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.
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.
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.
Electronic Neural-Network Simulator
NASA Technical Reports Server (NTRS)
Moopenn, Alex W.; Thakoor, Anilkumar P.; Lambe, John J.
1988-01-01
Experimental circuits faster than simulation programs run on digital computers. Serial shift register routes clock pulses C1 to neurons in sequence. Clock pulses C2 interrogate neurons. Neuron interconnection information stored in simulated synapses. Can be expanded to greater complexity.
Electronic Neural-Network Simulator
NASA Technical Reports Server (NTRS)
Moopenn, Alex W.; Thakoor, Anilkumar P.; Lambe, John J.
1988-01-01
Experimental circuits faster than simulation programs run on digital computers. Serial shift register routes clock pulses C1 to neurons in sequence. Clock pulses C2 interrogate neurons. Neuron interconnection information stored in simulated synapses. Can be expanded to greater complexity.
Conditional Simulation Using an Artificial Neural Network
NASA Astrophysics Data System (ADS)
Rizzo, D. M.; Besaw, L.
2005-12-01
Uncertainty in site characterization, due to sparsely distributed samples and incomplete site knowledge, is of major concern in resource mining and environmental engineering. Scientists are able to model the spatial continuity and quantify uncertainty of phenomena of interest (i.e. ore grade, subsurface contamination) through the generation and analysis of many equiprobable stochastic simulations (realizations) using concepts of probability theory. We have developed a method of generating equiprobable simulations by combining the traditional frame work of spatial dependencies witnessed in geostatistics with an artificial neural network (ANN) algorithm know as counterpropagation. This new method allows for the generation of simulations that respect the observed sample data as well as the data's underlying spatial structure. Conditional simulation is a natural product of the counterpropagation network using random initial weights while its architecture has computational advantages over other simulation generators due to its parallel information passing topology. Computational speedup, due to the implementation of the algorithm on a local cluster of off-the-shelf computational nodes and software, is another factor that will be discussed. The results of this research illustrate the potential applicability and utility of using the counterpropagation algorithm to conduct a probabilistic assessment while increasing interpretational value of site characterization data.
Simulation of large systems with neural networks
Paez, T.L.
1994-09-01
Artificial neural networks (ANNs) have been shown capable of simulating the behavior of complex, nonlinear, systems, including structural systems. Under certain circumstances, it is desirable to simulate structures that are analyzed with the finite element method. For example, when we perform a probabilistic analysis with the Monte Carlo method, we usually perform numerous (hundreds or thousands of) repetitions of a response simulation with different input and system parameters to estimate the chance of specific response behaviors. In such applications, efficiency in computation of response is critical, and response simulation with ANNs can be valuable. However, finite element analyses of complex systems involve the use of models with tens or hundreds of thousands of degrees of freedom, and ANNs are practically limited to simulations that involve far fewer variables. This paper develops a technique for reducing the amount of information required to characterize the response of a general structure. We show how the reduced information can be used to train a recurrent ANN. Then the trained ANN can be used to simulate the reduced behavior of the original system, and the reduction transformation can be inverted to provide a simulation of the original system. A numerical example is presented.
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.
Neural Network Simulation Package from Ohio State University
Wickham, K.L.
1990-08-01
This report describes the Neural Network Simulation Package acquired from Ohio State University. The package known as Neural Shell V2.1 was evaluated and benchmarked at the INEL Supercomputing Center (ISC). The emphasis was on the Back Propagation Net which is currently considered one of the more promising types of neural networks. This report also provides additional documentation that may be helpful to anyone using the package.
Toward unified hybrid simulation techniques for spiking neural networks.
D'Haene, Michiel; Hermans, Michiel; Schrauwen, Benjamin
2014-06-01
In the field of neural network simulation techniques, the common conception is that spiking neural network simulators can be divided in two categories: time-step-based and event-driven methods. In this letter, we look at state-of-the art simulation techniques in both categories and show that a clear distinction between both methods is increasingly difficult to define. In an attempt to improve the weak points of each simulation method, ideas of the alternative method are, sometimes unknowingly, incorporated in the simulation engine. Clearly the ideal simulation method is a mix of both methods. We formulate the key properties of such an efficient and generally applicable hybrid approach.
Simulating and Synthesizing Substructures Using Neural Network and Genetic Algorithms
NASA Technical Reports Server (NTRS)
Liu, Youhua; Kapania, Rakesh K.; VanLandingham, Hugh F.
