Hardware implementation of stochastic spiking neural networks.
Rosselló, Josep L; Canals, Vincent; Morro, Antoni; Oliver, Antoni
2012-08-01
Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.
Status of neural network hardware in high energy physics
NASA Astrophysics Data System (ADS)
Denby, Bruce
2001-08-01
This paper examines the current status of hardware implementations of neural networks in high energy physics experiments, as reflected in the applications presented at ACAT 2000, Fermilab, October, 2000.
Analog hardware for learning neural networks
NASA Technical Reports Server (NTRS)
Eberhardt, Silvio P. (Inventor)
1991-01-01
This is a recurrent or feedforward analog neural network processor having a multi-level neuron array and a synaptic matrix for storing weighted analog values of synaptic connection strengths which is characterized by temporarily changing one connection strength at a time to determine its effect on system output relative to the desired target. That connection strength is then adjusted based on the effect, whereby the processor is taught the correct response to training examples connection by connection.
Artificial Neural Network with Hardware Training and Hardware Refresh
NASA Technical Reports Server (NTRS)
Duong, Tuan A. (Inventor)
2003-01-01
A neural network circuit is provided having a plurality of circuits capable of charge storage. Also provided is a plurality of circuits each coupled to at least one of the plurality of charge storage circuits and constructed to generate an output in accordance with a neuron transfer function. Each of a plurality of circuits is coupled to one of the plurality of neuron transfer function circuits and constructed to generate a derivative of the output. A weight update circuit updates the charge storage circuits based upon output from the plurality of transfer function circuits and output from the plurality of derivative circuits. In preferred embodiments, separate training and validation networks share the same set of charge storage circuits and may operate concurrently. The validation network has a separate transfer function circuits each being coupled to the charge storage circuits so as to replicate the training network s coupling of the plurality of charge storage to the plurality of transfer function circuits. The plurality of transfer function circuits may be constructed each having a transconductance amplifier providing differential currents combined to provide an output in accordance with a transfer function. The derivative circuits may have a circuit constructed to generate a biased differential currents combined so as to provide the derivative of the transfer function.
Neural Networks Based Approach to Enhance Space Hardware Reliability
NASA Technical Reports Server (NTRS)
Zebulum, Ricardo S.; Thakoor, Anilkumar; Lu, Thomas; Franco, Lauro; Lin, Tsung Han; McClure, S. S.
2011-01-01
This paper demonstrates the use of Neural Networks as a device modeling tool to increase the reliability analysis accuracy of circuits targeted for space applications. The paper tackles a number of case studies of relevance to the design of Flight hardware. The results show that the proposed technique generates more accurate models than the ones regularly used to model circuits.
Design of coupling resistor networks for neural network hardware
NASA Astrophysics Data System (ADS)
Barkan, Ozdal; Smith, W. R.; Persky, George
1990-06-01
The specification of an artificial neural network includes (1) the transformation relating each neuron's output voltage to its input voltage, and (2) a set of coupling weight factors expressing the input voltage of any neuron as a linear combination of the output voltages of other neurons. In analog VLSI chips for direct hardware implementation of these networks, neurons are often represented by amplifier elements (e.g. operational amplifiers or opamps), and resistors or active transconductances are used to couple signals from the outputs of certain neurons to the inputs of other neurons. Each coupling conductance is proportional to a single, corresponding coupling weight only under the following 'ideal' conditions: (1) each opamp has negligible output impedance, and (2) the input voltage of each opamp is developed across a low-resistance sampling resistor that is not loaded by the opamp itself. By contrast, the output impedance of a practical opamp may not be negligible in comparison to that of the high-fan network that it drives, and the sampling resistances on the opamp inputs cannot be arbitrarily low lest the input voltages be corrupted by unavoidable opamp input voltage offsets.
Fault Tolerant Characteristics of Artificial Neural Network Electronic Hardware
NASA Technical Reports Server (NTRS)
Zee, Frank
1995-01-01
The fault tolerant characteristics of analog-VLSI artificial neural network (with 32 neurons and 532 synapses) chips are studied by exposing them to high energy electrons, high energy protons, and gamma ionizing radiations under biased and unbiased conditions. The biased chips became nonfunctional after receiving a cumulative dose of less than 20 krads, while the unbiased chips only started to show degradation with a cumulative dose of over 100 krads. As the total radiation dose increased, all the components demonstrated graceful degradation. The analog sigmoidal function of the neuron became steeper (increase in gain), current leakage from the synapses progressively shifted the sigmoidal curve, and the digital memory of the synapses and the memory addressing circuits began to gradually fail. From these radiation experiments, we can learn how to modify certain designs of the neural network electronic hardware without using radiation-hardening techniques to increase its reliability and fault tolerance.
Hardware Prototyping of Neural Network based Fetal Electrocardiogram Extraction
NASA Astrophysics Data System (ADS)
Hasan, M. A.; Reaz, M. B. I.
2012-01-01
The aim of this paper is to model the algorithm for Fetal ECG (FECG) extraction from composite abdominal ECG (AECG) using VHDL (Very High Speed Integrated Circuit Hardware Description Language) for FPGA (Field Programmable Gate Array) implementation. Artificial Neural Network that provides efficient and effective ways of separating FECG signal from composite AECG signal has been designed. The proposed method gives an accuracy of 93.7% for R-peak detection in FHR monitoring. The designed VHDL model is synthesized and fitted into Altera's Stratix II EP2S15F484C3 using the Quartus II version 8.0 Web Edition for FPGA implementation.
A hardware implementation of artificial neural networks using field programmable gate arrays
NASA Astrophysics Data System (ADS)
Won, E.
2007-11-01
An artificial neural network algorithm is implemented using a low-cost field programmable gate array hardware. One hidden layer is used in the feed-forward neural network structure in order to discriminate one class of patterns from the other class in real time. In this work, the training of the network is performed in the off-line computing environment and the results of the training are configured to the hardware in order to minimize the latency of the neural computation. With five 8-bit input patterns, six hidden nodes, and one 8-bit output, the implemented hardware neural network makes decisions on a set of input patterns in 11 clock cycles, or less than 200 ns with a 60 MHz clock. The result from the hardware neural computation is well predictable based on the off-line computation. This implementation may be used in level 1 hardware triggers in high energy physics experiments.
Analyzing the scaling of connectivity in neuromorphic hardware and in models of neural networks.
Partzsch, Johannes; Schüffny, René
2011-06-01
In recent years, neuromorphic hardware systems have significantly grown in size. With more and more neurons and synapses integrated in such systems, the neural connectivity and its configurability have become crucial design constraints. To tackle this problem, we introduce a generic extended graph description of connection topologies that allows a systematical analysis of connectivity in both neuromorphic hardware and neural network models. The unifying nature of our approach enables a close exchange between hardware and models. For an existing hardware system, the optimally matched network model can be extracted. Inversely, a hardware architecture may be fitted to a particular model network topology with our description method. As a further strength, the extended graph can be used to quantify the amount of configurability for a certain network topology. This is a hardware design variable that has widely been neglected, mainly because of a missing analysis method. To condense our analysis results, we develop a classification for the scaling complexity of network models and neuromorphic hardware, based on the total number of connections and the configurability. We find a gap between several models and existing hardware, making these hardware systems either impossible or inefficient to use for scaled-up network models. In this respect, our analysis results suggest models with locality in their connections as promising approach for tackling this scaling gap.
2012-11-01
manufacturability and usability . Concerning the former, the devices to be used must consist of materials that are permitted inside a CMOS foundry...ZISC neural networks may be usable to partially replicate some of the anticipated advantages of a memristive device-based hardware neural network...based on ZnxCd1-xS ferroelectric Schottky diodes”, Appl. Phys. Lett., Vol. 82, No. 23, p. 4089, 2003. [9] S. Seo , M. J. Lee, “Reproducible resistance
NASA Astrophysics Data System (ADS)
Prezioso, M.; Merrikh-Bayat, F.; Chakrabarti, B.; Strukov, D.
2016-02-01
Artificial neural networks have been receiving increasing attention due to their superior performance in many information processing tasks. Typically, scaling up the size of the network results in better performance and richer functionality. However, large neural networks are challenging to implement in software and customized hardware are generally required for their practical implementations. In this work, we will discuss our group's recent efforts on the development of such custom hardware circuits, based on hybrid CMOS/memristor circuits, in particular of CMOL variety. We will start by reviewing the basics of memristive devices and of CMOL circuits. We will then discuss our recent progress towards demonstration of hybrid circuits, focusing on the experimental and theoretical results for artificial neural networks based on crossbarintegrated metal oxide memristors. We will conclude presentation with the discussion of the remaining challenges and the most pressing research needs.
NASA Astrophysics Data System (ADS)
Pfeil, Thomas; Jordan, Jakob; Tetzlaff, Tom; Grübl, Andreas; Schemmel, Johannes; Diesmann, Markus; Meier, Karlheinz
2016-04-01
High-level brain function, such as memory, classification, or reasoning, can be realized by means of recurrent networks of simplified model neurons. Analog neuromorphic hardware constitutes a fast and energy-efficient substrate for the implementation of such neural computing architectures in technical applications and neuroscientific research. The functional performance of neural networks is often critically dependent on the level of correlations in the neural activity. In finite networks, correlations are typically inevitable due to shared presynaptic input. Recent theoretical studies have shown that inhibitory feedback, abundant in biological neural networks, can actively suppress these shared-input correlations and thereby enable neurons to fire nearly independently. For networks of spiking neurons, the decorrelating effect of inhibitory feedback has so far been explicitly demonstrated only for homogeneous networks of neurons with linear subthreshold dynamics. Theory, however, suggests that the effect is a general phenomenon, present in any system with sufficient inhibitory feedback, irrespective of the details of the network structure or the neuronal and synaptic properties. Here, we investigate the effect of network heterogeneity on correlations in sparse, random networks of inhibitory neurons with nonlinear, conductance-based synapses. Emulations of these networks on the analog neuromorphic-hardware system Spikey allow us to test the efficiency of decorrelation by inhibitory feedback in the presence of hardware-specific heterogeneities. The configurability of the hardware substrate enables us to modulate the extent of heterogeneity in a systematic manner. We selectively study the effects of shared input and recurrent connections on correlations in membrane potentials and spike trains. Our results confirm that shared-input correlations are actively suppressed by inhibitory feedback also in highly heterogeneous networks exhibiting broad, heavy-tailed firing
Johnston, S P; Prasad, G; Maguire, L; McGinnity, T M
2010-12-01
This paper presents an approach that permits the effective hardware realization of a novel Evolvable Spiking Neural Network (ESNN) paradigm on Field Programmable Gate Arrays (FPGAs). The ESNN possesses a hybrid learning algorithm that consists of a Spike Timing Dependent Plasticity (STDP) mechanism fused with a Genetic Algorithm (GA). The design and implementation direction utilizes the latest advancements in FPGA technology to provide a partitioned hardware/software co-design solution. The approach achieves the maximum FPGA flexibility obtainable for the ESNN paradigm. The algorithm was applied as an embedded intelligent system robotic controller to solve an autonomous navigation and obstacle avoidance problem.
Implementation of neural network hardware based on a floating point operation in an FPGA
NASA Astrophysics Data System (ADS)
Kim, Jeong-Seob; Jung, Seul
2007-12-01
This paper presents a hardware design and implementation of the radial basis function (RBF) neural network (NN) by the hardware description language. Due to its nonlinear characteristics, it is very difficult to implement for a system with integer-based operation. To develop nonlinear functions such sigmoid functions or exponential functions, floating point operations are required. The exponential function is designed based on the 32bit single-precision floating-point format. In addition, to update weights in the network, the back-propagation algorithm is also implemented in the hardware. Most operations are performed in the floating-point based arithmetic unit and accomplished sequentially by the instruction order stored in ROM. The NN is implemented and tested on the Altera FPGA "Cyclone2 EP2C70F672C8" for nonlinear classifications.
Hardware-based artificial neural networks for size, weight, and power constrained platforms
NASA Astrophysics Data System (ADS)
Wysocki, B. T.; McDonald, N. R.; Thiem, C. D.
2014-05-01
A fully parallel, silicon-based artificial neural network (CM1K) built on zero instruction set computer (ZISC) technology was used for change detection and object identification in video data. Fundamental pattern recognition capabilities were demonstrated with reduced neuron numbers utilizing only a few, or in some cases one, neuron per category. This simplified approach was used to validate the utility of few neuron networks for use in applications that necessitate severe size, weight, and power (SWaP) restrictions. The limited resource requirements and massively parallel nature of hardware-based artificial neural networks (ANNs) make them superior to many software approaches in resource limited systems, such as micro-UAVs, mobile sensor platforms, and pocket-sized robots.
Real-time classification of datasets with hardware embedded neuromorphic neural networks.
Bako, Laszlo
2010-05-01
Neuromorphic artificial neural networks attempt to understand the essential computations that take place in the dense networks of interconnected neurons making up the central nervous systems in living creatures. This article demonstrates that artificial spiking neural networks--built to resemble the biological model--encoding information in the timing of single spikes, are capable of computing and learning clusters from realistic data. It shows how a spiking neural network based on spike-time coding can successfully perform unsupervised and supervised clustering on real-world data. A temporal encoding procedure of continuously valued data is developed, together with a hardware implementation oriented new learning rule set. Solutions that make use of embedded soft-core microcontrollers are investigated, to implement some of the most resource-consuming components of the artificial neural network. Details of the implementations are given, with benchmark application evaluation and test bench description. Measurement results are presented, showing real-time and adaptive data processing capabilities, comparing these to related findings in the specific literature.
Large-Scale Simulations of Plastic Neural Networks on Neuromorphic Hardware
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
Large-Scale Simulations of Plastic Neural Networks on Neuromorphic Hardware.
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.
Event management for large scale event-driven digital hardware spiking neural networks.
Caron, Louis-Charles; D'Haene, Michiel; Mailhot, Frédéric; Schrauwen, Benjamin; Rouat, Jean
2013-09-01
The interest in brain-like computation has led to the design of a plethora of innovative neuromorphic systems. Individually, spiking neural networks (SNNs), event-driven simulation and digital hardware neuromorphic systems get a lot of attention. Despite the popularity of event-driven SNNs in software, very few digital hardware architectures are found. This is because existing hardware solutions for event management scale badly with the number of events. This paper introduces the structured heap queue, a pipelined digital hardware data structure, and demonstrates its suitability for event management. The structured heap queue scales gracefully with the number of events, allowing the efficient implementation of large scale digital hardware event-driven SNNs. The scaling is linear for memory, logarithmic for logic resources and constant for processing time. The use of the structured heap queue is demonstrated on a field-programmable gate array (FPGA) with an image segmentation experiment and a SNN of 65,536 neurons and 513,184 synapses. Events can be processed at the rate of 1 every 7 clock cycles and a 406×158 pixel image is segmented in 200 ms.
NASA Astrophysics Data System (ADS)
Karabiber, Fethullah; Vecchio, Pietro; Grassi, Giuseppe
2011-12-01
The Bio-inspired (Bi-i) Cellular Vision System is a computing platform consisting of sensing, array sensing-processing, and digital signal processing. The platform is based on the Cellular Neural/Nonlinear Network (CNN) paradigm. This article presents the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. Each part of the algorithm, along with the corresponding implementation on the hardware platform, is carefully described through the article. The experimental results, carried out for Foreman and Car-phone video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frames/s. Comparisons with existing CNN-based methods show that the conceived approach is more accurate, thus representing a good trade-off between real-time requirements and accuracy.
Electronic hardware implementations of neutral networks
NASA Technical Reports Server (NTRS)
Thakoor, A. P.; Moopenn, A.; Lambe, John; Khanna, S. K.
1987-01-01
This paper examines some of the present work on the development of electronic neural network hardware. In particular, the investigations currently under way at JPL on neural network hardware implementations based on custom VLSI technology, novel thin film materials, and an analog-digital hybrid architecture are reviewed. The availability of such hardware will greatly benefit and enhance the present intense research effort on the potential computational capabilities of highly parallel systems based on neural network models.
Li, Yongtao; Kurata, Shuhei; Morita, Shogo; Shimizu, So; Munetaka, Daigo; Nara, Shigetoshi
2008-09-01
Originating from a viewpoint that complex/chaotic dynamics would play an important role in biological system including brains, chaotic dynamics introduced in a recurrent neural network was applied to control. The results of computer experiment was successfully implemented into a novel autonomous roving robot, which can only catch rough target information with uncertainty by a few sensors. It was employed to solve practical two-dimensional mazes using adaptive neural dynamics generated by the recurrent neural network in which four prototype simple motions are embedded. Adaptive switching of a system parameter in the neural network results in stationary motion or chaotic motion depending on dynamical situations. The results of hardware implementation and practical experiment using it show that, in given two-dimensional mazes, the robot can successfully avoid obstacles and reach the target. Therefore, we believe that chaotic dynamics has novel potential capability in controlling, and could be utilized to practical engineering application.
Carrillo, Snaider; Harkin, Jim; McDaid, Liam; Pande, Sandeep; Cawley, Seamus; McGinley, Brian; Morgan, Fearghal
2012-09-01
The brain is highly efficient in how it processes information and tolerates faults. Arguably, the basic processing units are neurons and synapses that are interconnected in a complex pattern. Computer scientists and engineers aim to harness this efficiency and build artificial neural systems that can emulate the key information processing principles of the brain. However, existing approaches cannot provide the dense interconnect for the billions of neurons and synapses that are required. Recently a reconfigurable and biologically inspired paradigm based on network-on-chip (NoC) and spiking neural networks (SNNs) has been proposed as a new method of realising an efficient, robust computing platform. However, the use of the NoC as an interconnection fabric for large-scale SNNs demands a good trade-off between scalability, throughput, neuron/synapse ratio and power consumption. This paper presents a novel traffic-aware, adaptive NoC router, which forms part of a proposed embedded mixed-signal SNN architecture called EMBRACE (EMulating Biologically-inspiRed ArChitectures in hardwarE). The proposed adaptive NoC router provides the inter-neuron connectivity for EMBRACE, maintaining router communication and avoiding dropped router packets by adapting to router traffic congestion. Results are presented on throughput, power and area performance analysis of the adaptive router using a 90 nm CMOS technology which outperforms existing NoCs in this domain. The adaptive behaviour of the router is also verified on a Stratix II FPGA implementation of a 4 × 2 router array with real-time traffic congestion. The presented results demonstrate the feasibility of using the proposed adaptive NoC router within the EMBRACE architecture to realise large-scale SNNs on embedded hardware.
NASA Technical Reports Server (NTRS)
Thakoor, Anil
1990-01-01
Viewgraphs on electronic neural networks for space station are presented. Topics covered include: electronic neural networks; electronic implementations; VLSI/thin film hybrid hardware for neurocomputing; computations with analog parallel processing; features of neuroprocessors; applications of neuroprocessors; neural network hardware for terrain trafficability determination; a dedicated processor for path planning; neural network system interface; neural network for robotic control; error backpropagation algorithm for learning; resource allocation matrix; global optimization neuroprocessor; and electrically programmable read only thin-film synaptic array.
NASA Astrophysics Data System (ADS)
Hotta, Hirohisa; Murahashi, Yoshimitsu; Doki, Shinji; Okuma, Shigeru
In order to ride on the strength of paralell operation a feature of neural network, it is preferable that all neuron is implemented on hardware. Formerly, we combine Neural Network and ΔΣ modulation, which is a method of converting to 1bit pulsed signal. Then we succeeded to configurate “a Pulsed Neural Network based on ΔΣ modulation(DSM-PNN)", which keep the circuit scale as same as to operate precisely. In last paper, we proposed hardware implementation methods of DSM-PNN with GHA learning rule and show its availability in linear operation. However, since neural networks are characterized by nonlinear map, signals needs to be treated with sufficient precision, also in nonlinear operation. In this paper, in order to shows that the 1-bit signal processing by DSM-PNN can be available, even when it includes nonlinear operation, we proposed the technique of realizing algorithm of ICA including nonlinear operation in DSM-PNN and confirm the performance of it.
Sign Language Recognition System using Neural Network for Digital Hardware Implementation
NASA Astrophysics Data System (ADS)
Vargas, Lorena P.; Barba, Leiner; Torres, C. O.; Mattos, L.
2011-01-01
This work presents an image pattern recognition system using neural network for the identification of sign language to deaf people. The system has several stored image that show the specific symbol in this kind of language, which is employed to teach a multilayer neural network using a back propagation algorithm. Initially, the images are processed to adapt them and to improve the performance of discriminating of the network, including in this process of filtering, reduction and elimination noise algorithms as well as edge detection. The system is evaluated using the signs without including movement in their representation.
NASA Astrophysics Data System (ADS)
Zoev, I. V.; Beresnev, A. P.; Mytsko, E. A.; Malchukov, A. N.
2017-02-01
An important aspect of modern automation is machine learning. Specifically, neural networks are used for environment analysis and decision making based on available data. This article covers the most frequently performed operations on floating-point numbers in artificial neural networks. Also, a selection of the optimum value of the bit to 14-bit floating-point numbers for implementation on FPGAs was submitted based on the modern architecture of integrated circuits. The description of the floating-point multiplication (multiplier) algorithm was presented. In addition, features of the addition (adder) and subtraction (subtractor) operations were described in the article. Furthermore, operations for such variety of neural networks as a convolution network - mathematical comparison of a floating point (‘less than’ and ‘greater than or equal’) were presented. In conclusion, the comparison with calculating units of Atlera was made.
Standard cell-based implementation of a digital optoelectronic neural-network hardware.
Maier, K D; Beckstein, C; Blickhan, R; Erhard, W
2001-03-10
A standard cell-based implementation of a digital optoelectronic neural-network architecture is presented. The overall structure of the multilayer perceptron network that was used, the optoelectronic interconnection system between the layers, and all components required in each layer are defined. The design process from VHDL-based modeling from synthesis and partly automatic placing and routing to the final editing of one layer of the circuit of the multilayer perceptrons are described. A suitable approach for the standard cell-based design of optoelectronic systems is presented, and shortcomings of the design tool that was used are pointed out. The layout for the microelectronic circuit of one layer in a multilayer perceptron neural network with a performance potential 1 magnitude higher than neural networks that are purely electronic based has been successfully designed.
Standard Cell-Based Implementation of a Digital Optoelectronic Neural-Network Hardware
NASA Astrophysics Data System (ADS)
Maier, Klaus D.; Beckstein, Clemens; Blickhan, Reinhard; Erhard, Werner
2001-03-01
A standard cell-based implementation of a digital optoelectronic neural-network architecture is presented. The overall structure of the multilayer perceptron network that was used, the optoelectronic interconnection system between the layers, and all components required in each layer are defined. The design process from VHDL-based modeling from synthesis and partly automatic placing and routing to the final editing of one layer of the circuit of the multilayer perceptrons are described. A suitable approach for the standard cell-based design of optoelectronic systems is presented, and shortcomings of the design tool that was used are pointed out. The layout for the microelectronic circuit of one layer in a multilayer perceptron neural network with a performance potential 1 magnitude higher than neural networks that are purely electronic based has been successfully designed.
Comparison of GPU- and CPU-implementations of mean-firing rate neural networks on parallel hardware.
Dinkelbach, Helge Ülo; Vitay, Julien; Beuth, Frederik; Hamker, Fred H
2012-01-01
Modern parallel hardware such as multi-core processors (CPUs) and graphics processing units (GPUs) have a high computational power which can be greatly beneficial to the simulation of large-scale neural networks. Over the past years, a number of efforts have focused on developing parallel algorithms and simulators best suited for the simulation of spiking neural models. In this article, we aim at investigating the advantages and drawbacks of the CPU and GPU parallelization of mean-firing rate neurons, widely used in systems-level computational neuroscience. By comparing OpenMP, CUDA and OpenCL implementations towards a serial CPU implementation, we show that GPUs are better suited than CPUs for the simulation of very large networks, but that smaller networks would benefit more from an OpenMP implementation. As this performance strongly depends on data organization, we analyze the impact of various factors such as data structure, memory alignment and floating precision. We then discuss the suitability of the different hardware depending on the networks' size and connectivity, as random or sparse connectivities in mean-firing rate networks tend to break parallel performance on GPUs due to the violation of coalescence.
NASA Astrophysics Data System (ADS)
González, M.; Lamela, H.; Jiménez, M.; Gimeno, J.; Ruiz-Llata, M.
2007-04-01
In this paper we present the scheme for a control circuit used in an image processing system which is to be implemented in a neural network which has a high level of connectivity and reconfiguration of neurons for integration and trigger based on the Address-Event Representation. This scheme will be employed as a pre-processing stage for a vision system which employs as its core processing an Optical Broadcast Neural Network (OBNN). [Optical Engineering letters 42 (9), 2488(2003)]. The proposed vision system allows the possibility to introduce patterns from any acquisition system of images, for posterior processing.
Mahdiani, Hamid Reza; Fakhraie, Sied Mehdi; Lucas, Caro
2012-08-01
Reliability should be identified as the most important challenge in future nano-scale very large scale integration (VLSI) implementation technologies for the development of complex integrated systems. Normally, fault tolerance (FT) in a conventional system is achieved by increasing its redundancy, which also implies higher implementation costs and lower performance that sometimes makes it even infeasible. In contrast to custom approaches, a new class of applications is categorized in this paper, which is inherently capable of absorbing some degrees of vulnerability and providing FT based on their natural properties. Neural networks are good indicators of imprecision-tolerant applications. We have also proposed a new class of FT techniques called relaxed fault-tolerant (RFT) techniques which are developed for VLSI implementation of imprecision-tolerant applications. The main advantage of RFT techniques with respect to traditional FT solutions is that they exploit inherent FT of different applications to reduce their implementation costs while improving their performance. To show the applicability as well as the efficiency of the RFT method, the experimental results for implementation of a face-recognition computationally intensive neural network and its corresponding RFT realization are presented in this paper. The results demonstrate promising higher performance of artificial neural network VLSI solutions for complex applications in faulty nano-scale implementation environments.
Autonomous target tracking of UAVs based on low-power neural network hardware
NASA Astrophysics Data System (ADS)
Yang, Wei; Jin, Zhanpeng; Thiem, Clare; Wysocki, Bryant; Shen, Dan; Chen, Genshe
2014-05-01
Detecting and identifying targets in unmanned aerial vehicle (UAV) images and videos have been challenging problems due to various types of image distortion. Moreover, the significantly high processing overhead of existing image/video processing techniques and the limited computing resources available on UAVs force most of the processing tasks to be performed by the ground control station (GCS) in an off-line manner. In order to achieve fast and autonomous target identification on UAVs, it is thus imperative to investigate novel processing paradigms that can fulfill the real-time processing requirements, while fitting the size, weight, and power (SWaP) constrained environment. In this paper, we present a new autonomous target identification approach on UAVs, leveraging the emerging neuromorphic hardware which is capable of massively parallel pattern recognition processing and demands only a limited level of power consumption. A proof-of-concept prototype was developed based on a micro-UAV platform (Parrot AR Drone) and the CogniMemTMneural network chip, for processing the video data acquired from a UAV camera on the y. The aim of this study was to demonstrate the feasibility and potential of incorporating emerging neuromorphic hardware into next-generation UAVs and their superior performance and power advantages towards the real-time, autonomous target tracking.
Optimization of a hardware implementation for pulse coupled neural networks for image applications
NASA Astrophysics Data System (ADS)
Gimeno Sarciada, Jesús; Lamela Rivera, Horacio; Warde, Cardinal
2010-04-01
Pulse Coupled Neural Networks are a very useful tool for image processing and visual applications, since it has the advantages of being invariant to image changes as rotation, scale, or certain distortion. Among other characteristics, the PCNN changes a given image input into a temporal representation which can be easily later analyzed for pattern recognition. The structure of a PCNN though, makes it necessary to determine all of its parameters very carefully in order to function optimally, so that the responses to the kind of inputs it will be subjected are clearly discriminated allowing for an easy and fast post-processing yielding useful results. This tweaking of the system is a taxing process. In this paper we analyze and compare two methods for modeling PCNNs. A purely mathematical model is programmed and a similar circuital model is also designed. Both are then used to determine the optimal values of the several parameters of a PCNN: gain, threshold, time constants for feed-in and threshold and linking leading to an optimal design for image recognition. The results are compared for usefulness, accuracy and speed, as well as the performance and time requirements for fast and easy design, thus providing a tool for future ease of management of a PCNN for different tasks.
NASA Astrophysics Data System (ADS)
Chen, Jun; Shibata, Tadashi
2007-04-01
Pulse-coupled neural networks (PCNNs) are biologically inspired algorithms that have been shown to be highly effective for image feature generation. However, conventional PCNNs are software-oriented algorithms that are too complicated to implement as very-large-scale integration (VLSI) hardware. To employ PCNNs in image-feature-generation VLSIs, a hardware-implementation-friendly PCNN is proposed here. By introducing the concepts of exponentially decaying output and a one-branch dendritic tree, the new PCNN eliminates the large number of convolution operators and floating-point multipliers in conventional PCNNs without compromising its performance at image feature generation. As an analog VLSI implementation of the new PCNN, an image-feature-generation circuit is proposed. By employing floating-gate metal-oxide-semiconductor (MOS) technology, the circuit achieves a full voltage-mode implementation of the PCNN in a compact structure. Inheriting the merits of the PCNN, the circuit is capable of generating rotation-independent and translation-independent features for input patterns, which has been verified by SPICE simulation.
NASA Astrophysics Data System (ADS)
Mitchell, Kyle; Ebel, William J.; Watkins, Steve E.
2009-11-01
Artificial neural networks are studied for use in estimating strain in extrinsic Fabry-Pérot interferometric sensors. These networks can require large memory spaces and a large number of calculations for implementation. We describe a modified neural network solution that is suitable for implementation on relatively low cost, low-power hardware. Moreover, we give strain estimates resulting from an implementation of the artificial neural network algorithm on an 8-bit 8051 processor with 64 kbytes of memory. For example, one of our results shows that for 2048 samples of the transmittance signal, the presented neural network algorithm requires around 24,622 floating point multiplies and 35,835 adds, and where the data and algorithm fit within the 64-kbyte memory.
1994-11-01
This report addresses the functional behavior of Cellular Neural Networks (CNN). The impact of variable convergence times on the proper operation of...The report discusses the new fault model, presents the algorithmic procedures and shows simulated testing results. Cellular neural Networks , Testing.
A new wide range Euclidean distance circuit for neural network hardware implementations.
Gopalan, A; Titus, A H
2003-01-01
In this paper, we describe an analog very large-scale integration (VLSI) implementation of a wide range Euclidean distance computation circuit - the key element of many synapse circuits. This circuit is essentially a wide-range absolute value circuit that is designed to be as small as possible (80 /spl times/ 76 /spl mu/m) in order to achieve maximum synapse density while maintaining a wide range of operation (0.5 to 4.5 V) and low power consumption (less than 200 /spl mu/W). The circuit has been fabricated in 1.5-/spl mu/m technology through MOSIS. We present simulated and experimental results of the circuit, and compare these results. Ultimately, this circuit is intended for use as part of a high-density hardware implementation of a self-organizing map (SOM). We describe how this circuit can be used as part of the SOM and how the SOM is going to be used as part of a larger bio-inspired vision system based on the octopus visual system.
1990-01-01
FUNDING NUMBERS PROGRAM PROJECT TASK WORK UNIT ELEMENT NO. NO. NO. ACCESSION NO 11 TITLE (Include Security Classification) NEURAL NETWORKS 12. PERSONAL...SUB-GROUP Neural Networks Optical Architectures Nonlinear Optics Adaptation 19. ABSTRACT (Continue on reverse if necessary and identify by block number...341i Y C-odes , lo iii/(iv blank) 1. INTRODUCTION Neural networks are a type of distributed processing system [1
Design and Hardware Implementation of Neural Systems.
1991-12-15
orientation specificity in a neuron network for visual image decomposition. AIP Conference on Neuronal Networks for Computing, Snowbird, Utah, April, 1989...P. and Blackman, D. Orientation tuning and orientation specificity in a neuron network for visual image decomposition. AIP Conference on Neuronal ... Networks for Computing, Snowbird, Utah, April, 1989. Mueller, P., Neural computation of pattern primitives, (Abstract) AIP Conference, Snowbird, Utah
NASA Astrophysics Data System (ADS)
Wang, I.-Ting; Chang, Chih-Cheng; Chiu, Li-Wen; Chou, Teyuh; Hou, Tuo-Hung
2016-09-01
The implementation of highly anticipated hardware neural networks (HNNs) hinges largely on the successful development of a low-power, high-density, and reliable analog electronic synaptic array. In this study, we demonstrate a two-layer Ta/TaO x /TiO2/Ti cross-point synaptic array that emulates the high-density three-dimensional network architecture of human brains. Excellent uniformity and reproducibility among intralayer and interlayer cells were realized. Moreover, at least 50 analog synaptic weight states could be precisely controlled with minimal drifting during a cycling endurance test of 5000 training pulses at an operating voltage of 3 V. We also propose a new state-independent bipolar-pulse-training scheme to improve the linearity of weight updates. The improved linearity considerably enhances the fault tolerance of HNNs, thus improving the training accuracy.
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. Neural 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
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.
Optical Neural Network Classifier Architectures
1998-04-01
We present an adaptive opto-electronic neural network hardware architecture capable of exploiting parallel optics to realize real-time processing and...function neural network based on a previously demonstrated binary-input version. The greyscale-input capability broadens the range of applications for...a reduced feature set of multiwavelet images to improve training times and discrimination capability of the neural network . The design uses a joint
2D neural hardware versus 3D biological ones
Beiu, V.
1998-12-31
This paper will present important limitations of hardware neural nets as opposed to biological neural nets (i.e. the real ones). The author starts by discussing neural structures and their biological inspirations, while mentioning the simplifications leading to artificial neural nets. Going further, the focus will be on hardware constraints. The author will present recent results for three different alternatives of implementing neural networks: digital, threshold gate, and analog, while the area and the delay will be related to neurons' fan-in and weights' precision. Based on all of these, it will be shown why hardware implementations cannot cope with their biological inspiration with respect to their power of computation: the mapping onto silicon lacking the third dimension of biological nets. This translates into reduced fan-in, and leads to reduced precision. The main conclusion is that one is faced with the following alternatives: (1) try to cope with the limitations imposed by silicon, by speeding up the computation of the elementary silicon neurons; (2) investigate solutions which would allow one to use the third dimension, e.g. using optical interconnections.
NASA Astrophysics Data System (ADS)
Schwindling, Jerome
2010-04-01
This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p.) corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.
High-performance neural networks. [Neural computers
Dress, W.B.
1987-06-01
The new Forth hardware architectures offer an intermediate solution to high-performance neural networks while the theory and programming details of neural networks for synthetic intelligence are developed. This approach has been used successfully to determine the parameters and run the resulting network for a synthetic insect consisting of a 200-node ''brain'' with 1760 interconnections. Both the insect's environment and its sensor input have thus far been simulated. However, the frequency-coded nature of the Browning network allows easy replacement of the simulated sensors by real-world counterparts.
Neural networks for triggering
Denby, B. ); Campbell, M. ); Bedeschi, F. ); Chriss, N.; Bowers, C. ); Nesti, F. )
1990-01-01
Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab.
Neural Network Function Classifier
2003-02-07
neural network sets. Each of the neural networks in a particular set is trained to recognize a particular data set type. The best function representation of the data set is determined from the neural network output. The system comprises sets of trained neural networks having neural networks trained to identify different types of data. The number of neural networks within each neural network set will depend on the number of function types that are represented. The system further comprises
Neural Network Retinal Model Real Time Implementation
1992-09-02
addresses the specific needs of vision processing. The goal of this SBIR Phase I project has been to take a significant neural network vision...application and to map it onto dedicated hardware for real time implementation. The neural network was already demonstrated using software simulation on a...general purpose computer. During Phase 1, HNC took a neural network model of the retina and, using HNC’s Vision Processor (ViP) prototype hardware
Training Neural Networks with Weight Constraints
1993-03-01
Hardware implementation of artificial neural networks imposes a variety of constraints. Finite weight magnitudes exist in both digital and analog...optimizing a network with weight constraints. Comparisons are made to the backpropagation training algorithm for networks with both unconstrained and hard-limited weight magnitudes. Neural networks , Analog, Digital, Stochastic
Rostro-Gonzalez, Horacio; Cessac, Bruno; Girau, Bernard; Torres-Huitzil, Cesar
2011-01-01
This paper presents a numerical analysis of the role of asymptotic dynamics in the design of hardware-based implementations of the generalised integrate-and-fire (gIF) neuron models. These proposed implementations are based on extensions of the discrete-time spiking neuron model, which was introduced by Soula et al., and have been implemented on Field Programmable Gate Array (FPGA) devices using fixed-point arithmetic. Mathematical studies conducted by Cessac have evidenced the existence of three main regimes (neural death, periodic and chaotic regimes) in the activity of such neuron models. These activity regimes are characterised in hardware by considering a precision analysis in the design of an architecture for an FPGA-based implementation. The proposed approach, although based on gIF neuron models and FPGA hardware, can be extended to more complex neuron models as well as to different in silico implementations.
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.
1993-07-01
basic useful theorems and general rules which apply to neural networks (in ’Overview of Neural Network Theory’), studies of training time as the...The Neural Network , Bayes- Gaussian, and k-Nearest Neighbor Classifiers’), an analysis of fuzzy logic and its relationship to neural network (in ’Fuzzy
ANNarchy: a code generation approach to neural simulations on parallel hardware
Vitay, Julien; Dinkelbach, Helge Ü.; Hamker, Fred H.
2015-01-01
Many modern neural simulators focus on the simulation of networks of spiking neurons on parallel hardware. Another important framework in computational neuroscience, rate-coded neural networks, is mostly difficult or impossible to implement using these simulators. We present here the ANNarchy (Artificial Neural Networks architect) neural simulator, which allows to easily define and simulate rate-coded and spiking networks, as well as combinations of both. The interface in Python has been designed to be close to the PyNN interface, while the definition of neuron and synapse models can be specified using an equation-oriented mathematical description similar to the Brian neural simulator. This information is used to generate C++ code that will efficiently perform the simulation on the chosen parallel hardware (multi-core system or graphical processing unit). Several numerical methods are available to transform ordinary differential equations into an efficient C++code. We compare the parallel performance of the simulator to existing solutions. PMID:26283957
VLSI implementation of neural networks.
Wilamowski, B M; Binfet, J; Kaynak, M O
2000-06-01
Currently, fuzzy controllers are the most popular choice for hardware implementation of complex control surfaces because they are easy to design. Neural controllers are more complex and hard to train, but provide an outstanding control surface with much less error than that of a fuzzy controller. There are also some problems that have to be solved before the networks can be implemented on VLSI chips. First, an approximation function needs to be developed because CMOS neural networks have an activation function different than any function used in neural network software. Next, this function has to be used to train the network. Finally, the last problem for VLSI designers is the quantization effect caused by discrete values of the channel length (L) and width (W) of MOS transistor geometries. Two neural networks were designed in 1.5 microm technology. Using adequate approximation functions solved the problem of activation function. With this approach, trained networks were characterized by very small errors. Unfortunately, when the weights were quantized, errors were increased by an order of magnitude. However, even though the errors were enlarged, the results obtained from neural network hardware implementations were superior to the results obtained with fuzzy system approach.
Generalized classifier neural network.
