercube computer or other network of parallel data processors. Mapping algorithm needed when shape of domain complicated or otherwise not obvious what allocation of elements to subdomains minimizes cost of computation.

Parallel text rendering by a PostScript interpreter

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

Kritskii, S.P.; Zastavnoi, B.A.

1994-11-01

The most radical method of increasing the performance of devices controlled by PostScript interpreters may be the use of multiprocessor controllers. This paper presents a method for parallelizing the operation of a PostScript interpreter for rendering text. The proposed method is based on decomposition of the outlines of letters into horizontal strips covering equal areas. The subroutines thus obtained are distributed to the processors in a network and then filled in by conventional sequential algorithms. A special algorithm has been developed for dividing the outlines of characters into subroutines so that each may be colored independently of the others. Themore » algorithm uses special estimates for estimating the correct partition so that the corresponding outlines are divided into horizontal strips. A method is presented for finding such estimates. Two different processing approaches are presented. In the first, one of the processors performs the decomposition of the outlines and distributes the strips to the remaining processors, which are responsible for the rendering. In the second approach, the decomposition process is itself distributed among the processors 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.

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

NASA Astrophysics Data System (ADS)

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

2015-12-01

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

Neural net target-tracking system using structured laser patterns

NASA Astrophysics Data System (ADS)

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

1996-06-01

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

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

PubMed

Chen, Shyan-Shiou

2011-10-01

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

Modeling and control of magnetorheological fluid dampers using neural networks

NASA Astrophysics Data System (ADS)

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

2005-02-01

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

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

NASA Astrophysics Data System (ADS)

Mills, Kyle; Tamblyn, Isaac

2018-03-01

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

Multiscale Methods, Parallel Computation, and Neural Networks for Real-Time Computer Vision.

NASA Astrophysics Data System (ADS)

Battiti, Roberto

1990-01-01

This thesis presents new algorithms for low and intermediate level computer vision. The guiding ideas in the presented approach are those of hierarchical and adaptive processing, concurrent computation, and supervised learning. Processing of the visual data at different resolutions is used not only to reduce the amount of computation necessary to reach the fixed point, but also to produce a more accurate estimation of the desired parameters. The presented adaptive multiple scale technique is applied to the problem of motion field estimation. Different parts of the image are analyzed at a resolution that is chosen in order to minimize the error in the coefficients of the differential equations to be solved. Tests with video-acquired images show that velocity estimation is more accurate over a wide range of motion with respect to the homogeneous scheme. In some cases introduction of explicit discontinuities coupled to the continuous variables can be used to avoid propagation of visual information from areas corresponding to objects with different physical and/or kinematic properties. The human visual system uses concurrent computation in order to process the vast amount of visual data in "real -time." Although with different technological constraints, parallel computation can be used efficiently for computer vision. All the presented algorithms have been implemented on medium grain distributed memory multicomputers with a speed-up approximately proportional to the number of processors used. A simple two-dimensional domain decomposition assigns regions of the multiresolution pyramid to the different processors. The inter-processor communication needed during the solution process is proportional to the linear dimension of the assigned domain, so that efficiency is close to 100% if a large region is assigned to each processor. Finally, learning algorithms are shown to be a viable technique to engineer computer vision systems for different applications starting from multiple-purpose modules. In the last part of the thesis a well known optimization method (the Broyden-Fletcher-Goldfarb-Shanno memoryless quasi -Newton method) is applied to simple classification problems and shown to be superior to the "error back-propagation" algorithm for numerical stability, automatic selection of parameters, and convergence properties.

Tensor Basis Neural Network v. 1.0 (beta)

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

Ling, Julia; Templeton, Jeremy

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

Modeling of the ground-to-SSFMB link networking features using SPW

NASA Technical Reports Server (NTRS)

Watson, John C.

1993-01-01

This report describes the modeling and simulation of the networking features of the ground-to-Space Station Freedom manned base (SSFMB) link using COMDISCO signal processing work-system (SPW). The networking features modeled include the implementation of Consultative Committee for Space Data Systems (CCSDS) protocols in the multiplexing of digitized audio and core data into virtual channel data units (VCDU's) in the control center complex and the demultiplexing of VCDU's in the onboard baseband signal processor. The emphasis of this work has been placed on techniques for modeling the CCSDS networking features using SPW. The objectives for developing the SPW models are to test the suitability of SPW for modeling networking features and to develop SPW simulation models of the control center complex and space station baseband signal processor for use in end-to-end testing of the ground-to-SSFMB S-band single access forward (SSAF) link.

A renaissance of neural networks in drug discovery.

PubMed

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

2016-08-01

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

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

NASA Astrophysics Data System (ADS)

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

2016-12-01

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

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

PubMed

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

2016-12-01

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

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

PubMed Central

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

2016-01-01

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

Deinterlacing using modular neural network

NASA Astrophysics Data System (ADS)

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

2004-05-01

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

Pruning artificial neural networks using neural complexity measures.

PubMed

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

2008-10-01

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

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

PubMed

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

2013-09-01

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

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

PubMed

Liu, Qingshan; Wang, Jun

2011-04-01

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

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks

PubMed Central

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

2016-01-01

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

Periodicity and stability for variable-time impulsive neural networks.

PubMed

Li, Hongfei; Li, Chuandong; Huang, Tingwen

2017-10-01

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

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

NASA Technical Reports Server (NTRS)

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

1997-01-01

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

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.

PubMed

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

2016-01-01

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

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

NASA Astrophysics Data System (ADS)

Gao, Rong

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

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

NASA Technical Reports Server (NTRS)

Scott, Robert C.

2000-01-01

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

Modeling Aircraft Wing Loads from Flight Data Using Neural Networks

NASA Technical Reports Server (NTRS)

Allen, Michael J.; Dibley, Ryan P.

2003-01-01

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

Use of Soft Computing Technologies For Rocket Engine Control

NASA Technical Reports Server (NTRS)

Trevino, Luis C.; Olcmen, Semih; Polites, Michael

2003-01-01

The problem to be addressed in this paper is to explore how the use of Soft Computing Technologies (SCT) could be employed to further improve overall engine system reliability and performance. Specifically, this will be presented by enhancing rocket engine control and engine health management (EHM) using SCT coupled with conventional control technologies, and sound software engineering practices used in Marshall s Flight Software Group. The principle goals are to improve software management, software development time and maintenance, processor execution, fault tolerance and mitigation, and nonlinear control in power level transitions. The intent is not to discuss any shortcomings of existing engine control and EHM methodologies, but to provide alternative design choices for control, EHM, implementation, performance, and sustaining engineering. The approaches outlined in this paper will require knowledge in the fields of rocket engine propulsion, software engineering for embedded systems, and soft computing technologies (i.e., neural networks, fuzzy logic, and Bayesian belief networks), much of which is presented in this paper. The first targeted demonstration rocket engine platform is the MC-1 (formerly FASTRAC Engine) which is simulated with hardware and software in the Marshall Avionics & Software Testbed laboratory that

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

PubMed

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

2010-08-01

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

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

NASA Technical Reports Server (NTRS)

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

1991-01-01

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

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

NASA Technical Reports Server (NTRS)

Wiesenberg, Brent

1999-01-01

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

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

DTIC Science & Technology

2003-07-01

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

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

DTIC Science & Technology

1995-07-01

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

FPGA-based multiprocessor system for injection molding control.