1997-01-01
The feasibility of simulating and synthesizing substructures by computational neural network models is illustrated by investigating a statically indeterminate beam, using both a 1-D and a 2-D plane stress modelling. The beam can be decomposed into two cantilevers with free-end loads. By training neural networks to simulate the cantilever responses to different loads, the original beam problem can be solved as a match-up between two subsystems under compatible interface conditions. The genetic algorithms are successfully used to solve the match-up problem. Simulated results are found in good agreement with the analytical or FEM solutions.
Artificial neural network simulation of battery performance
O`Gorman, C.C.; Ingersoll, D.; Jungst, R.G.; Paez, T.L.
1998-12-31
Although they appear deceptively simple, batteries embody a complex set of interacting physical and chemical processes. While the discrete engineering characteristics of a battery such as the physical dimensions of the individual components, are relatively straightforward to define explicitly, their myriad chemical and physical processes, including interactions, are much more difficult to accurately represent. Within this category are the diffusive and solubility characteristics of individual species, reaction kinetics and mechanisms of primary chemical species as well as intermediates, and growth and morphology characteristics of reaction products as influenced by environmental and operational use profiles. For this reason, development of analytical models that can consistently predict the performance of a battery has only been partially successful, even though significant resources have been applied to this problem. As an alternative approach, the authors have begun development of a non-phenomenological model for battery systems based on artificial neural networks. Both recurrent and non-recurrent forms of these networks have been successfully used to develop accurate representations of battery behavior. The connectionist normalized linear spline (CMLS) network has been implemented with a self-organizing layer to model a battery system with the generalized radial basis function net. Concurrently, efforts are under way to use the feedforward back propagation network to map the {open_quotes}state{close_quotes} of a battery system. Because of the complexity of battery systems, accurate representation of the input and output parameters has proven to be very important. This paper describes these initial feasibility studies as well as the current models and makes comparisons between predicted and actual performance.
An artificial neural network based groundwater flow and transport simulator
Krom, T.D.; Rosbjerg, D.
1998-07-01
Artificial neural networks are investigated as a tool for the simulation of contaminant loss and recovery in three-dimensional heterogeneous groundwater flow and contaminant transport modeling. These methods have useful applications in expert system development, knowledge base development and optimization of groundwater pollution remediation. The numerical model runs used to develop the artificial neural networks can be re-used to develop artificial neural networks to address alternative optimization problems or changed formulations of the constraints and or objective function under optimization. Artificial neural networks have been analyzed with the goal of estimating objectives which normally require the use of traditional flow and transport codes: such as contaminant recovery, contaminant loss (unrecovered) and remediation failure. The inputs to the artificial neutral networks are variable pumping withdrawal rates at fairly unconstrained 3-D locations. A forward-feed backwards error propagation artificial neural network architecture is used. The significance of the size of the training set, network architecture, and network weight optimization algorithm with respect to the estimation accuracy and objective are shown to be important. Finally, the quality of the weight optimization is studied via cross-validation techniques. This is demonstrated to be a useful method for judging training performance for strongly under-described systems.
Simulation of nonlinear random vibrations using artificial neural networks
Paez, T.L.; Tucker, S.; O`Gorman, C.
1997-02-01
The simulation of mechanical system random vibrations is important in structural dynamics, but it is particularly difficult when the system under consideration is nonlinear. Artificial neural networks provide a useful tool for the modeling of nonlinear systems, however, such modeling may be inefficient or insufficiently accurate when the system under consideration is complex. This paper shows that there are several transformations that can be used to uncouple and simplify the components of motion of a complex nonlinear system, thereby making its modeling and random vibration simulation, via component modeling with artificial neural networks, a much simpler problem. A numerical example is presented.
Simulation of dynamic processes with adaptive neural networks.
Tzanos, C. P.
1998-02-03
Many industrial processes are highly non-linear and complex. Their simulation with first-principle or conventional input-output correlation models is not satisfactory, either because the process physics is not well understood, or it is so complex that direct simulation is either not adequately accurate, or it requires excessive computation time, especially for on-line applications. Artificial intelligence techniques (neural networks, expert systems, fuzzy logic) or their combination with simple process-physics models can be effectively used for the simulation of such processes. Feedforward (static) neural networks (FNNs) can be used effectively to model steady-state processes. They have also been used to model dynamic (time-varying) processes by adding to the network input layer input nodes that represent values of input variables at previous time steps. The number of previous time steps is problem dependent and, in general, can be determined after extensive testing. This work demonstrates that for dynamic processes that do not vary fast with respect to the retraining time of the neural network, an adaptive feedforward neural network can be an effective simulator that is free of the complexities introduced by the use of input values at previous time steps.
F77NNS - A FORTRAN-77 NEURAL NETWORK SIMULATOR
NASA Technical Reports Server (NTRS)
Mitchell, P. H.