Ozyildirim, Buse Melis; Avci, Mutlu
2013-03-01
In this work a new radial basis function based classification neural network named as generalized classifier neural network, is proposed. The proposed generalized classifier neural network has five layers, unlike other radial basis function based neural networks such as generalized regression neural network and probabilistic neural network. They are input, pattern, summation, normalization and output layers. In addition to topological difference, the proposed neural network has gradient descent based optimization of smoothing parameter approach and diverge effect term added calculation improvements. Diverge effect term is an improvement on summation layer calculation to supply additional separation ability and flexibility. Performance of generalized classifier neural network is compared with that of the probabilistic neural network, multilayer perceptron algorithm and radial basis function neural network on 9 different data sets and with that of generalized regression neural network on 3 different data sets include only two classes in MATLAB environment. Better classification performance up to %89 is observed. Improved classification performances proved the effectivity of the proposed neural network.
Nonlinear Neural Network Oscillator.
A nonlinear oscillator (10) includes a neural network (12) having at least one output (12a) for outputting a one dimensional vector. The neural ... neural network and the input of the input layer for modifying a magnitude and/or a polarity of the one dimensional output vector prior to the sample of...first or a second direction. Connection weights of the neural network are trained on a deterministic sequence of data from a chaotic source or may be a
Neural Networks for Flight Control
NASA Technical Reports Server (NTRS)
Jorgensen, Charles C.
1996-01-01
Neural networks are being developed at NASA Ames Research Center to permit real-time adaptive control of time varying nonlinear systems, enhance the fault-tolerance of mission hardware, and permit online system reconfiguration. In general, the problem of controlling time varying nonlinear systems with unknown structures has not been solved. Adaptive neural control techniques show considerable promise and are being applied to technical challenges including automated docking of spacecraft, dynamic balancing of the space station centrifuge, online reconfiguration of damaged aircraft, and reducing cost of new air and spacecraft designs. Our experiences have shown that neural network algorithms solved certain problems that conventional control methods have been unable to effectively address. These include damage mitigation in nonlinear reconfiguration flight control, early performance estimation of new aircraft designs, compensation for damaged planetary mission hardware by using redundant manipulator capability, and space sensor platform stabilization. This presentation explored these developments in the context of neural network control theory. The discussion began with an overview of why neural control has proven attractive for NASA application domains. The more important issues in control system development were then discussed with references to significant technical advances in the literature. Examples of how these methods have been applied were given, followed by projections of emerging application needs and directions.
A building block for hardware belief networks
Behin-Aein, Behtash; Diep, Vinh; Datta, Supriyo
2016-01-01
Belief networks represent a powerful approach to problems involving probabilistic inference, but much of the work in this area is software based utilizing standard deterministic hardware based on the transistor which provides the gain and directionality needed to interconnect billions of them into useful networks. This paper proposes a transistor like device that could provide an analogous building block for probabilistic networks. We present two proof-of-concept examples of belief networks, one reciprocal and one non-reciprocal, implemented using the proposed device which is simulated using experimentally benchmarked models. PMID:27443521
Neural Network Hurricane Tracker
1998-05-27
data about the hurricane and supplying the data to a trained neural network for yielding a predicted path for the hurricane. The system further includes...a device for displaying the predicted path of the hurricane. A method for using and training the neural network in the system is described. In the...method, the neural network is trained using information about hurricanes in a specific geographical area maintained in a database. The training involves
1991-01-01
N00014-87-K-0377 TITLE: "Studies in Neural Networks " fl.U Q l~~izie JUL 021991 "" " F.: L9’CO37 "I! c-1(.d Contract No.: N00014-87-K-0377 Final...34) have been very useful, both in understanding the dynamics of neural networks and in engineering networks to perform particular tasks. We have noted...understanding more complex network computation. Interest in applying ideas from biological neural networks to real problems of engineering raises the issues of
Low-power hardware for neural spike compression in BMIs.
Lapolli, Ângelo C; Coppa, Bertrand; Héliot, Rodolphe
2013-01-01
Within brain-machine interface systems, cortically implanted microelectrode arrays and associated hardware have a low-power budget for data sampling, processing, and transmission. Recent studies have shown the feasibility of data transmission rate reduction using compressed sensing on detected neural spikes. They provide power savings while maintaining clustering and classification abilities. We propose and analyze here a low-power hardware implementation for spike detection and compression. The resulting integrated circuit, designed in CMOS 65 nm technology, consumes 2.83 µW and provides 97% of data rate reduction.
Multispectral image fusion using neural networks
NASA Technical Reports Server (NTRS)
Kagel, J. H.; Platt, C. A.; Donaven, T. W.; Samstad, E. A.
1990-01-01
A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard, a circuit card assembly, and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations, results, and a description of the prototype system are presented.
Multispectral-image fusion using neural networks
NASA Astrophysics Data System (ADS)
Kagel, Joseph H.; Platt, C. A.; Donaven, T. W.; Samstad, Eric A.
1990-08-01
A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard a circuit card assembly and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations results and a description of the prototype system are presented. 1.
Fiber optic Adaline neural networks
NASA Astrophysics Data System (ADS)
Ghosh, Anjan K.; Trepka, Jim; Paparao, Palacharla
1993-02-01
Optoelectronic realization of adaptive filters and equalizers using fiber optic tapped delay lines and spatial light modulators has been discussed recently. We describe the design of a single layer fiber optic Adaline neural network which can be used as a bit pattern classifier. In our realization we employ as few electronic devices as possible and use optical computation to utilize the advantages of optics in processing speed, parallelism, and interconnection. The new optical neural network described in this paper is designed for optical processing of guided lightwave signals, not electronic signals. We analyzed the convergence or learning characteristics of the optically implemented Adaline in the presence of errors in the hardware, and we studied methods for improving the convergence rate of the Adaline.
James, Conrad D.; Aimone, James B.; Miner, Nadine E.; ...
2017-01-04
In this study, biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classesmore » such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.« less
James, Conrad D.; Aimone, James B.; Miner, Nadine E.; Vineyard, Craig M.; Rothganger, Fredrick H.; Carlson, Kristofor D.; Mulder, Samuel A.; Draelos, Timothy J.; Faust, Aleksandra; Marinella, Matthew J.; Naegle, John H.; Plimpton, Steven J.
2017-01-01
Biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classes such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.
Probabilistic Analysis of Neural Networks
1990-11-26
provide an understanding of the basic mechanisms of learning and recognition in neural networks . The main areas of progress were analysis of neural ... networks models, study of network connectivity, and investigation of computer network theory.
Learning in Neural Networks: VLSI Implementation Strategies
NASA Technical Reports Server (NTRS)
Duong, Tuan Anh
1995-01-01
Fully-parallel hardware neural network implementations may be applied to high-speed recognition, classification, and mapping tasks in areas such as vision, or can be used as low-cost self-contained units for tasks such as error detection in mechanical systems (e.g. autos). Learning is required not only to satisfy application requirements, but also to overcome hardware-imposed limitations such as reduced dynamic range of connections.
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.
Critical Branching Neural Networks
ERIC Educational Resources Information Center
Kello, Christopher T.
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…
1991-05-01
capture underlying relationships directly from observed behavior is one of the primary capabilities of neural networks. 29 Back P’ropagation Approximailon...model complex behavior patterns. Particularly in areas traditionally addressed by regression and other functional based techniques, neural networks...to.be determined directly from the observed behavior of a system or sample of individuals. This ability should prove important in personnel analysis and
Anderson, J.A.; Markman, A.B.; Viscuso, S.R.; Wisniewski, E.J.
1988-09-01
Neural networks ''compute'' though not in the way that traditional computers do. One must accept their weaknesses to use their strengths. The authors present several applications of a particular non-linear network (the BSB model) to illustrate some of the peculiarities inherent in this architecture.
Ultra-low noise miniaturized neural amplifier with hardware averaging
NASA Astrophysics Data System (ADS)
Dweiri, Yazan M.; Eggers, Thomas; McCallum, Grant; Durand, Dominique M.
2015-08-01
Objective. Peripheral nerves carry neural signals that could be used to control hybrid bionic systems. Cuff electrodes provide a robust and stable interface but the recorded signal amplitude is small (<3 μVrms 700 Hz-7 kHz), thereby requiring a baseline noise of less than 1 μVrms for a useful signal-to-noise ratio (SNR). Flat interface nerve electrode (FINE) contacts alone generate thermal noise of at least 0.5 μVrms therefore the amplifier should add as little noise as possible. Since mainstream neural amplifiers have a baseline noise of 2 μVrms or higher, novel designs are required. Approach. Here we apply the concept of hardware averaging to nerve recordings obtained with cuff electrodes. An optimization procedure is developed to minimize noise and power simultaneously. The novel design was based on existing neural amplifiers (Intan Technologies, LLC) and is validated with signals obtained from the FINE in chronic dog experiments. Main results. We showed that hardware averaging leads to a reduction in the total recording noise by a factor of 1/√N or less depending on the source resistance. Chronic recording of physiological activity with FINE using the presented design showed significant improvement on the recorded baseline noise with at least two parallel operation transconductance amplifiers leading to a 46.1% reduction at N = 8. The functionality of these recordings was quantified by the SNR improvement and shown to be significant for N = 3 or more. The present design was shown to be capable of generating <1.5 μVrms total recording baseline noise when connected to a FINE placed on the sciatic nerve of an awake animal. An algorithm was introduced to find the value of N that can minimize both the power consumption and the noise in order to design a miniaturized ultralow-noise neural amplifier. Significance. These results demonstrate the efficacy of hardware averaging on noise improvement for neural recording with cuff electrodes, and can accommodate the
Electronic device aspects of neural network memories
NASA Technical Reports Server (NTRS)
Lambe, J.; Moopenn, A.; Thakoor, A. P.
1985-01-01
The basic issues related to the electronic implementation of the neural network model (NNM) for content addressable memories are examined. A brief introduction to the principles of the NNM is followed by an analysis of the information storage of the neural network in the form of a binary connection matrix and the recall capability of such matrix memories based on a hardware simulation study. In addition, materials and device architecture issues involved in the future realization of such networks in VLSI-compatible ultrahigh-density memories are considered. A possible space application of such devices would be in the area of large-scale information storage without mechanical devices.
Tomography using neural networks
NASA Astrophysics Data System (ADS)
Demeter, G.
1997-03-01
We have utilized neural networks for fast evaluation of tomographic data on the MT-1M tokamak. The networks have proven useful in providing the parameters of a nonlinear fit to experimental data, producing results in a fraction of the time required for performing the nonlinear fit. Time required for training the networks makes the method worth applying only if a substantial amount of data are to be evaluated.
The Adaptive Kernel Neural Network
1989-10-01
A neural network architecture for clustering and classification is described. The Adaptive Kernel Neural Network (AKNN) is a density estimation...classification layer. The AKNN retains the inherent parallelism common in neural network models. Its relationship to the kernel estimator allows the network to
Hyperbolic Hopfield neural networks.
Kobayashi, M
2013-02-01
In recent years, several neural networks using Clifford algebra have been studied. Clifford algebra is also called geometric algebra. Complex-valued Hopfield neural networks (CHNNs) are the most popular neural networks using Clifford algebra. The aim of this brief is to construct hyperbolic HNNs (HHNNs) as an analog of CHNNs. Hyperbolic algebra is a Clifford algebra based on Lorentzian geometry. In this brief, a hyperbolic neuron is defined in a manner analogous to a phasor neuron, which is a typical complex-valued neuron model. HHNNs share common concepts with CHNNs, such as the angle and energy. However, HHNNs and CHNNs are different in several aspects. The states of hyperbolic neurons do not form a circle, and, therefore, the start and end states are not identical. In the quantized version, unlike complex-valued neurons, hyperbolic neurons have an infinite number of states.
Fast curve fitting using neural networks
NASA Astrophysics Data System (ADS)
Bishop, C. M.; Roach, C. M.
1992-10-01
Neural networks provide a new tool for the fast solution of repetitive nonlinear curve fitting problems. In this article we introduce the concept of a neural network, and we show how such networks can be used for fitting functional forms to experimental data. The neural network algorithm is typically much faster than conventional iterative approaches. In addition, further substantial improvements in speed can be obtained by using special purpose hardware implementations of the network, thus making the technique suitable for use in fast real-time applications. The basic concepts are illustrated using a simple example from fusion research, involving the determination of spectral line parameters from measurements of B iv impurity radiation in the COMPASS-C tokamak.
NASA Technical Reports Server (NTRS)
Baram, Yoram
1988-01-01
Nested neural networks, consisting of small interconnected subnetworks, allow for the storage and retrieval of neural state patterns of different sizes. The subnetworks are naturally categorized by layers of corresponding to spatial frequencies in the pattern field. The storage capacity and the error correction capability of the subnetworks generally increase with the degree of connectivity between layers (the nesting degree). Storage of only few subpatterns in each subnetworks results in a vast storage capacity of patterns and subpatterns in the nested network, maintaining high stability and error correction capability.
Neural networks in psychiatry.
Hulshoff Pol, Hilleke; Bullmore, Edward
2013-01-01
Over the past three decades numerous imaging studies have revealed structural and functional brain abnormalities in patients with neuropsychiatric diseases. These structural and functional brain changes are frequently found in multiple, discrete brain areas and may include frontal, temporal, parietal and occipital cortices as well as subcortical brain areas. However, while the structural and functional brain changes in patients are found in anatomically separated areas, these are connected through (long distance) fibers, together forming networks. Thus, instead of representing separate (patho)-physiological entities, these local changes in the brains of patients with psychiatric disorders may in fact represent different parts of the same 'elephant', i.e., the (altered) brain network. Recent developments in quantitative analysis of complex networks, based largely on graph theory, have revealed that the brain's structure and functions have features of complex networks. Here we briefly introduce several recent developments in neural network studies relevant for psychiatry, including from the 2013 special issue on Neural Networks in Psychiatry in European Neuropsychopharmacology. We conclude that new insights will be revealed from the neural network approaches to brain imaging in psychiatry that hold the potential to find causes for psychiatric disorders and (preventive) treatments in the future.
Neural networks counting chimes.
Amit, D J
1988-01-01
It is shown that the ideas that led to neural networks capable of recalling associatively and asynchronously temporal sequences of patterns can be extended to produce a neural network that automatically counts the cardinal number in a sequence of identical external stimuli. The network is explicitly constructed, analyzed, and simulated. Such a network may account for the cognitive effect of the automatic counting of chimes to tell the hour. A more general implication is that different electrophysiological responses to identical stimuli, at certain stages of cortical processing, do not necessarily imply synaptic modification, a la Hebb. Such differences may arise from the fact that consecutive identical inputs find the network in different stages of an active temporal sequence of cognitive states. These types of networks are then situated within a program for the study of cognition, which assigns the detection of meaning as the primary role of attractor neural networks rather than computation, in contrast to the parallel distributed processing attitude to the connectionist project. This interpretation is free of homunculus, as well as from the criticism raised against the cognitive model of symbol manipulation. Computation is then identified as the syntax of temporal sequences of quasi-attractors. PMID:3353371
Evolving Neural Network Pattern Classifiers
1994-05-01
This work investigates the application of evolutionary programming for automatically configuring neural network architectures for pattern...evaluating a multitude of neural network model hypotheses. The evolutionary programming search is augmented with the Solis & Wets random optimization
Mathematical Theory of Neural Networks
1994-08-31
This report provides a summary of the grant work by the principal investigators in the area of neural networks . The topics covered deal with...properties) for nets; and the use of neural networks for the control of nonlinear systems.
Lamela, Horacio; Ruiz-Llata, Marta
2008-04-01
We describe the concept of a vision system based on an optoelectronic hardware neural processor. The proposed system is composed of a pulse coupled neural network (PCNN) preprocessor stage that converts an input image into a temporal pulsed pattern. These pulses are inputs to the optical broadcast neural network (OBNN) processor, which classifies the input pattern between a set of reference patterns based on a pattern matching strategy. The PCNN is to provide immunity to the scale, rotation, and translation of objects in the image. The OBNN provides high parallelism and a high speed hardware neural processor.
Neural Network Communications Signal Processing
1994-08-01
This final technical report describes the research and development- results of the Neural Network Communications Signal Processing (NNCSP) Program...The objectives of the NNCSP program are to: (1) develop and implement a neural network and communications signal processing simulation system for the...purpose of exploring the applicability of neural network technology to communications signal processing; (2) demonstrate several configurations of the
Neural Networks for Speech Application.
1987-11-01
This is a general introduction to the reemerging technology called neural networks , and how these networks may provide an important alternative to...traditional forms of computing in speech applications. Neural networks , sometimes called Artificial Neural Systems (ANS), have shown promise for solving
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.
Improved Autoassociative Neural Networks
NASA Technical Reports Server (NTRS)
Hand, Charles
2003-01-01
Improved autoassociative neural networks, denoted nexi, have been proposed for use in controlling autonomous robots, including mobile exploratory robots of the biomorphic type. In comparison with conventional autoassociative neural networks, nexi would be more complex but more capable in that they could be trained to do more complex tasks. A nexus would use bit weights and simple arithmetic in a manner that would enable training and operation without a central processing unit, programs, weight registers, or large amounts of memory. Only a relatively small amount of memory (to hold the bit weights) and a simple logic application- specific integrated circuit would be needed. A description of autoassociative neural networks is prerequisite to a meaningful description of a nexus. An autoassociative network is a set of neurons that are completely connected in the sense that each neuron receives input from, and sends output to, all the other neurons. (In some instantiations, a neuron could also send output back to its own input terminal.) The state of a neuron is completely determined by the inner product of its inputs with weights associated with its input channel. Setting the weights sets the behavior of the network. The neurons of an autoassociative network are usually regarded as comprising a row or vector. Time is a quantized phenomenon for most autoassociative networks in the sense that time proceeds in discrete steps. At each time step, the row of neurons forms a pattern: some neurons are firing, some are not. Hence, the current state of an autoassociative network can be described with a single binary vector. As time goes by, the network changes the vector. Autoassociative networks move vectors over hyperspace landscapes of possibilities.
NASA Technical Reports Server (NTRS)
Villarreal, James A.
1991-01-01
A whole new arena of computer technologies is now beginning to form. Still in its infancy, neural network technology is a biologically inspired methodology which draws on nature's own cognitive processes. The Software Technology Branch has provided a software tool, Neural Execution and Training System (NETS), to industry, government, and academia to facilitate and expedite the use of this technology. NETS is written in the C programming language and can be executed on a variety of machines. Once a network has been debugged, NETS can produce a C source code which implements the network. This code can then be incorporated into other software systems. Described here are various software projects currently under development with NETS and the anticipated future enhancements to NETS and the technology.
Rule generation from neural networks
Fu, L.
1994-08-01
The neural network approach has proven useful for the development of artificial intelligence systems. However, a disadvantage with this approach is that the knowledge embedded in the neural network is opaque. In this paper, we show how to interpret neural network knowledge in symbolic form. We lay down required definitions for this treatment, formulate the interpretation algorithm, and formally verify its soundness. The main result is a formalized relationship between a neural network and a rule-based system. In addition, it has been demonstrated that the neural network generates rules of better performance than the decision tree approach in noisy conditions. 7 refs.
On sparsely connected optimal neural networks
Beiu, V.; Draghici, S.
1997-10-01
This paper uses two different approaches to show that VLSI- and size-optimal discrete neural networks are obtained for small fan-in values. These have applications to hardware implementations of neural networks, but also reveal an intrinsic limitation of digital VLSI technology: its inability to cope with highly connected structures. The first approach is based on implementing F{sub n,m} functions. The authors show that this class of functions can be implemented in VLSI-optimal (i.e., minimizing AT{sup 2}) neural networks of small constant fan-ins. In order to estimate the area (A) and the delay (T) of such networks, the following cost functions will be used: (i) the connectivity and the number-of-bits for representing the weights and thresholds--for good estimates of the area; and (ii) the fan-ins and the length of the wires--for good approximates of the delay. The second approach is based on implementing Boolean functions for which the classical Shannon`s decomposition can be used. Such a solution has already been used to prove bounds on the size of fan-in 2 neural networks. They will generalize the result presented there to arbitrary fan-in, and prove that the size is minimized by small fan-in values. Finally, a size-optimal neural network of small constant fan-ins will be suggested for F{sub n,m} functions.
Tracking and vertex finding with drift chambers and neural networks
Lindsey, C.
1991-09-01
Finding tracks, track vertices and event vertices with neural networks from drift chamber signals is discussed. Simulated feed-forward neural networks have been trained with back-propagation to give track parameters using Monte Carlo simulated tracks in one case and actual experimental data in another. Effects on network performance of limited weight resolution, noise and drift chamber resolution are given. Possible implementations in hardware are discussed. 7 refs., 10 figs.
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.
Stimulated Photorefractive Optical Neural Networks
1992-12-15
This final report describes research in optical neural networks performed under DARPA sponsorship at Hughes Aircraft Company during the period 1989...in photorefractive crystals. This approach reduces crosstalk and improves the utilization of the optical input device. Successfully implemented neural ... networks include the Perceptron, Bidirectional Associative Memory, and multi-layer backpropagation networks. Up to 104 neurons, 2xl0(7) weights, and
Computational chaos in massively parallel neural networks
NASA Technical Reports Server (NTRS)
Barhen, Jacob; Gulati, Sandeep
1989-01-01
A fundamental issue which directly impacts the scalability of current theoretical neural network models to massively parallel embodiments, in both software as well as hardware, is the inherent and unavoidable concurrent asynchronicity of emerging fine-grained computational ensembles and the possible emergence of chaotic manifestations. Previous analyses attributed dynamical instability to the topology of the interconnection matrix, to parasitic components or to propagation delays. However, researchers have observed the existence of emergent computational chaos in a concurrently asynchronous framework, independent of the network topology. Researcher present a methodology enabling the effective asynchronous operation of large-scale neural networks. Necessary and sufficient conditions guaranteeing concurrent asynchronous convergence are established in terms of contracting operators. Lyapunov exponents are computed formally to characterize the underlying nonlinear dynamics. Simulation results are presented to illustrate network convergence to the correct results, even in the presence of large delays.
NASA Technical Reports Server (NTRS)
1999-01-01
The full complement of EDOMP investigations called for a broad spectrum of flight hardware ranging from commercial items, modified for spaceflight, to custom designed hardware made to meet the unique requirements of testing in the space environment. In addition, baseline data collection before and after spaceflight required numerous items of ground-based hardware. Two basic categories of ground-based hardware were used in EDOMP testing before and after flight: (1) hardware used for medical baseline testing and analysis, and (2) flight-like hardware used both for astronaut training and medical testing. To ensure post-landing data collection, hardware was required at both the Kennedy Space Center (KSC) and the Dryden Flight Research Center (DFRC) landing sites. Items that were very large or sensitive to the rigors of shipping were housed permanently at the landing site test facilities. Therefore, multiple sets of hardware were required to adequately support the prime and backup landing sites plus the Johnson Space Center (JSC) laboratories. Development of flight hardware was a major element of the EDOMP. The challenges included obtaining or developing equipment that met the following criteria: (1) compact (small size and light weight), (2) battery-operated or requiring minimal spacecraft power, (3) sturdy enough to survive the rigors of spaceflight, (4) quiet enough to pass acoustics limitations, (5) shielded and filtered adequately to assure electromagnetic compatibility with spacecraft systems, (6) user-friendly in a microgravity environment, and (7) accurate and efficient operation to meet medical investigative requirements.
Analysis of Simple Neural Networks
1988-12-20
ANALYSIS OF SThlPLE NEURAL NETWORKS Chedsada Chinrungrueng Master’s Report Under the Supervision of Prof. Carlo H. Sequin Department of... Neural Networks 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e. TASK NUMBER 5f. WORK UNIT...and guidJ.nce. I have learned a great deal from his teaching, knowledge, and criti- cism. 1. MOTIVATION ANALYSIS OF SIMPLE NEURAL NETWORKS Chedsada
Neural Networks For Robot Control
2001-04-17
following: (a) Application of artificial neural networks (multi-layer perceptrons, MLPs) for 2D planar robot arm by using the dynamic backpropagation...methods for the adjustment of parameters; and optimization of the architecture; (b) Application of artificial neural networks in controlling closed...studies in controlling dynamic robot arms by using neural networks in real-time process; (2) Research of optimal architectures used in closed-loop systems in order to compare with adaptive and robust control.
Trimaran Resistance Artificial Neural Network
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
Neural Networks, Reliability and Data Analysis
1993-01-01
Neural network technology has been surveyed with the intent of determining the feasibility and impact neural networks may have in the area of...automated reliability tools. Data analysis capabilities of neural networks appear to be very applicable to reliability science due to similar mathematical...tendencies in data.... Neural networks , Reliability, Data analysis, Automated reliability tools, Automated intelligent information processing, Statistical neural network.
[Artificial neural networks in Neurosciences].
Porras Chavarino, Carmen; Salinas Martínez de Lecea, José María
2011-11-01
This article shows that artificial neural networks are used for confirming the relationships between physiological and cognitive changes. Specifically, we explore the influence of a decrease of neurotransmitters on the behaviour of old people in recognition tasks. This artificial neural network recognizes learned patterns. When we change the threshold of activation in some units, the artificial neural network simulates the experimental results of old people in recognition tasks. However, the main contributions of this paper are the design of an artificial neural network and its operation inspired by the nervous system and the way the inputs are coded and the process of orthogonalization of patterns.
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.
NASA Astrophysics Data System (ADS)
Metzler, R.; Kinzel, W.; Kanter, I.
2000-08-01
Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random.
Fast implementation of neural network classification
NASA Astrophysics Data System (ADS)
Seo, Guiwon; Ok, Jiheon; Lee, Chulhee
2013-09-01
Most artificial neural networks use a nonlinear activation function that includes sigmoid and hyperbolic tangent functions. Most artificial networks employ nonlinear functions such as these sigmoid and hyperbolic tangent functions, which incur high complexity costs, particularly during hardware implementation. In this paper, we propose new polynomial approximation methods for nonlinear activation functions that can substantially reduce complexity without sacrificing performance. The proposed approximation methods were applied to pattern classification problems. Experimental results show that the processing time was reduced by up to 50% without any performance degradations in terms of computer simulation.
Dynamic interactions in neural networks
Arbib, M.A. ); Amari, S. )
1989-01-01
The study of neural networks is enjoying a great renaissance, both in computational neuroscience, the development of information processing models of living brains, and in neural computing, the use of neurally inspired concepts in the construction of intelligent machines. This volume presents models and data on the dynamic interactions occurring in the brain, and exhibits the dynamic interactions between research in computational neuroscience and in neural computing. The authors present current research, future trends and open problems.
Technology Assessment of Neural Networks
1989-02-13
Unlike a Von Neumann type of computer which needs to be programmed to carry out an information-processing function, neural networks are promised as...trainable through a series of trials to learn how to process information. An assessment of the current, near-term (1995), and long-term (2010) trends in Neural Networks is given.
Phase Detection Using Neural Networks.
1997-03-10
A likelihood of detecting a reflected signal characterized by phase discontinuities and background noise is enhanced by utilizing neural networks to...identify coherency intervals. The received signal is processed into a predetermined format such as a digital time series. Neural networks perform
Neural network applications in telecommunications
NASA Technical Reports Server (NTRS)
Alspector, Joshua
1994-01-01
Neural network capabilities include automatic and organized handling of complex information, quick adaptation to continuously changing environments, nonlinear modeling, and parallel implementation. This viewgraph presentation presents Bellcore work on applications, learning chip computational function, learning system block diagram, neural network equalization, broadband access control, calling-card fraud detection, software reliability prediction, and conclusions.
Neural Networks for the Beginner.
ERIC Educational Resources Information Center
Snyder, Robin M.
Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…
Design of neural networks for classification of remotely sensed imagery
NASA Technical Reports Server (NTRS)
Chettri, Samir R.; Cromp, Robert F.; Birmingham, Mark
1992-01-01
Classification accuracies of a backpropagation neural network are discussed and compared with a maximum likelihood classifier (MLC) with multivariate normal class models. We have found that, because of its nonparametric nature, the neural network outperforms the MLC in this area. In addition, we discuss techniques for constructing optimal neural nets on parallel hardware like the MasPar MP-1 currently at GSFC. Other important discussions are centered around training and classification times of the two methods, and sensitivity to the training data. Finally, we discuss future work in the area of classification and neural nets.
Experimental fault characterization of a neural network
NASA Technical Reports Server (NTRS)
Tan, Chang-Huong
1990-01-01
The effects of a variety of faults on a neural network is quantified via simulation. The neural network consists of a single-layered clustering network and a three-layered classification network. The percentage of vectors mistagged by the clustering network, the percentage of vectors misclassified by the classification network, the time taken for the network to stabilize, and the output values are all measured. The results show that both transient and permanent faults have a significant impact on the performance of the measured network. The corresponding mistag and misclassification percentages are typically within 5 to 10 percent of each other. The average mistag percentage and the average misclassification percentage are both about 25 percent. After relearning, the percentage of misclassifications is reduced to 9 percent. In addition, transient faults are found to cause the network to be increasingly unstable as the duration of a transient is increased. The impact of link faults is relatively insignificant in comparison with node faults (1 versus 19 percent misclassified after relearning). There is a linear increase in the mistag and misclassification percentages with decreasing hardware redundancy. In addition, the mistag and misclassification percentages linearly decrease with increasing network size.
Hybrid Neural Network for Pattern Recognition.
1997-02-03
two one-layer neural networks and the second stage comprises a feedforward two-layer neural network . A method for recognizing patterns is also...topological representations of the input patterns using the first and second neural networks. The method further comprises providing a third neural network for...classifying and recognizing the inputted patterns and training the third neural network with a back-propagation algorithm so that the third neural network recognizes at least one interested pattern.
The next generation of neural network chips
Beiu, V.
1997-08-01
There have been many national and international neural networks research initiatives: USA (DARPA, NIBS), Canada (IRIS), Japan (HFSP) and Europe (BRAIN, GALA TEA, NERVES, ELENE NERVES 2) -- just to mention a few. Recent developments in the field of neural networks, cognitive science, bioengineering and electrical engineering have made it possible to understand more about the functioning of large ensembles of identical processing elements. There are more research papers than ever proposing solutions and hardware implementations are by no means an exception. Two fields (computing and neuroscience) are interacting in ways nobody could imagine just several years ago, and -- with the advent of new technologies -- researchers are focusing on trying to copy the Brain. Such an exciting confluence may quite shortly lead to revolutionary new computers and it is the aim of this invited session to bring to light some of the challenging research aspects dealing with the hardware realizability of future intelligent chips. Present-day (conventional) technology is (still) mostly digital and, thus, occupies wider areas and consumes much more power than the solutions envisaged. The innovative algorithmic and architectural ideals should represent important breakthroughs, paving the way towards making neural network chips available to the industry at competitive prices, in relatively small packages and consuming a fraction of the power required by equivalent digital solutions.
Neural Network Development Tool (NETS)
NASA Technical Reports Server (NTRS)
Baffes, Paul T.
1990-01-01
Artificial neural networks formed from hundreds or thousands of simulated neurons, connected in manner similar to that in human brain. Such network models learning behavior. Using NETS involves translating problem to be solved into input/output pairs, designing network configuration, and training network. Written in C.
Tagliaferri, Roberto; Longo, Giuseppe; Milano, Leopoldo; Acernese, Fausto; Barone, Fabrizio; Ciaramella, Angelo; De Rosa, Rosario; Donalek, Ciro; Eleuteri, Antonio; Raiconi, Giancarlo; Sessa, Salvatore; Staiano, Antonino; Volpicelli, Alfredo
2003-01-01
In the last decade, the use of neural networks (NN) and of other soft computing methods has begun to spread also in the astronomical community which, due to the required accuracy of the measurements, is usually reluctant to use automatic tools to perform even the most common tasks of data reduction and data mining. The federation of heterogeneous large astronomical databases which is foreseen in the framework of the astrophysical virtual observatory and national virtual observatory projects, is, however, posing unprecedented data mining and visualization problems which will find a rather natural and user friendly answer in artificial intelligence tools based on NNs, fuzzy sets or genetic algorithms. This review is aimed to both astronomers (who often have little knowledge of the methodological background) and computer scientists (who often know little about potentially interesting applications), and therefore will be structured as follows: after giving a short introduction to the subject, we shall summarize the methodological background and focus our attention on some of the most interesting fields of application, namely: object extraction and classification, time series analysis, noise identification, and data mining. Most of the original work described in the paper has been performed in the framework of the AstroNeural collaboration (Napoli-Salerno).
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.
Design of fiber optic adaline neural networks
NASA Astrophysics Data System (ADS)
Ghosh, Anjan K.; Trepka, Jim
1997-03-01
Based on possible optoelectronic realization of adaptive filters and equalizers using fiber optic tapped delay lines and spatial light modulators we describe the design of a single-layer fiber optic Adaline neural network that can be used as a bit pattern classifier. In our design, we employ as few electronic devices as possible and use optical computation to utilize the advantages of optics in processing speed, parallelism, and interconnection. The described new optical neural network design is for optical processing of guided light wave signals, not electronic signals. We analyze the convergence or learning characteristics of the optoelectronic Adaline in the presence of errors in the hardware. We show that with such an optoelectronic Adaline it is possible to detect a desired code word/token/header with good accuracy.
Scalable photonic neural networks for real-time pattern classification
NASA Astrophysics Data System (ADS)
Goldstein, Adam Arthur
1997-11-01
With the rapid advancement of photonic technology in recent years, the potential exists for the incorporation of photonic neural-network research into the development of opto-electronic real-time pattern classification systems. In this dissertation we present three classes of photonic neural-network models that were designed to be compatible with this emerging technology: (1) photonic neural networks based upon probability density estimation, (2) photorefractive neural-network models, and (3) vertically stacked photonic neural networks that utilize hybridized CMOS/GaAs chips and diffractive optical elements. In each case, we show how previously developed neural-network learning algorithms and/or architectures must be adapted in order to allow an efficient photonic implementation. For class (1), we show that conventional 'k-Nearest Neighbors' (k-NN) probability density estimation is not suitable for an analog photonic neural-network hardware implementation, and we introduce a new probability density estimation algorithm called 'Continuous k-Nearest Neighbors' (C-kNN) that is suitable. For class (2), we show that the diffraction-efficiency decay inherent to photorefractive grating formation adversely affects outer-product neural-network learning algorithms, and we introduce a gain and exposure scheduling technique that resolves the incompatibility. For class (3), the use of compact diffractive optical interconnections constrains the corresponding neural-network weights to be fixed and locally connected. We introduce a 3-D Photonic Multichip- Module (3-D PMCM) neural-network architecture that utilizes a fixed diffractive optical layer in conjunction with a programmable electronic layer, to obtain a multi- layer neural network capable of real-time pattern recognition tasks. The design and fabrication of key components of the 3-D PMCM neural-network architecture are presented, together with simulation results for the application of detecting and locating the eyes in an
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.
A novel technology for fabricating customizable VLSI artificial neural network chips
Fu, C.Y.; Law, B.; Chapline, G.; Swenson, D.
1992-02-05
This paper describes an implementation of hardware neural networks using highly linear thin-film resistor technology and an 8-bit binary weight circuit to produce customizable artificial neural network chips and systems. These neural networks are programmed using precision laser cutting and deposition. The fast turnaround of laser-based customization allows us to explore different neural network architectures and to rapidly program the synaptic weights. Our customizable chip allows us to expand an artificial network laterally and vertically. This flexibility permits us to build very large neural network systems.
Neural Networks for Readability Analysis.
ERIC Educational Resources Information Center
McEneaney, John E.
This paper describes and reports on the performance of six related artificial neural networks that have been developed for the purpose of readability analysis. Two networks employ counts of linguistic variables that simulate a traditional regression-based approach to readability. The remaining networks determine readability from "visual…
A Complexity Theory of Neural Networks
1990-04-14
Significant results have been obtained on the computation complexity of analog neural networks , and distribute voting. The computing power and...learning algorithms for limited precision analog neural networks have been investigated. Lower bounds for constant depth, polynomial size analog neural ... networks , and a limited version of discrete neural networks have been obtained. The work on distributed voting has important applications for distributed
Collective Computation of Neural Network
1990-03-15
Sciences, Beijing ABSTRACT Computational neuroscience is a new branch of neuroscience originating from current research on the theory of computer...scientists working in artificial intelligence engineering and neuroscience . The paper introduces the collective computational properties of model neural...vision research. On this basis, the authors analyzed the significance of the Hopfield model. Key phrases: Computational Neuroscience , Neural Network, Model
Artificial Neural Network Analysis System
2007-11-02
Target detection, multi-target tracking and threat identification of ICBM and its warheads by sensor fusion and data fusion of sensors in a fuzzy neural network system based on the compound eye of a fly.
The holographic neural network: Performance comparison with other neural networks
NASA Astrophysics Data System (ADS)
Klepko, Robert
1991-10-01
The artificial neural network shows promise for use in recognition of high resolution radar images of ships. The holographic neural network (HNN) promises a very large data storage capacity and excellent generalization capability, both of which can be achieved with only a few learning trials, unlike most neural networks which require on the order of thousands of learning trials. The HNN is specially designed for pattern association storage, and mathematically realizes the storage and retrieval mechanisms of holograms. The pattern recognition capability of the HNN was studied, and its performance was compared with five other commonly used neural networks: the Adaline, Hamming, bidirectional associative memory, recirculation, and back propagation networks. The patterns used for testing represented artificial high resolution radar images of ships, and appear as a two dimensional topology of peaks with various amplitudes. The performance comparisons showed that the HNN does not perform as well as the other neural networks when using the same test data. However, modification of the data to make it appear more Gaussian distributed, improved the performance of the network. The HNN performs best if the data is completely Gaussian distributed.
Hardware demonstration of high-speed networks for satellite applications.
Donaldson, Jonathon W.; Lee, David S.
2008-09-01
This report documents the implementation results of a hardware demonstration utilizing the Serial RapidIO{trademark} and SpaceWire protocols that was funded by Sandia National Laboratories (SNL's) Laboratory Directed Research and Development (LDRD) office. This demonstration was one of the activities in the Modeling and Design of High-Speed Networks for Satellite Applications LDRD. This effort has demonstrated the transport of application layer packets across both RapidIO and SpaceWire networks to a common downlink destination using small topologies comprised of commercial-off-the-shelf and custom devices. The RapidFET and NEX-SRIO debug and verification tools were instrumental in the successful implementation of the RapidIO hardware demonstration. The SpaceWire hardware demonstration successfully demonstrated the transfer and routing of application data packets between multiple nodes and also was able reprogram remote nodes using configuration bitfiles transmitted over the network, a key feature proposed in node-based architectures (NBAs). Although a much larger network (at least 18 to 27 nodes) would be required to fully verify the design for use in a real-world application, this demonstration has shown that both RapidIO and SpaceWire are capable of routing application packets across a network to a common downlink node, illustrating their potential use in real-world NBAs.
Adaptive Optimization of Aircraft Engine Performance Using Neural Networks
NASA Technical Reports Server (NTRS)
Simon, Donald L.; Long, Theresa W.