PubMed

Muñoz-Barron, Benigno; Morales-Velazquez, Luis; Romero-Troncoso, Rene J; Rodriguez-Donate, Carlos; Trejo-Hernandez, Miguel; Benitez-Rangel, Juan P; Osornio-Rios, Roque A

2012-10-18

The plastic industry is a very important manufacturing sector and injection molding is a widely used forming method in that industry. The contribution of this work is the development of a strategy to retrofit control of an injection molding machine based on an embedded system microprocessors sensor network on a field programmable gate array (FPGA) device. Six types of embedded processors are included in the system: a smart-sensor processor, a micro fuzzy logic controller, a programmable logic controller, a system manager, an IO processor and a communication processor. Temperature, pressure and position are controlled by the proposed system and experimentation results show its feasibility and robustness. As validation of the present work, a particular sample was successfully injected.

A Feasibility Study of Synthesizing Subsurfaces Modeled with Computational Neural Networks

NASA Technical Reports Server (NTRS)

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

1998-01-01

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

Optical-Correlator Neural Network Based On Neocognitron

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Stoner, William W.

1994-01-01

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

Neural network based system for equipment surveillance

DOEpatents

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

1998-01-01

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

Neural network based system for equipment surveillance

DOEpatents

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

1998-04-28

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

Neural networks for function approximation in nonlinear control

NASA Technical Reports Server (NTRS)

Linse, Dennis J.; Stengel, Robert F.

1990-01-01

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

Neural networks for vertical microcode compaction

NASA Astrophysics Data System (ADS)

Chu, Pong P.

1992-09-01

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

Advances in Artificial Neural Networks - Methodological Development and Application

USDA-ARS?s Scientific Manuscript database

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

Unified Compact ECC-AES Co-Processor with Group-Key Support for IoT Devices in Wireless Sensor Networks

PubMed Central

Castillo, Encarnación; López-Ramos, Juan A.; Morales, Diego P.

2018-01-01

Security is a critical challenge for the effective expansion of all new emerging applications in the Internet of Things paradigm. Therefore, it is necessary to define and implement different mechanisms for guaranteeing security and privacy of data interchanged within the multiple wireless sensor networks being part of the Internet of Things. However, in this context, low power and low area are required, limiting the resources available for security and thus hindering the implementation of adequate security protocols. Group keys can save resources and communications bandwidth, but should be combined with public key cryptography to be really secure. In this paper, a compact and unified co-processor for enabling Elliptic Curve Cryptography along to Advanced Encryption Standard with low area requirements and Group-Key support is presented. The designed co-processor allows securing wireless sensor networks with independence of the communications protocols used. With an area occupancy of only 2101 LUTs over Spartan 6 devices from Xilinx, it requires 15% less area while achieving near 490% better performance when compared to cryptoprocessors with similar features in the literature. PMID:29337921

Unified Compact ECC-AES Co-Processor with Group-Key Support for IoT Devices in Wireless Sensor Networks.

PubMed

Parrilla, Luis; Castillo, Encarnación; López-Ramos, Juan A; Álvarez-Bermejo, José A; García, Antonio; Morales, Diego P

2018-01-16

Security is a critical challenge for the effective expansion of all new emerging applications in the Internet of Things paradigm. Therefore, it is necessary to define and implement different mechanisms for guaranteeing security and privacy of data interchanged within the multiple wireless sensor networks being part of the Internet of Things. However, in this context, low power and low area are required, limiting the resources available for security and thus hindering the implementation of adequate security protocols. Group keys can save resources and communications bandwidth, but should be combined with public key cryptography to be really secure. In this paper, a compact and unified co-processor for enabling Elliptic Curve Cryptography along to Advanced Encryption Standard with low area requirements and Group-Key support is presented. The designed co-processor allows securing wireless sensor networks with independence of the communications protocols used. With an area occupancy of only 2101 LUTs over Spartan 6 devices from Xilinx, it requires 15% less area while achieving near 490% better performance when compared to cryptoprocessors with similar features in the literature.

A 64-channel ultra-low power system-on-chip for local field and action potentials recording

NASA Astrophysics Data System (ADS)

Rodríguez-Pérez, Alberto; Delgado-Restituto, Manuel; Darie, Angela; Soto-Sánchez, Cristina; Fernández-Jover, Eduardo; Rodríguez-Vázquez, Ángel

2015-06-01

This paper reports an integrated 64-channel neural recording sensor. Neural signals are acquired, filtered, digitized and compressed in the channels. Additionally, each channel implements an auto-calibration mechanism which configures the transfer characteristics of the recording site. The system has two transmission modes; in one case the information captured by the channels is sent as uncompressed raw data; in the other, feature vectors extracted from the detected neural spikes are released. Data streams coming from the channels are serialized by an embedded digital processor. Experimental results, including in vivo measurements, show that the power consumption of the complete system is lower than 330μW.

Artificial Neural Network Metamodels of Stochastic Computer Simulations

DTIC Science & Technology

1994-08-10

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

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

NASA Astrophysics Data System (ADS)

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

2018-01-01

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

Ring-array processor distribution topology for optical interconnects

NASA Technical Reports Server (NTRS)

Li, Yao; Ha, Berlin; Wang, Ting; Wang, Sunyu; Katz, A.; Lu, X. J.; Kanterakis, E.

1992-01-01

The existing linear and rectangular processor distribution topologies for optical interconnects, although promising in many respects, cannot solve problems such as clock skews, the lack of supporting elements for efficient optical implementation, etc. The use of a ring-array processor distribution topology, however, can overcome these problems. Here, a study of the ring-array topology is conducted with an aim of implementing various fast clock rate, high-performance, compact optical networks for digital electronic multiprocessor computers. Practical design issues are addressed. Some proof-of-principle experimental results are included.

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

PubMed

Ranganayaki, V; Deepa, S N

2016-01-01

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

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

PubMed Central

Ranganayaki, V.; Deepa, S. N.

2016-01-01

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

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

NASA Astrophysics Data System (ADS)

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

1995-10-01

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

Comparison of artificial intelligence classifiers for SIP attack data

NASA Astrophysics Data System (ADS)

Safarik, Jakub; Slachta, Jiri

2016-05-01

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

Parallel consensual neural networks.

PubMed

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

1997-01-01

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

Unfolding the neutron spectrum of a NE213 scintillator using artificial neural networks.