1995-01-01
Preliminary results are presented on the development of an adaptive neural network based control algorithm to enhance aircraft engine performance. This work builds upon a previous National Aeronautics and Space Administration (NASA) effort known as Performance Seeking Control (PSC). PSC is an adaptive control algorithm which contains a model of the aircraft's propulsion system which is updated on-line to match the operation of the aircraft's actual propulsion system. Information from the on-line model is used to adapt the control system during flight to allow optimal operation of the aircraft's propulsion system (inlet, engine, and nozzle) to improve aircraft engine performance without compromising reliability or operability. Performance Seeking Control has been shown to yield reductions in fuel flow, increases in thrust, and reductions in engine fan turbine inlet temperature. The neural network based adaptive control, like PSC, will contain a model of the propulsion system which will be used to calculate optimal control commands on-line. Hopes are that it will be able to provide some additional benefits above and beyond those of PSC. The PSC algorithm is computationally intensive, it is valid only at near steady-state flight conditions, and it has no way to adapt or learn on-line. These issues are being addressed in the development of the optimal neural controller. Specialized neural network processing hardware is being developed to run the software, the algorithm will be valid at steady-state and transient conditions, and will take advantage of the on-line learning capability of neural networks. Future plans include testing the neural network software and hardware prototype against an aircraft engine simulation. In this paper, the proposed neural network software and hardware is described and preliminary neural network training results are presented.
Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture
Disney, Adam; Reynolds, John
2015-01-01
Dynamic Adaptive Neural Network Array (DANNA) is a neuromorphic hardware implementation. It differs from most other neuromorphic projects in that it allows for programmability of structure, and it is trained or designed using evolutionary optimization. This paper describes the DANNA structure, how DANNA is trained using evolutionary optimization, and an application of DANNA to a very simple classification task.
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.
Simultaneous perturbation learning rule for recurrent neural networks and its FPGA implementation.
Maeda, Yutaka; Wakamura, Masatoshi
2005-11-01
Recurrent neural networks have interesting properties and can handle dynamic information processing unlike ordinary feedforward neural networks. However, they are generally difficult to use because there is no convenient learning scheme. In this paper, a recursive learning scheme for recurrent neural networks using the simultaneous perturbation method is described. The detailed procedure of the scheme for recurrent neural networks is explained. Unlike ordinary correlation learning, this method is applicable to analog learning and the learning of oscillatory solutions of recurrent neural networks. Moreover, as a typical example of recurrent neural networks, we consider the hardware implementation of Hopfield neural networks using a field-programmable gate array (FPGA). The details of the implementation are described. Two examples of a Hopfield neural network system for analog and oscillatory targets are shown. These results show that the learning scheme proposed here is feasible.
Antenna analysis using neural networks
NASA Technical Reports Server (NTRS)
Smith, William T.
1992-01-01
Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern
Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks.
Pu, Yi-Fei; Yi, Zhang; Zhou, Ji-Liu
2016-07-14
This paper mainly discusses a novel conceptual framework: fractional Hopfield neural networks (FHNN). As is commonly known, fractional calculus has been incorporated into artificial neural networks, mainly because of its long-term memory and nonlocality. Some researchers have made interesting attempts at fractional neural networks and gained competitive advantages over integer-order neural networks. Therefore, it is naturally makes one ponder how to generalize the first-order Hopfield neural networks to the fractional-order ones, and how to implement FHNN by means of fractional calculus. We propose to introduce a novel mathematical method: fractional calculus to implement FHNN. First, we implement fractor in the form of an analog circuit. Second, we implement FHNN by utilizing fractor and the fractional steepest descent approach, construct its Lyapunov function, and further analyze its attractors. Third, we perform experiments to analyze the stability and convergence of FHNN, and further discuss its applications to the defense against chip cloning attacks for anticounterfeiting. The main contribution of our work is to propose FHNN in the form of an analog circuit by utilizing a fractor and the fractional steepest descent approach, construct its Lyapunov function, prove its Lyapunov stability, analyze its attractors, and apply FHNN to the defense against chip cloning attacks for anticounterfeiting. A significant advantage of FHNN is that its attractors essentially relate to the neuron's fractional order. FHNN possesses the fractional-order-stability and fractional-order-sensitivity characteristics.
Tutorial on neural network applications in high energy physics: A 1992 perspective
Denby, B.
1992-04-01
Feed forward and recurrent neural networks are introduced and related to standard data analysis tools. Tips are given on applications of neural nets to various areas of high energy physics. A review of applications within high energy physics and a summary of neural net hardware status are given.
Efficient implementation of neural network deinterlacing
NASA Astrophysics Data System (ADS)
Seo, Guiwon; Choi, Hyunsoo; Lee, Chulhee
2009-02-01
Interlaced scanning has been widely used in most broadcasting systems. However, there are some undesirable artifacts such as jagged patterns, flickering, and line twitters. Moreover, most recent TV monitors utilize flat panel display technologies such as LCD or PDP monitors and these monitors require progressive formats. Consequently, the conversion of interlaced video into progressive video is required in many applications and a number of deinterlacing methods have been proposed. Recently deinterlacing methods based on neural network have been proposed with good results. On the other hand, with high resolution video contents such as HDTV, the amount of video data to be processed is very large. As a result, the processing time and hardware complexity become an important issue. In this paper, we propose an efficient implementation of neural network deinterlacing using polynomial approximation of the sigmoid function. Experimental results show that these approximations provide equivalent performance with a considerable reduction of complexity. This implementation of neural network deinterlacing can be efficiently incorporated in HW implementation.
64x64 Analog Input Array for 3-Dimensional Neural Network Processor
NASA Technical Reports Server (NTRS)
Duong, T. A.; Thomas, T.; Daud, T.; Thakoor, A.; Lee, B.
1997-01-01
In pattern recognition and classification for spatio-temporal problems, one of the most challenging tasks is to provide a good and valid solution in real-time. Because of time constraints, software-based neural network approaches may not be suitable for practical use. Hardware solutions seem to be good candidates for this class of problems. Currently, the Three Dimensional Analog Neural Network (3-DANN) is an effective approach to solving spatio-temporal problems in three-dimensional hardware.
Saini, K. K.; Saini, Sanju
2008-10-07
Neural networks are a relatively new artificial intelligence technique that emulates the behavior of biological neural systems in digital software or hardware. These networks can 'learn', automatically, complex relationships among data. This feature makes the technique very useful in modeling processes for which mathematical modeling is difficult or impossible. The work described here outlines some examples of the application of neural networks with artificial intelligence technique in the modeling of industrial processes.
Analog neural networks in an upgraded muon trigger for the DZero detector
Fortner, M.R.
1992-04-01
The use of analog neural networks as part of the DZero muon detector is considered. A study was made of tracking through a single muon chamber using neural network techniques. A hardware application based on Intel`s ETANN ship was designed and used in a test beam at Fermi National Accelerator Laboratory. Plans to implement a neural network trigger in DZero are also discussed.
NASA Astrophysics Data System (ADS)
Saini, K. K.; Saini, Sanju
2008-10-01
Neural networks are a relatively new artificial intelligence technique that emulates the behavior of biological neural systems in digital software or hardware. These networks can "learn," automatically, complex relationships among data. This feature makes the technique very useful in modeling processes for which mathematical modeling is difficult or impossible. The work described here outlines some examples of the application of neural networks with artificial intelligence technique in the modeling of industrial processes.
Stromatias, Evangelos; Neil, Daniel; Pfeiffer, Michael; Galluppi, Francesco; Furber, Steve B; Liu, Shih-Chii
2015-01-01
Increasingly large deep learning architectures, such as Deep Belief Networks (DBNs) are the focus of current machine learning research and achieve state-of-the-art results in different domains. However, both training and execution of large-scale Deep Networks require vast computing resources, leading to high power requirements and communication overheads. The on-going work on design and construction of spike-based hardware platforms offers an alternative for running deep neural networks with significantly lower power consumption, but has to overcome hardware limitations in terms of noise and limited weight precision, as well as noise inherent in the sensor signal. This article investigates how such hardware constraints impact the performance of spiking neural network implementations of DBNs. In particular, the influence of limited bit precision during execution and training, and the impact of silicon mismatch in the synaptic weight parameters of custom hybrid VLSI implementations is studied. Furthermore, the network performance of spiking DBNs is characterized with regard to noise in the spiking input signal. Our results demonstrate that spiking DBNs can tolerate very low levels of hardware bit precision down to almost two bits, and show that their performance can be improved by at least 30% through an adapted training mechanism that takes the bit precision of the target platform into account. Spiking DBNs thus present an important use-case for large-scale hybrid analog-digital or digital neuromorphic platforms such as SpiNNaker, which can execute large but precision-constrained deep networks in real time.
Reconfigurable hardware applications on NetFPGA for network monitoring in large area sensor networks
NASA Astrophysics Data System (ADS)
Belias, A.; Koutsoumpos, V.; Manolopoulos, K.; Kachris, C.
2013-10-01
A valuable functionality for sensor networks, distributed in large volumes is the capability to characterize and analyze the data traffic at wire speed and monitor the data prior to committing to permanent storage. As a demonstrator we use a reconfigurable hardware router for real-time monitoring of data before their transmission to further processing and storage. The reconfigurable hardware router is based on the NetFPGA platform. In this study we report on the hardware implementation to monitor web-based network applications and compare our results with a software based network analyzer.
Analog implementation of pulse-coupled neural networks.
Ota, Y; Wilamowski, B M
1999-01-01
This paper presents a compact architecture for analog CMOS hardware implementation of voltage-mode pulse-coupled neural networks (PCNN's). The hardware implementation methods shows inherent fault tolerance specialties and high speed, which is usually more than an order of magnitude over the software counterpart. A computational style described in this article mimics a biological neural network using pulse-stream signaling and analog summation and multiplication. Pulse-stream encoding technique uses pulse streams to carry information and control analog circuitry, while storing further analog information on the time axis. The main feature of the proposed neuron circuit is that the structure is compact, yet exhibiting all the basic properties of natural biological neurons. Functional and structural forms of neural and synaptic functions are presented along with simulation results. Finally, the proposed design is applied to image processing to demonstrate successful restoration of images and their features.
Electronic neural network for dynamic resource allocation
NASA Technical Reports Server (NTRS)
Thakoor, A. P.; Eberhardt, S. P.; Daud, T.
1991-01-01
A VLSI implementable neural network architecture for dynamic assignment is presented. The resource allocation problems involve assigning members of one set (e.g. resources) to those of another (e.g. consumers) such that the global 'cost' of the associations is minimized. The network consists of a matrix of sigmoidal processing elements (neurons), where the rows of the matrix represent resources and columns represent consumers. Unlike previous neural implementations, however, association costs are applied directly to the neurons, reducing connectivity of the network to VLSI-compatible 0 (number of neurons). Each row (and column) has an additional neuron associated with it to independently oversee activations of all the neurons in each row (and each column), providing a programmable 'k-winner-take-all' function. This function simultaneously enforces blocking (excitatory/inhibitory) constraints during convergence to control the number of active elements in each row and column within desired boundary conditions. Simulations show that the network, when implemented in fully parallel VLSI hardware, offers optimal (or near-optimal) solutions within only a fraction of a millisecond, for problems up to 128 resources and 128 consumers, orders of magnitude faster than conventional computing or heuristic search methods.
Communications, Navigation, and Network Reconfigurable Test-bed Flight Hardware Compatibility Test S
NASA Technical Reports Server (NTRS)
2010-01-01
Communications, Navigation, and Network Reconfigurable Test-bed Flight Hardware Compatibility Test Sets and Networks Integration Management Office Testing for the Tracking and Data Relay Satellite System
Signal Approximation with a Wavelet Neural Network
1992-12-01
specialized electronic devices like the Intel Electronically Trainable Analog Neural Network (ETANN) chip. The WNN representation allows the...accurately approximated with a WNN trained with irregularly sampled data. Signal approximation, Wavelet neural network .
A Neural Network Based Speech Recognition System
1990-02-01
encoder and identifies individual words. This use of neural networks offers two advantages over conventional algorithmic detectors: the detection...environment. Keywords: Artificial intelligence; Neural networks : Back propagation; Speech recognition.
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.
Analysis and Design of Neural Networks
1992-01-01
The training problem for feedforward neural networks is nonlinear parameter estimation that can be solved by a variety of optimization techniques...Much of the literature of neural networks has focused on variants of gradient descent. The training of neural networks using such techniques is known to...be a slow process with more sophisticated techniques not always performing significantly better. It is shown that feedforward neural networks can
Radar System Classification Using Neural Networks
1991-12-01
This study investigated methods of improving the accuracy of neural networks in the classification of large numbers of classes. A literature search...revealed that neural networks have been successful in the radar classification problem, and that many complex problems have been solved using systems...of multiple neural networks . The experiments conducted were based on 32 classes of radar system data. The neural networks were modelled using a program
Neural networks and applications tutorial
NASA Astrophysics Data System (ADS)
Guyon, I.
1991-09-01
The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.
Fault Tolerance of Neural Networks
1994-07-01
Systematic Ap - proach, Proc. Government Microcircuit Application Conf. (GOMAC), San Diego, Nov. 1986. [10] D.E.Goldberg, Genetic Algorithms in Search...s l m n ttempt to develop fault tolerant neural networks. The lows. Given a well-trained network, we first eliminate temp todevlopfaut tlernt eurl ...both ap - proaches, and this resulted in very slight improve- ments over the addition/deletion procedure. 103 Fisher’s Iris data in average case Fisher’s
FPGA implementation of a pyramidal Weightless Neural Networks learning system.
Al-Alawi, Raida
2003-08-01
A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.
Artificial neural networks in medicine
Keller, P.E.
1994-07-01
This Technology Brief provides an overview of artificial neural networks (ANN). A definition and explanation of an ANN is given and situations in which an ANN is used are described. ANN applications to medicine specifically are then explored and the areas in which it is currently being used are discussed. Included are medical diagnostic aides, biochemical analysis, medical image analysis and drug development.
Semantic Interpretation of An Artificial Neural Network
1995-12-01
success for stock market analysis/prediction is artificial neural networks. However, knowledge embedded in the neural network is not easily translated...interpret neural network knowledge. The first, called Knowledge Math, extends the use of connection weights, generating rules for general (i.e. non-binary
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.
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 networks for atmospheric retrievals
NASA Technical Reports Server (NTRS)
Motteler, Howard E.; Gualtieri, J. A.; Strow, L. Larrabee; Mcmillin, Larry
1993-01-01
We use neural networks to perform retrievals of temperature and water fractions from simulated clear air radiances for the Atmospheric Infrared Sounder (AIRS). Neural networks allow us to make effective use of the large AIRS channel set, and give good performance with noisy input. We retrieve surface temperature, air temperature at 64 distinct pressure levels, and water fractions at 50 distinct pressure levels. Using 728 temperature and surface sensitive channels, the RMS error for temperature retrievals with 0.2K input noise is 1.2K. Using 586 water and temperature sensitive channels, the mean error with 0.2K input noise is 16 percent. Our implementation of backpropagation training for neural networks on the 16,000-processor MasPar MP-1 runs at a rate of 90 million weight updates per second, and allows us to train large networks in a reasonable amount of time. Once trained, the network can be used to perform retrievals quickly on a workstation of moderate power.
Space station common module network topology and hardware development
NASA Technical Reports Server (NTRS)
Anderson, P.; Braunagel, L.; Chwirka, S.; Fishman, M.; Freeman, K.; Eason, D.; Landis, D.; Lech, L.; Martin, J.; Mccorkle, J.
1990-01-01
Conceptual space station common module power management and distribution (SSM/PMAD) network layouts and detailed network evaluations were developed. Individual pieces of hardware to be developed for the SSM/PMAD test bed were identified. A technology assessment was developed to identify pieces of equipment requiring development effort. Equipment lists were developed from the previously selected network schematics. Additionally, functional requirements for the network equipment as well as other requirements which affected the suitability of specific items for use on the Space Station Program were identified. Assembly requirements were derived based on the SSM/PMAD developed requirements and on the selected SSM/PMAD network concepts. Basic requirements and simplified design block diagrams are included. DC remote power controllers were successfully integrated into the DC Marshall Space Flight Center breadboard. Two DC remote power controller (RPC) boards experienced mechanical failure of UES 706 stud-mounted diodes during mechanical installation of the boards into the system. These broken diodes caused input to output shorting of the RPC's. The UES 706 diodes were replaced on these RPC's which eliminated the problem. The DC RPC's as existing in the present breadboard configuration do not provide ground fault protection because the RPC was designed to only switch the hot side current. If ground fault protection were to be implemented, it would be necessary to design the system so the RPC switched both the hot and the return sides of power.
A case for spiking neural network simulation based on configurable multiple-FPGA systems.
Yang, Shufan; Wu, Qiang; Li, Renfa
2011-09-01
Recent neuropsychological research has begun to reveal that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of neuronal systems. Simulation of the spiking neural networks in software is unable to rapidly generate output spikes in large-scale of neural network. An alternative approach, hardware implementation of such system, provides the possibility to generate independent spikes precisely and simultaneously output spike waves in real time, under the premise that spiking neural network can take full advantage of hardware inherent parallelism. We introduce a configurable FPGA-oriented hardware platform for spiking neural network simulation in this work. We aim to use this platform to combine the speed of dedicated hardware with the programmability of software so that it might allow neuroscientists to put together sophisticated computation experiments of their own model. A feed-forward hierarchy network is developed as a case study to describe the operation of biological neural systems (such as orientation selectivity of visual cortex) and computational models of such systems. This model demonstrates how a feed-forward neural network constructs the circuitry required for orientation selectivity and provides platform for reaching a deeper understanding of the primate visual system. In the future, larger scale models based on this framework can be used to replicate the actual architecture in visual cortex, leading to more detailed predictions and insights into visual perception phenomenon.
Entropy based comparison of neural networks for classification
Draghici, S.; Beiu, V.
1997-04-01
In recent years, multilayer feedforward neural networks (NN) have been shown to be very effective tools in many different applications. A natural and essential step in continuing the diffusion of these tools in day by day use is their hardware implementation which is by far the most cost effective solution for large scale use. When the hardware implementation is contemplated, the issue of the size of the NN becomes crucial because the size is directly proportional with the cost of the implementation. In this light, any theoretical results which establish bounds on the size of a NN for a given problem is extremely important. In the same context, a particularly interesting case is that of the neural networks using limited integer weights. These networks are particularly suitable for hardware implementation because they need less space for storing the weights and the fixed point, limited precision arithmetic has much cheaper implementations in comparison with its floating point counterpart. This paper presents an entropy based analysis which completes, unifies and correlates results partially presented in [Beiu, 1996, 1997a] and [Draghici, 1997]. Tight bounds for real and integer weight neural networks are calculated.
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.
Widrow-cellular neural network and optoelectronic implementation
NASA Astrophysics Data System (ADS)
Bal, Abdullah
A new type of optoelectronic cellular neural network has been developed by providing the capability of coefficients adjusment of cellular neural network (CNN) using Widrow based perceptron learning algorithm. The new supervised cellular neural network is called Widrow-CNN. Despite the unsupervised CNN, the proposed learning algorithm allows to use the Widrow-CNN for various image processing applications easily. Also, the capability of CNN for image processing and feature extraction has been improved using basic joint transform correlation architecture. This hardware application presents high speed processing capability compared to digital applications. The optoelectronic Widrow-CNN has been tested for classic CNN feature extraction problems. It yields the best results even in case of hard feature extraction problems such as diagonal line detection and vertical line determination.
Terminal attractors in neural networks
NASA Technical Reports Server (NTRS)
Zak, Michail
1989-01-01
A new type of attractor (terminal attractors) for content-addressable memory, associative memory, and pattern recognition in artificial neural networks operating in continuous time is introduced. The idea of a terminal attractor is based upon a violation of the Lipschitz condition at a fixed point. As a result, the fixed point becomes a singular solution which envelopes the family of regular solutions, while each regular solution approaches such an attractor in finite time. It will be shown that terminal attractors can be incorporated into neural networks such that any desired set of these attractors with prescribed basins is provided by an appropriate selection of the synaptic weights. The applications of terminal attractors for content-addressable and associative memories, pattern recognition, self-organization, and for dynamical training are illustrated.
Prototype neural network pattern recognition testbed
NASA Astrophysics Data System (ADS)
Worrell, Steven W.; Robertson, James A.; Varner, Thomas L.; Garvin, Charles G.
1991-02-01
Recent successes ofneural networks has led to an optimistic outlook for neural network applications to image processing(IP). This paperpresents a general architecture for performing comparative studies of neural processing and more conventional IF techniques as well as hybrid pattern recognition (PR) systems. Two hybrid PR systems have been simulated each of which incorporate both conventional and neural processing techniques.
Digital implementation of shunting-inhibitory cellular neural network
NASA Astrophysics Data System (ADS)
Hammadou, Tarik; Bouzerdoum, Abdesselam; Bermak, Amine
2000-05-01
Shunting inhibition is a model of early visual processing which can provide contrast and edge enhancement, and dynamic range compression. An architecture of digital Shunting Inhibitory Cellular Neural Network for real time image processing is presented. The proposed architecture is intended to be used in a complete vision system for edge detection and image enhancement. The present hardware architecture, is modeled and simulated in VHDL. Simulation results show the functional validity of the proposed architecture.
Neural Network for Visual Search Classification
2007-11-02
neural network used to perform visual search classification. The neural network consists of a Learning vector quantization network (LVQ) and a single layer perceptron. The objective of this neural network is to classify the various human visual search patterns into predetermined classes. The classes signify the different search strategies used by individuals to scan the same target pattern. The input search patterns are quantified with respect to an ideal search pattern, determined by the user. A supervised learning rule,
Neural network feature detector for real-time video signal processing.
Naylor, D; Jones, S; Myers, D; Vincent, J
1993-12-01
The application of artificial neural networks to real-time image processing tasks requires the use of dedicated, high performance hardware. A linear array processor called HANNIBAL has been developed which implements the backpropagation neural learning algorithm on-chip. This paper considers the design of a complete neural system which integrates HANNIBAL into an existing image processing environment. The goals for the design of the system have been set partly by the primary application, namely feature recognition, but mainly by the desire for a flexible, high performance hardware tool for the study and evaluation of range of neural image processing applications.
The LILARTI neural network system
Allen, J.D. Jr.; Schell, F.M.; Dodd, C.V.
1992-10-01
The material of this Technical Memorandum is intended to provide the reader with conceptual and technical background information on the LILARTI neural network system of detail sufficient to confer an understanding of the LILARTI method as it is presently allied and to facilitate application of the method to problems beyond the scope of this document. Of particular importance in this regard are the descriptive sections and the Appendices which include operating instructions, partial listings of program output and data files, and network construction information.
Room and Low Temperature Performance of High-Speed Neural Network Circuits
NASA Technical Reports Server (NTRS)
Daud, T.
1997-01-01
We have described a challenging neural-network hardware implementation that would mate a 64x64-pixel infrared sensor directly on to a 3-dimensionally packaged set of neural processing chips with parallel input for high speed image processing. Non linearity effects and range compression are also discussed.
Neural networks within multi-core optic fibers
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
NASA Astrophysics Data System (ADS)
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-01
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.
Neural networks within multi-core optic fibers.
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-07
Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.
Neural network implementation using bit streams.
Patel, Nitish D; Nguang, Sing Kiong; Coghill, George G
2007-09-01
A new method for the parallel hardware implementation of artificial neural networks (ANNs) using digital techniques is presented. Signals are represented using uniformly weighted single-bit streams. Techniques for generating bit streams from analog or multibit inputs are also presented. This single-bit representation offers significant advantages over multibit representations since they mitigate the fan-in and fan-out issues which are typical to distributed systems. To process these bit streams using ANNs concepts, functional elements which perform summing, scaling, and squashing have been implemented. These elements are modular and have been designed such that they can be easily interconnected. Two new architectures which act as monotonically increasing differentiable nonlinear squashing functions have also been presented. Using these functional elements, a multilayer perceptron (MLP) can be easily constructed. Two examples successfully demonstrate the use of bit streams in the implementation of ANNs. Since every functional element is individually instantiated, the implementation is genuinely parallel. The results clearly show that this bit-stream technique is viable for the hardware implementation of a variety of distributed systems and for ANNs in particular.
Permitted and forbidden sets in discrete-time linear threshold recurrent neural networks.
Yi, Zhang; Zhang, Lei; Yu, Jiali; Tan, Kok Kiong
2009-06-01
The concepts of permitted and forbidden sets enable a new perspective of the memory in neural networks. Such concepts exhibit interesting dynamics in recurrent neural networks. This paper studies the basic theories of permitted and forbidden sets of the linear threshold discrete-time recurrent neural networks. The linear threshold transfer function has been regarded as an adequate transfer function for recurrent neural networks. Networks with this transfer function form a class of hybrid analog and digital networks which are especially useful for perceptual computations. Networks in discrete time can directly provide algorithms for efficient implementation in digital hardware. The main contribution of this paper is to establish foundations of permitted and forbidden sets. Necessary and sufficient conditions for the linear threshold discrete-time recurrent neural networks are obtained for complete convergence, existence of permitted and forbidden sets, as well as conditionally multiattractivity, respectively. Simulation studies explore some possible interesting practical applications.
Narasimhan, Seetharam; Chiel, Hillel J; Bhunia, Swarup
2009-01-01
For implantable neural interface applications, it is important to compress data and analyze spike patterns across multiple channels in real time. Such a computational task for online neural data processing requires an innovative circuit-architecture level design approach for low-power, robust and area-efficient hardware implementation. Conventional microprocessor or Digital Signal Processing (DSP) chips would dissipate too much power and are too large in size for an implantable system. In this paper, we propose a novel hardware design approach, referred to as "Preferential Design" that exploits the nature of the neural signal processing algorithm to achieve a low-voltage, robust and area-efficient implementation using nanoscale process technology. The basic idea is to isolate the critical components with respect to system performance and design them more conservatively compared to the noncritical ones. This allows aggressive voltage scaling for low power operation while ensuring robustness and area efficiency. We have applied the proposed approach to a neural signal processing algorithm using the Discrete Wavelet Transform (DWT) and observed significant improvement in power and robustness over conventional design.
Neural network modeling of emotion
NASA Astrophysics Data System (ADS)
Levine, Daniel S.
2007-03-01
This article reviews the history and development of computational neural network modeling of cognitive and behavioral processes that involve emotion. The exposition starts with models of classical conditioning dating from the early 1970s. Then it proceeds toward models of interactions between emotion and attention. Then models of emotional influences on decision making are reviewed, including some speculative (not and not yet simulated) models of the evolution of decision rules. Through the late 1980s, the neural networks developed to model emotional processes were mainly embodiments of significant functional principles motivated by psychological data. In the last two decades, network models of these processes have become much more detailed in their incorporation of known physiological properties of specific brain regions, while preserving many of the psychological principles from the earlier models. Most network models of emotional processes so far have dealt with positive and negative emotion in general, rather than specific emotions such as fear, joy, sadness, and anger. But a later section of this article reviews a few models relevant to specific emotions: one family of models of auditory fear conditioning in rats, and one model of induced pleasure enhancing creativity in humans. Then models of emotional disorders are reviewed. The article concludes with philosophical statements about the essential contributions of emotion to intelligent behavior and the importance of quantitative theories and models to the interdisciplinary enterprise of understanding the interactions of emotion, cognition, and behavior.
Feature Extraction Using an Unsupervised Neural Network
1991-05-03
A novel unsupervised neural network for dimensionality reduction which seeks directions emphasizing distinguishing features in the data is presented. A statistical framework for the parameter estimation problem associated with this neural network is given and its connection to exploratory projection pursuit methods is established. The network is shown to minimize a loss function (projection index) over a
Neural networks and MIMD-multiprocessors
NASA Technical Reports Server (NTRS)
Vanhala, Jukka; Kaski, Kimmo
1990-01-01
Two artificial neural network models are compared. They are the Hopfield Neural Network Model and the Sparse Distributed Memory model. Distributed algorithms for both of them are designed and implemented. The run time characteristics of the algorithms are analyzed theoretically and tested in practice. The storage capacities of the networks are compared. Implementations are done using a distributed multiprocessor system.
Neural-Network Computer Transforms Coordinates
NASA Technical Reports Server (NTRS)
Josin, Gary M.
1990-01-01
Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.
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.
On limited fan-in optimal neural networks
Beiu, V.; Makaruk, H.E.; Draghici, S.
1998-03-01
Because VLSI implementations do not cope well with highly interconnected nets the area of a chip growing as the cube of the fan-in--this paper analyses the influence of limited fan in on the size and VLSI optimality of such nets. Two different approaches will show that VLSI- and size-optimal discrete neural networks can be obtained for small (i.e. lower than linear) fan-in values. They have applications to hardware implementations of neural networks. The first approach is based on implementing a certain sub class of Boolean functions, IF{sub n,m} functions. The authors will show that this class of functions can be implemented in VLSI optimal (i.e., minimizing AT{sup 2}) neural networks of small constant fan ins. The second approach is based on implementing Boolean functions for which the classical Shannon`s decomposition can be used. Such a solution has already been used to prove bounds on neural networks with fan-ins limited to 2. They generalize the result presented there to arbitrary fan-in, and prove that the size is minimized by small fan in values, while relative minimum size solutions can be obtained for fan-ins strictly lower than linear. Finally, a size-optimal neural network having small constant fan-ins will be suggested for IF{sub n,m} functions.
Oil reservoir properties estimation using neural networks
Toomarian, N.B.; Barhen, J.; Glover, C.W.; Aminzadeh, F.
1997-02-01
This paper investigates the applicability as well as the accuracy of artificial neural networks for estimating specific parameters that describe reservoir properties based on seismic data. This approach relies on JPL`s adjoint operators general purpose neural network code to determine the best suited architecture. The authors believe that results presented in this work demonstrate that artificial neural networks produce surprisingly accurate estimates of the reservoir parameters.
Adaptive optimization and control using neural networks
Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.
1993-10-22
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.
Neural Network False Alarm Filter. Volume 1.
1994-12-01
This effort identified, developed and demonstrated a set of approaches for applying neural network learning techniques to the development of a real... neural network models, 9 fault report causes and 12 common groups of BIT techniques was identified. From this space, 4 unique, high-potential...of their strengths and weaknesses were performed along with cost/ benefit analyses. This study concluded that the best candidates for neural network insert
A Neural Network Object Recognition System
1990-07-01
useful for exploring different neural network configurations. There are three main computation phases of a model based object recognition system...segmentation, feature extraction, and object classification. This report focuses on the object classification stage. For segmentation, a neural network based...are available with the current system. Neural network based feature extraction may be added at a later date. The classification stage consists of a
Neural Networks Applied to Signal Processing
1989-09-01
DTIC FILE COpy NAVAL POSTGRADUATE SCHOOL . Monterey, California Lf 0 (0 V’ STATES 4 THESIS NEURAL NETWORKS APPLIED TO SIGNAL PROCESSING by Mark D...FUNDING NUMBERS PROGRAM PROJECT TASK WORK UNIT ELEMENT NO NO NO ACCESSION NO. 11. TITLE (Include Security Classification) NEURAL NETWORKS APPLIED TO...for public release; distribution is unlimited Neural Networks Applied to Signal Processing by Mark D. Baehre Captain, United States Army B.S., United
A Complexity Theory of Neural Networks
1991-08-09
Significant progress has been made in laying the foundations of a complexity theory of neural networks . The fundamental complexity classes have been...identified and studied. The class of problems solvable by small, shallow neural networks has been found to be the same class even if (1) probabilistic...behaviour (2)Multi-valued logic, and (3)analog behaviour, are allowed (subject to certain resonable technical assumptions). Neural networks can be
Stromatias, Evangelos; Neil, Daniel; Pfeiffer, Michael; Galluppi, Francesco; Furber, Steve B.; Liu, Shih-Chii
2015-01-01
Increasingly large deep learning architectures, such as Deep Belief Networks (DBNs) are the focus of current machine learning research and achieve state-of-the-art results in different domains. However, both training and execution of large-scale Deep Networks require vast computing resources, leading to high power requirements and communication overheads. The on-going work on design and construction of spike-based hardware platforms offers an alternative for running deep neural networks with significantly lower power consumption, but has to overcome hardware limitations in terms of noise and limited weight precision, as well as noise inherent in the sensor signal. This article investigates how such hardware constraints impact the performance of spiking neural network implementations of DBNs. In particular, the influence of limited bit precision during execution and training, and the impact of silicon mismatch in the synaptic weight parameters of custom hybrid VLSI implementations is studied. Furthermore, the network performance of spiking DBNs is characterized with regard to noise in the spiking input signal. Our results demonstrate that spiking DBNs can tolerate very low levels of hardware bit precision down to almost two bits, and show that their performance can be improved by at least 30% through an adapted training mechanism that takes the bit precision of the target platform into account. Spiking DBNs thus present an important use-case for large-scale hybrid analog-digital or digital neuromorphic platforms such as SpiNNaker, which can execute large but precision-constrained deep networks in real time. PMID:26217169
Neural network architecture for crossbar switch control
NASA Technical Reports Server (NTRS)
Troudet, Terry P.; Walters, Stephen M.
1991-01-01
A Hopfield neural network architecture for the real-time control of a crossbar switch for switching packets at maximum throughput is proposed. The network performance and processing time are derived from a numerical simulation of the transitions of the neural network. A method is proposed to optimize electronic component parameters and synaptic connections, and it is fully illustrated by the computer simulation of a VLSI implementation of 4 x 4 neural net controller. The extension to larger size crossbars is demonstrated through the simulation of an 8 x 8 crossbar switch controller, where the performance of the neural computation is discussed in relation to electronic noise and inhomogeneities of network components.
Neural network based system for equipment surveillance
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 network based system for equipment surveillance
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.
Advances in neural networks research: an introduction.
Kozma, Robert; Bressler, Steven; Perlovsky, Leonid; Venayagamoorthy, Ganesh Kumar
2009-01-01
The present Special Issue "Advances in Neural Networks Research: IJCNN2009" provides a state-of-art overview of the field of neural networks. It includes 39 papers from selected areas of the 2009 International Joint Conference on Neural Networks (IJCNN2009). IJCNN2009 took place on June 14-19, 2009 in Atlanta, Georgia, USA, and it represents an exemplary collaboration between the International Neural Networks Society and the IEEE Computational Intelligence Society. Topics in this issue include neuroscience and cognitive science, computational intelligence and machine learning, hybrid techniques, nonlinear dynamics and chaos, various soft computing technologies, intelligent signal processing and pattern recognition, bioinformatics and biomedicine, and engineering applications.
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.
Aerodynamic Design Using Neural Networks
NASA Technical Reports Server (NTRS)
Rai, Man Mohan; Madavan, Nateri K.
2003-01-01
The design of aerodynamic components of aircraft, such as wings or engines, involves a process of obtaining the most optimal component shape that can deliver the desired level of component performance, subject to various constraints, e.g., total weight or cost, that the component must satisfy. Aerodynamic design can thus be formulated as an optimization problem that involves the minimization of an objective function subject to constraints. A new aerodynamic design optimization procedure based on neural networks and response surface methodology (RSM) incorporates the advantages of both traditional RSM and neural networks. The procedure uses a strategy, denoted parameter-based partitioning of the design space, to construct a sequence of response surfaces based on both neural networks and polynomial fits to traverse the design space in search of the optimal solution. Some desirable characteristics of the new design optimization procedure include the ability to handle a variety of design objectives, easily impose constraints, and incorporate design guidelines and rules of thumb. It provides an infrastructure for variable fidelity analysis and reduces the cost of computation by using less-expensive, lower fidelity simulations in the early stages of the design evolution. The initial or starting design can be far from optimal. The procedure is easy and economical to use in large-dimensional design space and can be used to perform design tradeoff studies rapidly. Designs involving multiple disciplines can also be optimized. Some practical applications of the design procedure that have demonstrated some of its capabilities include the inverse design of an optimal turbine airfoil starting from a generic shape and the redesign of transonic turbines to improve their unsteady aerodynamic characteristics.
Neural networks for nuclear spectroscopy
Keller, P.E.; Kangas, L.J.; Hashem, S.; Kouzes, R.T.
1995-12-31
In this paper two applications of artificial neural networks (ANNs) in nuclear spectroscopy analysis are discussed. In the first application, an ANN assigns quality coefficients to alpha particle energy spectra. These spectra are used to detect plutonium contamination in the work environment. The quality coefficients represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with quality coefficients by an expert and used to train the ANN expert system. Our investigation shows that the expert knowledge of spectral quality can be transferred to an ANN system. The second application combines a portable gamma-ray spectrometer with an ANN. In this system the ANN is used to automatically identify, radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perception and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perception for this application. Both networks have a linear response and are useful in determining the composition of an unknown sample when the spectrum of the unknown is a linear superposition of known spectra. One feature of this technique is that it uses the whole spectrum in the identification process instead of only the individual photo-peaks. For this reason, it is potentially more useful for processing data from lower resolution gamma-ray spectrometers. This approach has been tested with data generated by Monte Carlo simulations and with field data from sodium iodide and Germanium detectors. With the ANN approach, the intense computation takes place during the training process. Once the network is trained, normal operation consists of propagating the data through the network, which results in rapid identification of samples. This approach is useful in situations that require fast response where precise quantification is less important.
Flow Control Using Neural Networks
2007-11-02
FEB 93 - 31 DEC 96 4. TITLE AND SUBTITLE 5 . FUNDING NUMBERS FLOW CONTROL USING NEURAL NETWORKS F49620-93-1-0135 61102F 6. AUTHOR(S) 2307/BS THORWALD...OFFICE OF SCIENTIFIC RESEARCH (AFOSRO AGENCY REPORT NUMBER 110 DUNCAN AVENUE, ROOM B115 BOLLING AFB DC 20332- 8050 11. SUPPLEMENTARY NOTES 12a...signals. Figure 5 shows a time series for an actuator that performs a ramp motion in the streamwise direction over about 1 % of the TS period and remains
Neural Network Classifies Teleoperation Data
NASA Technical Reports Server (NTRS)
Fiorini, Paolo; Giancaspro, Antonio; Losito, Sergio; Pasquariello, Guido
1994-01-01
Prototype artificial neural network, implemented in software, identifies phases of telemanipulator tasks in real time by analyzing feedback signals from force sensors on manipulator hand. Prototype is early, subsystem-level product of continuing effort to develop automated system that assists in training and supervising human control operator: provides symbolic feedback (e.g., warnings of impending collisions or evaluations of performance) to operator in real time during successive executions of same task. Also simplifies transition between teleoperation and autonomous modes of telerobotic system.
Optogenetics in Silicon: A Neural Processor for Predicting Optically Active Neural Networks.
Luo, Junwen; Nikolic, Konstantin; Evans, Benjamin D; Dong, Na; Sun, Xiaohan; Andras, Peter; Yakovlev, Alex; Degenaar, Patrick
2016-08-17
We present a reconfigurable neural processor for real-time simulation and prediction of opto-neural behaviour. We combined a detailed Hodgkin-Huxley CA3 neuron integrated with a four-state Channelrhodopsin-2 (ChR2) model into reconfigurable silicon hardware. Our architecture consists of a Field Programmable Gated Array (FPGA) with a custom-built computing data-path, a separate data management system and a memory approach based router. Advancements over previous work include the incorporation of short and long-term calcium and light-dependent ion channels in reconfigurable hardware. Also, the developed processor is computationally efficient, requiring only 0.03 ms processing time per sub-frame for a single neuron and 9.7 ms for a fully connected network of 500 neurons with a given FPGA frequency of 56.7 MHz. It can therefore be utilized for exploration of closed loop processing and tuning of biologically realistic optogenetic circuitry.
The Laplacian spectrum of neural networks.
de Lange, Siemon C; de Reus, Marcel A; van den Heuvel, Martijn P
2014-01-13
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.