PubMed

Sharghi Ido, A; Bonyadi, M R; Etaati, G R; Shahriari, M

2009-10-01

Artificial neural networks technology has been applied to unfold the neutron spectra from the pulse height distribution measured with NE213 liquid scintillator. Here, both the single and multi-layer perceptron neural network models have been implemented to unfold the neutron spectrum from an Am-Be neutron source. The activation function and the connectivity of the neurons have been investigated and the results have been analyzed in terms of the network's performance. The simulation results show that the neural network that utilizes the Satlins transfer function has the best performance. In addition, omitting the bias connection of the neurons improve the performance of the network. Also, the SCINFUL code is used for generating the response functions in the training phase of the process. Finally, the results of the neural network simulation have been compared with those of the FORIST unfolding code for both (241)Am-Be and (252)Cf neutron sources. The results of neural network are in good agreement with FORIST code.

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

PubMed

Guarneri, Paolo; Rocca, Gianpiero; Gobbi, Massimiliano

2008-09-01

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

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

NASA Astrophysics Data System (ADS)

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

2018-02-01

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

Plant Growth Models Using Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Bubenheim, David

1997-01-01

In this paper, we descrive our motivation and approach to devloping models and the neural network architecture. Initial use of the artificial neural network for modeling the single plant process of transpiration is presented.

Artificial Neural Network for the Prediction of Chromosomal Abnormalities in Azoospermic Males.

PubMed

Akinsal, Emre Can; Haznedar, Bulent; Baydilli, Numan; Kalinli, Adem; Ozturk, Ahmet; Ekmekçioğlu, Oğuz

2018-02-04

To evaluate whether an artifical neural network helps to diagnose any chromosomal abnormalities in azoospermic males. The data of azoospermic males attending to a tertiary academic referral center were evaluated retrospectively. Height, total testicular volume, follicle stimulating hormone, luteinising hormone, total testosterone and ejaculate volume of the patients were used for the analyses. In artificial neural network, the data of 310 azoospermics were used as the education and 115 as the test set. Logistic regression analyses and discriminant analyses were performed for statistical analyses. The tests were re-analysed with a neural network. Both logistic regression analyses and artificial neural network predicted the presence or absence of chromosomal abnormalities with more than 95% accuracy. The use of artificial neural network model has yielded satisfactory results in terms of distinguishing patients whether they have any chromosomal abnormality or not.

Synchronization criteria for generalized reaction-diffusion neural networks via periodically intermittent control.

PubMed

Gan, Qintao; Lv, Tianshi; Fu, Zhenhua

2016-04-01

In this paper, the synchronization problem for a class of generalized neural networks with time-varying delays and reaction-diffusion terms is investigated concerning Neumann boundary conditions in terms of p-norm. The proposed generalized neural networks model includes reaction-diffusion local field neural networks and reaction-diffusion static neural networks as its special cases. By establishing a new inequality, some simple and useful conditions are obtained analytically to guarantee the global exponential synchronization of the addressed neural networks under the periodically intermittent control. According to the theoretical results, the influences of diffusion coefficients, diffusion space, and control rate on synchronization are analyzed. Finally, the feasibility and effectiveness of the proposed methods are shown by simulation examples, and by choosing different diffusion coefficients, diffusion spaces, and control rates, different controlled synchronization states can be obtained.

Global exponential stability of inertial memristor-based neural networks with time-varying delays and impulses.

PubMed

Zhang, Wei; Huang, Tingwen; He, Xing; Li, Chuandong

2017-11-01

In this study, we investigate the global exponential stability of inertial memristor-based neural networks with impulses and time-varying delays. We construct inertial memristor-based neural networks based on the characteristics of the inertial neural networks and memristor. Impulses with and without delays are considered when modeling the inertial neural networks simultaneously, which are of great practical significance in the current study. Some sufficient conditions are derived under the framework of the Lyapunov stability method, as well as an extended Halanay differential inequality and a new delay impulsive differential inequality, which depend on impulses with and without delays, in order to guarantee the global exponential stability of the inertial memristor-based neural networks. Finally, two numerical examples are provided to illustrate the efficiency of the proposed methods. Copyright © 2017 Elsevier Ltd. All rights reserved.

Neural joint control for Space Shuttle Remote Manipulator System

NASA Technical Reports Server (NTRS)

Atkins, Mark A.; Cox, Chadwick J.; Lothers, Michael D.; Pap, Robert M.; Thomas, Charles R.

1992-01-01

Neural networks are being used to control a robot arm in a telerobotic operation. The concept uses neural networks for both joint and inverse kinematics in a robotic control application. An upper level neural network is trained to learn inverse kinematic mappings. The output, a trajectory, is then fed to the Decentralized Adaptive Joint Controllers. This neural network implementation has shown that the controlled arm recovers from unexpected payload changes while following the reference trajectory. The neural network-based decentralized joint controller is faster, more robust and efficient than conventional approaches. Implementations of this architecture are discussed that would relax assumptions about dynamics, obstacles, and heavy loads. This system is being developed to use with the Space Shuttle Remote Manipulator System.

Application of a neural network for reflectance spectrum classification

NASA Astrophysics Data System (ADS)

Yang, Gefei; Gartley, Michael

2017-05-01

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

QSAR modelling using combined simple competitive learning networks and RBF neural networks.

PubMed

Sheikhpour, R; Sarram, M A; Rezaeian, M; Sheikhpour, E

2018-04-01

The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.

Nanophotonic particle simulation and inverse design using artificial neural networks.

PubMed

Peurifoy, John; Shen, Yichen; Jing, Li; Yang, Yi; Cano-Renteria, Fidel; DeLacy, Brendan G; Joannopoulos, John D; Tegmark, Max; Soljačić, Marin

2018-06-01

We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.

Application of Artificial Neural Networks in the Heart Electrical Axis Position Conclusion Modeling

NASA Astrophysics Data System (ADS)

Bakanovskaya, L. N.

2016-08-01

The article touches upon building of a heart electrical axis position conclusion model using an artificial neural network. The input signals of the neural network are the values of deflections Q, R and S; and the output signal is the value of the heart electrical axis position. Training of the network is carried out by the error propagation method. The test results allow concluding that the created neural network makes a conclusion with a high degree of accuracy.

Parallel Simulation of Subsonic Fluid Dynamics on a Cluster of Workstations.

DTIC Science & Technology

1994-11-01

inside wind musical instruments. Typical simulations achieve $80\\%$ parallel efficiency (speedup/processors) using 20 HP-Apollo workstations. Detailed...TERMS AI, MIT, Artificial Intelligence, Distributed Computing, Workstation Cluster, Network, Fluid Dynamics, Musical Instruments 17. SECURITY...for example, the flow of air inside wind musical instruments. Typical simulations achieve 80% parallel efficiency (speedup/processors) using 20 HP

CMOS VLSI Layout and Verification of a SIMD Computer

NASA Technical Reports Server (NTRS)

Zheng, Jianqing

1996-01-01

A CMOS VLSI layout and verification of a 3 x 3 processor parallel computer has been completed. The layout was done using the MAGIC tool and the verification using HSPICE. Suggestions for expanding the computer into a million processor network are presented. Many problems that might be encountered when implementing a massively parallel computer are discussed.