An Analysis of Hardware Requirements for Airborne Tactical Mesh Networking Nodes
2005-03-01
Global PAGES Information Grid, MANET, Wireless, OLSR, Sensor Networks, Tactical 53 Network Topology, Single Board Computer , PC/104, Tern UAV 16. PRICE...21 A . HARDWARE .......................................... 21 1. Single Board Computer ........................ 21 2. Compact Flash...logical choice was to base an improved design on the PC/104 standard for embedded PC architecture. A. HARDWARE 1. Single Board Computer Embedded
Three dimensional living neural networks
NASA Astrophysics Data System (ADS)
Linnenberger, Anna; McLeod, Robert R.; Basta, Tamara; Stowell, Michael H. B.
2015-08-01
We investigate holographic optical tweezing combined with step-and-repeat maskless projection micro-stereolithography for fine control of 3D positioning of living cells within a 3D microstructured hydrogel grid. Samples were fabricated using three different cell lines; PC12, NT2/D1 and iPSC. PC12 cells are a rat cell line capable of differentiation into neuron-like cells NT2/D1 cells are a human cell line that exhibit biochemical and developmental properties similar to that of an early embryo and when exposed to retinoic acid the cells differentiate into human neurons useful for studies of human neurological disease. Finally induced pluripotent stem cells (iPSC) were utilized with the goal of future studies of neural networks fabricated from human iPSC derived neurons. Cells are positioned in the monomer solution with holographic optical tweezers at 1064 nm and then are encapsulated by photopolymerization of polyethylene glycol (PEG) hydrogels formed by thiol-ene photo-click chemistry via projection of a 512x512 spatial light modulator (SLM) illuminated at 405 nm. Fabricated samples are incubated in differentiation media such that cells cease to divide and begin to form axons or axon-like structures. By controlling the position of the cells within the encapsulating hydrogel structure the formation of the neural circuits is controlled. The samples fabricated with this system are a useful model for future studies of neural circuit formation, neurological disease, cellular communication, plasticity, and repair mechanisms.
Essential SpaceWire Hardware Capabilities for a Robust Network
NASA Technical Reports Server (NTRS)
Birmingham, Michael; Krimchansky, Alexander; Anderson, William; Lombardi, Matthew
2016-01-01
The Geostationary Operational Environmental Satellite R-Series Program (GOES-R) mission is a joint program between National Oceanic & Atmospheric Administration (NOAA) and National Aeronautics & Space Administration (NASA) Goddard Space Flight Center (GSFC). GOES-R project selected SpaceWire as the best solution to satisfy the desire for simple and flexible instrument to spacecraft command and telemetry communications. GOES-R development and integration is complete and the observatory is scheduled for launch October 2016. The spacecraft design was required to support redundant SpaceWire links for each instrument side, as well as to route the fewest number of connections through a Slip Ring Assembly necessary to support Solar pointing instruments. The final design utilized two different router designs. The SpaceWire standard alone does not ensure the most practical or reliable network. On GOES-R a few key hardware capabilities were identified that merit serious consideration for future designs. Primarily these capabilities address persistent port stalls and the prevention of receive buffer overflows. Workarounds were necessary to overcome shortcomings that could be avoided in future designs if they utilize the capabilities, discussed in this paper, above and beyond the requirements of the SpaceWire standard.
Neural Network Controlled Visual Saccades
NASA Astrophysics Data System (ADS)
Johnson, Jeffrey D.; Grogan, Timothy A.
1989-03-01
The paper to be presented will discuss research on a computer vision system controlled by a neural network capable of learning through classical (Pavlovian) conditioning. Through the use of unconditional stimuli (reward and punishment) the system will develop scan patterns of eye saccades necessary to differentiate and recognize members of an input set. By foveating only those portions of the input image that the system has found to be necessary for recognition the drawback of computational explosion as the size of the input image grows is avoided. The model incorporates many features found in animal vision systems, and is governed by understandable and modifiable behavior patterns similar to those reported by Pavlov in his classic study. These behavioral patterns are a result of a neuronal model, used in the network, explicitly designed to reproduce this behavior.
An overview on development of neural network technology
NASA Technical Reports Server (NTRS)
Lin, Chun-Shin
1993-01-01
The study has been to obtain a bird's-eye view of the current neural network technology and the neural network research activities in NASA. The purpose was two fold. One was to provide a reference document for NASA researchers who want to apply neural network techniques to solve their problems. Another one was to report out survey results regarding NASA research activities and provide a view on what NASA is doing, what potential difficulty exists and what NASA can/should do. In a ten week study period, we interviewed ten neural network researchers in the Langley Research Center and sent out 36 survey forms to researchers at the Johnson Space Center, Lewis Research Center, Ames Research Center and Jet Propulsion Laboratory. We also sent out 60 similar forms to educators and corporation researchers to collect general opinions regarding this field. Twenty-eight survey forms, 11 from NASA researchers and 17 from outside, were returned. Survey results were reported in our final report. In the final report, we first provided an overview on the neural network technology. We reviewed ten neural network structures, discussed the applications in five major areas, and compared the analog, digital and hybrid electronic implementation of neural networks. In the second part, we summarized known NASA neural network research studies and reported the results of the questionnaire survey. Survey results show that most studies are still in the development and feasibility study stage. We compared the techniques, application areas, researchers' opinions on this technology, and many aspects between NASA and non-NASA groups. We also summarized their opinions on difficulties encountered. Applications are considered the top research priority by most researchers. Hardware development and learning algorithm improvement are the next. The lack of financial and management support is among the difficulties in research study. All researchers agree that the use of neural networks could result in
Hand Gesture Recognition Using Neural Networks.
1996-05-01
inherent in the model. The high gesture recognition rates and quick network retraining times found in the present study suggest that a neural network approach to gesture recognition be further evaluated.
A new formulation for feedforward neural networks.
Razavi, Saman; Tolson, Bryan A
2011-10-01
Feedforward neural network is one of the most commonly used function approximation techniques and has been applied to a wide variety of problems arising from various disciplines. However, neural networks are black-box models having multiple challenges/difficulties associated with training and generalization. This paper initially looks into the internal behavior of neural networks and develops a detailed interpretation of the neural network functional geometry. Based on this geometrical interpretation, a new set of variables describing neural networks is proposed as a more effective and geometrically interpretable alternative to the traditional set of network weights and biases. Then, this paper develops a new formulation for neural networks with respect to the newly defined variables; this reformulated neural network (ReNN) is equivalent to the common feedforward neural network but has a less complex error response surface. To demonstrate the learning ability of ReNN, in this paper, two training methods involving a derivative-based (a variation of backpropagation) and a derivative-free optimization algorithms are employed. Moreover, a new measure of regularization on the basis of the developed geometrical interpretation is proposed to evaluate and improve the generalization ability of neural networks. The value of the proposed geometrical interpretation, the ReNN approach, and the new regularization measure are demonstrated across multiple test problems. Results show that ReNN can be trained more effectively and efficiently compared to the common neural networks and the proposed regularization measure is an effective indicator of how a network would perform in terms of generalization.
Extrapolation limitations of multilayer feedforward neural networks
NASA Technical Reports Server (NTRS)
Haley, Pamela J.; Soloway, Donald
1992-01-01
The limitations of backpropagation used as a function extrapolator were investigated. Four common functions were used to investigate the network's extrapolation capability. The purpose of the experiment was to determine whether neural networks are capable of extrapolation and, if so, to determine the range for which networks can extrapolate. The authors show that neural networks cannot extrapolate and offer an explanation to support this result.
Problem Specific applications for Neural Networks
1988-12-01
97 iv List Of Figures Figure Page 1. Neural Network Models ...... ............. 2 2. A Single - Layer Perceptron ..... ........... 4...the network is in use. Three of the most well-known neural networks are the single - layer perceptron , the multi-layer perceptron, and the Kohonen self...three of these networks can accept discrete (binary) or continuous inputs (5:6). 3 Single-Laver Perceptron. The single - layer perceptron (shown in Figure 2
Drift chamber tracking with neural networks
Lindsey, C.S.; Denby, B.; Haggerty, H.
1992-10-01
We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed.
Coherence resonance in bursting neural networks.
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.
Customizable VLSI artificial neural network chips based on a novel technology
Fu, C. Y.; Law, B.; Chapline, G.; Swenson, D.
1993-09-14
The human cerebral cortex contains approximately 10{sup 11} neurons and 10{sup 14} synapses. It thus seems logical that any technology intended to mimic human capabilities should have the ability to fabricate a very large number of neurons and even larger numbers of synapses. This paper describes an implementation of hardware neural networks using highly linear thin-film resistor technology and an 8-bit binary weight circuit to produce customizable artificial neural network chips and systems.
Neural Network Classification of Cerebral Embolic Signals
2007-11-02
application of new signal processing techniques to the analysis and classification of embolic signals. We applied a Wavelet Neural Network algorithm...to approximate the embolic signals, with the parameters of the wavelet nodes being used to train a Neural Network to classify these signals as resulting from normal flow, or from gaseous or solid emboli.
Multidisciplinary Studies of Integrated Neural Network Systems
1994-03-01
They accomplish this by partitioning the system into functional sub-units in a quasi-hierarchical structure of neural network modules. We studied...three specific examples of this system integration strategy and modeled their operation for the purpose of creating new neural network architectures and
Neural Network Research: A Personal Perspective,
1988-03-01
These vision preprocessor and ART autonomous classifier examples are just two of the many neural network architectures now being developed by...computational theories with natural realizations as real-time adaptive neural network architectures with promising properties for tackling some of the
Neural Network Based Helicopter Low Airspeed Indicator
1996-10-24
This invention relates generally to virtual sensors and, more particularly, to a means and method utilizing a neural network for estimating...helicopter airspeed at speeds below about 50 knots using only fixed system parameters (i.e., parameters measured or determined in a reference frame fixed relative to the helicopter fuselage) as inputs to the neural network .
Evolving Neural Networks for Nonlinear Control.
1996-09-30
An approach to creating Amorphous Recurrent Neural Networks (ARNN) using Genetic Algorithms (GA) called 2pGA has been developed and shown to be...effective in evolving neural networks for the control and stabilization of both linear and nonlinear plants, the optimal control for a nonlinear regulator
Online guidance updates using neural networks
NASA Astrophysics Data System (ADS)
Filici, Cristian; Sánchez Peña, Ricardo S.
2010-02-01
The aim of this article is to present a method for the online guidance update for a launcher ascent trajectory that is based on the utilization of a neural network approximator. Generation of training patterns and selection of the input and output spaces of the neural network are presented, and implementation issues are discussed. The method is illustrated by a 2-dimensional launcher simulation.
Neural network based architectures for aerospace applications
NASA Technical Reports Server (NTRS)
Ricart, Richard
1987-01-01
A brief history of the field of neural networks research is given and some simple concepts are described. In addition, some neural network based avionics research and development programs are reviewed. The need for the United States Air Force and NASA to assume a leadership role in supporting this technology is stressed.
Isolated Speech Recognition Using Artificial Neural Networks
2007-11-02
In this project Artificial Neural Networks are used as research tool to accomplish Automated Speech Recognition of normal speech. A small size...the first stage of this work are satisfactory and thus the application of artificial neural networks in conjunction with cepstral analysis in isolated word recognition holds promise.
Self-organization of neural networks
NASA Astrophysics Data System (ADS)
Clark, John W.; Winston, Jeffrey V.; Rafelski, Johann
1984-05-01
The plastic development of a neural-network model operating autonomously in discrete time is described by the temporal modification of interneuronal coupling strengths according to momentary neural activity. A simple algorithm (“brainwashing”) is found which, applied to nets with initially quasirandom connectivity, leads to model networks with properties conductive to the simulation of memory and learning phenomena.
Neural network classification - A Bayesian interpretation
NASA Technical Reports Server (NTRS)
Wan, Eric A.
1990-01-01
The relationship between minimizing a mean squared error and finding the optimal Bayesian classifier is reviewed. This provides a theoretical interpretation for the process by which neural networks are used in classification. A number of confidence measures are proposed to evaluate the performance of the neural network classifier within a statistical framework.
Radiation Behavior of Analog Neural Network Chip
NASA Technical Reports Server (NTRS)
Langenbacher, H.; Zee, F.; Daud, T.; Thakoor, A.
1996-01-01
A neural network experiment conducted for the Space Technology Research Vehicle (STRV-1) 1-b launched in June 1994. Identical sets of analog feed-forward neural network chips was used to study and compare the effects of space and ground radiation on the chips. Three failure mechanisms are noted.
Medical image analysis with artificial neural networks.
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.
Neural Networks for Handwritten English Alphabet Recognition
NASA Astrophysics Data System (ADS)
Perwej, Yusuf; Chaturvedi, Ashish
2011-04-01
This paper demonstrates the use of neural networks for developing a system that can recognize hand-written English alphabets. In this system, each English alphabet is represented by binary values that are used as input to a simple feature extraction system, whose output is fed to our neural network system.
A Survey of Neural Network Publications.
ERIC Educational Resources Information Center
Vijayaraman, Bindiganavale S.; Osyk, Barbara
This paper is a survey of publications on artificial neural networks published in business journals for the period ending July 1996. Its purpose is to identify and analyze trends in neural network research during that period. This paper shows which topics have been heavily researched, when these topics were researched, and how that research has…
Applications of Neural Networks in Finance.
ERIC Educational Resources Information Center
Crockett, Henry; Morrison, Ronald
1994-01-01
Discusses research with neural networks in the area of finance. Highlights include bond pricing, theoretical exposition of primary bond pricing, bond pricing regression model, and an example that created networks with corporate bonds and NeuralWare Neuralworks Professional H software using the back-propagation technique. (LRW)
Neural Network Algorithm for Particle Loading
J. L. V. Lewandowski
2003-04-25
An artificial neural network algorithm for continuous minimization is developed and applied to the case of numerical particle loading. It is shown that higher-order moments of the probability distribution function can be efficiently renormalized using this technique. A general neural network for the renormalization of an arbitrary number of moments is given.
Adaptive Neurons For Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Tawel, Raoul
1990-01-01
Training time decreases dramatically. In improved mathematical model of neural-network processor, temperature of neurons (in addition to connection strengths, also called weights, of synapses) varied during supervised-learning phase of operation according to mathematical formalism and not heuristic rule. Evidence that biological neural networks also process information at neuronal level.
Neural networks applications to control and computations
NASA Technical Reports Server (NTRS)
Luxemburg, Leon A.
1994-01-01
Several interrelated problems in the area of neural network computations are described. First an interpolation problem is considered, then a control problem is reduced to a problem of interpolation by a neural network via Lyapunov function approach, and finally a new, faster method of learning as compared with the gradient descent method, was introduced.
Forecasting Jet Fuel Prices Using Artificial Neural Networks.
1995-03-01
Artificial neural networks provide a new approach to commodity forecasting that does not require algorithm or rule development. Neural networks have...NeuralWare, more people can take advantage of the power of artificial neural networks . This thesis provides an introduction to neural networks, and reviews
Introduction to Concepts in Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Niebur, Dagmar
1995-01-01
This introduction to artificial neural networks summarizes some basic concepts of computational neuroscience and the resulting models of artificial neurons. The terminology of biological and artificial neurons, biological and machine learning and neural processing is introduced. The concepts of supervised and unsupervised learning are explained with examples from the power system area. Finally, a taxonomy of different types of neurons and different classes of artificial neural networks is presented.
Pruning artificial neural networks using neural complexity measures.
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.
Enhancing neural-network performance via assortativity
Franciscis, Sebastiano de; Johnson, Samuel; Torres, Joaquin J.
2011-03-15
The performance of attractor neural networks has been shown to depend crucially on the heterogeneity of the underlying topology. We take this analysis a step further by examining the effect of degree-degree correlations - assortativity - on neural-network behavior. We make use of a method recently put forward for studying correlated networks and dynamics thereon, both analytically and computationally, which is independent of how the topology may have evolved. We show how the robustness to noise is greatly enhanced in assortative (positively correlated) neural networks, especially if it is the hub neurons that store the information.
Enhancing neural-network performance via assortativity.
de Franciscis, Sebastiano; Johnson, Samuel; Torres, Joaquín J
2011-03-01
The performance of attractor neural networks has been shown to depend crucially on the heterogeneity of the underlying topology. We take this analysis a step further by examining the effect of degree-degree correlations--assortativity--on neural-network behavior. We make use of a method recently put forward for studying correlated networks and dynamics thereon, both analytically and computationally, which is independent of how the topology may have evolved. We show how the robustness to noise is greatly enhanced in assortative (positively correlated) neural networks, especially if it is the hub neurons that store the information.
Sunspot prediction using neural networks
NASA Technical Reports Server (NTRS)
Villarreal, James; Baffes, Paul
1990-01-01
The earliest systematic observance of sunspot activity is known to have been discovered by the Chinese in 1382 during the Ming Dynasty (1368 to 1644) when spots on the sun were noticed by looking at the sun through thick, forest fire smoke. Not until after the 18th century did sunspot levels become more than a source of wonderment and curiosity. Since 1834 reliable sunspot data has been collected by the National Oceanic and Atmospheric Administration (NOAA) and the U.S. Naval Observatory. Recently, considerable effort has been placed upon the study of the effects of sunspots on the ecosystem and the space environment. The efforts of the Artificial Intelligence Section of the Mission Planning and Analysis Division of the Johnson Space Center involving the prediction of sunspot activity using neural network technologies are described.
Wavelet differential neural network observer.
Chairez, Isaac
2009-09-01
State estimation for uncertain systems affected by external noises is an important problem in control theory. This paper deals with a state observation problem when the dynamic model of a plant contains uncertainties or it is completely unknown. Differential neural network (NN) approach is applied in this uninformative situation but with activation functions described by wavelets. A new learning law, containing an adaptive adjustment rate, is suggested to imply the stability condition for the free parameters of the observer. Nominal weights are adjusted during the preliminary training process using the least mean square (LMS) method. Lyapunov theory is used to obtain the upper bounds for the weights dynamics as well as for the mean squared estimation error. Two numeric examples illustrate this approach: first, a nonlinear electric system, governed by the Chua's equation and second the Lorentz oscillator. Both systems are assumed to be affected by external perturbations and their parameters are unknown.
Forecasting disruptions in the ADITYA tokamak using neural networks
NASA Astrophysics Data System (ADS)
Sengupta, A.; Ranjan, P.
2000-12-01
A neural network technique has been used to predict disruptions in the ADITYA tokamak. A time series prediction method is employed whereby a series of past values of some time dependent quantity is used to predict its value in the future. The time varying observables used in the present work are the different diagnostic signals from four Mirnov probes, one soft X ray monitor and one Hα monitor. The predicted quantities are the same observables at some future time. The neural network is trained with the past values of the different diagnostic signals as inputs and the future values of the same quantities as targets. The trained neural network is used to forecast in a multistep sequence. This amounts to a prediction several time steps earlier. Very good prediction results have been obtained up to 8 ms earlier with little distortion of the signals and no appreciable time lag, a capability which is believed to be well suited to the task of on-line predictions of disruptions in ADITYA. As actual experimental signals are used, confidence regarding the performance of the neural network on hardware implementation is automatically ensured.
Application of neural networks to flight test diagnostics
Wheeler, R.M. Jr.; Sheaffer, D.A.
1991-08-01
A system has been designed which can provide summary information about specific noisy electric pulses that are generated during flight testing. This is important from a telemetry viewpoint, since limited bandwidth often rules out transmitting all of the pulse data. The system is based on a neural network processing paradigm. The neural network serves as a mapping between pulse data inputs and pulse category outputs. Output categories correspond to presence or type of component failure. Extensive computer simulations have shown that the system can recognize qualitative pulse features which are useful for diagnostic purposes. A second version of the system, also using a neural network, was designed to perform data compression. In this case, an entire pulse is efficiently coded for transmission and the original signal is reconstructed upon receiving the coded transmission. Successful simulations for both systems have demonstrated feasibility and have led to a hardware development effort aimed at prototyping a fieldable system. Based on these results, it appears that the neural network approach may be applicable to other diagnostic and data analysis problems arising in component or system testing. 3 refs., 16 figs., 2 tabs.
Tampa Electric Neural Network Sootblowing
Mark A. Rhode
2002-09-30
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NO{sub x} formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent soot-blowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, online, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce {sub x} emissions and improve heat rate
Tampa Electric Neural Network Sootblowing
Mark A. Rhode
2004-09-30
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NOx formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent sootblowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate around
Tampa Electric Neural Network Sootblowing
Mark A. Rhode
2004-03-31
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NOx formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing co-funding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent sootblowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate around
Tampa Electric Neural Network Sootblowing
Mark A. Rhode
2003-12-31
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NO{sub x} formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent soot-blowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate
Neural networks for damage identification
Paez, T.L.; Klenke, S.E.
1997-11-01
Efforts to optimize the design of mechanical systems for preestablished use environments and to extend the durations of use cycles establish a need for in-service health monitoring. Numerous studies have proposed measures of structural response for the identification of structural damage, but few have suggested systematic techniques to guide the decision as to whether or not damage has occurred based on real data. Such techniques are necessary because in field applications the environments in which systems operate and the measurements that characterize system behavior are random. This paper investigates the use of artificial neural networks (ANNs) to identify damage in mechanical systems. Two probabilistic neural networks (PNNs) are developed and used to judge whether or not damage has occurred in a specific mechanical system, based on experimental measurements. The first PNN is a classical type that casts Bayesian decision analysis into an ANN framework; it uses exemplars measured from the undamaged and damaged system to establish whether system response measurements of unknown origin come from the former class (undamaged) or the latter class (damaged). The second PNN establishes the character of the undamaged system in terms of a kernel density estimator of measures of system response; when presented with system response measures of unknown origin, it makes a probabilistic judgment whether or not the data come from the undamaged population. The physical system used to carry out the experiments is an aerospace system component, and the environment used to excite the system is a stationary random vibration. The results of damage identification experiments are presented along with conclusions rating the effectiveness of the approaches.
Nonlinear programming with feedforward neural networks.
Reifman, J.
1999-06-02
We provide a practical and effective method for solving constrained optimization problems by successively training a multilayer feedforward neural network in a coupled neural-network/objective-function representation. Nonlinear programming problems are easily mapped into this representation which has a simpler and more transparent method of solution than optimization performed with Hopfield-like networks and poses very mild requirements on the functions appearing in the problem. Simulation results are illustrated and compared with an off-the-shelf optimization tool.
VLSI Cells Placement Using the Neural Networks
Azizi, Hacene; Zouaoui, Lamri; Mokhnache, Salah
2008-06-12
The artificial neural networks have been studied for several years. Their effectiveness makes it possible to expect high performances. The privileged fields of these techniques remain the recognition and classification. Various applications of optimization are also studied under the angle of the artificial neural networks. They make it possible to apply distributed heuristic algorithms. In this article, a solution to placement problem of the various cells at the time of the realization of an integrated circuit is proposed by using the KOHONEN network.
Memristor-based neural networks: Synaptic versus neuronal stochasticity
NASA Astrophysics Data System (ADS)
Naous, Rawan; AlShedivat, Maruan; Neftci, Emre; Cauwenberghs, Gert; Salama, Khaled Nabil
2016-11-01
In neuromorphic circuits, stochasticity in the cortex can be mapped into the synaptic or neuronal components. The hardware emulation of these stochastic neural networks are currently being extensively studied using resistive memories or memristors. The ionic process involved in the underlying switching behavior of the memristive elements is considered as the main source of stochasticity of its operation. Building on its inherent variability, the memristor is incorporated into abstract models of stochastic neurons and synapses. Two approaches of stochastic neural networks are investigated. Aside from the size and area perspective, the impact on the system performance, in terms of accuracy, recognition rates, and learning, among these two approaches and where the memristor would fall into place are the main comparison points to be considered.
Neural network regulation driven by autonomous neural firings
NASA Astrophysics Data System (ADS)
Cho, Myoung Won
2016-07-01
Biological neurons naturally fire spontaneously due to the existence of a noisy current. Such autonomous firings may provide a driving force for network formation because synaptic connections can be modified due to neural firings. Here, we study the effect of autonomous firings on network formation. For the temporally asymmetric Hebbian learning, bidirectional connections lose their balance easily and become unidirectional ones. Defining the difference between reciprocal connections as new variables, we could express the learning dynamics as if Ising model spins interact with each other in magnetism. We present a theoretical method to estimate the interaction between the new variables in a neural system. We apply the method to some network systems and find some tendencies of autonomous neural network regulation.
Object detection using pulse coupled neural networks.
Ranganath, H S; Kuntimad, G
1999-01-01
This paper describes an object detection system based on pulse coupled neural networks. The system is designed and implemented to illustrate the power, flexibility and potential the pulse coupled neural networks have in real-time image processing. In the preprocessing stage, a pulse coupled neural network suppresses noise by smoothing the input image. In the segmentation stage, a second pulse coupled neural-network iteratively segments the input image. During each iteration, with the help of a control module, the segmentation network deletes regions that do not satisfy the retention criteria from further processing and produces an improved segmentation of the retained image. In the final stage each group of connected regions that satisfies the detection criteria is identified as an instance of the object of interest.
A neural network prototyping package within IRAF
NASA Technical Reports Server (NTRS)
Bazell, D.; Bankman, I.
1992-01-01
We outline our plans for incorporating a Neural Network Prototyping Package into the IRAF environment. The package we are developing will allow the user to choose between different types of networks and to specify the details of the particular architecture chosen. Neural networks consist of a highly interconnected set of simple processing units. The strengths of the connections between units are determined by weights which are adaptively set as the network 'learns'. In some cases, learning can be a separate phase of the user cycle of the network while in other cases the network learns continuously. Neural networks have been found to be very useful in pattern recognition and image processing applications. They can form very general 'decision boundaries' to differentiate between objects in pattern space and they can be used for associative recall of patterns based on partial cures and for adaptive filtering. We discuss the different architectures we plan to use and give examples of what they can do.
Description of interatomic interactions with neural networks
NASA Astrophysics Data System (ADS)
Hajinazar, Samad; Shao, Junping; Kolmogorov, Aleksey N.
Neural networks are a promising alternative to traditional classical potentials for describing interatomic interactions. Recent research in the field has demonstrated how arbitrary atomic environments can be represented with sets of general functions which serve as an input for the machine learning tool. We have implemented a neural network formalism in the MAISE package and developed a protocol for automated generation of accurate models for multi-component systems. Our tests illustrate the performance of neural networks and known classical potentials for a range of chemical compositions and atomic configurations. Supported by NSF Grant DMR-1410514.
Pricing financial derivatives with neural networks
NASA Astrophysics Data System (ADS)
Morelli, Marco J.; Montagna, Guido; Nicrosini, Oreste; Treccani, Michele; Farina, Marco; Amato, Paolo
2004-07-01
Neural network algorithms are applied to the problem of option pricing and adopted to simulate the nonlinear behavior of such financial derivatives. Two different kinds of neural networks, i.e. multi-layer perceptrons and radial basis functions, are used and their performances compared in detail. The analysis is carried out both for standard European options and American ones, including evaluation of the Greek letters, necessary for hedging purposes. Detailed numerical investigation show that, after a careful phase of training, neural networks are able to predict the value of options and Greek letters with high accuracy and competitive computational time.
Genetic algorithm for neural networks optimization
NASA Astrophysics Data System (ADS)
Setyawati, Bina R.; Creese, Robert C.; Sahirman, Sidharta
2004-11-01
This paper examines the forecasting performance of multi-layer feed forward neural networks in modeling a particular foreign exchange rates, i.e. Japanese Yen/US Dollar. The effects of two learning methods, Back Propagation and Genetic Algorithm, in which the neural network topology and other parameters fixed, were investigated. The early results indicate that the application of this hybrid system seems to be well suited for the forecasting of foreign exchange rates. The Neural Networks and Genetic Algorithm were programmed using MATLAB«.
Noise cancellation of memristive neural networks.
Wen, Shiping; Zeng, Zhigang; Huang, Tingwen; Yu, Xinghuo
2014-12-01
This paper investigates noise cancellation problem of memristive neural networks. Based on the reproducible gradual resistance tuning in bipolar mode, a first-order voltage-controlled memristive model is employed with asymmetric voltage thresholds. Since memristive devices are especially tiny to be densely packed in crossbar-like structures and possess long time memory needed by neuromorphic synapses, this paper shows how to approximate the behavior of synapses in neural networks using this memristive device. Also certain templates of memristive neural networks are established to implement the noise cancellation.
Neural network with formed dynamics of activity
Dunin-Barkovskii, V.L.; Osovets, N.B.
1995-03-01
The problem of developing a neural network with a given pattern of the state sequence is considered. A neural network structure and an algorithm, of forming its bond matrix which lead to an approximate but robust solution of the problem are proposed and discussed. Limiting characteristics of the serviceability of the proposed structure are studied. Various methods of visualizing dynamic processes in a neural network are compared. Possible applications of the results obtained for interpretation of neurophysiological data and in neuroinformatics systems are discussed.
Neural networks techniques applied to reservoir engineering
Flores, M.; Barragan, C.
1995-12-31
Neural Networks are considered the greatest technological advance since the transistor. They are expected to be a common household item by the year 2000. An attempt to apply Neural Networks to an important geothermal problem has been made, predictions on the well production and well completion during drilling in a geothermal field. This was done in Los Humeros geothermal field, using two common types of Neural Network models, available in commercial software. Results show the learning capacity of the developed model, and its precision in the predictions that were made.
Stock market index prediction using neural networks
NASA Astrophysics Data System (ADS)
Komo, Darmadi; Chang, Chein-I.; Ko, Hanseok
1994-03-01
A neural network approach to stock market index prediction is presented. Actual data of the Wall Street Journal's Dow Jones Industrial Index has been used for a benchmark in our experiments where Radial Basis Function based neural networks have been designed to model these indices over the period from January 1988 to Dec 1992. A notable success has been achieved with the proposed model producing over 90% prediction accuracies observed based on monthly Dow Jones Industrial Index predictions. The model has also captured both moderate and heavy index fluctuations. The experiments conducted in this study demonstrated that the Radial Basis Function neural network represents an excellent candidate to predict stock market index.
Review On Applications Of Neural Network To Computer Vision
NASA Astrophysics Data System (ADS)
Li, Wei; Nasrabadi, Nasser M.
1989-03-01
Neural network models have many potential applications to computer vision due to their parallel structures, learnability, implicit representation of domain knowledge, fault tolerance, and ability of handling statistical data. This paper demonstrates the basic principles, typical models and their applications in this field. Variety of neural models, such as associative memory, multilayer back-propagation perceptron, self-stabilized adaptive resonance network, hierarchical structured neocognitron, high order correlator, network with gating control and other models, can be applied to visual signal recognition, reinforcement, recall, stereo vision, motion, object tracking and other vision processes. Most of the algorithms have been simulated on com-puters. Some have been implemented with special hardware. Some systems use features, such as edges and profiles, of images as the data form for input. Other systems use raw data as input signals to the networks. We will present some novel ideas contained in these approaches and provide a comparison of these methods. Some unsolved problems are mentioned, such as extracting the intrinsic properties of the input information, integrating those low level functions to a high-level cognitive system, achieving invariances and other problems. Perspectives of applications of some human vision models and neural network models are analyzed.
Threshold control of chaotic neural network.
He, Guoguang; Shrimali, Manish Dev; Aihara, Kazuyuki
2008-01-01
The chaotic neural network constructed with chaotic neurons exhibits rich dynamic behaviour with a nonperiodic associative memory. In the chaotic neural network, however, it is difficult to distinguish the stored patterns in the output patterns because of the chaotic state of the network. In order to apply the nonperiodic associative memory into information search, pattern recognition etc. it is necessary to control chaos in the chaotic neural network. We have studied the chaotic neural network with threshold activated coupling, which provides a controlled network with associative memory dynamics. The network converges to one of its stored patterns or/and reverse patterns which has the smallest Hamming distance from the initial state of the network. The range of the threshold applied to control the neurons in the network depends on the noise level in the initial pattern and decreases with the increase of noise. The chaos control in the chaotic neural network by threshold activated coupling at varying time interval provides controlled output patterns with different temporal periods which depend upon the control parameters.
Nonequilibrium landscape theory of neural networks.
Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin
2013-11-05
The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape-flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments.
Implementation of pattern recognition algorithm based on RBF neural network
NASA Astrophysics Data System (ADS)
Bouchoux, Sophie; Brost, Vincent; Yang, Fan; Grapin, Jean Claude; Paindavoine, Michel
2002-12-01
In this paper, we present implementations of a pattern recognition algorithm which uses a RBF (Radial Basis Function) neural network. Our aim is to elaborate a quite efficient system which realizes real time faces tracking and identity verification in natural video sequences. Hardware implementations have been realized on an embedded system developed by our laboratory. This system is based on a DSP (Digital Signal Processor) TMS320C6x. The optimization of implementations allow us to obtain a processing speed of 4.8 images (240x320 pixels) per second with a correct rate of 95% of faces tracking and identity verification.
Low Temperature Performance of High-Speed Neural Network Circuits
NASA Technical Reports Server (NTRS)
Duong, T.; Tran, M.; Daud, T.; Thakoor, A.
1995-01-01
Artificial neural networks, derived from their biological counterparts, offer a new and enabling computing paradigm specially suitable for such tasks as image and signal processing with feature classification/object recognition, global optimization, and adaptive control. When implemented in fully parallel electronic hardware, it offers orders of magnitude speed advantage. Basic building blocks of the new architecture are the processing elements called neurons implemented as nonlinear operational amplifiers with sigmoidal transfer function, interconnected through weighted connections called synapses implemented using circuitry for weight storage and multiply functions either in an analog, digital, or hybrid scheme.
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…
Results of the neural network investigation
NASA Astrophysics Data System (ADS)
Uvanni, Lee A.
1992-04-01
Rome Laboratory has designed and implemented a neural network based automatic target recognition (ATR) system under contract F30602-89-C-0079 with Booz, Allen & Hamilton (BAH), Inc., of Arlington, Virginia. The system utilizes a combination of neural network paradigms and conventional image processing techniques in a parallel environment on the IE- 2000 SUN 4 workstation at Rome Laboratory. The IE-2000 workstation was designed to assist the Air Force and Department of Defense to derive the needs for image exploitation and image exploitation support for the late 1990s - year 2000 time frame. The IE-2000 consists of a developmental testbed and an applications testbed, both with the goal of solving real world problems on real-world facilities for image exploitation. To fully exploit the parallel nature of neural networks, 18 Inmos T800 transputers were utilized, in an attempt to provide a near- linear speed-up for each subsystem component implemented on them. The initial design contained three well-known neural network paradigms, each modified by BAH to some extent: the Selective Attention Neocognitron (SAN), the Binary Contour System/Feature Contour System (BCS/FCS), and Adaptive Resonance Theory 2 (ART-2), and one neural network designed by BAH called the Image Variance Exploitation Network (IVEN). Through rapid prototyping, the initial system evolved into a completely different final design, called the Neural Network Image Exploitation System (NNIES), where the final system consists of two basic components: the Double Variance (DV) layer and the Multiple Object Detection And Location System (MODALS). A rapid prototyping neural network CAD Tool, designed by Booz, Allen & Hamilton, was used to rapidly build and emulate the neural network paradigms. Evaluation of the completed ATR system included probability of detections and probability of false alarms among other measures.
Recognition of Telugu characters using neural networks.
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.
Neural Networks for Dynamic Flight Control
1993-12-01
uses the Adaline (22) model for development of the neural networks. Neural Graphics and other AFIT applications use a slightly different model. The...primary difference in the Nguyen application is that the Adaline uses the nonlinear function .f(a) = tanh(a) where standard backprop uses the sigmoid
Radar signal categorization using a neural network
NASA Technical Reports Server (NTRS)
Anderson, James A.; Gately, Michael T.; Penz, P. Andrew; Collins, Dean R.
1991-01-01
Neural networks were used to analyze a complex simulated radar environment which contains noisy radar pulses generated by many different emitters. The neural network used is an energy minimizing network (the BSB model) which forms energy minima - attractors in the network dynamical system - based on learned input data. The system first determines how many emitters are present (the deinterleaving problem). Pulses from individual simulated emitters give rise to separate stable attractors in the network. Once individual emitters are characterized, it is possible to make tentative identifications of them based on their observed parameters. As a test of this idea, a neural network was used to form a small data base that potentially could make emitter identifications.
Constructive Autoassociative Neural Network for Facial Recognition
Fernandes, Bruno J. T.; Cavalcanti, George D. C.; Ren, Tsang I.
2014-01-01
Autoassociative artificial neural networks have been used in many different computer vision applications. However, it is difficult to define the most suitable neural network architecture because this definition is based on previous knowledge and depends on the problem domain. To address this problem, we propose a constructive autoassociative neural network called CANet (Constructive Autoassociative Neural Network). CANet integrates the concepts of receptive fields and autoassociative memory in a dynamic architecture that changes the configuration of the receptive fields by adding new neurons in the hidden layer, while a pruning algorithm removes neurons from the output layer. Neurons in the CANet output layer present lateral inhibitory connections that improve the recognition rate. Experiments in face recognition and facial expression recognition show that the CANet outperforms other methods presented in the literature. PMID:25542018
A neural network architecture for data classification.
Lezoray, O
2001-02-01
This article aims at showing an architecture of neural networks designed for the classification of data distributed among a high number of classes. A significant gain in the global classification rate can be obtained by using our architecture. This latter is based on a set of several little neural networks, each one discriminating only two classes. The specialization of each neural network simplifies their structure and improves the classification. Moreover, the learning step automatically determines the number of hidden neurons. The discussion is illustrated by tests on databases from the UCI machine learning database repository. The experimental results show that this architecture can achieve a faster learning, simpler neural networks and an improved performance in classification.
Neural Network Solutions to Optical Absorption Spectra
NASA Astrophysics Data System (ADS)
Rosenbrock, Conrad
2012-10-01
Artificial neural networks have been effective in reducing computation time while achieving remarkable accuracy for a variety of difficult physics problems. Neural networks are trained iteratively by adjusting the size and shape of sums of non-linear functions by varying the function parameters to fit results for complex non-linear systems. For smaller structures, ab initio simulation methods can be used to determine absorption spectra under field perturbations. However, these methods are impractical for larger structures. Designing and training an artificial neural network with simulated data from time-dependent density functional theory may allow time-dependent perturbation effects to be calculated more efficiently. I investigate the design considerations and results of neural network implementations for calculating perturbation-coupled electron oscillations in small molecules.
Imbibition well stimulation via neural network design
Weiss, William
2007-08-14
A method for stimulation of hydrocarbon production via imbibition by utilization of surfactants. The method includes use of fuzzy logic and neural network architecture constructs to determine surfactant use.
Temporal Coding in Realistic Neural Networks
NASA Astrophysics Data System (ADS)
Gerasyuta, S. M.; Ivanov, D. V.
1995-10-01
The modification of realistic neural network model have been proposed. The model differs from the Hopfield model because of the two characteristic contributions to synaptic efficacious: the short-time contribution which is determined by the chemical reactions in the synapses and the long-time contribution corresponding to the structural changes of synaptic contacts. The approximation solution of the realistic neural network model equations is obtained. This solution allows us to calculate the postsynaptic potential as function of input. Using the approximate solution of realistic neural network model equations the behaviour of postsynaptic potential of realistic neural network as function of time for the different temporal sequences of stimuli is described. The various outputs are obtained for the different temporal sequences of the given stimuli. These properties of the temporal coding can be exploited as a recognition element capable of being selectively tuned to different inputs.
A neural network for bounded linear programming
Culioli, J.C.; Protopopescu, V.; Britton, C.; Ericson, N. )
1989-01-01
The purpose of this paper is to describe a neural network implementation of an algorithm recently designed at ORNL to solve the Transportation and the Assignment Problems, and, more generally, any explicitly bounded linear program. 9 refs.
Blood glucose prediction using neural network
NASA Astrophysics Data System (ADS)
Soh, Chit Siang; Zhang, Xiqin; Chen, Jianhong; Raveendran, P.; Soh, Phey Hong; Yeo, Joon Hock
2008-02-01
We used neural network for blood glucose level determination in this study. The data set used in this study was collected using a non-invasive blood glucose monitoring system with six laser diodes, each laser diode operating at distinct near infrared wavelength between 1500nm and 1800nm. The neural network is specifically used to determine blood glucose level of one individual who participated in an oral glucose tolerance test (OGTT) session. Partial least squares regression is also used for blood glucose level determination for the purpose of comparison with the neural network model. The neural network model performs better in the prediction of blood glucose level as compared with the partial least squares model.
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.
Neural networks in front-end processing and control
Lister, J.B.; Schnurrenberger, H.; Staeheli, N.; Stockhammer, N.; Duperrex, P.A.; Moret, J.M. )
1992-04-01
Research into neural networks has gained a large following in recent years. In spite of the long term timescale of this Artificial Intelligence research, the tools which the community is developing can already find useful applications to real practical problems in experimental research. One of the main advantages of the parallel algorithms being developed in AI is the structural simplicity of the required hardware implementation, and the simple nature of the calculations involved. This makes these techniques ideal for problems in which both speed and data volume reduction are important, the case for most front-end processing tasks. In this paper the authors illustrate the use of a particular neural network known as the Multi-Layer Perceptron as a method for solving several different tasks, all drawn from the field of Tokamak research. The authors also briefly discuss the use of the Multi-Layer Perceptron as a non-linear controller in a feedback loop. The authors outline the type of problem which can be usefully addressed by these techniques, even before the large-scale parallel processing hardware currently under development becomes cheaply available. The authors also present some of the difficulties encountered in applying these networks.
A New Stochastic Computing Methodology for Efficient Neural Network Implementation.
Canals, Vincent; Morro, Antoni; Oliver, Antoni; Alomar, Miquel L; Rosselló, Josep L
2016-03-01
This paper presents a new methodology for the hardware implementation of neural networks (NNs) based on probabilistic laws. The proposed encoding scheme circumvents the limitations of classical stochastic computing (based on unipolar or bipolar encoding) extending the representation range to any real number using the ratio of two bipolar-encoded pulsed signals. Furthermore, the novel approach presents practically a total noise-immunity capability due to its specific codification. We introduce different designs for building the fundamental blocks needed to implement NNs. The validity of the present approach is demonstrated through a regression and a pattern recognition task. The low cost of the methodology in terms of hardware, along with its capacity to implement complex mathematical functions (such as the hyperbolic tangent), allows its use for building highly reliable systems and parallel computing.
Application of artificial neural networks to gaming
NASA Astrophysics Data System (ADS)
Baba, Norio; Kita, Tomio; Oda, Kazuhiro
1995-04-01
Recently, neural network technology has been applied to various actual problems. It has succeeded in producing a large number of intelligent systems. In this article, we suggest that it could be applied to the field of gaming. In particular, we suggest that the neural network model could be used to mimic players' characters. Several computer simulation results using a computer gaming system which is a modified version of the COMMONS GAME confirm our idea.
Using neural networks in software repositories
NASA Technical Reports Server (NTRS)
Eichmann, David (Editor); Srinivas, Kankanahalli; Boetticher, G.
1992-01-01
The first topic is an exploration of the use of neural network techniques to improve the effectiveness of retrieval in software repositories. The second topic relates to a series of experiments conducted to evaluate the feasibility of using adaptive neural networks as a means of deriving (or more specifically, learning) measures on software. Taken together, these two efforts illuminate a very promising mechanism supporting software infrastructures - one based upon a flexible and responsive technology.
Limitations of opto-electronic neural networks
NASA Technical Reports Server (NTRS)
Yu, Jeffrey; Johnston, Alan; Psaltis, Demetri; Brady, David
1989-01-01
Consideration is given to the limitations of implementing neurons, weights, and connections in neural networks for electronics and optics. It is shown that the advantages of each technology are utilized when electronically fabricated neurons are included and a combination of optics and electronics are employed for the weights and connections. The relationship between the types of neural networks being constructed and the choice of technologies to implement the weights and connections is examined.
Predicting Car Production using a Neural Network
2003-04-24
World Almanac Education Group, 2003 [8] E. Petroutsos, Mastering Visual Basic .NET, SYBEX Inc., 2002 [9] D. E. Rumelhart, J. L. McClelland, Parallel...In this example, 100,000 cycles (epochs) were used to train it. The initial weights were randomly selected from values between 1 and -1. Visual ... basic .NET was used to program the neural network [8]. The neural network algorithm followed the steps outlined in [9]. As stated above, a 3 layer
Neural network for image segmentation
NASA Astrophysics Data System (ADS)
Skourikhine, Alexei N.; Prasad, Lakshman; Schlei, Bernd R.
2000-10-01
Image analysis is an important requirement of many artificial intelligence systems. Though great effort has been devoted to inventing efficient algorithms for image analysis, there is still much work to be done. It is natural to turn to mammalian vision systems for guidance because they are the best known performers of visual tasks. The pulse- coupled neural network (PCNN) model of the cat visual cortex has proven to have interesting properties for image processing. This article describes the PCNN application to the processing of images of heterogeneous materials; specifically PCNN is applied to image denoising and image segmentation. Our results show that PCNNs do well at segmentation if we perform image smoothing prior to segmentation. We use PCNN for obth smoothing and segmentation. Combining smoothing and segmentation enable us to eliminate PCNN sensitivity to the setting of the various PCNN parameters whose optimal selection can be difficult and can vary even for the same problem. This approach makes image processing based on PCNN more automatic in our application and also results in better segmentation.
Artificial neural network and medicine.
Khan, Z H; Mohapatra, S K; Khodiar, P K; Ragu Kumar, S N
1998-07-01
The introduction of human brain functions such as perception and cognition into the computer has been made possible by the use of Artificial Neural Network (ANN). ANN are computer models inspired by the structure and behavior of neurons. Like the brain, ANN can recognize patterns, manage data and most significantly, learn. This learning ability, not seen in other computer models simulating human intelligence, constantly improves its functional accuracy as it keeps on performing. Experience is as important for an ANN as it is for man. It is being increasingly used to supplement and even (may be) replace experts, in medicine. However, there is still scope for improvement in some areas. Its ability to classify and interpret various forms of medical data comes as a helping hand to clinical decision making in both diagnosis and treatment. Treatment planning in medicine, radiotherapy, rehabilitation, etc. is being done using ANN. Morbidity and mortality prediction by ANN in different medical situations can be very helpful for hospital management. ANN has a promising future in fundamental research, medical education and surgical robotics.
A neural network simulation package in CLIPS
NASA Technical Reports Server (NTRS)
Bhatnagar, Himanshu; Krolak, Patrick D.; Mcgee, Brenda J.; Coleman, John
1990-01-01
The intrinsic similarity between the firing of a rule and the firing of a neuron has been captured in this research to provide a neural network development system within an existing production system (CLIPS). A very important by-product of this research has been the emergence of an integrated technique of using rule based systems in conjunction with the neural networks to solve complex problems. The systems provides a tool kit for an integrated use of the two techniques and is also extendible to accommodate other AI techniques like the semantic networks, connectionist networks, and even the petri nets. This integrated technique can be very useful in solving complex AI problems.
Real-time neural network inversion on the SRC-6e reconfigurable computer.
Duren, Russell W; Marks, Robert J; Reynolds, Paul D; Trumbo, Matthew L
2007-05-01
Implementation of real-time neural network inversion on the SRC-6e, a computer that uses multiple field-programmable gate arrays (FPGAs) as reconfigurable computing elements, is examined using a sonar application as a specific case study. A feedforward multilayer perceptron neural network is used to estimate the performance of the sonar system (Jung et al., 2001). A particle swarm algorithm uses the trained network to perform a search for the control parameters required to optimize the output performance of the sonar system in the presence of imposed environmental constraints (Fox et al., 2002). The particle swarm optimization (PSO) requires repetitive queries of the neural network. Alternatives for implementing neural networks and particle swarm algorithms in reconfigurable hardware are contrasted. The final implementation provides nearly two orders of magnitude of speed increase over a state-of-the-art personal computer (PC), providing a real-time solution.
Logarithmic learning for generalized classifier neural network.
Ozyildirim, Buse Melis; Avci, Mutlu
2014-12-01
Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning approach is proposed. The proposed method uses logarithmic cost function instead of squared error. Minimization of this cost function reduces the number of iterations used for reaching the minima. The proposed method is tested on 15 different data sets and performance of logarithmic learning generalized classifier neural network is compared with that of standard one. Thanks to operation range of radial basis function included by generalized classifier neural network, proposed logarithmic approach and its derivative has continuous values. This makes it possible to adopt the advantage of logarithmic fast convergence by the proposed learning method. Due to fast convergence ability of logarithmic cost function, training time is maximally decreased to 99.2%. In addition to decrease in training time, classification performance may also be improved till 60%. According to the test results, while the proposed method provides a solution for time requirement problem of generalized classifier neural network, it may also improve the classification accuracy. The proposed method can be considered as an efficient way for reducing the time requirement problem of generalized classifier neural network.
Neural networks for segmentation, tracking, and identification
NASA Astrophysics Data System (ADS)
Rogers, Steven K.; Ruck, Dennis W.; Priddy, Kevin L.; Tarr, Gregory L.
1992-09-01
The main thrust of this paper is to encourage the use of neural networks to process raw data for subsequent classification. This article addresses neural network techniques for processing raw pixel information. For this paper the definition of neural networks includes the conventional artificial neural networks such as the multilayer perceptrons and also biologically inspired processing techniques. Previously, we have successfully used the biologically inspired Gabor transform to process raw pixel information and segment images. In this paper we extend those ideas to both segment and track objects in multiframe sequences. It is also desirable for the neural network processing data to learn features for subsequent recognition. A common first step for processing raw data is to transform the data and use the transform coefficients as features for recognition. For example, handwritten English characters become linearly separable in the feature space of the low frequency Fourier coefficients. Much of human visual perception can be modelled by assuming low frequency Fourier as the feature space used by the human visual system. The optimum linear transform, with respect to reconstruction, is the Karhunen-Loeve transform (KLT). It has been shown that some neural network architectures can compute approximations to the KLT. The KLT coefficients can be used for recognition as well as for compression. We tested the use of the KLT on the problem of interfacing a nonverbal patient to a computer. The KLT uses an optimal basis set for object reconstruction. For object recognition, the KLT may not be optimal.
Neural-Network Object-Recognition Program
NASA Technical Reports Server (NTRS)
Spirkovska, L.; Reid, M. B.
1993-01-01
HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.
A neural network for visual pattern recognition
Fukushima, K.
1988-03-01
A modeling approach, which is a synthetic approach using neural network models, continues to gain importance. In the modeling approach, the authors study how to interconnect neurons to synthesize a brain model, which is a network with the same functions and abilities as the brain. The relationship between modeling neutral networks and neurophysiology resembles that between theoretical physics and experimental physics. Modeling takes synthetic approach, while neurophysiology or psychology takes an analytical approach. Modeling neural networks is useful in explaining the brain and also in engineering applications. It brings the results of neurophysiological and psychological research to engineering applications in the most direct way possible. This article discusses a neural network model thus obtained, a model with selective attention in visual pattern recognition.
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.
Artificial Astrocytes Improve Neural Network Performance
Porto-Pazos, Ana B.; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso
2011-01-01
Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function. PMID:21526157
Artificial astrocytes improve neural network performance.
Porto-Pazos, Ana B; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso
2011-04-19
Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.
Optical neural stimulation modeling on degenerative neocortical neural networks
NASA Astrophysics Data System (ADS)
Zverev, M.; Fanjul-Vélez, F.; Salas-García, I.; Arce-Diego, J. L.
2015-07-01
Neurodegenerative diseases usually appear at advanced age. Medical advances make people live longer and as a consequence, the number of neurodegenerative diseases continuously grows. There is still no cure for these diseases, but several brain stimulation techniques have been proposed to improve patients' condition. One of them is Optical Neural Stimulation (ONS), which is based on the application of optical radiation over specific brain regions. The outer cerebral zones can be noninvasively stimulated, without the common drawbacks associated to surgical procedures. This work focuses on the analysis of ONS effects in stimulated neurons to determine their influence in neuronal activity. For this purpose a neural network model has been employed. The results show the neural network behavior when the stimulation is provided by means of different optical radiation sources and constitute a first approach to adjust the optical light source parameters to stimulate specific neocortical areas.
Implementation of a pulse coupled neural network in FPGA.
Waldemark, J; Millberg, M; Lindblad, T; Waldemark, K; Becanovic, V
2000-06-01
The Pulse Coupled neural network, PCNN, is a biologically inspired neural net and it can be used in various image analysis applications, e.g. time-critical applications in the field of image pre-processing like segmentation, filtering, etc. a VHDL implementation of the PCNN targeting FPGA was undertaken and the results presented here. The implementation contains many interesting features. By pipelining the PCNN structure a very high throughput of 55 million neuron iterations per second could be achieved. By making the coefficients re-configurable during operation, a complete recognition system could be implemented on one, or maybe two, chip(s). Reconsidering the ranges and resolutions of the constants may save a lot of hardware, since the higher resolution requires larger multipliers, adders, memories etc.
Sequential state generation by model neural networks.
Kleinfeld, D
1986-01-01
Sequential patterns of neural output activity form the basis of many biological processes, such as the cyclic pattern of outputs that control locomotion. I show how such sequences can be generated by a class of model neural networks that make defined sets of transitions between selected memory states. Sequence-generating networks depend upon the interplay between two sets of synaptic connections. One set acts to stabilize the network in its current memory state, while the second set, whose action is delayed in time, causes the network to make specified transitions between the memories. The dynamic properties of these networks are described in terms of motion along an energy surface. The performance of the networks, both with intact connections and with noisy or missing connections, is illustrated by numerical examples. In addition, I present a scheme for the recognition of externally generated sequences by these networks. PMID:3467316
Some neural networks compute, others don't.
Piccinini, Gualtiero
2008-01-01
I address whether neural networks perform computations in the sense of computability theory and computer science. I explicate and defend the following theses. (1) Many neural networks compute--they perform computations. (2) Some neural networks compute in a classical way. Ordinary digital computers, which are very large networks of logic gates, belong in this class of neural networks. (3) Other neural networks compute in a non-classical way. (4) Yet other neural networks do not perform computations. Brains may well fall into this last class.
Computational inference of neural information flow networks.
Smith, V Anne; Yu, Jing; Smulders, Tom V; Hartemink, Alexander J; Jarvis, Erich D
2006-11-24
Determining how information flows along anatomical brain pathways is a fundamental requirement for understanding how animals perceive their environments, learn, and behave. Attempts to reveal such neural information flow have been made using linear computational methods, but neural interactions are known to be nonlinear. Here, we demonstrate that a dynamic Bayesian network (DBN) inference algorithm we originally developed to infer nonlinear transcriptional regulatory networks from gene expression data collected with microarrays is also successful at inferring nonlinear neural information flow networks from electrophysiology data collected with microelectrode arrays. The inferred networks we recover from the songbird auditory pathway are correctly restricted to a subset of known anatomical paths, are consistent with timing of the system, and reveal both the importance of reciprocal feedback in auditory processing and greater information flow to higher-order auditory areas when birds hear natural as opposed to synthetic sounds. A linear method applied to the same data incorrectly produces networks with information flow to non-neural tissue and over paths known not to exist. To our knowledge, this study represents the first biologically validated demonstration of an algorithm to successfully infer neural information flow networks.
Artificial Neural Networks and Instructional Technology.
ERIC Educational Resources Information Center
Carlson, Patricia A.
1991-01-01
Artificial neural networks (ANN), part of artificial intelligence, are discussed. Such networks are fed sample cases (training sets), learn how to recognize patterns in the sample data, and use this experience in handling new cases. Two cognitive roles for ANNs (intelligent filters and spreading, associative memories) are examined. Prototypes…
Higher-Order Neural Networks Recognize Patterns
NASA Technical Reports Server (NTRS)
Reid, Max B.; Spirkovska, Lilly; Ochoa, Ellen
1996-01-01
Networks of higher order have enhanced capabilities to distinguish between different two-dimensional patterns and to recognize those patterns. Also enhanced capabilities to "learn" patterns to be recognized: "trained" with far fewer examples and, therefore, in less time than necessary to train comparable first-order neural networks.
Orthogonal Patterns In A Binary Neural Network
NASA Technical Reports Server (NTRS)
Baram, Yoram
1991-01-01
Report presents some recent developments in theory of binary neural networks. Subject matter relevant to associate (content-addressable) memories and to recognition of patterns - both of considerable importance in advancement of robotics and artificial intelligence. When probed by any pattern, network converges to one of stored patterns.
Neural-Network Modeling Of Arc Welding
NASA Technical Reports Server (NTRS)
Anderson, Kristinn; Barnett, Robert J.; Springfield, James F.; Cook, George E.; Strauss, Alvin M.; Bjorgvinsson, Jon B.
1994-01-01
Artificial neural networks considered for use in monitoring and controlling gas/tungsten arc-welding processes. Relatively simple network, using 4 welding equipment parameters as inputs, estimates 2 critical weld-bead paramaters within 5 percent. Advantage is computational efficiency.
Neural networks as perpetual information generators
NASA Astrophysics Data System (ADS)
Englisch, Harald; Xiao, Yegao; Yao, Kailun
1991-07-01
The information gain in a neural network cannot be larger than the bit capacity of the synapses. It is shown that the equation derived by Engel et al. [Phys. Rev. A 42, 4998 (1990)] for the strongly diluted network with persistent stimuli contradicts this condition. Furthermore, for any time step the correct equation is derived by taking the correlation between random variables into account.
Disruption forecasting at JET using neural networks
NASA Astrophysics Data System (ADS)
Cannas, B.; Fanni, A.; Marongiu, E.; Sonato, P.
2004-01-01
Neural networks are trained to evaluate the risk of plasma disruptions in a tokamak experiment using several diagnostic signals as inputs. A saliency analysis confirms the goodness of the chosen inputs, all of which contribute to the network performance. Tests that were carried out refer to data collected from succesfully terminated and disruption terminated pulses performed during two years of JET tokamak experiments. Results show the possibility of developing a neural network predictor that intervenes well in advance in order to avoid plasma disruption or mitigate its effects.
Multiwavelet neural network and its approximation properties.
Jiao, L; Pan, J; Fang, Y
2001-01-01
A model of multiwavelet-based neural networks is proposed. Its universal and L(2) approximation properties, together with its consistency are proved, and the convergence rates associated with these properties are estimated. The structure of this network is similar to that of the wavelet network, except that the orthonormal scaling functions are replaced by orthonormal multiscaling functions. The theoretical analyses show that the multiwavelet network converges more rapidly than the wavelet network, especially for smooth functions. To make a comparison between both networks, experiments are carried out with the Lemarie-Meyer wavelet network, the Daubechies2 wavelet network and the GHM multiwavelet network, and the results support the theoretical analysis well. In addition, the results also illustrate that at the jump discontinuities, the approximation performance of the two networks are about the same.
Neural Network Based Montioring and Control of Fluidized Bed.
Bodruzzaman, M.; Essawy, M.A.
1996-04-01
The goal of this project was to develop chaos analysis and neural network-based modeling techniques and apply them to the pressure-drop data obtained from the Fluid Bed Combustion (FBC) system (a small scale prototype model) located at the Federal Energy Technology Center (FETC)-Morgantown. The second goal was to develop neural network-based chaos control techniques and provide a suggestive prototype for possible real-time application to the FBC system. The experimental pressure data were collected from a cold FBC experimental set-up at the Morgantown Center. We have performed several analysis on these data in order to unveil their dynamical and chaotic characteristics. The phase-space attractors were constructed from the one dimensional time series data, using the time-delay embedding method, for both normal and abnormal conditions. Several identifying parameters were also computed from these attractors such as the correlation dimension, the Kolmogorov entropy, and the Lyapunov exponents. These chaotic attractor parameters can be used to discriminate between the normal and abnormal operating conditions of the FBC system. It was found that, the abnormal data has higher correlation dimension, larger Kolmogorov entropy and larger positive Lyapunov exponents as compared to the normal data. Chaotic system control using neural network based techniques were also investigated and compared to conventional chaotic system control techniques. Both types of chaotic system control techniques were applied to some typical chaotic systems such as the logistic, the Henon, and the Lorenz systems. A prototype model for real-time implementation of these techniques has been suggested to control the FBC system. These models can be implemented for real-time control in a next phase of the project after obtaining further measurements from the experimental model. After testing the control algorithms developed for the FBC model, the next step is to implement them on hardware and link them to
Applications of Neural Networks to Adaptive Control
1989-12-01
DTIC ;- E py 00 NAVAL POSTGRADUATE SCHOOL Monterey, California I.$ RDTIC IELECTE fl THESIS BEG7V°U APPLICATIONS OF NEURAL NETWORKS TO ADAPTIVE CONTROL...Second keader E . Robert Wood, Chairman, Department of Aeronautics and Astronautics Gordoii E . Schacher, Dean of Faculty and Graduate Education ii ABSTRACT...23: Network Dynamic Stability for q(t) . ............................. 55 ix Figure 24: Network Dynamic Stability for e (t
Using Neural Networks to Describe Tracer Correlations
NASA Technical Reports Server (NTRS)
Lary, D. J.; Mueller, M. D.; Mussa, H. Y.
2003-01-01
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.). In this study a neural network using Quickprop learning and one hidden layer with eight nodes was able to reproduce the CH4-N2O correlation with a correlation co- efficient of 0.9995. Such an accurate representation of tracer-tracer correlations allows more use to be made of long-term datasets to constrain chemical models. Such as the dataset from the Halogen Occultation Experiment (HALOE) which has continuously observed CH4, (but not N2O) from 1991 till the present. The neural network Fortran code used is available for download.
Learning and diagnosing faults using neural networks
NASA Technical Reports Server (NTRS)
Whitehead, Bruce A.; Kiech, Earl L.; Ali, Moonis
1990-01-01
Neural networks have been employed for learning fault behavior from rocket engine simulator parameters and for diagnosing faults on the basis of the learned behavior. Two problems in applying neural networks to learning and diagnosing faults are (1) the complexity of the sensor data to fault mapping to be modeled by the neural network, which implies difficult and lengthy training procedures; and (2) the lack of sufficient training data to adequately represent the very large number of different types of faults which might occur. Methods are derived and tested in an architecture which addresses these two problems. First, the sensor data to fault mapping is decomposed into three simpler mappings which perform sensor data compression, hypothesis generation, and sensor fusion. Efficient training is performed for each mapping separately. Secondly, the neural network which performs sensor fusion is structured to detect new unknown faults for which training examples were not presented during training. These methods were tested on a task of fault diagnosis by employing rocket engine simulator data. Results indicate that the decomposed neural network architecture can be trained efficiently, can identify faults for which it has been trained, and can detect the occurrence of faults for which it has not been trained.
Neural network technologies for image classification
NASA Astrophysics Data System (ADS)
Korikov, A. M.; Tungusova, A. V.
2015-11-01
We analyze the classes of problems with an objective necessity to use neural network technologies, i.e. representation and resolution problems in the neural network logical basis. Among these problems, image recognition takes an important place, in particular the classification of multi-dimensional data based on information about textural characteristics. These problems occur in aerospace and seismic monitoring, materials science, medicine and other. We reviewed different approaches for the texture description: statistical, structural, and spectral. We developed a neural network technology for resolving a practical problem of cloud image classification for satellite snapshots from the spectroradiometer MODIS. The cloud texture is described by the statistical characteristics of the GLCM (Gray Level Co- Occurrence Matrix) method. From the range of neural network models that might be applied for image classification, we chose the probabilistic neural network model (PNN) and developed an implementation which performs the classification of the main types and subtypes of clouds. Also, we chose experimentally the optimal architecture and parameters for the PNN model which is used for image classification.
Neurale Netwerken en Radarsystemen (Neural Networks and Radar Systems)
1989-08-01
general issues in cognitive science", Parallel distributed processing, Vol 1: Foundations, Rumelhart et al. 1986 pp 110-146 THO rapport Pagina 151 36 D.E...34Neural networks (part 2)",Expert Focus, IEEE Expert, Spring 1988. 61 J.A. Anderson, " Cognitive and Psychological Computations with Neural Models", IEEE...Pagina 154 69 David H. Ackley, Geoffrey E. Hinton and Terrence J. Sejnowski, "A Learning Algorithm for Boltzmann machines", cognitive science 9, 147-169
Estimates on compressed neural networks regression.
Zhang, Yongquan; Li, Youmei; Sun, Jianyong; Ji, Jiabing
2015-03-01
When the neural element number n of neural networks is larger than the sample size m, the overfitting problem arises since there are more parameters than actual data (more variable than constraints). In order to overcome the overfitting problem, we propose to reduce the number of neural elements by using compressed projection A which does not need to satisfy the condition of Restricted Isometric Property (RIP). By applying probability inequalities and approximation properties of the feedforward neural networks (FNNs), we prove that solving the FNNs regression learning algorithm in the compressed domain instead of the original domain reduces the sample error at the price of an increased (but controlled) approximation error, where the covering number theory is used to estimate the excess error, and an upper bound of the excess error is given.
Open hardware: a role to play in wireless sensor networks?
Fisher, Roy; Ledwaba, Lehlogonolo; Hancke, Gerhard; Kruger, Carel
2015-03-20
The concept of the Internet of Things is rapidly becoming a reality, with many applications being deployed within industrial and consumer sectors. At the 'thing' level-devices and inter-device network communication-the core technical building blocks are generally the same as those found in wireless sensor network implementations. For the Internet of Things to continue growing, we need more plentiful resources for building intelligent devices and sensor networks. Unfortunately, current commercial devices, e.g., sensor nodes and network gateways, tend to be expensive and proprietary, which presents a barrier to entry and arguably slows down further development. There are, however, an increasing number of open embedded platforms available and also a wide selection of off-the-shelf components that can quickly and easily be built into device and network gateway solutions. The question is whether these solutions measure up to built-for-purpose devices. In the paper, we provide a comparison of existing built-for-purpose devices against open source devices. For comparison, we have also designed and rapidly prototyped a sensor node based on off-the-shelf components. We show that these devices compare favorably to built-for-purpose devices in terms of performance, power and cost. Using open platforms and off-the-shelf components would allow more developers to build intelligent devices and sensor networks, which could result in a better overall development ecosystem, lower barriers to entry and rapid growth in the number of IoT applications.
Open Hardware: A Role to Play in Wireless Sensor Networks?
Fisher, Roy; Ledwaba, Lehlogonolo; Hancke, Gerhard; Kruger, Carel
2015-01-01
The concept of the Internet of Things is rapidly becoming a reality, with many applications being deployed within industrial and consumer sectors. At the ‘thing’ level—devices and inter-device network communication—the core technical building blocks are generally the same as those found in wireless sensor network implementations. For the Internet of Things to continue growing, we need more plentiful resources for building intelligent devices and sensor networks. Unfortunately, current commercial devices, e.g., sensor nodes and network gateways, tend to be expensive and proprietary, which presents a barrier to entry and arguably slows down further development. There are, however, an increasing number of open embedded platforms available and also a wide selection of off-the-shelf components that can quickly and easily be built into device and network gateway solutions. The question is whether these solutions measure up to built-for-purpose devices. In the paper, we provide a comparison of existing built-for-purpose devices against open source devices. For comparison, we have also designed and rapidly prototyped a sensor node based on off-the-shelf components. We show that these devices compare favorably to built-for-purpose devices in terms of performance, power and cost. Using open platforms and off-the-shelf components would allow more developers to build intelligent devices and sensor networks, which could result in a better overall development ecosystem, lower barriers to entry and rapid growth in the number of IoT applications. PMID:25803706
An efficient automated parameter tuning framework for spiking neural networks.
Carlson, Kristofor D; Nageswaran, Jayram Moorkanikara; Dutt, Nikil; Krichmar, Jeffrey L
2014-01-01
As the desire for biologically realistic spiking neural networks (SNNs) increases, tuning the enormous number of open parameters in these models becomes a difficult challenge. SNNs have been used to successfully model complex neural circuits that explore various neural phenomena such as neural plasticity, vision systems, auditory systems, neural oscillations, and many other important topics of neural function. Additionally, SNNs are particularly well-adapted to run on neuromorphic hardware that will support biological brain-scale architectures. Although the inclusion of realistic plasticity equations, neural dynamics, and recurrent topologies has increased the descriptive power of SNNs, it has also made the task of tuning these biologically realistic SNNs difficult. To meet this challenge, we present an automated parameter tuning framework capable of tuning SNNs quickly and efficiently using evolutionary algorithms (EA) and inexpensive, readily accessible graphics processing units (GPUs). A sample SNN with 4104 neurons was tuned to give V1 simple cell-like tuning curve responses and produce self-organizing receptive fields (SORFs) when presented with a random sequence of counterphase sinusoidal grating stimuli. A performance analysis comparing the GPU-accelerated implementation to a single-threaded central processing unit (CPU) implementation was carried out and showed a speedup of 65× of the GPU implementation over the CPU implementation, or 0.35 h per generation for GPU vs. 23.5 h per generation for CPU. Additionally, the parameter value solutions found in the tuned SNN were studied and found to be stable and repeatable. The automated parameter tuning framework presented here will be of use to both the computational neuroscience and neuromorphic engineering communities, making the process of constructing and tuning large-scale SNNs much quicker and easier.
Flexible body control using neural networks
NASA Technical Reports Server (NTRS)
Mccullough, Claire L.
1992-01-01
Progress is reported on the control of Control Structures Interaction suitcase demonstrator (a flexible structure) using neural networks and fuzzy logic. It is concluded that while control by neural nets alone (i.e., allowing the net to design a controller with no human intervention) has yielded less than optimal results, the neural net trained to emulate the existing fuzzy logic controller does produce acceptible system responses for the initial conditions examined. Also, a neural net was found to be very successful in performing the emulation step necessary for the anticipatory fuzzy controller for the CSI suitcase demonstrator. The fuzzy neural hybrid, which exhibits good robustness and noise rejection properties, shows promise as a controller for practical flexible systems, and should be further evaluated.
Implementing Signature Neural Networks with Spiking Neurons
Carrillo-Medina, José Luis; Latorre, Roberto
2016-01-01
Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm—i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data—to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the
Implementing Signature Neural Networks with Spiking Neurons.
Carrillo-Medina, José Luis; Latorre, Roberto
2016-01-01
Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm-i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data-to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the absence
Training Deep Spiking Neural Networks Using Backpropagation
Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael
2016-01-01
Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations. PMID:27877107
Foreign currency rate forecasting using neural networks
NASA Astrophysics Data System (ADS)
Pandya, Abhijit S.; Kondo, Tadashi; Talati, Amit; Jayadevappa, Suryaprasad
2000-03-01
Neural networks are increasingly being used as a forecasting tool in many forecasting problems. This paper discusses the application of neural networks in predicting daily foreign exchange rates between the USD, GBP as well as DEM. We approach the problem from a time-series analysis framework - where future exchange rates are forecasted solely using past exchange rates. This relies on the belief that the past prices and future prices are very close related, and interdependent. We present the result of training a neural network with historical USD-GBP data. The methodology used in explained, as well as the training process. We discuss the selection of inputs to the network, and present a comparison of using the actual exchange rates and the exchange rate differences as inputs. Price and rate differences are the preferred way of training neural network in financial applications. Results of both approaches are present together for comparison. We show that the network is able to learn the trends in the exchange rate movements correctly, and present the results of the prediction over several periods of time.
Training Deep Spiking Neural Networks Using Backpropagation.
Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael
2016-01-01
Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.
Neural network approaches for noisy language modeling.
Li, Jun; Ouazzane, Karim; Kazemian, Hassan B; Afzal, Muhammad Sajid
2013-11-01
Text entry from people is not only grammatical and distinct, but also noisy. For example, a user's typing stream contains all the information about the user's interaction with computer using a QWERTY keyboard, which may include the user's typing mistakes as well as specific vocabulary, typing habit, and typing performance. In particular, these features are obvious in disabled users' typing streams. This paper proposes a new concept called noisy language modeling by further developing information theory and applies neural networks to one of its specific application-typing stream. This paper experimentally uses a neural network approach to analyze the disabled users' typing streams both in general and specific ways to identify their typing behaviors and subsequently, to make typing predictions and typing corrections. In this paper, a focused time-delay neural network (FTDNN) language model, a time gap model, a prediction model based on time gap, and a probabilistic neural network model (PNN) are developed. A 38% first hitting rate (HR) and a 53% first three HR in symbol prediction are obtained based on the analysis of a user's typing history through the FTDNN language modeling, while the modeling results using the time gap prediction model and the PNN model demonstrate that the correction rates lie predominantly in between 65% and 90% with the current testing samples, and 70% of all test scores above basic correction rates, respectively. The modeling process demonstrates that a neural network is a suitable and robust language modeling tool to analyze the noisy language stream. The research also paves the way for practical application development in areas such as informational analysis, text prediction, and error correction by providing a theoretical basis of neural network approaches for noisy language modeling.
Signal dispersion within a hippocampal neural network
NASA Technical Reports Server (NTRS)
Horowitz, J. M.; Mates, J. W. B.
1975-01-01
A model network is described, representing two neural populations coupled so that one population is inhibited by activity it excites in the other. Parameters and operations within the model represent EPSPs, IPSPs, neural thresholds, conduction delays, background activity and spatial and temporal dispersion of signals passing from one population to the other. Simulations of single-shock and pulse-train driving of the network are presented for various parameter values. Neuronal events from 100 to 300 msec following stimulation are given special consideration in model calculations.
Intelligent neural network classifier for automatic testing
NASA Astrophysics Data System (ADS)
Bai, Baoxing; Yu, Heping
1996-10-01
This paper is concerned with an application of a multilayer feedforward neural network for the vision detection of industrial pictures, and introduces a high characteristics image processing and recognizing system which can be used for real-time testing blemishes, streaks and cracks, etc. on the inner walls of high-accuracy pipes. To take full advantage of the functions of the artificial neural network, such as the information distributed memory, large scale self-adapting parallel processing, high fault-tolerance ability, this system uses a multilayer perceptron as a regular detector to extract features of the images to be inspected and classify them.
Implementation aspects of Graph Neural Networks
NASA Astrophysics Data System (ADS)
Barcz, A.; Szymański, Z.; Jankowski, S.
2013-10-01
This article summarises the results of implementation of a Graph Neural Network classi er. The Graph Neural Network model is a connectionist model, capable of processing various types of structured data, including non- positional and cyclic graphs. In order to operate correctly, the GNN model must implement a transition function being a contraction map, which is assured by imposing a penalty on model weights. This article presents research results concerning the impact of the penalty parameter on the model training process and the practical decisions that were made during the GNN implementation process.
Livermore Big Artificial Neural Network Toolkit
Essen, Brian Van; Jacobs, Sam; Kim, Hyojin; Dryden, Nikoli; Moon, Tim
2016-07-01
LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.
Simulation of photosynthetic production using neural network
NASA Astrophysics Data System (ADS)
Kmet, Tibor; Kmetova, Maria
2013-10-01
This paper deals with neural network based optimal control synthesis for solving optimal control problems with control and state constraints and discrete time delay. The optimal control problem is transcribed into nonlinear programming problem which is implemented with adaptive critic neural network. This approach is applicable to a wide class of nonlinear systems. The proposed simulation methods is illustrated by the optimal control problem of photosynthetic production described by discrete time delay differential equations. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.
Automatic identification of species with neural networks
Jiménez-Segura, Luz Fernanda
2014-01-01
A new automatic identification system using photographic images has been designed to recognize fish, plant, and butterfly species from Europe and South America. The automatic classification system integrates multiple image processing tools to extract the geometry, morphology, and texture of the images. Artificial neural networks (ANNs) were used as the pattern recognition method. We tested a data set that included 740 species and 11,198 individuals. Our results show that the system performed with high accuracy, reaching 91.65% of true positive fish identifications, 92.87% of plants and 93.25% of butterflies. Our results highlight how the neural networks are complementary to species identification. PMID:25392749
Porosity Log Prediction Using Artificial Neural Network
NASA Astrophysics Data System (ADS)
Dwi Saputro, Oki; Lazuardi Maulana, Zulfikar; Dzar Eljabbar Latief, Fourier
2016-08-01
Well logging is important in oil and gas exploration. Many physical parameters of reservoir is derived from well logging measurement. Geophysicists often use well logging to obtain reservoir properties such as porosity, water saturation and permeability. Most of the time, the measurement of the reservoir properties are considered expensive. One of method to substitute the measurement is by conducting a prediction using artificial neural network. In this paper, artificial neural network is performed to predict porosity log data from other log data. Three well from ‘yy’ field are used to conduct the prediction experiment. The log data are sonic, gamma ray, and porosity log. One of three well is used as training data for the artificial neural network which employ the Levenberg-Marquardt Backpropagation algorithm. Through several trials, we devise that the most optimal input training is sonic log data and gamma ray log data with 10 hidden layer. The prediction result in well 1 has correlation of 0.92 and mean squared error of 5.67 x10-4. Trained network apply to other well data. The result show that correlation in well 2 and well 3 is 0.872 and 0.9077 respectively. Mean squared error in well 2 and well 3 is 11 x 10-4 and 9.539 x 10-4. From the result we can conclude that sonic log and gamma ray log could be good combination for predicting porosity with neural network.
Payload Invariant Control via Neural Networks: Development and Experimental Evaluation
1989-12-01
control is proposed and experimentally evaluated. An Adaptive Model-Based Neural Network Controller (AMBNNC) uses multilayer perceptron artificial neural ... networks to estimate the payload during high speed manipulator motion. The payload estimate adapts the feedforward compensator to unmodeled system
Embedded Streaming Deep Neural Networks Accelerator With Applications.
Dundar, Aysegul; Jin, Jonghoon; Martini, Berin; Culurciello, Eugenio
2016-04-08
Deep convolutional neural networks (DCNNs) have become a very powerful tool in visual perception. DCNNs have applications in autonomous robots, security systems, mobile phones, and automobiles, where high throughput of the feedforward evaluation phase and power efficiency are important. Because of this increased usage, many field-programmable gate array (FPGA)-based accelerators have been proposed. In this paper, we present an optimized streaming method for DCNNs' hardware accelerator on an embedded platform. The streaming method acts as a compiler, transforming a high-level representation of DCNNs into operation codes to execute applications in a hardware accelerator. The proposed method utilizes maximum computational resources available based on a novel-scheduled routing topology that combines data reuse and data concatenation. It is tested with a hardware accelerator implemented on the Xilinx Kintex-7 XC7K325T FPGA. The system fully explores weight-level and node-level parallelizations of DCNNs and achieves a peak performance of 247 G-ops while consuming less than 4 W of power. We test our system with applications on object classification and object detection in real-world scenarios. Our results indicate high-performance efficiency, outperforming all other presented platforms while running these applications.