Enhancement of electrical signaling in neural networks on graphene films.

PubMed

Tang, Mingliang; Song, Qin; Li, Ning; Jiang, Ziyun; Huang, Rong; Cheng, Guosheng

2013-09-01

One of the key challenges for neural tissue engineering is to exploit supporting materials with robust functionalities not only to govern cell-specific behaviors, but also to form functional neural network. The unique electrical and mechanical properties of graphene imply it as a promising candidate for neural interfaces, but little is known about the details of neural network formation on graphene as a scaffold material for tissue engineering. Therapeutic regenerative strategies aim to guide and enhance the intrinsic capacity of the neurons to reorganize by promoting plasticity mechanisms in a controllable manner. Here, we investigated the impact of graphene on the formation and performance in the assembly of neural networks in neural stem cell (NSC) culture. Using calcium imaging and electrophysiological recordings, we demonstrate the capabilities of graphene to support the growth of functional neural circuits, and improve neural performance and electrical signaling in the network. These results offer a better understanding of interactions between graphene and NSCs, also they clearly present the great potentials of graphene as neural interface in tissue engineering. Copyright © 2013 Elsevier Ltd. All rights reserved.

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

PubMed Central

Tonelli, Paul; Mouret, Jean-Baptiste

2013-01-01

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

Modular representation of layered neural networks.

PubMed

Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

2018-01-01

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

Bio-inspired spiking neural network for nonlinear systems control.

PubMed

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

2018-08-01

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

A sweep algorithm for massively parallel simulation of circuit-switched networks

NASA Technical Reports Server (NTRS)

Gaujal, Bruno; Greenberg, Albert G.; Nicol, David M.

1992-01-01

A new massively parallel algorithm is presented for simulating large asymmetric circuit-switched networks, controlled by a randomized-routing policy that includes trunk-reservation. A single instruction multiple data (SIMD) implementation is described, and corresponding experiments on a 16384 processor MasPar parallel computer are reported. A multiple instruction multiple data (MIMD) implementation is also described, and corresponding experiments on an Intel IPSC/860 parallel computer, using 16 processors, are reported. By exploiting parallelism, our algorithm increases the possible execution rate of such complex simulations by as much as an order of magnitude.

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.

Criteria for Choosing the Best Neural Network: Part 1

DTIC Science & Technology

1991-07-24

Touretzky, pp. 177-185. San Mateo: Morgan Kaufmann. Harp, S.A., Samad , T., and Guha, A . (1990). Designing application-specific neural networks using genetic...determining a parsimonious neural network for use in prediction/generalization based on a given fixed learning sample. Both the classification and...statistical settings, algorithms for selecting the number of hidden layer nodes in a three layer, feedforward neural network are presented. The selection

Keypoint Density-Based Region Proposal for Fine-Grained Object Detection and Classification Using Regions with Convolutional Neural Network Features

DTIC Science & Technology

2015-12-15

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network ... Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their...detection accuracy and speed on the fine-grained Caltech UCSD bird dataset (Wah et al., 2011). Recently, Convolutional Neural Networks (CNNs), a deep

Modeling Training Site Vegetation Coverage Probability with a Random Optimizing Procedure: An Artificial Neural Network Approach.

DTIC Science & Technology

1998-05-01

Coverage Probability with a Random Optimization Procedure: An Artificial Neural Network Approach by Biing T. Guan, George Z. Gertner, and Alan B...Modeling Training Site Vegetation Coverage Probability with a Random Optimizing Procedure: An Artificial Neural Network Approach 6. AUTHOR(S) Biing...coverage based on past coverage. Approach A literature survey was conducted to identify artificial neural network analysis techniques applicable for

Semantic Interpretation of An Artificial Neural Network

DTIC Science & Technology

1995-12-01

ARTIFICIAL NEURAL NETWORK .7,’ THESIS Stanley Dale Kinderknecht Captain, USAF 770 DEAT7ET77,’H IR O C 7... ARTIFICIAL NEURAL NETWORK THESIS Stanley Dale Kinderknecht Captain, USAF AFIT/GCS/ENG/95D-07 Approved for public release; distribution unlimited The views...Government. AFIT/GCS/ENG/95D-07 SEMANTIC INTERPRETATION OF AN ARTIFICIAL NEURAL NETWORK THESIS Presented to the Faculty of the School of Engineering of

Trimaran Resistance Artificial Neural Network

DTIC Science & Technology

2011-01-01

11th International Conference on Fast Sea Transportation FAST 2011, Honolulu, Hawaii, USA, September 2011 Trimaran Resistance Artificial Neural Network Richard...Trimaran Resistance Artificial Neural Network 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e... Artificial Neural Network and is restricted to the center and side-hull configurations tested. The value in the parametric model is that it is able to

Application of Fuzzy-Logic Controller and Neural Networks Controller in Gas Turbine Speed Control and Overheating Control and Surge Control on Transient Performance

NASA Astrophysics Data System (ADS)

Torghabeh, A. A.; Tousi, A. M.

2007-08-01

This paper presents Fuzzy Logic and Neural Networks approach to Gas Turbine Fuel schedules. Modeling of non-linear system using feed forward artificial Neural Networks using data generated by a simulated gas turbine program is introduced. Two artificial Neural Networks are used , depicting the non-linear relationship between gas generator speed and fuel flow, and turbine inlet temperature and fuel flow respectively . Off-line fast simulations are used for engine controller design for turbojet engine based on repeated simulation. The Mamdani and Sugeno models are used to expression the Fuzzy system . The linguistic Fuzzy rules and membership functions are presents and a Fuzzy controller will be proposed to provide an Open-Loop control for the gas turbine engine during acceleration and deceleration . MATLAB Simulink was used to apply the Fuzzy Logic and Neural Networks analysis. Both systems were able to approximate functions characterizing the acceleration and deceleration schedules . Surge and Flame-out avoidance during acceleration and deceleration phases are then checked . Turbine Inlet Temperature also checked and controls by Neural Networks controller. This Fuzzy Logic and Neural Network Controllers output results are validated and evaluated by GSP software . The validation results are used to evaluate the generalization ability of these artificial Neural Networks and Fuzzy Logic controllers.

A research using hybrid RBF/Elman neural networks for intrusion detection system secure model

NASA Astrophysics Data System (ADS)

Tong, Xiaojun; Wang, Zhu; Yu, Haining

2009-10-01

A hybrid RBF/Elman neural network model that can be employed for both anomaly detection and misuse detection is presented in this paper. The IDSs using the hybrid neural network can detect temporally dispersed and collaborative attacks effectively because of its memory of past events. The RBF network is employed as a real-time pattern classification and the Elman network is employed to restore the memory of past events. The IDSs using the hybrid neural network are evaluated against the intrusion detection evaluation data sponsored by U.S. Defense Advanced Research Projects Agency (DARPA). Experimental results are presented in ROC curves. Experiments show that the IDSs using this hybrid neural network improve the detection rate and decrease the false positive rate effectively.