Unconventional optical imaging using a high-speed neural network based smart sensor
NASA Astrophysics Data System (ADS)
Arrasmith, William W.
2006-05-01
The advancement of neural network methods and technologies is finding applications in many fields and disciplines of interest to the defense, intelligence, and homeland security communities. Rapidly reconfigurable sensors for real or near-real time signal or image processing can be used for multi-functional purposes such as image compression, target tracking, image fusion, edge detection, thresholding, pattern recognition, and atmospheric turbulence compensation to name a few. A neural network based smart sensor is described that can accomplish these tasks individually or in combination, in real-time or near real-time. As a computationally intensive example, the case of optical imaging through volume turbulence is addressed. For imaging systems in the visible and near infrared part of the electromagnetic spectrum, the atmosphere is often the dominant factor in reducing the imaging system's resolution and image quality. The neural network approach described in this paper is shown to present a viable means for implementing turbulence compensation techniques for near-field and distributed turbulence scenarios. Representative high-speed neural network hardware is presented. Existing 2-D cellular neural network (CNN) hardware is capable of 3 trillion operations per second with peta-operations per second possible using current 3-D manufacturing processes. This hardware can be used for high-speed applications that require fast convolutions and de-convolutions. Existing 3-D artificial neural network technology is capable of peta-operations per second and can be used for fast array processing operations. Methods for optical imaging through distributed turbulence are discussed, simulation results are presented and computational and performance assessments are provided.
The labeled systems of multiple neural networks.
Nemissi, M; Seridi, H; Akdag, H
2008-08-01
This paper proposes an implementation scheme of K-class classification problem using systems of multiple neural networks. Usually, a multi-class problem is decomposed into simple sub-problems solved independently using similar single neural networks. For the reason that these sub-problems are not equivalent in their complexity, we propose a system that includes reinforced networks destined to solve complicated parts of the entire problem. Our approach is inspired from principles of the multi-classifiers systems and the labeled classification, which aims to improve performances of the networks trained by the Back-Propagation algorithm. We propose two implementation schemes based on both OAO (one-against-all) and OAA (one-against-one). The proposed models are evaluated using iris and human thigh databases.
Development of programmable artificial neural networks
NASA Technical Reports Server (NTRS)
Meade, Andrew J.
1993-01-01
Conventionally programmed digital computers can process numbers with great speed and precision, but do not easily recognize patterns or imprecise or contradictory data. Instead of being programmed in the conventional sense, artificial neural networks are capable of self-learning through exposure to repeated examples. However, the training of an ANN can be a time consuming and unpredictable process. A general method is being developed to mate the adaptability of the ANN with the speed and precision of the digital computer. This method was successful in building feedforward networks that can approximate functions and their partial derivatives from examples in a single iteration. The general method also allows the formation of feedforward networks that can approximate the solution to nonlinear ordinary and partial differential equations to desired accuracy without the need of examples. It is believed that continued research will produce artificial neural networks that can be used with confidence in practical scientific computing and engineering applications.
A neural network based speech recognition system
NASA Astrophysics Data System (ADS)
Carroll, Edward J.; Coleman, Norman P., Jr.; Reddy, G. N.
1990-02-01
An overview is presented of the development of a neural network based speech recognition system. The two primary tasks involved were the development of a time invariant speech encoder and a pattern recognizer or detector. The speech encoder uses amplitude normalization and a Fast Fourier Transform to eliminate amplitude and frequency shifts of acoustic clues. The detector consists of a back-propagation network which accepts data from the encoder and identifies individual words. This use of neural networks offers two advantages over conventional algorithmic detectors: the detection time is no more than a few network time constants, and its recognition speed is independent of the number of the words in the vocabulary. The completed system has functioned as expected with high tolerance to input variation and with error rates comparable to a commercial system when used in a noisy environment.
A neural network with modular hierarchical learning
NASA Technical Reports Server (NTRS)
Baldi, Pierre F. (Inventor); Toomarian, Nikzad (Inventor)
1994-01-01
This invention provides a new hierarchical approach for supervised neural learning of time dependent trajectories. The modular hierarchical methodology leads to architectures which are more structured than fully interconnected networks. The networks utilize a general feedforward flow of information and sparse recurrent connections to achieve dynamic effects. The advantages include the sparsity of units and connections, the modular organization. A further advantage is that the learning is much more circumscribed learning than in fully interconnected systems. The present invention is embodied by a neural network including a plurality of neural modules each having a pre-established performance capability wherein each neural module has an output outputting present results of the performance capability and an input for changing the present results of the performance capabilitiy. For pattern recognition applications, the performance capability may be an oscillation capability producing a repeating wave pattern as the present results. In the preferred embodiment, each of the plurality of neural modules includes a pre-established capability portion and a performance adjustment portion connected to control the pre-established capability portion.
Neural Network Noise Anomaly Recognition System and Method
2000-10-04
determine when an input waveform deviates from learned noise characteristics. A plurality of neural networks is preferably provided, which each receives a...plurality of samples of intervals or windows of the input waveform. Each of the neural networks produces an output based on whether an anomaly is...detected with respect to the noise, which the neural network is trained to detect. The plurality of outputs of the neural networks is preferably applied to
Analysis of Wideband Beamformers Designed with Artificial Neural Networks
1990-12-01
TECHNICAL REPORT 0-90-1 ANALYSIS OF WIDEBAND BEAMFORMERS DESIGNED WITH ARTIFICIAL NEURAL NETWORKS by Cary Cox Instrumentation Services Division...included. A briel tutorial on beamformers and neural networks is also provided. 14. SUBJECT TERMS 15, NUMBER OF PAGES Artificial neural networks Fecdforwa:,l...Beamformers Designed with Artificial Neural Networks ". The study was conducted under the general supervision of Messrs. George P. Bonner, Chief
Knowledge learning on fuzzy expert neural networks
NASA Astrophysics Data System (ADS)
Fu, Hsin-Chia; Shann, J.-J.; Pao, Hsiao-Tien
1994-03-01
The proposed fuzzy expert network is an event-driven, acyclic neural network designed for knowledge learning on a fuzzy expert system. Initially, the network is constructed according to a primitive (rough) expert rules including the input and output linguistic variables and values of the system. For each inference rule, it corresponds to an inference network, which contains five types of nodes: Input, Membership-Function, AND, OR, and Defuzzification Nodes. We propose a two-phase learning procedure for the inference network. The first phase is the competitive backpropagation (CBP) training phase, and the second phase is the rule- pruning phase. The CBP learning algorithm in the training phase enables the network to learn the fuzzy rules as precisely as backpropagation-type learning algorithms and yet as quickly as competitive-type learning algorithms. After the CBP training, the rule-pruning process is performed to delete redundant weight connections for simple network structures and yet compatible retrieving performance.
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.
Simplified Learning Scheme For Analog Neural Network
NASA Technical Reports Server (NTRS)
Eberhardt, Silvio P.
1991-01-01
Synaptic connections adjusted one at a time in small increments. Simplified gradient-descent learning scheme for electronic neural-network processor less efficient than better-known back-propagation scheme, but offers two advantages: easily implemented in circuitry because data-access circuitry separated from learning circuitry; and independence of data-access circuitry makes possible to implement feedforward as well as feedback networks, including those of multiple-attractor type. Important in such applications as recognition of patterns.
Using neural networks to model chaos
Upadhyay, M.D.
1996-12-31
Two types of neural networks -- backpropagation and radial basis function -- are presented for modeling dynamical systems. They were trained to model the Henon, Ikeda and Tinkerbell dynamical systems by providing a set of points randomly chosen from orbits under the functions. After training, the networks were used to simulate the functions to determine the extent to which they could generate the chaotic attractors associated with these systems.
Auto-associative nanoelectronic neural network
Nogueira, C. P. S. M.; Guimarães, J. G.
2014-05-15
In this paper, an auto-associative neural network using single-electron tunneling (SET) devices is proposed and simulated at low temperature. The nanoelectronic auto-associative network is able to converge to a stable state, previously stored during training. The recognition of the pattern involves decreasing the energy of the input state until it achieves a point of local minimum energy, which corresponds to one of the stored patterns.
Are artificial neural networks black boxes?
Benitez, J M; Castro, J L; Requena, I
1997-01-01
Artificial neural networks are efficient computing models which have shown their strengths in solving hard problems in artificial intelligence. They have also been shown to be universal approximators. Notwithstanding, one of the major criticisms is their being black boxes, since no satisfactory explanation of their behavior has been offered. In this paper, we provide such an interpretation of neural networks so that they will no longer be seen as black boxes. This is stated after establishing the equality between a certain class of neural nets and fuzzy rule-based systems. This interpretation is built with fuzzy rules using a new fuzzy logic operator which is defined after introducing the concept of f-duality. In addition, this interpretation offers an automated knowledge acquisition procedure.
Neural Network Classification of Environmental Samples
1996-12-01
Biological and Artificial Neural Networks. Air Force Institute of Technology, 1990. 24. Rosenblatt. Principles of Neurodynamics . New York, NY: Spartan...Parallel Distributed Processing: Explorations in the Microstructure of Cognition . MIT Press, 1986. 29. Smagt, Patrick P. Van Der. "Minimisation Methods
Psychometric Measurement Models and Artificial Neural Networks
ERIC Educational Resources Information Center
Sese, Albert; Palmer, Alfonso L.; Montano, Juan J.
2004-01-01
The study of measurement models in psychometrics by means of dimensionality reduction techniques such as Principal Components Analysis (PCA) is a very common practice. In recent times, an upsurge of interest in the study of artificial neural networks apt to computing a principal component extraction has been observed. Despite this interest, the…
Localizing Tortoise Nests by Neural Networks.
Barbuti, Roberto; Chessa, Stefano; Micheli, Alessio; Pucci, Rita
2016-01-01
The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating). Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS) which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN). We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours), the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition.
Neural network application to comprehensive engine diagnostics
NASA Technical Reports Server (NTRS)
Marko, Kenneth A.
1994-01-01
We have previously reported on the use of neural networks for detection and identification of faults in complex microprocessor controlled powertrain systems. The data analyzed in those studies consisted of the full spectrum of signals passing between the engine and the real-time microprocessor controller. The specific task of the classification system was to classify system operation as nominal or abnormal and to identify the fault present. The primary concern in earlier work was the identification of faults, in sensors or actuators in the powertrain system as it was exercised over its full operating range. The use of data from a variety of sources, each contributing some potentially useful information to the classification task, is commonly referred to as sensor fusion and typifies the type of problems successfully addressed using neural networks. In this work we explore the application of neural networks to a different diagnostic problem, the diagnosis of faults in newly manufactured engines and the utility of neural networks for process control.
Multidimensional neural growing networks and computer intelligence
Yashchenko, V.A.
1995-03-01
This paper examines information-computation processes in time and in space and some aspects of computer intelligence using multidimensional matrix neural growing networks. In particular, issues of object-oriented {open_quotes}thinking{close_quotes} of computers are considered.
Nonlinear Time Series Analysis via Neural Networks
NASA Astrophysics Data System (ADS)
Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin
This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.
Automatic target identification using neural networks
NASA Astrophysics Data System (ADS)
Abdallah, Mahmoud A.; Samu, Tayib I.; Grissom, William A.
1995-10-01
Neural network theories are applied to attain human-like performance in areas such as speech recognition, statistical mapping, and target recognition or identification. In target identification, one of the difficult tasks has been the extraction of features to be used to train the neural network which is subsequently used for the target's identification. The purpose of this paper is to describe the development of an automatic target identification system using features extracted from a specific class of targets. The extracted features were the graphical representations of the silhouettes of the targets. Image processing techniques and some Fast Fourier Transform (FFT) properties were implemented to extract the features. The FFT eliminates variations in the extracted features due to rotation or scaling. A Neural Network was trained with the extracted features using the Learning Vector Quantization paradigm. An identification system was set up to test the algorithm. The image processing software was interfaced with MATLAB Neural Network Toolbox via a computer program written in C language to automate the target identification process. The system performed well as at classified the objects used to train it irrespective of rotation, scaling, and translation. This automatic target identification system had a classification success rate of about 95%.
Optoelectronic Integrated Circuits For Neural Networks
NASA Technical Reports Server (NTRS)
Psaltis, D.; Katz, J.; Kim, Jae-Hoon; Lin, S. H.; Nouhi, A.
1990-01-01
Many threshold devices placed on single substrate. Integrated circuits containing optoelectronic threshold elements developed for use as planar arrays of artificial neurons in research on neural-network computers. Mounted with volume holograms recorded in photorefractive crystals serving as dense arrays of variable interconnections between neurons.
Neural networks in the former Soviet Union
Wunsch, D.C. II.
1993-01-01
A brief overview is given of neural networks activities in the former Soviet Union that have potential aerospace applications. Activities at institutes in Moscow, the former Leningrad, Kiev, Taganrog, Rostov-on-Don, and Krasnoyarsk are addressed, including the most important scientists involved. 21 refs.
Localizing Tortoise Nests by Neural Networks
2016-01-01
The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating). Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS) which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN). We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours), the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition. PMID:26985660
Chaotic time series prediction using artificial neural networks
Bartlett, E.B.
1991-12-31
This paper describes the use of artificial neural networks to model the complex oscillations defined by a chaotic Verhuist animal population dynamic. A predictive artificial neural network model is developed and tested, and results of computer simulations are given. These results show that the artificial neural network model predicts the chaotic time series with various initial conditions, growth parameters, or noise.
Chaotic time series prediction using artificial neural networks
Bartlett, E.B.
1991-01-01
This paper describes the use of artificial neural networks to model the complex oscillations defined by a chaotic Verhuist animal population dynamic. A predictive artificial neural network model is developed and tested, and results of computer simulations are given. These results show that the artificial neural network model predicts the chaotic time series with various initial conditions, growth parameters, or noise.
Neural Network Design on the SRC-6 Reconfigurable Computer
2006-12-01
speeds of FPGA systems. This thesis explores the use of a Feed-forward, Multi-Layer Perceptron (MLP) Artificial Neural Network (ANN) architecture... Implementation of a Fast Artificial Neural Network Library (FANN), Graduate Project Report, Department of Computer Science, University of Copenhagen (DIKU...NAVAL POSTGRADUATE SCHOOL MONTEREY, CALIFORNIA THESIS Approved for public release; distribution is unlimited NEURAL NETWORK
Hyperspectral Imagery Classification Using a Backpropagation Neural Network
1993-12-01
A backpropagation neural network was developed and implemented for classifying AVIRIS (Airborne Visible/Infrared Imaging Spectrometer) hyperspectral...imagery. It is a fully interconnected linkage of three layers of neural network . Fifty input layer neurons take in signals from Bands 41 to 90 of the...moderate AVIRIS pixel resolution of 20 meters by 20 meters. Backpropagation neural network , Hyperspectral imagery
Electrically Modifiable Nonvolatile SONOS Synapses for Electronic Neural Networks.
1992-09-30
for the electrically reprogrammable analog conductance in an artificial neural network. We have demonstrated the attractive featuies of this synaptic ...Electrically Modifiable Synaptic Element for VLSI Neural Network Implementation", Proceedings of the 1991 IEEE Nonvolatile Semiconductor Memory Workshop...Nonvolatile Eletrically Modifiable Synaptic Element for VLSI Neural Network Implementation", 11th IEEE Nonvolatile Semiconductor Memory Workshop, 1991. 19. A
[Application of artificial neural networks in infectious diseases].
Xu, Jun-fang; Zhou, Xiao-nong
2011-02-28
With the development of information technology, artificial neural networks has been applied to many research fields. Due to the special features such as nonlinearity, self-adaptation, and parallel processing, artificial neural networks are applied in medicine and biology. This review summarizes the application of artificial neural networks in the relative factors, prediction and diagnosis of infectious diseases in recent years.
Brain tumor grading based on Neural Networks and Convolutional Neural Networks.
Yuehao Pan; Weimin Huang; Zhiping Lin; Wanzheng Zhu; Jiayin Zhou; Wong, Jocelyn; Zhongxiang Ding
2015-08-01
This paper studies brain tumor grading using multiphase MRI images and compares the results with various configurations of deep learning structure and baseline Neural Networks. The MRI images are used directly into the learning machine, with some combination operations between multiphase MRIs. Compared to other researches, which involve additional effort to design and choose feature sets, the approach used in this paper leverages the learning capability of deep learning machine. We present the grading performance on the testing data measured by the sensitivity and specificity. The results show a maximum improvement of 18% on grading performance of Convolutional Neural Networks based on sensitivity and specificity compared to Neural Networks. We also visualize the kernels trained in different layers and display some self-learned features obtained from Convolutional Neural Networks.
Neural network method applied to particle image velocimetry
NASA Astrophysics Data System (ADS)
Grant, Ian; Pan, X.
1993-12-01
The last two decades have seen rapid developments in computing taking as their inspiration the human brain. The human brain functions in a highly parallel and distributed fashion. The adaptive structure of the brain means that learning or training can accompany decision making. This basic neural model has inspired computer hardware exhibiting a parallelism which has revolutionised processing speeds in complex task analysis. Similarly there has been substantial activity in the field of intelligent software and in particular in the area ofneural computing. The human brain may viewed as composed of approximately 1 dbasic units, the neurons. Each neuron exhibits a high degree of interconnectivity with connections to approximately 1 O other neurons. Each neuron accepts many inputs which are added or integrated in some fashion and this causes the neuron to become active or passive. The active neuron emits an output to interconnected neurons. The importance of any one input is controlled by the effectiveness of the corresponding interconnection or weight. One area that has attracted attention in the application of neural networks is pattern recognition. Here the functions of feature classification and extraction are handled by a network which receives some education or training prior to the task of recognition. A priori knowledge of expected outcomes is used as a starting point with the network being allowed to modify or enlarge its knowledge base as the task proceeds. Various models or approaches to adaptive problem solving have been developed. The pattern recognition problem considered in the present paper is the identification of image grouping in double exposure PIV images. The aim is to provide an adaptive net which, following initial training, is able to identify image partners and adapt to changing flow conditions. This latter feature is seen as essential in order that the full potential of the neural net in temporally or spatially changing flow regimes can be
The Irpinia Seismic Network (ISNet): hardware and data management
NASA Astrophysics Data System (ADS)
Iannaccone, G.
2009-04-01
The Irpinia Seismic Network, operating in southern Italy, is primarily aimed at providing an alert for moderate to large earthquakes in selected target sites in the Campania Region, and it also provides data for rapid computation of regional ground-shaking maps. ISNet is deployed over the active seismic faults system of Irpinia, southern Italy. It features 28 seismic stations and 5 data processing sites (local control centers - LCC). All stations are equipped with a strong-motion accelerometer and a three component velocimeter, with a one second natural period, for a high dynamic recording range. Five stations host broadband sensors, for recording regional and teleseismic events. The recorded seismic data are sent from each station to the nearby LCC, through a Wi-Fi directional antenna, in SeedLink format. Each LCC runs: the SeisComP software, to relay the data to outside SeedLink clients; the Earthworm system, for real-time processing (e.g. to produce a bulletin of automatically detected events); the Winston software, for data storage and visualization. To monitor and maintain all of the described ISNet instrumentation, and to access, analyze and edit the seismic data produced, we developed a software application, SeismNet Manager, that implements a web-based user interface to a database of all the ISNet information and data. For early warning applications, a high bandwidth radio links backbone is being deployed, interconnecting the LCCs and the Network Control Center in Naples. We developed a software application that processes the live streams of 3-component acceleration from the stations and, while an energetic event is occurring, promptly performs picking, event detection, event location and magnitude estimation. The earthquake location uses an evolutionary, real-time technique based on an equal differential time (EDT) formulation, and a probabilistic approach for describing the hypocenter. This algorithm, at each time step, relies on both the information from
Hybrid neural networks--combining abstract and realistic neural units.
Lytton, William W; Hines, Michael
2004-01-01
There is a trade-off in neural network simulation between simulations that embody the details of neuronal biology and those that omit these details in favor of abstractions. The former approach appeals to physiologists and pharmacologists who can directly relate their experimental manipulations to parameter changes in the model. The latter approach appeals to physicists and mathematicians who seek analytic understanding of the behavior of large numbers of coupled simple units. This simplified approach is also valuable for practical reasons a highly simplified unit will run several orders of magnitude faster than a complex, biologically realistic unit. In order to have our cake and eat it, we have developed hybrid networks in the Neuron simulator package. These make use of Neuron's local variable timestep method to permit simplified integrate-and-fire units to move ahead quickly while realistic neurons in the same network are integrated slowly.
Optical implementation of neural networks
NASA Astrophysics Data System (ADS)
Yu, Francis T. S.; Guo, Ruyan
2002-12-01
An adaptive optical neuro-computing (ONC) using inexpensive pocket size liquid crystal televisions (LCTVs) had been developed by the graduate students in the Electro-Optics Laboratory at The Pennsylvania State University. Although this neuro-computing has only 8×8=64 neurons, it can be easily extended to 16×20=320 neurons. The major advantages of this LCTV architecture as compared with other reported ONCs, are low cost and the flexibility to operate. To test the performance, several neural net models are used. These models are Interpattern Association, Hetero-association and unsupervised learning algorithms. The system design considerations and experimental demonstrations are also included.
Evolving unipolar memristor spiking neural networks
NASA Astrophysics Data System (ADS)
Howard, David; Bull, Larry; De Lacy Costello, Ben
2015-10-01
Neuromorphic computing - brain-like computing in hardware - typically requires myriad complimentary metal oxide semiconductor spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently cited as strong synapse candidates due to their statefulness and potential for low-power implementations. To date, plentiful research has focused on the bipolar memristor synapse, which is capable of incremental weight alterations and can provide adaptive self-organisation under a Hebbian learning scheme. In this paper, we consider the unipolar memristor synapse - a device capable of non-Hebbian switching between only two states (conductive and resistive) through application of a suitable input voltage - and discuss its suitability for neuromorphic systems. A self-adaptive evolutionary process is used to autonomously find highly fit network configurations. Experimentation on two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant non-plastic connections whilst performing at least comparably.
Intrinsic adaptation in autonomous recurrent neural networks.
Marković, Dimitrije; Gros, Claudius
2012-02-01
A massively recurrent neural network responds on one side to input stimuli and is autonomously active, on the other side, in the absence of sensory inputs. Stimuli and information processing depend crucially on the quality of the autonomous-state dynamics of the ongoing neural activity. This default neural activity may be dynamically structured in time and space, showing regular, synchronized, bursting, or chaotic activity patterns. We study the influence of nonsynaptic plasticity on the default dynamical state of recurrent neural networks. The nonsynaptic adaption considered acts on intrinsic neural parameters, such as the threshold and the gain, and is driven by the optimization of the information entropy. We observe, in the presence of the intrinsic adaptation processes, three distinct and globally attracting dynamical regimes: a regular synchronized, an overall chaotic, and an intermittent bursting regime. The intermittent bursting regime is characterized by intervals of regular flows, which are quite insensitive to external stimuli, interceded by chaotic bursts that respond sensitively to input signals. We discuss these findings in the context of self-organized information processing and critical brain dynamics.
Neural networks in windprofiler data processing
NASA Astrophysics Data System (ADS)
Weber, H.; Richner, H.; Kretzschmar, R.; Ruffieux, D.
2003-04-01
Wind profilers are basically Doppler radars yielding 3-dimensional wind profiles that are deduced from the Doppler shift caused by turbulent elements in the atmosphere. These signals can be contaminated by other airborne elements such as birds or hydrometeors. Using a feed-forward neural network with one hidden layer and one output unit, birds and hydrometeors can be successfully identified in non-averaged single spectra; theses are subsequently removed in the wind computation. An infrared camera was used to identify birds in one of the beams of the wind profiler. After training the network with about 6000 contaminated data sets, it was able to identify contaminated data in a test data set with a reliability of 96 percent. The assumption was made that the neural network parameters obtained in the beam for which bird data was collected can be transferred to the other beams (at least three beams are needed for computing wind vectors). Comparing the evolution of a wind field with and without the neural network shows a significant improvement of wind data quality. Current work concentrates on training the network also for hydrometeors. It is hoped that the instrument's capability can thus be expanded to measure not only correct winds, but also observe bird migration, estimate precipitation and -- by combining precipitation information with vertical velocity measurement -- the monitoring of the height of the melting layer.
Classifying multispectral data by neural networks
NASA Technical Reports Server (NTRS)
Telfer, Brian A.; Szu, Harold H.; Kiang, Richard K.
1993-01-01
Several energy functions for synthesizing neural networks are tested on 2-D synthetic data and on Landsat-4 Thematic Mapper data. These new energy functions, designed specifically for minimizing misclassification error, in some cases yield significant improvements in classification accuracy over the standard least mean squares energy function. In addition to operating on networks with one output unit per class, a new energy function is tested for binary encoded outputs, which result in smaller network sizes. The Thematic Mapper data (four bands were used) is classified on a single pixel basis, to provide a starting benchmark against which further improvements will be measured. Improvements are underway to make use of both subpixel and superpixel (i.e. contextual or neighborhood) information in tile processing. For single pixel classification, the best neural network result is 78.7 percent, compared with 71.7 percent for a classical nearest neighbor classifier. The 78.7 percent result also improves on several earlier neural network results on this data.
Back propagation neural networks for facial verification
Garnett, A.E.; Solheim, I.; Payne, T.; Castain, R.H.
1992-10-01
We conducted a test to determine the aptitude of neural networks to recognize human faces. The pictures we collected of 511 subjects captured both profiles and many natural expressions. Some of the subjects were wearing glasses, sunglasses, or hats in some of the pictures. The images were compressed by a factor of 100 and converted into image vectors of 1400 pixels. The image vectors were fed into a back propagation neural network with one hidden layer and one output node. The networks were trained to recognize one target person and to reject all other persons. Neural networks for 37 target subjects were trained with 8 different training sets that consisted of different subsets of the data. The networks were then tested on the rest of the data, which consisted of 7000 or more unseen pictures. Results indicate that a false acceptance rate of less than 1 percent can be obtained, and a false rejection rate of 2 percent can be obtained when certain restrictions are followed.
a Heterosynaptic Learning Rule for Neural Networks
NASA Astrophysics Data System (ADS)
Emmert-Streib, Frank
In this article we introduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.
Fuzzy logic and neural network technologies
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Lea, Robert N.; Savely, Robert T.
1992-01-01
Applications of fuzzy logic technologies in NASA projects are reviewed to examine their advantages in the development of neural networks for aerospace and commercial expert systems and control. Examples of fuzzy-logic applications include a 6-DOF spacecraft controller, collision-avoidance systems, and reinforcement-learning techniques. The commercial applications examined include a fuzzy autofocusing system, an air conditioning system, and an automobile transmission application. The practical use of fuzzy logic is set in the theoretical context of artificial neural systems (ANSs) to give the background for an overview of ANS research programs at NASA. The research and application programs include the Network Execution and Training Simulator and faster training algorithms such as the Difference Optimized Training Scheme. The networks are well suited for pattern-recognition applications such as predicting sunspots, controlling posture maintenance, and conducting adaptive diagnoses.
A Topological Perspective of Neural Network Structure
NASA Astrophysics Data System (ADS)
Sizemore, Ann; Giusti, Chad; Cieslak, Matthew; Grafton, Scott; Bassett, Danielle
The wiring patterns of white matter tracts between brain regions inform functional capabilities of the neural network. Indeed, densely connected and cyclically arranged cognitive systems may communicate and thus perform distinctly. However, previously employed graph theoretical statistics are local in nature and thus insensitive to such global structure. Here we present an investigation of the structural neural network in eight healthy individuals using persistent homology. An extension of homology to weighted networks, persistent homology records both circuits and cliques (all-to-all connected subgraphs) through a repetitive thresholding process, thus perceiving structural motifs. We report structural features found across patients and discuss brain regions responsible for these patterns, finally considering the implications of such motifs in relation to cognitive function.
Neural networks: Application to medical imaging
NASA Technical Reports Server (NTRS)
Clarke, Laurence P.
1994-01-01
The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.
Controlling neural network responsiveness: tradeoffs and constraints
Keren, Hanna; Marom, Shimon
2014-01-01
In recent years much effort is invested in means to control neural population responses at the whole brain level, within the context of developing advanced medical applications. The tradeoffs and constraints involved, however, remain elusive due to obvious complications entailed by studying whole brain dynamics. Here, we present effective control of response features (probability and latency) of cortical networks in vitro over many hours, and offer this approach as an experimental toy for studying controllability of neural networks in the wider context. Exercising this approach we show that enforcement of stable high activity rates by means of closed loop control may enhance alteration of underlying global input–output relations and activity dependent dispersion of neuronal pair-wise correlations across the network. PMID:24808860
Computationally Efficient Neural Network Intrusion Security Awareness
Todd Vollmer; Milos Manic
2009-08-01
An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.
Do neural networks offer something for you?
Ramchandran, S.; Rhinehart, R.R.
1995-11-01
The concept of neural network computation was inspired by the hope to artifically reproduce some of the flexibility and power of the human brain. Human beings can recognize different patterns and voices even though these signals do not have a simple phenomenological understanding. Scientists have developed artificial neural networks (ANNs) for modeling processes that do not have a simple phenomenological explanation, such as voice recognition. Consequently, ANN jargon can be confusing to process and control engineers. In simple terms, ANNs take a nonlinear regression modeling approach. Like any regression curve-fitting approach, a least-squares optimization can generate model parameters. One advantage of ANNs is that they require neither a priori understanding of the process behavior nor phenomenological understanding of the process. ANNs use data describing the input/output relationship in a process to {open_quotes}learn{close_quotes} about the underlying process behavior. As a result of this, ANNs have a wide range of applicability. Furthermore, ANNs are computationally efficient and can replace models that are computationally intensive. This can make real-time online model-based applications practicable. A neural network is a dense mesh of nodes and connections. The basic processing elements of a network are called neurons. Neural networks are organized in layers, and typically consist of at least three layers: an input layer, one or more hidden layers, and an output layer. The input and output layers serve as interfaces that perform appropriate scaling between `real-world` and network data. Hidden layers are so termed because their neurons are hidden to the real-world data. Connections are the means for information flow. Each connection has an associated adjustable weight, w{sub i}. The weight can be regarded as a measure of the importance of the signals between the two neurons. 7 figs.
Neural networks in the process industries
Ben, L.R.; Heavner, L.
1996-12-01
Neural networks, or more precisely, artificial neural networks (ANNs), are rapidly gaining in popularity. They first began to appear on the process-control scene in the early 1990s, but have been a research focus for more than 30 years. Neural networks are really empirical models that approximate the way man thinks neurons in the human brain work. Neural-net technology is not trying to produce computerized clones, but to model nature in an effort to mimic some of the brain`s capabilities. Modeling, for the purposes of this article, means developing a mathematical description of physical phenomena. The physics and chemistry of industrial processes are usually quite complex and sometimes poorly understood. Our process understanding, and our imperfect ability to describe complexity in mathematical terms, limit fidelity of first-principle models. Computational requirements for executing these complex models are a further limitation. It is often not possible to execute first-principle model algorithms at the high rate required for online control. Nevertheless, rigorous first principle models are commonplace design tools. Process control is another matter. Important model inputs are often not available as process measurements, making real-time application difficult. In fact, engineers often use models to infer unavailable measurements. 5 figs.
Exceptional reducibility of complex-valued neural networks.
Kobayashi, Masaki
2010-07-01
A neural network is referred to as minimal if it cannot reduce the number of hidden neurons that maintain the input-output map. The condition in which the number of hidden neurons can be reduced is referred to as reducibility. Real-valued neural networks have only three simple types of reducibility. It can be naturally extended to complex-valued neural networks without bias terms of hidden neurons. However, general complex-valued neural networks have another type of reducibility, referred to herein as exceptional reducibility. In this paper, another type of reducibility is presented, and a method by which to minimize complex-valued neural networks is proposed.
Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks.
Walter, Florian; Röhrbein, Florian; Knoll, Alois
2015-12-01
The application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high level of abstraction but employs highly realistic simulations of actual biological nervous systems. Even today, carrying out these simulations efficiently at appropriate timescales is challenging. Neuromorphic chip designs specially tailored to this task therefore offer an interesting perspective for neurorobotics. Unlike Von Neumann CPUs, these chips cannot be simply programmed with a standard programming language. Like real brains, their functionality is determined by the structure of neural connectivity and synaptic efficacies. Enabling higher cognitive functions for neurorobotics consequently requires the application of neurobiological learning algorithms to adjust synaptic weights in a biologically plausible way. In this paper, we therefore investigate how to program neuromorphic chips by means of learning. First, we provide an overview over selected neuromorphic chip designs and analyze them in terms of neural computation, communication systems and software infrastructure. On the theoretical side, we review neurobiological learning techniques. Based on this overview, we then examine on-die implementations of these learning algorithms on the considered neuromorphic chips. A final discussion puts the findings of this work into context and highlights how neuromorphic hardware can potentially advance the field of autonomous robot systems. The paper thus gives an in-depth overview of neuromorphic implementations of basic mechanisms of synaptic plasticity which are required to realize advanced cognitive capabilities with spiking neural networks.
Pruning Neural Networks with Distribution Estimation Algorithms
Cantu-Paz, E
2003-01-15
This paper describes the application of four evolutionary algorithms to the pruning of neural networks used in classification problems. Besides of a simple genetic algorithm (GA), the paper considers three distribution estimation algorithms (DEAs): a compact GA, an extended compact GA, and the Bayesian Optimization Algorithm. The objective is to determine if the DEAs present advantages over the simple GA in terms of accuracy or speed in this problem. The experiments used a feed forward neural network trained with standard back propagation and public-domain and artificial data sets. The pruned networks seemed to have better or equal accuracy than the original fully-connected networks. Only in a few cases, pruning resulted in less accurate networks. We found few differences in the accuracy of the networks pruned by the four EAs, but found important differences in the execution time. The results suggest that a simple GA with a small population might be the best algorithm for pruning networks on the data sets we tested.
Neural network computer simulation of medical aerosols.
Richardson, C J; Barlow, D J
1996-06-01
Preliminary investigations have been conducted to assess the potential for using artificial neural networks to simulate aerosol behaviour, with a view to employing this type of methodology in the evaluation and design of pulmonary drug-delivery systems. Details are presented of the general purpose software developed for these tasks; it implements a feed-forward back-propagation algorithm with weight decay and connection pruning, the user having complete run-time control of the network architecture and mode of training. A series of exploratory investigations is then reported in which different network structures and training strategies are assessed in terms of their ability to simulate known patterns of fluid flow in simple model systems. The first of these involves simulations of cellular automata-generated data for fluid flow through a partially obstructed two-dimensional pipe. The artificial neural networks are shown to be highly successful in simulating the behaviour of this simple linear system, but with important provisos relating to the information content of the training data and the criteria used to judge when the network is properly trained. A second set of investigations is then reported in which similar networks are used to simulate patterns of fluid flow through aerosol generation devices, using training data furnished through rigorous computational fluid dynamics modelling. These more complex three-dimensional systems are modelled with equal success. It is concluded that carefully tailored, well trained networks could provide valuable tools not just for predicting but also for analysing the spatial dynamics of pharmaceutical aerosols.
Membership generation using multilayer neural network
NASA Technical Reports Server (NTRS)
Kim, Jaeseok
1992-01-01
There has been intensive research in neural network applications to pattern recognition problems. Particularly, the back-propagation network has attracted many researchers because of its outstanding performance in pattern recognition applications. In this section, we describe a new method to generate membership functions from training data using a multilayer neural network. The basic idea behind the approach is as follows. The output values of a sigmoid activation function of a neuron bear remarkable resemblance to membership values. Therefore, we can regard the sigmoid activation values as the membership values in fuzzy set theory. Thus, in order to generate class membership values, we first train a suitable multilayer network using a training algorithm such as the back-propagation algorithm. After the training procedure converges, the resulting network can be treated as a membership generation network, where the inputs are feature values and the outputs are membership values in the different classes. This method allows fairly complex membership functions to be generated because the network is highly nonlinear in general. Also, it is to be noted that the membership functions are generated from a classification point of view. For pattern recognition applications, this is highly desirable, although the membership values may not be indicative of the degree of typicality of a feature value in a particular class.
Multivariate Cryptography Based on Clipped Hopfield Neural Network.
Wang, Jia; Cheng, Lee-Ming; Su, Tong
2016-11-23
Designing secure and efficient multivariate public key cryptosystems [multivariate cryptography (MVC)] to strengthen the security of RSA and ECC in conventional and quantum computational environment continues to be a challenging research in recent years. In this paper, we will describe multivariate public key cryptosystems based on extended Clipped Hopfield Neural Network (CHNN) and implement it using the MVC (CHNN-MVC) framework operated in GF(p) space. The Diffie--Hellman key exchange algorithm is extended into the matrix field, which illustrates the feasibility of its new applications in both classic and postquantum cryptography. The efficiency and security of our proposed new public key cryptosystem CHNN-MVC are simulated and found to be NP-hard. The proposed algorithm will strengthen multivariate public key cryptosystems and allows hardware realization practicality.
Improving health care organizational management through neural network learning.
Goss, Ernest Preston; Vozikis, George S
2002-08-01
In order to provide more ethical and objective measures of the likelihood of Intensive Care Unit (ICU) recovery, hospitals have turned increasingly to decision support system software packages, such as APACHE. However, these packages derive estimates from parametric techniques, such as Binary Logit Regression (BLR) in the APACHE case, and require the developer to specify in advance the functional relationships among variables in the model. Recent rapid advancements in computer software and hardware technology have encouraged researchers to use more computationally intensive, non-parametric techniques such as Neural Networks (NNs), which are purported to be better than parametric models in terms of prediction capabilities. The present study applies both methodologies to a sample of ICU patients and shows that the NN technique predicts mortality rates more correctly than BLR, and offers a promising non-parametric alternative to the parametric methodologies in hospital settings.
Efficiently passing messages in distributed spiking neural network simulation.
Thibeault, Corey M; Minkovich, Kirill; O'Brien, Michael J; Harris, Frederick C; Srinivasa, Narayan
2013-01-01
Efficiently passing spiking messages in a neural model is an important aspect of high-performance simulation. As the scale of networks has increased so has the size of the computing systems required to simulate them. In addition, the information exchange of these resources has become more of an impediment to performance. In this paper we explore spike message passing using different mechanisms provided by the Message Passing Interface (MPI). A specific implementation, MVAPICH, designed for high-performance clusters with Infiniband hardware is employed. The focus is on providing information about these mechanisms for users of commodity high-performance spiking simulators. In addition, a novel hybrid method for spike exchange was implemented and benchmarked.
NASA Astrophysics Data System (ADS)
Ji, Zhengping; Ovsiannikov, Ilia; Wang, Yibing; Shi, Lilong; Zhang, Qiang
2015-05-01
In this paper, we develop a server-client quantization scheme to reduce bit resolution of deep learning architecture, i.e., Convolutional Neural Networks, for image recognition tasks. Low bit resolution is an important factor in bringing the deep learning neural network into hardware implementation, which directly determines the cost and power consumption. We aim to reduce the bit resolution of the network without sacrificing its performance. To this end, we design a new quantization algorithm called supervised iterative quantization to reduce the bit resolution of learned network weights. In the training stage, the supervised iterative quantization is conducted via two steps on server - apply k-means based adaptive quantization on learned network weights and retrain the network based on quantized weights. These two steps are alternated until the convergence criterion is met. In this testing stage, the network configuration and low-bit weights are loaded to the client hardware device to recognize coming input in real time, where optimized but expensive quantization becomes infeasible. Considering this, we adopt a uniform quantization for the inputs and internal network responses (called feature maps) to maintain low on-chip expenses. The Convolutional Neural Network with reduced weight and input/response precision is demonstrated in recognizing two types of images: one is hand-written digit images and the other is real-life images in office scenarios. Both results show that the new network is able to achieve the performance of the neural network with full bit resolution, even though in the new network the bit resolution of both weight and input are significantly reduced, e.g., from 64 bits to 4-5 bits.