Advanced obstacle avoidance for a laser based wheelchair using optimised Bayesian neural networks.

PubMed

Trieu, Hoang T; Nguyen, Hung T; Willey, Keith

2008-01-01

In this paper we present an advanced method of obstacle avoidance for a laser based intelligent wheelchair using optimized Bayesian neural networks. Three neural networks are designed for three separate sub-tasks: passing through a door way, corridor and wall following and general obstacle avoidance. The accurate usable accessible space is determined by including the actual wheelchair dimensions in a real-time map used as inputs to each networks. Data acquisitions are performed separately to collect the patterns required for specified sub-tasks. Bayesian frame work is used to determine the optimal neural network structure in each case. Then these networks are trained under the supervision of Bayesian rule. Experiment results showed that compare to the VFH algorithm our neural networks navigated a smoother path following a near optimum trajectory.

Influence of neural adaptation on dynamics and equilibrium state of neural activities in a ring neural network

NASA Astrophysics Data System (ADS)

Takiyama, Ken

2017-12-01

How neural adaptation affects neural information processing (i.e. the dynamics and equilibrium state of neural activities) is a central question in computational neuroscience. In my previous works, I analytically clarified the dynamics and equilibrium state of neural activities in a ring-type neural network model that is widely used to model the visual cortex, motor cortex, and several other brain regions. The neural dynamics and the equilibrium state in the neural network model corresponded to a Bayesian computation and statistically optimal multiple information integration, respectively, under a biologically inspired condition. These results were revealed in an analytically tractable manner; however, adaptation effects were not considered. Here, I analytically reveal how the dynamics and equilibrium state of neural activities in a ring neural network are influenced by spike-frequency adaptation (SFA). SFA is an adaptation that causes gradual inhibition of neural activity when a sustained stimulus is applied, and the strength of this inhibition depends on neural activities. I reveal that SFA plays three roles: (1) SFA amplifies the influence of external input in neural dynamics; (2) SFA allows the history of the external input to affect neural dynamics; and (3) the equilibrium state corresponds to the statistically optimal multiple information integration independent of the existence of SFA. In addition, the equilibrium state in a ring neural network model corresponds to the statistically optimal integration of multiple information sources under biologically inspired conditions, independent of the existence of SFA.

Ultrasonographic Diagnosis of Cirrhosis Based on Preprocessing Using Pyramid Recurrent Neural Network

NASA Astrophysics Data System (ADS)

Lu, Jianming; Liu, Jiang; Zhao, Xueqin; Yahagi, Takashi

In this paper, a pyramid recurrent neural network is applied to characterize the hepatic parenchymal diseases in ultrasonic B-scan texture. The cirrhotic parenchymal diseases are classified into 4 types according to the size of hypoechoic nodular lesions. The B-mode patterns are wavelet transformed , and then the compressed data are feed into a pyramid neural network to diagnose the type of cirrhotic diseases. Compared with the 3-layer neural networks, the performance of the proposed pyramid recurrent neural network is improved by utilizing the lower layer effectively. The simulation result shows that the proposed system is suitable for diagnosis of cirrhosis diseases.

Application of artificial neural networks to composite ply micromechanics

NASA Technical Reports Server (NTRS)

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

1991-01-01

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

Using Neural Networks for Sensor Validation

NASA Technical Reports Server (NTRS)

Mattern, Duane L.; Jaw, Link C.; Guo, Ten-Huei; Graham, Ronald; McCoy, William

1998-01-01

This paper presents the results of applying two different types of neural networks in two different approaches to the sensor validation problem. The first approach uses a functional approximation neural network as part of a nonlinear observer in a model-based approach to analytical redundancy. The second approach uses an auto-associative neural network to perform nonlinear principal component analysis on a set of redundant sensors to provide an estimate for a single failed sensor. The approaches are demonstrated using a nonlinear simulation of a turbofan engine. The fault detection and sensor estimation results are presented and the training of the auto-associative neural network to provide sensor estimates is discussed.

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.

A Comparison of Conventional Linear Regression Methods and Neural Networks for Forecasting Educational Spending.

ERIC Educational Resources Information Center

Baker, Bruce D.; Richards, Craig E.

1999-01-01

Applies neural network methods for forecasting 1991-95 per-pupil expenditures in U.S. public elementary and secondary schools. Forecasting models included the National Center for Education Statistics' multivariate regression model and three neural architectures. Regarding prediction accuracy, neural network results were comparable or superior to…

A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses

PubMed Central

Qiao, Ning; Mostafa, Hesham; Corradi, Federico; Osswald, Marc; Stefanini, Fabio; Sumislawska, Dora; Indiveri, Giacomo

2015-01-01

Implementing compact, low-power artificial neural processing systems with real-time on-line learning abilities is still an open challenge. In this paper we present a full-custom mixed-signal VLSI device with neuromorphic learning circuits that emulate the biophysics of real spiking neurons and dynamic synapses for exploring the properties of computational neuroscience models and for building brain-inspired computing systems. The proposed architecture allows the on-chip configuration of a wide range of network connectivities, including recurrent and deep networks, with short-term and long-term plasticity. The device comprises 128 K analog synapse and 256 neuron circuits with biologically plausible dynamics and bi-stable spike-based plasticity mechanisms that endow it with on-line learning abilities. In addition to the analog circuits, the device comprises also asynchronous digital logic circuits for setting different synapse and neuron properties as well as different network configurations. This prototype device, fabricated using a 180 nm 1P6M CMOS process, occupies an area of 51.4 mm2, and consumes approximately 4 mW for typical experiments, for example involving attractor networks. Here we describe the details of the overall architecture and of the individual circuits and present experimental results that showcase its potential. By supporting a wide range of cortical-like computational modules comprising plasticity mechanisms, this device will enable the realization of intelligent autonomous systems with on-line learning capabilities. PMID:25972778

An Artificial Neural Network Controller for Intelligent Transportation Systems Applications

DOT National Transportation Integrated Search

1996-01-01

An Autonomous Intelligent Cruise Control (AICC) has been designed using a feedforward artificial neural network, as an example for utilizing artificial neural networks for nonlinear control problems arising in intelligent transportation systems appli...

Deconvolution using a neural network

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

Lehman, S.K.

1990-11-15

Viewing one dimensional deconvolution as a matrix inversion problem, we compare a neural network backpropagation matrix inverse with LMS, and pseudo-inverse. This is a largely an exercise in understanding how our neural network code works. 1 ref.

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.

Flank wears Simulation by using back propagation neural network when cutting hardened H-13 steel in CNC End Milling

NASA Astrophysics Data System (ADS)

Hazza, Muataz Hazza F. Al; Adesta, Erry Y. T.; Riza, Muhammad

2013-12-01

High speed milling has many advantages such as higher removal rate and high productivity. However, higher cutting speed increase the flank wear rate and thus reducing the cutting tool life. Therefore estimating and predicting the flank wear length in early stages reduces the risk of unaccepted tooling cost. This research presents a neural network model for predicting and simulating the flank wear in the CNC end milling process. A set of sparse experimental data for finish end milling on AISI H13 at hardness of 48 HRC have been conducted to measure the flank wear length. Then the measured data have been used to train the developed neural network model. Artificial neural network (ANN) was applied to predict the flank wear length. The neural network contains twenty hidden layer with feed forward back propagation hierarchical. The neural network has been designed with MATLAB Neural Network Toolbox. The results show a high correlation between the predicted and the observed flank wear which indicates the validity of the models.

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

NASA Technical Reports Server (NTRS)

Lary, David J.; Mussa, Yussuf

2004-01-01

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

Neural network classification of clinical neurophysiological data for acute care monitoring

NASA Technical Reports Server (NTRS)

Sgro, Joseph

1994-01-01

The purpose of neurophysiological monitoring of the 'acute care' patient is to allow the accurate recognition of changing or deteriorating neurological function as close to the moment of occurrence as possible, thus permitting immediate intervention. Results confirm that: (1) neural networks are able to accurately identify electroencephalogram (EEG) patterns and evoked potential (EP) wave components, and measuring EP waveform latencies and amplitudes; (2) neural networks are able to accurately detect EP and EEG recordings that have been contaminated by noise; (3) the best performance was obtained consistently with the back propagation network for EP and the HONN for EEG's; (4) neural network performed consistently better than other methods evaluated; and (5) neural network EEG and EP analyses are readily performed on multichannel data.

Neural computation of arithmetic functions

NASA Technical Reports Server (NTRS)

Siu, Kai-Yeung; Bruck, Jehoshua

1990-01-01

An area of application of neural networks is considered. A neuron is modeled as a linear threshold gate, and the network architecture considered is the layered feedforward network. It is shown how common arithmetic functions such as multiplication and sorting can be efficiently computed in a shallow neural network. Some known results are improved by showing that the product of two n-bit numbers and sorting of n n-bit numbers can be computed by a polynomial-size neural network using only four and five unit delays, respectively. Moreover, the weights of each threshold element in the neural networks require O(log n)-bit (instead of n-bit) accuracy. These results can be extended to more complicated functions such as multiple products, division, rational functions, and approximation of analytic functions.

Recognition of Telugu characters using neural networks.

PubMed

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

1995-09-01

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

Multistability in bidirectional associative memory neural networks

NASA Astrophysics Data System (ADS)

Huang, Gan; Cao, Jinde

2008-04-01

In this Letter, the multistability issue is studied for Bidirectional Associative Memory (BAM) neural networks. Based on the existence and stability analysis of the neural networks with or without delay, it is found that the 2 n-dimensional networks can have 3 equilibria and 2 equilibria of them are locally exponentially stable, where each layer of the BAM network has n neurons. Furthermore, the results has been extended to (n+m)-dimensional BAM neural networks, where there are n and m neurons on the two layers respectively. Finally, two numerical examples are presented to illustrate the validity of our results.

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

NASA Astrophysics Data System (ADS)

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

2018-03-01

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

Verification and Validation Methodology of Real-Time Adaptive Neural Networks for Aerospace Applications

NASA Technical Reports Server (NTRS)

Gupta, Pramod; Loparo, Kenneth; Mackall, Dale; Schumann, Johann; Soares, Fola

2004-01-01

Recent research has shown that adaptive neural based control systems are very effective in restoring stability and control of an aircraft in the presence of damage or failures. The application of an adaptive neural network with a flight critical control system requires a thorough and proven process to ensure safe and proper flight operation. Unique testing tools have been developed as part of a process to perform verification and validation (V&V) of real time adaptive neural networks used in recent adaptive flight control system, to evaluate the performance of the on line trained neural networks. The tools will help in certification from FAA and will help in the successful deployment of neural network based adaptive controllers in safety-critical applications. The process to perform verification and validation is evaluated against a typical neural adaptive controller and the results are discussed.

Parallel computing on Unix workstation arrays

NASA Astrophysics Data System (ADS)

Reale, F.; Bocchino, F.; Sciortino, S.

1994-12-01

We have tested arrays of general-purpose Unix workstations used as MIMD systems for massive parallel computations. In particular we have solved numerically a demanding test problem with a 2D hydrodynamic code, generally developed to study astrophysical flows, by exucuting it on arrays either of DECstations 5000/200 on Ethernet LAN, or of DECstations 3000/400, equipped with powerful Alpha processors, on FDDI LAN. The code is appropriate for data-domain decomposition, and we have used a library for parallelization previously developed in our Institute, and easily extended to work on Unix workstation arrays by using the PVM software toolset. We have compared the parallel efficiencies obtained on arrays of several processors to those obtained on a dedicated MIMD parallel system, namely a Meiko Computing Surface (CS-1), equipped with Intel i860 processors. We discuss the feasibility of using non-dedicated parallel systems and conclude that the convenience depends essentially on the size of the computational domain as compared to the relative processor power and network bandwidth. We point out that for future perspectives a parallel development of processor and network technology is important, and that the software still offers great opportunities of improvement, especially in terms of latency times in the message-passing protocols. In conditions of significant gain in terms of speedup, such workstation arrays represent a cost-effective approach to massive parallel computations.

Pulse Coupled Neural Networks for the Segmentation of Magnetic Resonance Brain Images.

DTIC Science & Technology

1996-12-01

PULSE COUPLED NEURAL NETWORKS FOR THE SEGMENTATION OF MAGNETIC RESONANCE BRAIN IMAGES THESIS Shane Lee Abrahamson First Lieutenant, USAF AFIT/GCS/ENG...COUPLED NEURAL NETWORKS FOR THE SEGMENTATION OF MAGNETIC RESONANCE BRAIN IMAGES THESIS Shane Lee Abrahamson First Lieutenant, USAF AFIT/GCS/ENG/96D-01...research develops an automated method for segmenting Magnetic Resonance (MR) brain images based on Pulse Coupled Neural Networks (PCNN). MR brain image

Angle of Arrival Detection Through Artificial Neural Network Analysis of Optical Fiber Intensity Patterns

DTIC Science & Technology

1990-12-01

ARTIFICIAL NEURAL NETWORK ANALYSIS OF OPTICAL FIBER INTENSITY PATTERNS THESIS Scott Thomas Captain, USAF AFIT/GE/ENG/90D-62 DTIC...ELECTE ao • JAN08 1991 Approved for public release; distribution unlimited. AFIT/GE/ENG/90D-62 ANGLE OF ARRIVAL DETECTION THROUGH ARTIFICIAL NEURAL NETWORK ANALYSIS... ARTIFICIAL NEURAL NETWORK ANALYSIS OF OPTICAL FIBER INTENSITY PATTERNS L Introduction The optical sensors of United States Air Force reconnaissance

Reconfigurable Flight Control Design using a Robust Servo LQR and Radial Basis Function Neural Networks

NASA Technical Reports Server (NTRS)

Burken, John J.