Non-Intrusive Gaze Tracking Using Artificial Neural Networks
1994-01-05
Artificial Neural Networks Shumeet Baluja & Dean...this paper appear in: Baluja, S. & Pomerleau, D.A. "Non-Intrusive Gaze Tracking Using Artificial Neural Networks ", Advances in Neural Information...document hLc-s been opproved t0T 011bhiC leleWOe cad ý’ir/4 its di stT-b’ution Ls •_nii•ite6. - Keywords Gaze Tracking, Artificial Neural Networks ,
A Projection Neural Network for Constrained Quadratic Minimax Optimization.
Liu, Qingshan; Wang, Jun
2015-11-01
This paper presents a projection neural network described by a dynamic system for solving constrained quadratic minimax programming problems. Sufficient conditions based on a linear matrix inequality are provided for global convergence of the proposed neural network. Compared with some of the existing neural networks for quadratic minimax optimization, the proposed neural network in this paper is capable of solving more general constrained quadratic minimax optimization problems, and the designed neural network does not include any parameter. Moreover, the neural network has lower model complexities, the number of state variables of which is equal to that of the dimension of the optimization problems. The simulation results on numerical examples are discussed to demonstrate the effectiveness and characteristics of the proposed neural network.
Toward implementation of artificial neural networks that "really work".
Leon, M. A.; Keller, J.
1997-01-01
Artificial neural networks are established analytical methods in bio-medical research. They have repeatedly outperformed traditional tools for pattern recognition and clinical outcome prediction while assuring continued adaptation and learning. However, successful experimental neural networks systems seldom reach a production state. That is, they are not incorporated into clinical information systems. It could be speculated that neural networks simply must undergo a lengthy acceptance process before they become part of the day to day operations of health care systems. However, our experience trying to incorporate experimental neural networks into information systems lead us to believe that there are technical and operational barriers that greatly difficult neural network implementation. A solution for these problems may be the delineation of policies and procedures for neural network implementation and the development a new class of neural network client/server applications that fit the needs of current clinical information systems. PMID:9357613
Correcting wave predictions with artificial neural networks
NASA Astrophysics Data System (ADS)
Makarynskyy, O.; Makarynska, D.
2003-04-01
The predictions of wind waves with different lead times are necessary in a large scope of coastal and open ocean activities. Numerical wave models, which usually provide this information, are based on deterministic equations that do not entirely account for the complexity and uncertainty of the wave generation and dissipation processes. An attempt to improve wave parameters short-term forecasts based on artificial neural networks is reported. In recent years, artificial neural networks have been used in a number of coastal engineering applications due to their ability to approximate the nonlinear mathematical behavior without a priori knowledge of interrelations among the elements within a system. The common multilayer feed-forward networks, with a nonlinear transfer functions in the hidden layers, were developed and employed to forecast the wave characteristics over one hour intervals starting from one up to 24 hours, and to correct these predictions. Three non-overlapping data sets of wave characteristics, both from a buoy, moored roughly 60 miles west of the Aran Islands, west coast of Ireland, were used to train and validate the neural nets involved. The networks were trained with error back propagation algorithm. Time series plots and scatterplots of the wave characteristics as well as tables with statistics show an improvement of the results achieved due to the correction procedure employed.
Applications of neural networks in training science.
Pfeiffer, Mark; Hohmann, Andreas
2012-04-01
Training science views itself as an integrated and applied science, developing practical measures founded on scientific method. Therefore, it demands consideration of a wide spectrum of approaches and methods. Especially in the field of competitive sports, research questions are usually located in complex environments, so that mainly field studies are drawn upon to obtain broad external validity. Here, the interrelations between different variables or variable sets are mostly of a nonlinear character. In these cases, methods like neural networks, e.g., the pattern recognizing methods of Self-Organizing Kohonen Feature Maps or similar instruments to identify interactions might be successfully applied to analyze data. Following on from a classification of data analysis methods in training-science research, the aim of the contribution is to give examples of varied sports in which network approaches can be effectually used in training science. First, two examples are given in which neural networks are employed for pattern recognition. While one investigation deals with the detection of sporting talent in swimming, the other is located in game sports research, identifying tactical patterns in team handball. The third and last example shows how an artificial neural network can be used to predict competitive performance in swimming.
Functional expansion representations of artificial neural networks
NASA Technical Reports Server (NTRS)
Gray, W. Steven
1992-01-01
In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.
Character Recognition Using Genetically Trained Neural Networks
Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.
1998-10-01
Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the amount of
Chemical implementation of neural networks and Turing machines.
Hjelmfelt, A; Weinberger, E D; Ross, J
1991-01-01
We propose a reversible reaction mechanism with a single stationary state in which certain concentrations assume either high or low values dependent on the concentration of a catalyst. The properties of this mechanism are those of a McCulloch-Pitts neuron. We suggest a mechanism of interneuronal connections in which the stationary state of a chemical neuron is determined by the state of other neurons in a homogeneous chemical system and is thus a "hardware" chemical implementation of neural networks. Specific connections are determined for the construction of logic gates: AND, NOR, etc. Neural networks may be constructed in which the flow of time is continuous and computations are achieved by the attainment of a stationary state of the entire chemical reaction system, or in which the flow of time is discretized by an oscillatory reaction. In another article, we will give a chemical implementation of finite state machines and stack memories, with which in principle the construction of a universal Turing machine is possible. PMID:1763012
Yang, Changju; Kim, Hyongsuk; Adhikari, Shyam Prasad; Chua, Leon O.
2016-01-01
A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems. PMID:28025566
Yang, Changju; Kim, Hyongsuk; Adhikari, Shyam Prasad; Chua, Leon O
2016-12-23
A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems.
On lateral competition in dynamic neural networks
Bellyustin, N.S.
1995-02-01
Artificial neural networks connected homogeneously, which use retinal image processing methods, are considered. We point out that there are probably two different types of lateral inhibition for each neural element by the neighboring ones-due to the negative connection coefficients between elements and due to the decreasing neuron`s response to a too high input signal. The first case characterized by stable dynamics, which is given by the Lyapunov function, while in the second case, stability is absent and two-dimensional dynamic chaos occurs if the time step in the integration of model equations is large enough. The continuous neural medium approximation is used for analytical estimation in both cases. The result is the partition of the parameter space into domains with qualitatively different dynamic modes. Computer simulations confirm the estimates and show that joining two-dimensional chaos with symmetries provided by the initial and boundary conditions may produce patterns which are genuine pieces of art.
Neural networks as a control methodology
NASA Technical Reports Server (NTRS)
Mccullough, Claire L.
1990-01-01
While conventional computers must be programmed in a logical fashion by a person who thoroughly understands the task to be performed, the motivation behind neural networks is to develop machines which can train themselves to perform tasks, using available information about desired system behavior and learning from experience. There are three goals of this fellowship program: (1) to evaluate various neural net methods and generate computer software to implement those deemed most promising on a personal computer equipped with Matlab; (2) to evaluate methods currently in the professional literature for system control using neural nets to choose those most applicable to control of flexible structures; and (3) to apply the control strategies chosen in (2) to a computer simulation of a test article, the Control Structures Interaction Suitcase Demonstrator, which is a portable system consisting of a small flexible beam driven by a torque motor and mounted on springs tuned to the first flexible mode of the beam. Results of each are discussed.
Neural network models of categorical perception.
Damper, R I; Harnad, S R
2000-05-01
Studies of the categorical perception (CP) of sensory continua have a long and rich history in psychophysics. In 1977, Macmillan, Kaplan, and Creelman introduced the use of signal detection theory to CP studies. Anderson and colleagues simultaneously proposed the first neural model for CP, yet this line of research has been less well explored. In this paper, we assess the ability of neural-network models of CP to predict the psychophysical performance of real observers with speech sounds and artificial/novel stimuli. We show that a variety of neural mechanisms are capable of generating the characteristics of CP. Hence, CP may not be a special model of perception but an emergent property of any sufficiently powerful general learning system.
Speed up Neural Network Learning by GPGPU
NASA Astrophysics Data System (ADS)
Tsuchida, Yuta; Yoshioka, Michifumi
Recently, graphic boards have higher performance with development of 3DCG and movie processing than CPU, and widely used with progress of computer entertainment. Implementation of the General-purpose computing on GPU (GPGPU) become more easier by the integrated development environment, CUDA distributed by NVIDIA. GPU has dozens or a hundred arithmetic circuits, whose allocations are controlled by CUDA. In the previous researches, the implementation of the neural network using GPGPU have been studied, however the learning of networks was not mentioned because the GPU performance is low in conditional processing whereas high in linear algebra processing. Therefore we have proposed two methods. At first, a whole network is implemented as a thread, and some networks are taught in parallel to shorten the time necessary to find the optimal weight coefficients. Secondly, this paper introduces parallelization in the neural network structure, that is, the calculation of neurons in the same layers can be paralleled. And the processes to teach for same network with different patterns are independent also. As a result, the second method is 20 times faster than CPU, and compared with the first proposed method, that is about 6 times faster.
Open-source hardware and software and web application for gamma dose rate network operation.
Luff, R; Zähringer, M; Harms, W; Bleher, M; Prommer, B; Stöhlker, U
2014-08-01
The German Federal Office for Radiation Protection operates a network of about 1800 gamma dose rate stations as a part of the national emergency preparedness plan. Each of the six network centres is capable of operating the network alone. Most of the used hardware and software have been developed in-house under open-source license. Short development cycles and close cooperation between developers and users ensure robustness, transparency and fast maintenance procedures, thus avoiding unnecessary complex solutions. This also reduces the overall costs of the network operation. An easy-to-expand web interface has been developed to make the complete system available to other interested network operators in order to increase cooperation between different countries. The interface is also regularly in use for education during scholarships of trainees supported, e.g. by the 'International Atomic Energy Agency' to operate a local area dose rate monitoring test network.
Visual grammars and their neural networks
NASA Astrophysics Data System (ADS)
Mjolsness, Eric
1992-07-01
We exhibit a systematic way to derive neural nets for vision problems. It involves formulating a vision problem as Bayesian inference or decision on a comprehensive model of the visual domain given by a probabilistic grammar. A key feature of this grammar is the way in which it eliminates model information, such as object labels, as it produces an image; correspondence problems and other noise removal tasks result. The neural nets that arise most directly are generalized assignment networks. Also there are transformations which naturally yield improved algorithms such as correlation matching in scale space and the Frameville neural nets for high-level vision. Networks derived this way generally have objective functions with spurious local minima; such minima may commonly be avoided by dynamics that include deterministic annealing, for example recent improvements to Mean Field Theory dynamics. The grammatical method of neural net design allows domain knowledge to enter from all levels of the grammar, including `abstract' levels remote from the final image data, and may permit new kinds of learning as well.
Complex Chebyshev-polynomial-based unified model (CCPBUM) neural networks
NASA Astrophysics Data System (ADS)
Jeng, Jin-Tsong; Lee, Tsu-Tian
1998-03-01
In this paper, we propose complex Chebyshev Polynomial Based unified model neural network for the approximation of complex- valued function. Based on this approximate transformable technique, we have derived the relationship between the single-layered neural network and multi-layered perceptron neural network. It is shown that the complex Chebyshev Polynomial Based unified model neural network can be represented as a functional link network that are based on Chebyshev polynomial. We also derived a new learning algorithm for the proposed network. It turns out that the complex Chebyshev Polynomial Based unified model neural network not only has the same capability of universal approximator, but also has faster learning speed than conventional complex feedforward/recurrent neural network.
Automatic breast density classification using neural network
NASA Astrophysics Data System (ADS)
Arefan, D.; Talebpour, A.; Ahmadinejhad, N.; Kamali Asl, A.
2015-12-01
According to studies, the risk of breast cancer directly associated with breast density. Many researches are done on automatic diagnosis of breast density using mammography. In the current study, artifacts of mammograms are removed by using image processing techniques and by using the method presented in this study, including the diagnosis of points of the pectoral muscle edges and estimating them using regression techniques, pectoral muscle is detected with high accuracy in mammography and breast tissue is fully automatically extracted. In order to classify mammography images into three categories: Fatty, Glandular, Dense, a feature based on difference of gray-levels of hard tissue and soft tissue in mammograms has been used addition to the statistical features and a neural network classifier with a hidden layer. Image database used in this research is the mini-MIAS database and the maximum accuracy of system in classifying images has been reported 97.66% with 8 hidden layers in neural network.
Application of neural networks in space construction
NASA Technical Reports Server (NTRS)
Thilenius, Stephen C.; Barnes, Frank
1990-01-01
When trying to decide what task should be done by robots and what tasks should be done by humans with respect to space construction, there has been one decisive barrier which ultimately divides the tasks: can a computer do the job? Von Neumann type computers have great difficulty with problems that the human brain seems to do instantaneously and with little effort. Some of these problems are pattern recognition, speech recognition, content addressable memories, and command interpretation. In an attempt to simulate these talents of the human brain, much research was currently done into the operations and construction of artificial neural networks. The efficiency of the interface between man and machine, robots in particular, can therefore be greatly improved with the use of neural networks. For example, wouldn't it be easier to command a robot to 'fetch an object' rather then having to remotely control the entire operation with remote control?
Neural networks predict tomato maturity stage
NASA Astrophysics Data System (ADS)
Hahn, Federico
1999-03-01
Almost 40% of the total horticultural produce exported from Mexico the USA is tomato, and quality is fundamental for maintaining the market. Many fruits packed at the green-mature stage do not mature towards a red color as they were harvested before achieving its physiological maturity. Tomato gassed for advancing maturation does not respond on those fruits, and repacking is necessary at terminal markets, causing losses to the producer. Tomato spectral signatures are different on each maturity stage and tomato size was poorly correlated against peak wavelengths. A back-propagation neural network was used to predict tomato maturity using reflectance ratios as inputs. Higher success rates were achieved on tomato maturity stage recognition with neural networks than with discriminant analysis.
Privacy-preserving backpropagation neural network learning.
Chen, Tingting; Zhong, Sheng
2009-10-01
With the development of distributed computing environment , many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms. In this paper, we focus on preserving the privacy in an important learning model, multilayer neural networks. We present a privacy-preserving two-party distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other. We provide complete correctness and security analysis of our algorithms. The effectiveness of our algorithms is verified by experiments on various real world data sets.
Neural networks for aerosol particles characterization
NASA Astrophysics Data System (ADS)
Berdnik, V. V.; Loiko, V. A.
2016-11-01
Multilayer perceptron neural networks with one, two and three inputs are built to retrieve parameters of spherical homogeneous nonabsorbing particle. The refractive index ranges from 1.3 to 1.7; particle radius ranges from 0.251 μm to 56.234 μm. The logarithms of the scattered radiation intensity are used as input signals. The problem of the most informative scattering angles selection is elucidated. It is shown that polychromatic illumination helps one to increase significantly the retrieval accuracy. In the absence of measurement errors relative error of radius retrieval by the neural network with three inputs is 0.54%, relative error of the refractive index retrieval is 0.84%. The effect of measurement errors on the result of retrieval is simulated.
Pattern recognition, neural networks, and artificial intelligence
NASA Astrophysics Data System (ADS)
Bezdek, James C.
1991-03-01
We write about the relationship between numerical patten recognition and neural-like computation networks. Extensive research that proposes the use of neural models for a wide variety of applications has been conducted in the past few years. Sometimes justification for investigating the potential of neural nets (NNs) is obvious. On the other hand, current enthusiasm for this approach has also led to the use of neural models when the apparent rationale for their use has been justified by what is best described as 'feeding frenzy'. In this latter instance there is at times concomitant lack of concern about many 'side issues' connected with algorithms (e.g., complexity, convergence, stability, robustness and performance validation) that need attention before any computational model becomes part of an operation system. These issues are examined with a view towards guessing how best to integrate and exploit the promise of the neural approach with there efforts aimed at advancing the art and science of pattern recognition and its applications in fielded systems in the next decade.
When Networks Disagree: Ensemble Methods for Hybrid Neural Networks
1992-10-27
takes the form of repeated on-line stochastic gradient descent of randomly initialized nets. However, unlike the combination process in parametric ... estimation which usually takes the form of a simple average in parameter space, the parameters in a neural network take the form of neuronal weights which
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.
Cognitively Inspired Neural Network for Situation Recognition
2010-01-14
Neurodynamics of Higher-Level Cognition and Consciousness, Eds. Perlovsky, 1.I., Kozma, R. Springer Verlag, Heidelberg, Germany. Perlovsky, L.I., Deming...Perlovsky L. I., Kozma R. (2007) Eds. Neurodynamics of Higher-Level Cognition and Consciousness. Heidelberg, Germany: Springer-Verlag. Perlovsky, L.1...AFRL-RY -HS-TR-20 10-0028 Cognitively Inspired Neural Network for Situation Recognition Roman Ilin and Leonid Perlovsky AFRURYHE 80 Scott Drive
Correlation Filter Synthesis Using Neural Networks.
1993-12-01
distortions, and this approach has clear advantages compared to searching stored filters. I)jL.,i.A I £EJTCMD 3 14. SUBJECT TERMS I NUMBER OF...distortions. They also indicate possible significant advantages compared to searching stored filters. ii 1. INTRODUCTION This section briefly...possible significant advantages compared to searching stored filters. The technical effort on correlation filter synthesis using neural networks was
Program PSNN (Plasma Spectroscopy Neural Network)
Morgan, W.L.; Larsen, J.T.
1993-08-01
This program uses the standard ``delta rule`` back-propagation supervised training algorithm for multi-layer neural networks. The inputs are line intensities in arbitrary units, which are then normalized within the program. The outputs are T{sub e}(eV), N{sub e}(cm{sup {minus}3}), and a fractional ionization, which in our testing using H- and He-like spectra, was N(He)/[N(H) + N(He)].
Nonvolatile Array Of Synapses For Neural Network
NASA Technical Reports Server (NTRS)
Tawel, Raoul
1993-01-01
Elements of array programmed with help of ultraviolet light. A 32 x 32 very-large-scale integrated-circuit array of electronic synapses serves as building-block chip for analog neural-network computer. Synaptic weights stored in nonvolatile manner. Makes information content of array invulnerable to loss of power, and, by eliminating need for circuitry to refresh volatile synaptic memory, makes architecture simpler and more compact.
Adaptive Filtering Using Recurrent Neural Networks
NASA Technical Reports Server (NTRS)
Parlos, Alexander G.; Menon, Sunil K.; Atiya, Amir F.
2005-01-01
A method for adaptive (or, optionally, nonadaptive) filtering has been developed for estimating the states of complex process systems (e.g., chemical plants, factories, or manufacturing processes at some level of abstraction) from time series of measurements of system inputs and outputs. The method is based partly on the fundamental principles of the Kalman filter and partly on the use of recurrent neural networks. The standard Kalman filter involves an assumption of linearity of the mathematical model used to describe a process system. The extended Kalman filter accommodates a nonlinear process model but still requires linearization about the state estimate. Both the standard and extended Kalman filters involve the often unrealistic assumption that process and measurement noise are zero-mean, Gaussian, and white. In contrast, the present method does not involve any assumptions of linearity of process models or of the nature of process noise; on the contrary, few (if any) assumptions are made about process models, noise models, or the parameters of such models. In this regard, the method can be characterized as one of nonlinear, nonparametric filtering. The method exploits the unique ability of neural networks to approximate nonlinear functions. In a given case, the process model is limited mainly by limitations of the approximation ability of the neural networks chosen for that case. Moreover, despite the lack of assumptions regarding process noise, the method yields minimum- variance filters. In that they do not require statistical models of noise, the neural- network-based state filters of this method are comparable to conventional nonlinear least-squares estimators.
Artificial neural network cardiopulmonary modeling and diagnosis
Kangas, L.J.; Keller, P.E.
1997-10-28
The present invention is a method of diagnosing a cardiopulmonary condition in an individual by comparing data from a progressive multi-stage test for the individual to a non-linear multi-variate model, preferably a recurrent artificial neural network having sensor fusion. The present invention relies on a cardiovascular model developed from physiological measurements of an individual. Any differences between the modeled parameters and the parameters of an individual at a given time are used for diagnosis. 12 figs.
Artificial neural network cardiopulmonary modeling and diagnosis
Kangas, Lars J.; Keller, Paul E.
1997-01-01
The present invention is a method of diagnosing a cardiopulmonary condition in an individual by comparing data from a progressive multi-stage test for the individual to a non-linear multi-variate model, preferably a recurrent artificial neural network having sensor fusion. The present invention relies on a cardiovascular model developed from physiological measurements of an individual. Any differences between the modeled parameters and the parameters of an individual at a given time are used for diagnosis.
Neural network architectures to analyze OPAD data
NASA Technical Reports Server (NTRS)
Whitaker, Kevin W.
1992-01-01
A prototype Optical Plume Anomaly Detection (OPAD) system is now installed on the space shuttle main engine (SSME) Technology Test Bed (TTB) at MSFC. The OPAD system requirements dictate the need for fast, efficient data processing techniques. To address this need of the OPAD system, a study was conducted into how artificial neural networks could be used to assist in the analysis of plume spectral data.
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.
Development and Organization of Neural Networks.
1988-01-01
the Hopfield relaxation model . 9 br GENERAL POTENTIAL SURFACES AN4D NEURAL NETWORKS Amir Dembo and Ofer Zeitouni Division of Applied Mathematics...Report, June 9, 1987. The Hopfield Model and Beyond, Bachmann, C. M., ARO Technical Report, December 15, 1986. A Relaxation Model for Memory with High...storage efficiencey in the Hopfield model . The original model was capable of accurate storage and retrieval, with some error correction, for up to
Neural Network-Based Hyperspectral Algorithms
2016-06-07
our effort is development of robust numerical inversion algorithms, which will retrieve inherent optical properties of the water column as well as...combination of in-situ and model data of water column variables (IOP’s, depth, bottom type, upwelling radiance, etc.) a neural network non-linear...function approximation model will be used to establish the inverse relationship between upwelling surface radiance and the water column variables, 2
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Shelton, Robert O.
1991-01-01
Introduced here is a novel technique which adds the dimension of time to the well known back propagation neural network algorithm. Cited here are several reasons why the inclusion of automated spatial and temporal associations are crucial to effective systems modeling. An overview of other works which also model spatiotemporal dynamics is furnished. A detailed description is given of the processes necessary to implement the space-time network algorithm. Several demonstrations that illustrate the capabilities and performance of this new architecture are given.
Deep learning in neural networks: an overview.
Schmidhuber, Jürgen
2015-01-01
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
Phase Transitions in Living Neural Networks
NASA Astrophysics Data System (ADS)
Williams-Garcia, Rashid Vladimir
Our nervous systems are composed of intricate webs of interconnected neurons interacting in complex ways. These complex interactions result in a wide range of collective behaviors with implications for features of brain function, e.g., information processing. Under certain conditions, such interactions can drive neural network dynamics towards critical phase transitions, where power-law scaling is conjectured to allow optimal behavior. Recent experimental evidence is consistent with this idea and it seems plausible that healthy neural networks would tend towards optimality. This hypothesis, however, is based on two problematic assumptions, which I describe and for which I present alternatives in this thesis. First, critical transitions may vanish due to the influence of an environment, e.g., a sensory stimulus, and so living neural networks may be incapable of achieving "critical" optimality. I develop a framework known as quasicriticality, in which a relative optimality can be achieved depending on the strength of the environmental influence. Second, the power-law scaling supporting this hypothesis is based on statistical analysis of cascades of activity known as neuronal avalanches, which conflate causal and non-causal activity, thus confounding important dynamical information. In this thesis, I present a new method to unveil causal links, known as causal webs, between neuronal activations, thus allowing for experimental tests of the quasicriticality hypothesis and other practical applications.
Constrained Least Absolute Deviation Neural Networks
Wang, Zhishun; Peterson, Bradley S.
2008-01-01
It is well known that least absolute deviation (LAD) criterion or L1-norm used for estimation of parameters is characterized by robustness, i.e., the estimated parameters are totally resistant (insensitive) to large changes in the sampled data. This is an extremely useful feature, especially, when the sampled data are known to be contaminated by occasionally occurring outliers or by spiky noise. In our previous works, we have proposed the least absolute deviation neural network (LADNN) to solve unconstrained LAD problems. The theoretical proofs and numerical simulations have shown that the LADNN is Lyapunov-stable and it can globally converge to the exact solution to a given unconstrained LAD problem. We have also demonstrated its excellent application value in time-delay estimation. More generally, a practical LAD application problem may contain some linear constraints, such as a set of equalities and/or inequalities, which is called constrained LAD problem, whereas the unconstrained LAD can be considered as a special form of the constrained LAD. In this paper, we present a new neural network called constrained least absolute deviation neural network (CLADNN) to solve general constrained LAD problems. Theoretical proofs and numerical simulations demonstrate that the proposed CLADNN is Lyapunov stable and globally converges to the exact solution to a given constrained LAD problem, independent of initial values. The numerical simulations have also illustrated that the proposed CLADNN can be used to robustly estimate parameters for nonlinear curve fitting, which is extensively used in signal and image processing. PMID:18269958
Random interactions in higher order neural networks
NASA Technical Reports Server (NTRS)
Baldi, Pierre; Venkatesh, Santosh S.
1993-01-01
Recurrent networks of polynomial threshold elements with random symmetric interactions are studied. Precise asymptotic estimates are derived for the expected number of fixed points as a function of the margin of stability. In particular, it is shown that there is a critical range of margins of stability (depending on the degree of polynomial interaction) such that the expected number of fixed points with margins below the critical range grows exponentially with the number of nodes in the network, while the expected number of fixed points with margins above the critical range decreases exponentially with the number of nodes in the network. The random energy model is also briefly examined and links with higher order neural networks and higher order spin glass models made explicit.
Categorization in neural networks and prosopagnosia
NASA Astrophysics Data System (ADS)
Virasoro, M. A.
1989-12-01
Prosopagnosia is a syndrome characterized by a generalized difficulty to visually recognize individual patterns among those that are similar, and can therefore be said to belong to the same category. I suggest that the existence of this disfunction may be an important clue for understanding the categorization process in the brain. In this direction the performance of neural networks under random destruction of synapses is analysed. It is found that in almost every network that stores correlated patterns the coding of the discriminating details between individuals inside a class is more sensitive to noise or to random destruction than the coding that distinguishes between classes. It follows that a process of death and/or deterioration at an intermediate level of intensity, even if it acts randomly on the network may lead to a malfunctioning of the network that resembles prosopagnosia.
Desynchronization in diluted neural networks.
Zillmer, Rüdiger; Livi, Roberto; Politi, Antonio; Torcini, Alessandro
2006-09-01
The dynamical behavior of a weakly diluted fully inhibitory network of pulse-coupled spiking neurons is investigated. Upon increasing the coupling strength, a transition from regular to stochasticlike regime is observed. In the weak-coupling phase, a periodic dynamics is rapidly approached, with all neurons firing with the same rate and mutually phase locked. The strong-coupling phase is characterized by an irregular pattern, even though the maximum Lyapunov exponent is negative. The paradox is solved by drawing an analogy with the phenomenon of "stable chaos," i.e., by observing that the stochasticlike behavior is "limited" to an exponentially long (with the system size) transient. Remarkably, the transient dynamics turns out to be stationary.
NASA Astrophysics Data System (ADS)
Botwicz, Jakub; Buciak, Piotr; Sapiecha, Piotr
2006-03-01
Intrusion Prevention Systems (IPSs) have become widely recognized as a powerful tool and an important element of IT security safeguards. The essential feature of network IPSs is searching through network packets and matching multiple strings, that are fingerprints of known attacks. String matching is highly resource consuming and also the most significant bottleneck of IPSs. In this article an extension of the classical Karp-Rabin algorithm and its implementation architectures were examined. The result is a software, which generates a source code of a string matching module in hardware description language, that could be easily used to create an Intrusion Prevention System implemented in reconfigurable hardware. The prepared module matches the complete set of Snort IPS signatures achieving throughput of over 2 Gbps on an Altera Stratix I1 evaluation board. The most significant advantage of the proposed architecture is that the update of the patterns database does not require reconfiguration of the circuitry.
Locating hardware faults in a data communications network of a parallel computer
Archer, Charles J.; Megerian, Mark G.; Ratterman, Joseph D.; Smith, Brian E.
2010-01-12
Hardware faults location in a data communications network of a parallel computer. Such a parallel computer includes a plurality of compute nodes and a data communications network that couples the compute nodes for data communications and organizes the compute node as a tree. Locating hardware faults includes identifying a next compute node as a parent node and a root of a parent test tree, identifying for each child compute node of the parent node a child test tree having the child compute node as root, running a same test suite on the parent test tree and each child test tree, and identifying the parent compute node as having a defective link connected from the parent compute node to a child compute node if the test suite fails on the parent test tree and succeeds on all the child test trees.
Neural networks optimally trained with noisy data
NASA Astrophysics Data System (ADS)
Wong, K. Y. Michael; Sherrington, David
1993-06-01
We study the retrieval behaviors of neural networks which are trained to optimize their performance for an ensemble of noisy example patterns. In particular, we consider (1) the performance overlap, which reflects the performance of the network in an operating condition identical to the training condition; (2) the storage overlap, which reflects the ability of the network to merely memorize the stored information; (3) the attractor overlap, which reflects the precision of retrieval for dilute feedback networks; and (4) the boundary overlap, which defines the boundary of the basin of attraction, and hence the associative ability for dilute feedback networks. We find that for sufficiently low training noise, the network optimizes its overall performance by sacrificing the individual performance of a minority of patterns, resulting in a two-band distribution of the aligning fields. For a narrow range of storage level, the network loses and then regains its retrieval capability when the training noise level increases, and we interpret that this reentrant retrieval behavior is related to competing tendencies in structuring the basins of attraction for the stored patterns. Reentrant behavior is also observed in the space of synaptic interactions, in which the replica symmetric solution of the optimal network destabilizes and then restabilizes when the training noise level increases. We summarize these observations by picturing training noises as an instrument for widening the basins of attractions of the stored patterns at the expense of reducing the precision of retrieval.
Models of neural networks with fuzzy activation functions
NASA Astrophysics Data System (ADS)
Nguyen, A. T.; Korikov, A. M.
2017-02-01
This paper investigates the application of a new form of neuron activation functions that are based on the fuzzy membership functions derived from the theory of fuzzy systems. On the basis of the results regarding neuron models with fuzzy activation functions, we created the models of fuzzy-neural networks. These fuzzy-neural network models differ from conventional networks that employ the fuzzy inference systems using the methods of neural networks. While conventional fuzzy-neural networks belong to the first type, fuzzy-neural networks proposed here are defined as the second-type models. The simulation results show that the proposed second-type model can successfully solve the problem of the property prediction for time – dependent signals. Neural networks with fuzzy impulse activation functions can be widely applied in many fields of science, technology and mechanical engineering to solve the problems of classification, prediction, approximation, etc.
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.
A Wavelet Neural Network for SAR Image Segmentation
Wen, Xian-Bin; Zhang, Hua; Wang, Fa-Yu
2009-01-01
This paper proposes a wavelet neural network (WNN) for SAR image segmentation by combining the wavelet transform and an artificial neural network. The WNN combines the multiscale analysis ability of the wavelet transform and the classification capability of the artificial neural network by setting the wavelet function as the transfer function of the neural network. Several SAR images are segmented by the network whose transfer functions are the Morlet and Mexihat functions, respectively. The experimental results show the proposed method is very effective and accurate. PMID:22400005
A neural network short-term forecast of significant thunderstorms
Mccann, D.W. )
1992-09-01
Neural networks, an artificial-intelligence tools that excels in pattern recognition, are reviewed, and a 3-7-h significant thunderstorm forecast developed with this technique is discussed. Two neural networks learned to forecast significant thunderstorms from fields of surface-based lifted index and surface moisture convergence. These networks are sensitive to the patterns that skilled forecasters recognize as occurring prior to strong thunderstorms. The two neural networks are combined operationally at the National Severe Storm Forecast Center into a single hourly product that enhances pattern-recognition skills. Examples of neural network products are shown, and their potential impact on significant thunderstorm forecasting is demonstrated. 22 refs.
The effect of the neural activity on topological properties of growing neural networks.
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.
Network traffic anomaly prediction using Artificial Neural Network
NASA Astrophysics Data System (ADS)
Ciptaningtyas, Hening Titi; Fatichah, Chastine; Sabila, Altea
2017-03-01
As the excessive increase of internet usage, the malicious software (malware) has also increase significantly. Malware is software developed by hacker for illegal purpose(s), such as stealing data and identity, causing computer damage, or denying service to other user[1]. Malware which attack computer or server often triggers network traffic anomaly phenomena. Based on Sophos's report[2], Indonesia is the riskiest country of malware attack and it also has high network traffic anomaly. This research uses Artificial Neural Network (ANN) to predict network traffic anomaly based on malware attack in Indonesia which is recorded by Id-SIRTII/CC (Indonesia Security Incident Response Team on Internet Infrastructure/Coordination Center). The case study is the highest malware attack (SQL injection) which has happened in three consecutive years: 2012, 2013, and 2014[4]. The data series is preprocessed first, then the network traffic anomaly is predicted using Artificial Neural Network and using two weight update algorithms: Gradient Descent and Momentum. Error of prediction is calculated using Mean Squared Error (MSE) [7]. The experimental result shows that MSE for SQL Injection is 0.03856. So, this approach can be used to predict network traffic anomaly.
Marginalization in Random Nonlinear Neural Networks
NASA Astrophysics Data System (ADS)
Vasudeva Raju, Rajkumar; Pitkow, Xaq
2015-03-01
Computations involved in tasks like causal reasoning in the brain require a type of probabilistic inference known as marginalization. Marginalization corresponds to averaging over irrelevant variables to obtain the probability of the variables of interest. This is a fundamental operation that arises whenever input stimuli depend on several variables, but only some are task-relevant. Animals often exhibit behavior consistent with marginalizing over some variables, but the neural substrate of this computation is unknown. It has been previously shown (Beck et al. 2011) that marginalization can be performed optimally by a deterministic nonlinear network that implements a quadratic interaction of neural activity with divisive normalization. We show that a simpler network can perform essentially the same computation. These Random Nonlinear Networks (RNN) are feedforward networks with one hidden layer, sigmoidal activation functions, and normally-distributed weights connecting the input and hidden layers. We train the output weights connecting the hidden units to an output population, such that the output model accurately represents a desired marginal probability distribution without significant information loss compared to optimal marginalization. Simulations for the case of linear coordinate transformations show that the RNN model has good marginalization performance, except for highly uncertain inputs that have low amplitude population responses. Behavioral experiments, based on these results, could then be used to identify if this model does indeed explain how the brain performs marginalization.
Brain tumor segmentation with Deep Neural Networks.
Havaei, Mohammad; Davy, Axel; Warde-Farley, David; Biard, Antoine; Courville, Aaron; Bengio, Yoshua; Pal, Chris; Jodoin, Pierre-Marc; Larochelle, Hugo
2017-01-01
In this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and high grade) pictured in MR images. By their very nature, these tumors can appear anywhere in the brain and have almost any kind of shape, size, and contrast. These reasons motivate our exploration of a machine learning solution that exploits a flexible, high capacity DNN while being extremely efficient. Here, we give a description of different model choices that we've found to be necessary for obtaining competitive performance. We explore in particular different architectures based on Convolutional Neural Networks (CNN), i.e. DNNs specifically adapted to image data. We present a novel CNN architecture which differs from those traditionally used in computer vision. Our CNN exploits both local features as well as more global contextual features simultaneously. Also, different from most traditional uses of CNNs, our networks use a final layer that is a convolutional implementation of a fully connected layer which allows a 40 fold speed up. We also describe a 2-phase training procedure that allows us to tackle difficulties related to the imbalance of tumor labels. Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN. Results reported on the 2013 BRATS test data-set reveal that our architecture improves over the currently published state-of-the-art while being over 30 times faster.
Neural Network Model of Memory Retrieval
Recanatesi, Stefano; Katkov, Mikhail; Romani, Sandro; Tsodyks, Misha
2015-01-01
Human memory can store large amount of information. Nevertheless, recalling is often a challenging task. In a classical free recall paradigm, where participants are asked to repeat a briefly presented list of words, people make mistakes for lists as short as 5 words. We present a model for memory retrieval based on a Hopfield neural network where transition between items are determined by similarities in their long-term memory representations. Meanfield analysis of the model reveals stable states of the network corresponding (1) to single memory representations and (2) intersection between memory representations. We show that oscillating feedback inhibition in the presence of noise induces transitions between these states triggering the retrieval of different memories. The network dynamics qualitatively predicts the distribution of time intervals required to recall new memory items observed in experiments. It shows that items having larger number of neurons in their representation are statistically easier to recall and reveals possible bottlenecks in our ability of retrieving memories. Overall, we propose a neural network model of information retrieval broadly compatible with experimental observations and is consistent with our recent graphical model (Romani et al., 2013). PMID:26732491
Current-mode implementation of processing modules in ART-based neural networks
NASA Astrophysics Data System (ADS)
Lopez-Alcantud, Jose-Alejandro; Hauer, Hans; Diaz-Madrid, Jose-Angel; Ruiz-Merino, Ramon
2003-04-01
This paper describes implementation of neural network processing layers using basic current-mode operating modules. The research work has been focused on the implementation of neural networks based on the Adaptive Resonance Theory, developed by S. Grossberg and G.A. Carpenter. The ART-based neural network whose operating modules have been choosen for development is the one called MART, proposed by F. Delgado, because of its complex architecture, auto--adaptive self-learning process, able to discard unmeaningful cathegories. Our presentation starts introducing the behaviour of MART with an analysis of its structure. The development described by this research work is focused on the monochannel block included in the main signal processing part of the MART neural network. The description of the computing algorithm of the layers inside a monochannel block are also provided in order to show what operational current-mode modules are needed (multiplier, divider, square-rooter, adder, substractor, absolute value, maximum and minimum evaluator...). Descriptions at schematic and layout levels of all the processing layers are given. All of them have been designed using AMS 0.35 micron technology with a supply voltage of 3.3 volts. The modules are designed to deal with input currents in the range of 20 to 50 microamps, showing a lineal behaviour and an output error of less than 10%, which is good enough for neural signal processing systems. The maximum frecuency of operation is around 200 kHz. Simulation results are included to show that the operation performed by the hardware designed matches the behaviour described by the MART neural network. For testing purposes we show the design of a monochannel block hardware implementation restricted to five inputs and three cathegories.
Nelson, Austin; Chakraborty, Sudipta; Wang, Dexin; Singh, Pawan; Cui, Qiang; Yang, Liuqing; Suryanarayanan, Siddharth
2016-11-14
This paper presents a cyber-physical testbed, developed to investigate the complex interactions between emerging microgrid technologies such as grid-interactive power sources, control systems, and a wide variety of communication platforms and bandwidths. The cyber-physical testbed consists of three major components for testing and validation: real time models of a distribution feeder model with microgrid assets that are integrated into the National Renewable Energy Laboratory's (NREL) power hardware-in-the-loop (PHIL) platform; real-time capable network-simulator-in-the-loop (NSIL) models; and physical hardware including inverters and a simple system controller. Several load profiles and microgrid configurations were tested to examine the effect on system performance with increasing channel delays and router processing delays in the network simulator. Testing demonstrated that the controller's ability to maintain a target grid import power band was severely diminished with increasing network delays and laid the foundation for future testing of more complex cyber-physical systems.