2005-01-01

This viewgraph presentation reviews the use of a Robust Servo Linear Quadratic Regulator (LQR) and a Radial Basis Function (RBF) Neural Network in reconfigurable flight control designs in adaptation to a aircraft part failure. The method uses a robust LQR servomechanism design with model Reference adaptive control, and RBF neural networks. During the failure the LQR servomechanism behaved well, and using the neural networks improved the tracking.

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

DTIC Science & Technology

2015-06-11

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

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

NASA Technical Reports Server (NTRS)

Ramamoorthy, P. A.

1991-01-01

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

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

PubMed

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

2016-10-01

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

A comparison of neural network architectures for the prediction of MRR in EDM

NASA Astrophysics Data System (ADS)

Jena, A. R.; Das, Raja

2017-11-01

The aim of the research work is to predict the material removal rate of a work-piece in electrical discharge machining (EDM). Here, an effort has been made to predict the material removal rate through back-propagation neural network (BPN) and radial basis function neural network (RBFN) for a work-piece of AISI D2 steel. The input parameters for the architecture are discharge-current (Ip), pulse-duration (Ton), and duty-cycle (τ) taken for consideration to obtained the output for material removal rate of the work-piece. In the architecture, it has been observed that radial basis function neural network is comparatively faster than back-propagation neural network but logically back-propagation neural network results more real value. Therefore BPN may consider as a better process in this architecture for consistent prediction to save time and money for conducting experiments.

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

DOE PAGES

Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy

2016-10-18

There exists significant demand for improved Reynolds-averaged Navier–Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents a method of using deep neural networks to learn a model for the Reynolds stress anisotropy tensor from high-fidelity simulation data. A novel neural network architecture is proposed which uses a multiplicative layer with an invariant tensor basis to embed Galilean invariance into the predicted anisotropy tensor. It is demonstrated that this neural network architecture provides improved prediction accuracy compared with a generic neural network architecture that does not embed this invariance property.more » Furthermore, the Reynolds stress anisotropy predictions of this invariant neural network are propagated through to the velocity field for two test cases. For both test cases, significant improvement versus baseline RANS linear eddy viscosity and nonlinear eddy viscosity models is demonstrated.« less

Synchronization of Switched Neural Networks With Communication Delays via the Event-Triggered Control.

PubMed

Wen, Shiping; Zeng, Zhigang; Chen, Michael Z Q; Huang, Tingwen

2017-10-01

This paper addresses the issue of synchronization of switched delayed neural networks with communication delays via event-triggered control. For synchronizing coupled switched neural networks, we propose a novel event-triggered control law which could greatly reduce the number of control updates for synchronization tasks of coupled switched neural networks involving embedded microprocessors with limited on-board resources. The control signals are driven by properly defined events, which depend on the measurement errors and current-sampled states. By using a delay system method, a novel model of synchronization error system with delays is proposed with the communication delays and event-triggered control in the unified framework for coupled switched neural networks. The criteria are derived for the event-triggered synchronization analysis and control synthesis of switched neural networks via the Lyapunov-Krasovskii functional method and free weighting matrix approach. A numerical example is elaborated on to illustrate the effectiveness of the derived results.

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

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

Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy

There exists significant demand for improved Reynolds-averaged Navier–Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents a method of using deep neural networks to learn a model for the Reynolds stress anisotropy tensor from high-fidelity simulation data. A novel neural network architecture is proposed which uses a multiplicative layer with an invariant tensor basis to embed Galilean invariance into the predicted anisotropy tensor. It is demonstrated that this neural network architecture provides improved prediction accuracy compared with a generic neural network architecture that does not embed this invariance property.more » Furthermore, the Reynolds stress anisotropy predictions of this invariant neural network are propagated through to the velocity field for two test cases. For both test cases, significant improvement versus baseline RANS linear eddy viscosity and nonlinear eddy viscosity models is demonstrated.« less

A One-Layer Recurrent Neural Network for Real-Time Portfolio Optimization With Probability Criterion.

PubMed

Liu, Qingshan; Dang, Chuangyin; Huang, Tingwen

2013-02-01

This paper presents a decision-making model described by a recurrent neural network for dynamic portfolio optimization. The portfolio-optimization problem is first converted into a constrained fractional programming problem. Since the objective function in the programming problem is not convex, the traditional optimization techniques are no longer applicable for solving this problem. Fortunately, the objective function in the fractional programming is pseudoconvex on the feasible region. It leads to a one-layer recurrent neural network modeled by means of a discontinuous dynamic system. To ensure the optimal solutions for portfolio optimization, the convergence of the proposed neural network is analyzed and proved. In fact, the neural network guarantees to get the optimal solutions for portfolio-investment advice if some mild conditions are satisfied. A numerical example with simulation results substantiates the effectiveness and illustrates the characteristics of the proposed neural network.

Fast and Accurate Simulation of the Cray XMT Multithreaded Supercomputer

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

Villa, Oreste; Tumeo, Antonino; Secchi, Simone

Irregular applications, such as data mining and analysis or graph-based computations, show unpredictable memory/network access patterns and control structures. Highly multithreaded architectures with large processor counts, like the Cray MTA-1, MTA-2 and XMT, appear to address their requirements better than commodity clusters. However, the research on highly multithreaded systems is currently limited by the lack of adequate architectural simulation infrastructures due to issues such as size of the machines, memory footprint, simulation speed, accuracy and customization. At the same time, Shared-memory MultiProcessors (SMPs) with multi-core processors have become an attractive platform to simulate large scale machines. In this paper, wemore » introduce a cycle-level simulator of the highly multithreaded Cray XMT supercomputer. The simulator runs unmodified XMT applications. We discuss how we tackled the challenges posed by its development, detailing the techniques introduced to make the simulation as fast as possible while maintaining a high accuracy. By mapping XMT processors (ThreadStorm with 128 hardware threads) to host computing cores, the simulation speed remains constant as the number of simulated processors increases, up to the number of available host cores. The simulator supports zero-overhead switching among different accuracy levels at run-time and includes a network model that takes into account contention. On a modern 48-core SMP host, our infrastructure simulates a large set of irregular applications 500 to 2000 times slower than real time when compared to a 128-processor XMT, while remaining within 10\\% of accuracy. Emulation is only from 25 to 200 times slower than real time.« less

Application of two neural network paradigms to the study of voluntary employee turnover.

PubMed

Somers, M J

1999-04-01

Two neural network paradigms--multilayer perceptron and learning vector quantization--were used to study voluntary employee turnover with a sample of 577 hospital employees. The objectives of the study were twofold. The 1st was to assess whether neural computing techniques offered greater predictive accuracy than did conventional turnover methodologies. The 2nd was to explore whether computer models of turnover based on neural network technologies offered new insights into turnover processes. When compared with logistic regression analysis, both neural network paradigms provided considerably more accurate predictions of turnover behavior, particularly with respect to the correct classification of leavers. In addition, these neural network paradigms captured nonlinear relationships that are relevant for theory development. Results are discussed in terms of their implications for future research.

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

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.

Artificial neural network intelligent method for prediction

NASA Astrophysics Data System (ADS)

Trifonov, Roumen; Yoshinov, Radoslav; Pavlova, Galya; Tsochev, Georgi

2017-09-01

Accounting and financial classification and prediction problems are high challenge and researchers use different methods to solve them. Methods and instruments for short time prediction of financial operations using artificial neural network are considered. The methods, used for prediction of financial data as well as the developed forecasting system with neural network are described in the paper. The architecture of a neural network used four different technical indicators, which are based on the raw data and the current day of the week is presented. The network developed is used for forecasting movement of stock prices one day ahead and consists of an input layer, one hidden layer and an output layer. The training method is algorithm with back propagation of the error. The main advantage of the developed system is self-determination of the optimal topology of neural network, due to which it becomes flexible and more precise The proposed system with neural network is universal and can be applied to various financial instruments using only basic technical indicators as input data.

Seismic signal auto-detecing from different features by using Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Huang, Y.; Zhou, Y.; Yue, H.; Zhou, S.

2017-12-01

We try Convolutional Neural Network to detect some features of seismic data and compare their efficience. The features include whether a signal is seismic signal or noise and the arrival time of P and S phase and each feature correspond to a Convolutional Neural Network. We first use traditional STA/LTA to recongnize some events and then use templete matching to find more events as training set for the Neural Network. To make the training set more various, we add some noise to the seismic data and make some synthetic seismic data and noise. The 3-component raw signal and time-frequancy ananlyze are used as the input data for our neural network. Our Training is performed on GPUs to achieve efficient convergence. Our method improved the precision in comparison with STA/LTA and template matching. We will move to recurrent neural network to see if this kind network is better in detect P and S phase.

Geometrical structure of Neural Networks: Geodesics, Jeffrey's Prior and Hyper-ribbons

NASA Astrophysics Data System (ADS)

Hayden, Lorien; Alemi, Alex; Sethna, James

2014-03-01

Neural networks are learning algorithms which are employed in a host of Machine Learning problems including speech recognition, object classification and data mining. In practice, neural networks learn a low dimensional representation of high dimensional data and define a model manifold which is an embedding of this low dimensional structure in the higher dimensional space. In this work, we explore the geometrical structure of a neural network model manifold. A Stacked Denoising Autoencoder and a Deep Belief Network are trained on handwritten digits from the MNIST database. Construction of geodesics along the surface and of slices taken from the high dimensional manifolds reveal a hierarchy of widths corresponding to a hyper-ribbon structure. This property indicates that neural networks fall into the class of sloppy models, in which certain parameter combinations dominate the behavior. Employing this information could prove valuable in designing both neural network architectures and training algorithms. This material is based upon work supported by the National Science Foundation Graduate Research Fellowship under Grant No . DGE-1144153.

Neural networks within multi-core optic fibers

PubMed Central

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

2016-01-01

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

Neural networks within multi-core optic fibers.

PubMed

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

2016-07-07

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

Method of gear fault diagnosis based on EEMD and improved Elman neural network

NASA Astrophysics Data System (ADS)

Zhang, Qi; Zhao, Wei; Xiao, Shungen; Song, Mengmeng

2017-05-01

Aiming at crack and wear and so on of gears Fault information is difficult to diagnose usually due to its weak, a gear fault diagnosis method that is based on EEMD and improved Elman neural network fusion is proposed. A number of IMF components are obtained by decomposing denoised all kinds of fault signals with EEMD, and the pseudo IMF components is eliminated by using the correlation coefficient method to obtain the effective IMF component. The energy characteristic value of each effective component is calculated as the input feature quantity of Elman neural network, and the improved Elman neural network is based on standard network by adding a feedback factor. The fault data of normal gear, broken teeth, cracked gear and attrited gear were collected by field collecting. The results were analyzed by the diagnostic method proposed in this paper. The results show that compared with the standard Elman neural network, Improved Elman neural network has the advantages of high diagnostic efficiency.

Optimal exponential synchronization of general chaotic delayed neural networks: an LMI approach.

PubMed

Liu, Meiqin

2009-09-01

This paper investigates the optimal exponential synchronization problem of general chaotic neural networks with or without time delays by virtue of Lyapunov-Krasovskii stability theory and the linear matrix inequality (LMI) technique. This general model, which is the interconnection of a linear delayed dynamic system and a bounded static nonlinear operator, covers several well-known neural networks, such as Hopfield neural networks, cellular neural networks (CNNs), bidirectional associative memory (BAM) networks, and recurrent multilayer perceptrons (RMLPs) with or without delays. Using the drive-response concept, time-delay feedback controllers are designed to synchronize two identical chaotic neural networks as quickly as possible. The control design equations are shown to be a generalized eigenvalue problem (GEVP) which can be easily solved by various convex optimization algorithms to determine the optimal control law and the optimal exponential synchronization rate. Detailed comparisons with existing results are made and numerical simulations are carried out to demonstrate the effectiveness of the established synchronization laws.

FPGA-Based Multiprocessor System for Injection Molding Control

PubMed Central

Muñoz-Barron, Benigno; Morales-Velazquez, Luis; Romero-Troncoso, Rene J.; Rodriguez-Donate, Carlos; Trejo-Hernandez, Miguel; Benitez-Rangel, Juan P.; Osornio-Rios, Roque A.

2012-01-01

The plastic industry is a very important manufacturing sector and injection molding is a widely used forming method in that industry. The contribution of this work is the development of a strategy to retrofit control of an injection molding machine based on an embedded system microprocessors sensor network on a field programmable gate array (FPGA) device. Six types of embedded processors are included in the system: a smart-sensor processor, a micro fuzzy logic controller, a programmable logic controller, a system manager, an IO processor and a communication processor. Temperature, pressure and position are controlled by the proposed system and experimentation results show its feasibility and robustness. As validation of the present work, a particular sample was successfully injected. PMID:23202036

Nanophotonic particle simulation and inverse design using artificial neural networks

PubMed Central

Peurifoy, John; Shen, Yichen; Jing, Li; Cano-Renteria, Fidel; DeLacy, Brendan G.; Joannopoulos, John D.; Tegmark, Max

2018-01-01

We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical. PMID:29868640