The NIDS Cluster: Scalable, Stateful Network Intrusion Detection on Commodity Hardware
Tierney, Brian L; Vallentin, Matthias; Sommer, Robin; Lee, Jason; Leres, Craig; Paxson, Vern; Tierney, Brian
2007-09-19
In this work we present a NIDS cluster as a scalable solution for realizing high-performance, stateful network intrusion detection on commodity hardware. The design addresses three challenges: (i) distributing traffic evenly across an extensible set of analysis nodes in a fashion that minimizes the communication required for coordination, (ii) adapting the NIDS's operation to support coordinating its low-level analysis rather than just aggregating alerts; and (iii) validating that the cluster produces sound results. Prototypes of our NIDS cluster now operate at the Lawrence Berkeley National Laboratory and the University of California at Berkeley. In both environments the clusters greatly enhance the power of the network security monitoring.
Solving quadratic programming problems by delayed projection neural network.
Yang, Yongqing; Cao, Jinde
2006-11-01
In this letter, the delayed projection neural network for solving convex quadratic programming problems is proposed. The neural network is proved to be globally exponentially stable and can converge to an optimal solution of the optimization problem. Three examples show the effectiveness of the proposed network.
Dynamic Attractors and Basin Class Capacity in Binary Neural Networks
1994-12-21
The wide repertoire of attractors and basins of attraction that appear in dynamic neural networks not only serve as models of brain activity patterns...limitations of static neural networks by use of dynamic attractors and their basins. The results show that dynamic networks have a high capacity for
Advances in Artificial Neural Networks - Methodological Development and Application
Technology Transfer Automated Retrieval System (TEKTRAN)
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...
Nonlinear system identification and control based on modular neural networks.
Puscasu, Gheorghe; Codres, Bogdan
2011-08-01
A new approach for nonlinear system identification and control based on modular neural networks (MNN) is proposed in this paper. The computational complexity of neural identification can be greatly reduced if the whole system is decomposed into several subsystems. This is obtained using a partitioning algorithm. Each local nonlinear model is associated with a nonlinear controller. These are also implemented by neural networks. The switching between the neural controllers is done by a dynamical switcher, also implemented by neural networks, that tracks the different operating points. The proposed multiple modelling and control strategy has been successfully tested on simulated laboratory scale liquid-level system.
Applying neural networks to ultrasonographic texture recognition
NASA Astrophysics Data System (ADS)
Gallant, Jean-Francois; Meunier, Jean; Stampfler, Robert; Cloutier, Jocelyn
1993-09-01
A neural network was trained to classify ultrasound image samples of normal, adenomatous (benign tumor) and carcinomatous (malignant tumor) thyroid gland tissue. The samples themselves, as well as their Fourier spectrum, miscellaneous cooccurrence matrices and 'generalized' cooccurrence matrices, were successively submitted to the network, to determine if it could be trained to identify discriminating features of the texture of the image, and if not, which feature extractor would give the best results. Results indicate that the network could indeed extract some distinctive features from the textures, since it could accomplish a partial classification when trained with the samples themselves. But a significant improvement both in learning speed and performance was observed when it was trained with the generalized cooccurrence matrices of the samples.
Survey on Neural Networks Used for Medical Image Processing.
Shi, Zhenghao; He, Lifeng; Suzuki, Kenji; Nakamura, Tsuyoshi; Itoh, Hidenori
2009-02-01
This paper aims to present a review of neural networks used in medical image processing. We classify neural networks by its processing goals and the nature of medical images. Main contributions, advantages, and drawbacks of the methods are mentioned in the paper. Problematic issues of neural network application for medical image processing and an outlook for the future research are also discussed. By this survey, we try to answer the following two important questions: (1) What are the major applications of neural networks in medical image processing now and in the nearby future? (2) What are the major strengths and weakness of applying neural networks for solving medical image processing tasks? We believe that this would be very helpful researchers who are involved in medical image processing with neural network techniques.
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks
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
An introduction to bio-inspired artificial neural network architectures.
Fasel, B
2003-03-01
In this introduction to artificial neural networks we attempt to give an overview of the most important types of neural networks employed in engineering and explain shortly how they operate and also how they relate to biological neural networks. The focus will mainly be on bio-inspired artificial neural network architectures and specifically to neo-perceptions. The latter belong to the family of convolutional neural networks. Their topology is somewhat similar to the one of the human visual cortex and they are based on receptive fields that allow, in combination with sub-sampling layers, for an improved robustness with regard to local spatial distortions. We demonstrate the application of artificial neural networks to face analysis--a domain we human beings are particularly good at, yet which poses great difficulties for digital computers running deterministic software programs.
ARMA Neural Networks for Predicting DGPS Pseudorange Correction
NASA Astrophysics Data System (ADS)
Jwo, Dah-Jing; Lee, Tai-Shen; Tseng, Ying-Wei
2004-05-01
In this paper, the Auto-Regressive Moving-Averaging (ARMA) neural networks (NNs) will be incorporated for predicting the differential Global Positioning System (DGPS) pseudorange correction (PRC) information. The neural network is employed to realize the time-varying ARMA implementation. Online training for real-time prediction of the PRC enhances the continuity of service on the differential correction signals and therefore improves the positioning accuracy. When the PRC signal is lost, the ARMA neural network predicted PRC would temporarily provide correction data with very good accuracy. Simulation is conducted for evaluating the ARMA NN based DGPS PRC prediction accuracy. A comparative performance study based on two types of ARMA neural networks, i.e. Back-propagation Neural Network (BPNN) and General Regression Neural Network (GRNN), will be provided.
Higherorder neural network group models for financial simulation.
Zhang, M; Zhang, J C; Fulcher, J
2000-04-01
Real world financial data is often discontinuous and non-smooth. If we attempt to use neural networks to simulate such functions, then accuracy will be a problem. Neural network group models perform this function much better. Both Polynomial Higher Order Neural network Group (PHONG) and Trigonometric polynomial Higher Order Neural network Group (THONG) models are developed. These HONG models are open box, convergent models capable of approximating any kind of piecewise continuous function, to any degree of accuracy. Moreover they are capable of handling higher frequency, higher order non-linear and discontinuous data. Results obtained using a Higher Order Neural network Group financial simulator are presented, which confirm that HONG group models converge without difficulty, and are considerably more accurate than neural network models (more specifically, around twice as good for prediction, and a factor of four improvement in the case of simulation).
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.
NASA Technical Reports Server (NTRS)
Hepner, George F.; Logan, Thomas; Ritter, Niles; Bryant, Nevin
1990-01-01
Recent research has shown an artificial neural network (ANN) to be capable of pattern recognition and the classification of image data. This paper examines the potential for the application of neural network computing to satellite image processing. A second objective is to provide a preliminary comparison and ANN classification. An artificial neural network can be trained to do land-cover classification of satellite imagery using selected sites representative of each class in a manner similar to conventional supervised classification. One of the major problems associated with recognition and classifications of pattern from remotely sensed data is the time and cost of developing a set of training sites. This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set. When using a minimal training set, the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure. This research is the foundation for developing application parameters for further prototyping of software and hardware implementations for artificial neural networks in satellite image and geographic information processing.
Three-dimensional thinning by neural networks
NASA Astrophysics Data System (ADS)
Shen, Jun; Shen, Wei
1995-10-01
3D thinning is widely used in 3D object representation in computer vision and in trajectory planning in robotics to find the topological structure of the free space. In the present paper, we propose a 3D image thinning method by neural networks. Each voxel in the 3D image corresponds to a set of neurons, called 3D Thinron, in the network. Taking the 3D Thinron as the elementary unit, the global structure of the network is a 3D array in which each Thinron is connected with the 26 neighbors in the neighborhood 3 X 3 X 3. As to the Thinron itself, the set of neurons are organized in multiple layers. In the first layer, we have neurons for boundary analysis, connectivity analysis and connectivity verification, taking as input the voxels in the 3 X 3 X 3 neighborhood and the intermediate outputs of neighboring Thinrons. In the second layer, we have the neurons for synthetical analysis to give the intermediate output of Thinron. In the third layer, we have the decision neurons whose state determines the final output. All neurons in the Thinron are the adaline neurons of Widrow, except the connectivity analysis and verification neurons which are nonlinear neurons. With the 3D Thinron neural network, the state transition of the network will take place automatically, and the network converges to the final steady state, which gives the result medial surface of 3D objects, preserving the connectivity in the initial image. The method presented is simulated and tested for 3D images, experimental results are reported.
Energy coding in biological neural networks.
Wang, Rubin; Zhang, Zhikang
2007-09-01
According to the experimental result of signal transmission and neuronal energetic demands being tightly coupled to information coding in the cerebral cortex, we present a brand new scientific theory that offers an unique mechanism for brain information processing. We demonstrate that the neural coding produced by the activity of the brain is well described by our theory of energy coding. Due to the energy coding model's ability to reveal mechanisms of brain information processing based upon known biophysical properties, we can not only reproduce various experimental results of neuro-electrophysiology, but also quantitatively explain the recent experimental results from neuroscientists at Yale University by means of the principle of energy coding. Due to the theory of energy coding to bridge the gap between functional connections within a biological neural network and energetic consumption, we estimate that the theory has very important consequences for quantitative research of cognitive function.
Training product unit neural networks with genetic algorithms
NASA Technical Reports Server (NTRS)
Janson, D. J.; Frenzel, J. F.; Thelen, D. C.
1991-01-01
The training of product neural networks using genetic algorithms is discussed. Two unusual neural network techniques are combined; product units are employed instead of the traditional summing units and genetic algorithms train the network rather than backpropagation. As an example, a neural netork is trained to calculate the optimum width of transistors in a CMOS switch. It is shown how local minima affect the performance of a genetic algorithm, and one method of overcoming this is presented.
Implementation of Fuzzy Inference Systems Using Neural Network Techniques
1992-03-01
rules required to implement the system, which are usually supplied by ’experts’. One alternative is to use a neural network -type architecture to implement...the fuzzy inference system, and neural network -type training techniques to ’learn’ the control parameters needed by the fuzzy inference system. By...using a generalized version of a neural network , the rules of the fuzzy inference system can be learned without the assistance of experts.
An Artificial Neural Network Control System for Spacecraft Attitude Stabilization
1990-06-01
training is based on the concept of enforced performance. A neural network will learn to meet a specific performance goal if the performance standard...is the only solution to a problem. Performance index training is devised to teach the neural network the time-optimal control law for the system. Real...time adaptation of a neural network in closed loop control of the Crew/Equipment Retriever was demonstrated in computer simulations.
Prediction of Buffet Loads Using Artificial Neural Networks
2001-09-01
The use of artificial neural networks (ANN) for predicting the empennage buffet pressures as a function of aircraft state has been investigated. The...with additional data. The study confirmed that neural networks have a great potential as a method for modelling buffet data. The ability of neural ... networks to accurately predict magnitude and spectral content of unsteady buffet pressures was demonstrated. Based on the ANN methodology investigated, a
Adaptive Control of Visually Guided Grasping in Neural Networks
1990-03-12
U01ITU S.WM NONnumsen Adaptive Control of Visually Guided Grasping in Neural Networks AFOSR-89-&CO030 88-NL-209 L AUTHOrSF 2313/A8 00 61102F (V) Dr...FINAL REPORT ADAPTIVE CONTROL OF VISUALLY GUIDED GRASPING IN NEURAL NETWORKS Neurogen Laboratories Inc. Project Summary Research performed for AFOSR...arm’s length in position and 6 degrees in orientation. Keywords: Neural Networks , Adaptive Motor Control, Sensory-Motor sensation Introduction The human
An Evaluation of Artificial Neural Network Modeling for Manpower Analysis
1993-09-01
This thesis evaluates the capabilities of artificial neural networks in forecasting the take-rates of the Voluntary Separations Incentive/Special...Separations Benefit (VSI/SSB) programs for male, Marine Corps Enlisted Personnel in the grades of E-5 and E-6. The Artificial Neural Networks models are...results indicate that artificial neural networks provide forecasting results at least as good as, if not better than, those obtained using classical
Equations of Learning and Capacity of Layered Neural Networks
1989-05-01
I-ILL ~Ut *4 (V) NWCTP 7013 (0 Equations of Learning and Capacity of 0Layered Neural Networks by Jorge M. Martin Applied Mathematics Research Group...multilayered neural networks that were discovered during the initial phase of the Independent Research project entitled "The Mathematics of Artificial...represent a small contribution to the basic knowledge of the mathematical aspects of the newly emergent theory of Artificial Neural Networks . This
Improved Landmine Detection by Complex-Valued Artificial Neural Networks
2002-12-04
IMPROVED LANDMINE DETECTION BY COMPLEX-VALUED ARTIFICIAL NEURAL NETWORKS Research was Sponsored by: U. S. ARMY RESEARCH OFFICE Program Manager... artificial neural networks in conjunction with fuzzy logic for improved system performance over and above the good results already attained are...of detecting mines. One of the more promising avenues of research in this area involves the use of artificial neural networks [3]. More specifically
One pass learning for generalized classifier neural network.
Ozyildirim, Buse Melis; Avci, Mutlu
2016-01-01
Generalized classifier neural network introduced as a kind of radial basis function neural network, uses gradient descent based optimized smoothing parameter value to provide efficient classification. However, optimization consumes quite a long time and may cause a drawback. In this work, one pass learning for generalized classifier neural network is proposed to overcome this disadvantage. Proposed method utilizes standard deviation of each class to calculate corresponding smoothing parameter. Since different datasets may have different standard deviations and data distributions, proposed method tries to handle these differences by defining two functions for smoothing parameter calculation. Thresholding is applied to determine which function will be used. One of these functions is defined for datasets having different range of values. It provides balanced smoothing parameters for these datasets through logarithmic function and changing the operation range to lower boundary. On the other hand, the other function calculates smoothing parameter value for classes having standard deviation smaller than the threshold value. Proposed method is tested on 14 datasets and performance of one pass learning generalized classifier neural network is compared with that of probabilistic neural network, radial basis function neural network, extreme learning machines, and standard and logarithmic learning generalized classifier neural network in MATLAB environment. One pass learning generalized classifier neural network provides more than a thousand times faster classification than standard and logarithmic generalized classifier neural network. Due to its classification accuracy and speed, one pass generalized classifier neural network can be considered as an efficient alternative to probabilistic neural network. Test results show that proposed method overcomes computational drawback of generalized classifier neural network and may increase the classification performance.
Position Sensorless Driving of BLDCM Using Neural Networks
NASA Astrophysics Data System (ADS)
Guo, Hai-Jiao; Sagawa, Seiji; Ichinokura, Osamu
A sensorless driving method of brushless DC Motors (BLDCM) using neural network has been studied in this paper. Considering the nonlinear characteristics and the parameter error of the modeling, neural networks are introduced to estimate the electromotive force (EMF). The results of simulation and experiment using offline trained neural networks show the proposed method is useful. In addition, the robustness about the parameters is discussed.
Geophysical phenomena classification by artificial neural networks
NASA Technical Reports Server (NTRS)
Gough, M. P.; Bruckner, J. R.
1995-01-01
Space science information systems involve accessing vast data bases. There is a need for an automatic process by which properties of the whole data set can be assimilated and presented to the user. Where data are in the form of spectrograms, phenomena can be detected by pattern recognition techniques. Presented are the first results obtained by applying unsupervised Artificial Neural Networks (ANN's) to the classification of magnetospheric wave spectra. The networks used here were a simple unsupervised Hamming network run on a PC and a more sophisticated CALM network run on a Sparc workstation. The ANN's were compared in their geophysical data recognition performance. CALM networks offer such qualities as fast learning, superiority in generalizing, the ability to continuously adapt to changes in the pattern set, and the possibility to modularize the network to allow the inter-relation between phenomena and data sets. This work is the first step toward an information system interface being developed at Sussex, the Whole Information System Expert (WISE). Phenomena in the data are automatically identified and provided to the user in the form of a data occurrence morphology, the Whole Information System Data Occurrence Morphology (WISDOM), along with relationships to other parameters and phenomena.
Learning and optimization with cascaded VLSI neural network building-block chips
NASA Technical Reports Server (NTRS)
Duong, T.; Eberhardt, S. P.; Tran, M.; Daud, T.; Thakoor, A. P.
1992-01-01
To demonstrate the versatility of the building-block approach, two neural network applications were implemented on cascaded analog VLSI chips. Weights were implemented using 7-b multiplying digital-to-analog converter (MDAC) synapse circuits, with 31 x 32 and 32 x 32 synapses per chip. A novel learning algorithm compatible with analog VLSI was applied to the two-input parity problem. The algorithm combines dynamically evolving architecture with limited gradient-descent backpropagation for efficient and versatile supervised learning. To implement the learning algorithm in hardware, synapse circuits were paralleled for additional quantization levels. The hardware-in-the-loop learning system allocated 2-5 hidden neurons for parity problems. Also, a 7 x 7 assignment problem was mapped onto a cascaded 64-neuron fully connected feedback network. In 100 randomly selected problems, the network found optimal or good solutions in most cases, with settling times in the range of 7-100 microseconds.
Physical connections between different SSVEP neural networks
Wu, Zhenghua
2016-01-01
This work investigates the mechanism of the Steady-State Visual Evoked Potential (SSVEP). One theory suggests that different SSVEP neural networks exist whose strongest response are located in different frequency bands. This theory is based on the fact that there are similar SSVEP frequency-amplitude response curves in these bands. Previous studies that employed simultaneous stimuli of different frequencies illustrated that the distribution of these networks were similar, but did not discuss the physical connection between them. By comparing the SSVEP power and distribution under a single-eye stimulus and a simultaneous, dual-eye stimulus, this work demonstrates that the distributions of different SSVEP neural networks are similar to each other and that there should be physical overlapping between them. According to the band-pass filter theory in a signal transferring channel, which we propose in this work for the first time, there are different amounts of neurons that are involved under repetitive stimuli of different frequencies and that the response intensity of each neuron is similar to each other so that the total response (i.e., the SSVEP) that is observed from the scalp is different. PMID:26952961
Representational Distance Learning for Deep Neural Networks.
McClure, Patrick; Kriegeskorte, Nikolaus
2016-01-01
Deep neural networks (DNNs) provide useful models of visual representational transformations. We present a method that enables a DNN (student) to learn from the internal representational spaces of a reference model (teacher), which could be another DNN or, in the future, a biological brain. Representational spaces of the student and the teacher are characterized by representational distance matrices (RDMs). We propose representational distance learning (RDL), a stochastic gradient descent method that drives the RDMs of the student to approximate the RDMs of the teacher. We demonstrate that RDL is competitive with other transfer learning techniques for two publicly available benchmark computer vision datasets (MNIST and CIFAR-100), while allowing for architectural differences between student and teacher. By pulling the student's RDMs toward those of the teacher, RDL significantly improved visual classification performance when compared to baseline networks that did not use transfer learning. In the future, RDL may enable combined supervised training of deep neural networks using task constraints (e.g., images and category labels) and constraints from brain-activity measurements, so as to build models that replicate the internal representational spaces of biological brains.
Representational Distance Learning for Deep Neural Networks
McClure, Patrick; Kriegeskorte, Nikolaus
2016-01-01
Deep neural networks (DNNs) provide useful models of visual representational transformations. We present a method that enables a DNN (student) to learn from the internal representational spaces of a reference model (teacher), which could be another DNN or, in the future, a biological brain. Representational spaces of the student and the teacher are characterized by representational distance matrices (RDMs). We propose representational distance learning (RDL), a stochastic gradient descent method that drives the RDMs of the student to approximate the RDMs of the teacher. We demonstrate that RDL is competitive with other transfer learning techniques for two publicly available benchmark computer vision datasets (MNIST and CIFAR-100), while allowing for architectural differences between student and teacher. By pulling the student's RDMs toward those of the teacher, RDL significantly improved visual classification performance when compared to baseline networks that did not use transfer learning. In the future, RDL may enable combined supervised training of deep neural networks using task constraints (e.g., images and category labels) and constraints from brain-activity measurements, so as to build models that replicate the internal representational spaces of biological brains. PMID:28082889
Correlated neural variability in persistent state networks.
Polk, Amber; Litwin-Kumar, Ashok; Doiron, Brent
2012-04-17
Neural activity that persists long after stimulus presentation is a biological correlate of short-term memory. Variability in spiking activity causes persistent states to drift over time, ultimately degrading memory. Models of short-term memory often assume that the input fluctuations to neural populations are independent across cells, a feature that attenuates population-level variability and stabilizes persistent activity. However, this assumption is at odds with experimental recordings from pairs of cortical neurons showing that both the input currents and output spike trains are correlated. It remains unclear how correlated variability affects the stability of persistent activity and the performance of cognitive tasks that it supports. We consider the stochastic long-timescale attractor dynamics of pairs of mutually inhibitory populations of spiking neurons. In these networks, persistent activity was less variable when correlated variability was globally distributed across both populations compared with the case when correlations were locally distributed only within each population. Using a reduced firing rate model with a continuum of persistent states, we show that, when input fluctuations are correlated across both populations, they drive firing rate fluctuations orthogonal to the persistent state attractor, thereby causing minimal stochastic drift. Using these insights, we establish that distributing correlated fluctuations globally as opposed to locally improves network's performance on a two-interval, delayed response discrimination task. Our work shows that the correlation structure of input fluctuations to a network is an important factor when determining long-timescale, persistent population spiking activity.
Neural network for solving convex quadratic bilevel programming problems.
He, Xing; Li, Chuandong; Huang, Tingwen; Li, Chaojie
2014-03-01
In this paper, using the idea of successive approximation, we propose a neural network to solve convex quadratic bilevel programming problems (CQBPPs), which is modeled by a nonautonomous differential inclusion. Different from the existing neural network for CQBPP, the model has the least number of state variables and simple structure. Based on the theory of nonsmooth analysis, differential inclusions and Lyapunov-like method, the limit equilibrium points sequence of the proposed neural networks can approximately converge to an optimal solution of CQBPP under certain conditions. Finally, simulation results on two numerical examples and the portfolio selection problem show the effectiveness and performance of the proposed neural network.
Developing a Neural Network to Act as a Noise Filter
1992-10-02
This study uses the neural network simulator called NETS to determine if neural networks could perform a non-linear filtering operation to remove...noise from two-dimensional (2-D) data and produce a noise-free image. Application is geared toward the development and performance of neural network filters...including the development of an optional neural network architecture and the use of-criteria in determining how accurate the net filtered noise-to produce a noise-free image.
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.
Neural network models: Insights and prescriptions from practical applications
Samad, T.
1995-12-31
Neural networks are no longer just a research topic; numerous applications are now testament to their practical utility. In the course of developing these applications, researchers and practitioners have been faced with a variety of issues. This paper briefly discusses several of these, noting in particular the rich connections between neural networks and other, more conventional technologies. A more comprehensive version of this paper is under preparation that will include illustrations on real examples. Neural networks are being applied in several different ways. Our focus here is on neural networks as modeling technology. However, much of the discussion is also relevant to other types of applications such as classification, control, and optimization.
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 and its application to CT imaging
Nikravesh, M.; Kovscek, A.R.; Patzek, T.W.
1997-02-01
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.
Neural networks and their application to nuclear power plant diagnosis
Reifman, J.
1997-10-01
The authors present a survey of artificial neural network-based computer systems that have been proposed over the last decade for the detection and identification of component faults in thermal-hydraulic systems of nuclear power plants. The capabilities and advantages of applying neural networks as decision support systems for nuclear power plant operators and their inherent characteristics are discussed along with their limitations and drawbacks. The types of neural network structures used and their applications are described and the issues of process diagnosis and neural network-based diagnostic systems are identified. A total of thirty-four publications are reviewed.
Using neural networks for dynamic light scattering time series processing
NASA Astrophysics Data System (ADS)
Chicea, Dan
2017-04-01
A basic experiment to record dynamic light scattering (DLS) time series was assembled using basic components. The DLS time series processing using the Lorentzian function fit was considered as reference. A Neural Network was designed and trained using simulated frequency spectra for spherical particles in the range 0–350 nm, assumed to be scattering centers, and the neural network design and training procedure are described in detail. The neural network output accuracy was tested both on simulated and on experimental time series. The match with the DLS results, considered as reference, was good serving as a proof of concept for using neural networks in fast DLS time series processing.
Parameterizing Stellar Spectra Using Deep Neural Networks
NASA Astrophysics Data System (ADS)
Li, Xiang-Ru; Pan, Ru-Yang; Duan, Fu-Qing
2017-03-01
Large-scale sky surveys are observing massive amounts of stellar spectra. The large number of stellar spectra makes it necessary to automatically parameterize spectral data, which in turn helps in statistically exploring properties related to the atmospheric parameters. This work focuses on designing an automatic scheme to estimate effective temperature ({T}{eff}), surface gravity ({log}g) and metallicity [Fe/H] from stellar spectra. A scheme based on three deep neural networks (DNNs) is proposed. This scheme consists of the following three procedures: first, the configuration of a DNN is initialized using a series of autoencoder neural networks; second, the DNN is fine-tuned using a gradient descent scheme; third, three atmospheric parameters {T}{eff}, {log}g and [Fe/H] are estimated using the computed DNNs. The constructed DNN is a neural network with six layers (one input layer, one output layer and four hidden layers), for which the number of nodes in the six layers are 3821, 1000, 500, 100, 30 and 1, respectively. This proposed scheme was tested on both real spectra and theoretical spectra from Kurucz’s new opacity distribution function models. Test errors are measured with mean absolute errors (MAEs). The errors on real spectra from the Sloan Digital Sky Survey (SDSS) are 0.1477, 0.0048 and 0.1129 dex for {log}g, {log}{T}{eff} and [Fe/H] (64.85 K for {T}{eff}), respectively. Regarding theoretical spectra from Kurucz’s new opacity distribution function models, the MAE of the test errors are 0.0182, 0.0011 and 0.0112 dex for {log}g, {log}{T}{eff} and [Fe/H] (14.90 K for {T}{eff}), respectively.
Deep Recurrent Neural Networks for Supernovae Classification
NASA Astrophysics Data System (ADS)
Charnock, Tom; Moss, Adam
2017-03-01
We apply deep recurrent neural networks, which are capable of learning complex sequential information, to classify supernovae (code available at https://github.com/adammoss/supernovae). The observational time and filter fluxes are used as inputs to the network, but since the inputs are agnostic, additional data such as host galaxy information can also be included. Using the Supernovae Photometric Classification Challenge (SPCC) data, we find that deep networks are capable of learning about light curves, however the performance of the network is highly sensitive to the amount of training data. For a training size of 50% of the representational SPCC data set (around 104 supernovae) we obtain a type-Ia versus non-type-Ia classification accuracy of 94.7%, an area under the Receiver Operating Characteristic curve AUC of 0.986 and an SPCC figure-of-merit F 1 = 0.64. When using only the data for the early-epoch challenge defined by the SPCC, we achieve a classification accuracy of 93.1%, AUC of 0.977, and F 1 = 0.58, results almost as good as with the whole light curve. By employing bidirectional neural networks, we can acquire impressive classification results between supernovae types I, II and III at an accuracy of 90.4% and AUC of 0.974. We also apply a pre-trained model to obtain classification probabilities as a function of time and show that it can give early indications of supernovae type. Our method is competitive with existing algorithms and has applications for future large-scale photometric surveys.
Resource constrained design of artificial neural networks using comparator neural network
NASA Technical Reports Server (NTRS)
Wah, Benjamin W.; Karnik, Tanay S.
1992-01-01
We present a systematic design method executed under resource constraints for automating the design of artificial neural networks using the back error propagation algorithm. Our system aims at finding the best possible configuration for solving the given application with proper tradeoff between the training time and the network complexity. The design of such a system is hampered by three related problems. First, there are infinitely many possible network configurations, each may take an exceedingly long time to train; hence, it is impossible to enumerate and train all of them to completion within fixed time, space, and resource constraints. Second, expert knowledge on predicting good network configurations is heuristic in nature and is application dependent, rendering it difficult to characterize fully in the design process. A learning procedure that refines this knowledge based on examples on training neural networks for various applications is, therefore, essential. Third, the objective of the network to be designed is ill-defined, as it is based on a subjective tradeoff between the training time and the network cost. A design process that proposes alternate configurations under different cost-performance tradeoff is important. We have developed a Design System which schedules the available time, divided into quanta, for testing alternative network configurations. Its goal is to select/generate and test alternative network configurations in each quantum, and find the best network when time is expended. Since time is limited, a dynamic schedule that determines the network configuration to be tested in each quantum is developed. The schedule is based on relative comparison of predicted training times of alternative network configurations using comparator network paradigm. The comparator network has been trained to compare training times for a large variety of traces of TSSE-versus-time collected during back-propagation learning of various applications.
Neural Networks and other Techniques for Fault Identification and Isolation of Aircraft Systems
NASA Technical Reports Server (NTRS)
Innocenti, M.; Napolitano, M.
2003-01-01
Fault identification, isolation, and accomodation have become critical issues in the overall performance of advanced aircraft systems. Neural Networks have shown to be a very attractive alternative to classic adaptation methods for identification and control of non-linear dynamic systems. The purpose of this paper is to show the improvements in neural network applications achievable through the use of learning algorithms more efficient than the classic Back-Propagation, and through the implementation of the neural schemes in parallel hardware. The results of the analysis of a scheme for Sensor Failure, Detection, Identification and Accommodation (SFDIA) using experimental flight data of a research aircraft model are presented. Conventional approaches to the problem are based on observers and Kalman Filters while more recent methods are based on neural approximators. The work described in this paper is based on the use of neural networks (NNs) as on-line learning non-linear approximators. The performances of two different neural architectures were compared. The first architecture is based on a Multi Layer Perceptron (MLP) NN trained with the Extended Back Propagation algorithm (EBPA). The second architecture is based on a Radial Basis Function (RBF) NN trained with the Extended-MRAN (EMRAN) algorithms. In addition, alternative methods for communications links fault detection and accomodation are presented, relative to multiple unmanned aircraft applications.
Neural Network Architectures for General Image Recognition.
1992-07-21
Design Procedure 88 A.5 Examples 92 A.6 Scaling Laws for Cooperative-Competitive Neural Networks 98 A.7 Discussion 100 REFERENCES 101 viii LIST OF...control law for vertical pull-in of the window. The two V2 outputs, NORTH and SOUTH, are subtracted and the window is moved if the thresholds are exceeded...An input pattern, shown in cross-hatching, is irapressed on M neurons. Each input neuron is connected to N hidden neutons and a single output neuron
Artificial Neural Network applied to lightning flashes
NASA Astrophysics Data System (ADS)
Gin, R. B.; Guedes, D.; Bianchi, R.
2013-05-01
The development of video cameras enabled cientists to study lightning discharges comportment with more precision. The main goal of this project is to create a system able to detect images of lightning discharges stored in videos and classify them using an Artificial Neural Network (ANN)using C Language and OpenCV libraries. The developed system, can be split in two different modules: detection module and classification module. The detection module uses OpenCV`s computer vision libraries and image processing techniques to detect if there are significant differences between frames in a sequence, indicating that something, still not classified, occurred. Whenever there is a significant difference between two consecutive frames, two main algorithms are used to analyze the frame image: brightness and shape algorithms. These algorithms detect both shape and brightness of the event, removing irrelevant events like birds, as well as detecting the relevant events exact position, allowing the system to track it over time. The classification module uses a neural network to classify the relevant events as horizontal or vertical lightning, save the event`s images and calculates his number of discharges. The Neural Network was implemented using the backpropagation algorithm, and was trained with 42 training images , containing 57 lightning events (one image can have more than one lightning). TheANN was tested with one to five hidden layers, with up to 50 neurons each. The best configuration achieved a success rate of 95%, with one layer containing 20 neurons (33 test images with 42 events were used in this phase). This configuration was implemented in the developed system to analyze 20 video files, containing 63 lightning discharges previously manually detected. Results showed that all the lightning discharges were detected, many irrelevant events were unconsidered, and the event's number of discharges was correctly computed. The neural network used in this project achieved a
Solving inversion problems with neural networks
NASA Technical Reports Server (NTRS)
Kamgar-Parsi, Behzad; Gualtieri, J. A.
1990-01-01
A class of inverse problems in remote sensing can be characterized by Q = F(x), where F is a nonlinear and noninvertible (or hard to invert) operator, and the objective is to infer the unknowns, x, from the observed quantities, Q. Since the number of observations is usually greater than the number of unknowns, these problems are formulated as optimization problems, which can be solved by a variety of techniques. The feasibility of neural networks for solving such problems is presently investigated. As an example, the problem of finding the atmospheric ozone profile from measured ultraviolet radiances is studied.
Finite time stabilization of delayed neural networks.
Wang, Leimin; Shen, Yi; Ding, Zhixia
2015-10-01
In this paper, the problem of finite time stabilization for a class of delayed neural networks (DNNs) is investigated. The general conditions on the feedback control law are provided to ensure the finite time stabilization of DNNs. Then some specific conditions are derived by designing two different controllers which include the delay-dependent and delay-independent ones. In addition, the upper bound of the settling time for stabilization is estimated. Under fixed control strength, discussions of the extremum of settling time functional are made and a switched controller is designed to optimize the settling time. Finally, numerical simulations are carried out to demonstrate the effectiveness of the obtained results.
Bacterial colony counting by Convolutional Neural Networks.
Ferrari, Alessandro; Lombardi, Stefano; Signoroni, Alberto
2015-01-01
Counting bacterial colonies on microbiological culture plates is a time-consuming, error-prone, nevertheless fundamental task in microbiology. Computer vision based approaches can increase the efficiency and the reliability of the process, but accurate counting is challenging, due to the high degree of variability of agglomerated colonies. In this paper, we propose a solution which adopts Convolutional Neural Networks (CNN) for counting the number of colonies contained in confluent agglomerates, that scored an overall accuracy of the 92.8% on a large challenging dataset. The proposed CNN-based technique for estimating the cardinality of colony aggregates outperforms traditional image processing approaches, becoming a promising approach to many related applications.
Zebrafish tracking using convolutional neural networks
XU, Zhiping; Cheng, Xi En
2017-01-01
Keeping identity for a long term after occlusion is still an open problem in the video tracking of zebrafish-like model animals, and accurate animal trajectories are the foundation of behaviour analysis. We utilize the highly accurate object recognition capability of a convolutional neural network (CNN) to distinguish fish of the same congener, even though these animals are indistinguishable to the human eye. We used data augmentation and an iterative CNN training method to optimize the accuracy for our classification task, achieving surprisingly accurate trajectories of zebrafish of different size and age zebrafish groups over different time spans. This work will make further behaviour analysis more reliable. PMID:28211462
Binaural Sound Localization Using Neural Networks
1991-12-12
by Brennan, involved the implementation of a neural network to model the ability of a bat to discriminate between a mealworm and an inedible object...locate, identify and capture airborne prey (6:2). The sonar returns were collected from the mealworms , spheres and disks at various rotations (90 to...order to meet the criteria. If 75 out of 100 test vectors met the criteria, then P(HHN) = 0.75. P(FBE I E): The probability that a classification error
Zebrafish tracking using convolutional neural networks
NASA Astrophysics Data System (ADS)
Xu, Zhiping; Cheng, Xi En
2017-02-01
Keeping identity for a long term after occlusion is still an open problem in the video tracking of zebrafish-like model animals, and accurate animal trajectories are the foundation of behaviour analysis. We utilize the highly accurate object recognition capability of a convolutional neural network (CNN) to distinguish fish of the same congener, even though these animals are indistinguishable to the human eye. We used data augmentation and an iterative CNN training method to optimize the accuracy for our classification task, achieving surprisingly accurate trajectories of zebrafish of different size and age zebrafish groups over different time spans. This work will make further behaviour analysis more reliable.
Digital Image Compression Using Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Serra-Ricart, M.; Garrido, L.; Gaitan, V.; Aloy, A.
1993-01-01
The problem of storing, transmitting, and manipulating digital images is considered. Because of the file sizes involved, large amounts of digitized image information are becoming common in modern projects. Our goal is to described an image compression transform coder based on artificial neural networks techniques (NNCTC). A comparison of the compression results obtained from digital astronomical images by the NNCTC and the method used in the compression of the digitized sky survey from the Space Telescope Science Institute based on the H-transform is performed in order to assess the reliability of the NNCTC.
Neural network models for Linear Programming
Culioli, J.C.; Protopopescu, V.; Britton, C.; Ericson, N. )
1989-01-01
The purpose of this paper is to present a neural network that solves the general Linear Programming (LP) problem. In the first part, we recall Hopfield and Tank's circuit for LP and show that although it converges to stable states, it does not, in general, yield admissible solutions. This is due to the penalization treatment of the constraints. In the second part, we propose an approach based on Lagragrange multipliers that converges to primal and dual admissible solutions. We also show that the duality gap (measuring the optimality) can be rendered, in principle, as small as needed. 11 refs.
Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan
2016-01-01
A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.
Characterization of Early Cortical Neural Network ...
We examined the development of neural network activity using microelectrode array (MEA) recordings made in multi-well MEA plates (mwMEAs) over the first 12 days in vitro (DIV). In primary cortical cultures made from postnatal rats, action potential spiking activity was essentially absent on DIV 2 and developed rapidly between DIV 5 and 12. Spiking activity was primarily sporadic and unorganized at early DIV, and became progressively more organized with time in culture, with bursting parameters, synchrony and network bursting increasing between DIV 5 and 12. We selected 12 features to describe network activity and principal components analysis using these features demonstrated a general segregation of data by age at both the well and plate levels. Using a combination of random forest classifiers and Support Vector Machines, we demonstrated that 4 features (CV of within burst ISI, CV of IBI, network spike rate and burst rate) were sufficient to predict the age (either DIV 5, 7, 9 or 12) of each well recording with >65% accuracy. When restricting the classification problem to a binary decision, we found that classification improved dramatically, e.g. 95% accuracy for discriminating DIV 5 vs DIV 12 wells. Further, we present a novel resampling approach to determine the number of wells that might be needed for conducting comparisons of different treatments using mwMEA plates. Overall, these results demonstrate that network development on mwMEA plates is similar to
Phase diagram of spiking neural networks
Seyed-allaei, Hamed
2015-01-01
In computer simulations of spiking neural networks, often it is assumed that every two neurons of the network are connected by a probability of 2%, 20% of neurons are inhibitory and 80% are excitatory. These common values are based on experiments, observations, and trials and errors, but here, I take a different perspective, inspired by evolution, I systematically simulate many networks, each with a different set of parameters, and then I try to figure out what makes the common values desirable. I stimulate networks with pulses and then measure their: dynamic range, dominant frequency of population activities, total duration of activities, maximum rate of population and the occurrence time of maximum rate. The results are organized in phase diagram. This phase diagram gives an insight into the space of parameters – excitatory to inhibitory ratio, sparseness of connections and synaptic weights. This phase diagram can be used to decide the parameters of a model. The phase diagrams show that networks which are configured according to the common values, have a good dynamic range in response to an impulse and their dynamic range is robust in respect to synaptic weights, and for some synaptic weights they oscillates in α or β frequencies, independent of external stimuli. PMID:25788885