1994-01-01
F77NNS (A FORTRAN-77 Neural Network Simulator) simulates the popular back error propagation neural network. F77NNS is an ANSI-77 FORTRAN program designed to take advantage of vectorization when run on machines having this capability, but it will run on any computer with an ANSI-77 FORTRAN Compiler. Artificial neural networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to biological nerve cells. Problems which involve pattern matching or system modeling readily fit the class of problems which F77NNS is designed to solve. The program's formulation trains a neural network using Rumelhart's back-propagation algorithm. Typically the nodes of a network are grouped together into clumps called layers. A network will generally have an input layer through which the various environmental stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. The back-propagation training algorithm can require massive computational resources to implement a large network such as a network capable of learning text-to-phoneme pronunciation rules as in the famous Sehnowski experiment. The Sehnowski neural network learns to pronounce 1000 common English words. The standard input data defines the specific inputs that control the type of run to be made, and input files define the NN in terms of the layers and nodes, as well as the input/output (I/O) pairs. The program has a restart capability so that a neural network can be solved in stages suitable to the user's resources and desires. F77NNS allows the user to customize the patterns of connections between layers of a network. The size of the neural network to be solved is limited only by the amount of random access memory (RAM) available to the
F77NNS - A FORTRAN-77 NEURAL NETWORK SIMULATOR
NASA Technical Reports Server (NTRS)
Mitchell, P. H.
1994-01-01
F77NNS (A FORTRAN-77 Neural Network Simulator) simulates the popular back error propagation neural network. F77NNS is an ANSI-77 FORTRAN program designed to take advantage of vectorization when run on machines having this capability, but it will run on any computer with an ANSI-77 FORTRAN Compiler. Artificial neural networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to biological nerve cells. Problems which involve pattern matching or system modeling readily fit the class of problems which F77NNS is designed to solve. The program's formulation trains a neural network using Rumelhart's back-propagation algorithm. Typically the nodes of a network are grouped together into clumps called layers. A network will generally have an input layer through which the various environmental stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. The back-propagation training algorithm can require massive computational resources to implement a large network such as a network capable of learning text-to-phoneme pronunciation rules as in the famous Sehnowski experiment. The Sehnowski neural network learns to pronounce 1000 common English words. The standard input data defines the specific inputs that control the type of run to be made, and input files define the NN in terms of the layers and nodes, as well as the input/output (I/O) pairs. The program has a restart capability so that a neural network can be solved in stages suitable to the user's resources and desires. F77NNS allows the user to customize the patterns of connections between layers of a network. The size of the neural network to be solved is limited only by the amount of random access memory (RAM) available to the
Multiscale Quantum Mechanics/Molecular Mechanics Simulations with Neural Networks.
Shen, Lin; Wu, Jingheng; Yang, Weitao
2016-10-11
Molecular dynamics simulation with multiscale quantum mechanics/molecular mechanics (QM/MM) methods is a very powerful tool for understanding the mechanism of chemical and biological processes in solution or enzymes. However, its computational cost can be too high for many biochemical systems because of the large number of ab initio QM calculations. Semiempirical QM/MM simulations have much higher efficiency. Its accuracy can be improved with a correction to reach the ab initio QM/MM level. The computational cost on the ab initio calculation for the correction determines the efficiency. In this paper we developed a neural network method for QM/MM calculation as an extension of the neural-network representation reported by Behler and Parrinello. With this approach, the potential energy of any configuration along the reaction path for a given QM/MM system can be predicted at the ab initio QM/MM level based on the semiempirical QM/MM simulations. We further applied this method to three reactions in water to calculate the free energy changes. The free-energy profile obtained from the semiempirical QM/MM simulation is corrected to the ab initio QM/MM level with the potential energies predicted with the constructed neural network. The results are in excellent accordance with the reference data that are obtained from the ab initio QM/MM molecular dynamics simulation or corrected with direct ab initio QM/MM potential energies. Compared with the correction using direct ab initio QM/MM potential energies, our method shows a speed-up of 1 or 2 orders of magnitude. It demonstrates that the neural network method combined with the semiempirical QM/MM calculation can be an efficient and reliable strategy for chemical reaction simulations.
Integrated Circuit For Simulation Of Neural Network
NASA Technical Reports Server (NTRS)
Thakoor, Anilkumar P.; Moopenn, Alexander W.; Khanna, Satish K.
1988-01-01
Ballast resistors deposited on top of circuit structure. Cascadable, programmable binary connection matrix fabricated in VLSI form as basic building block for assembly of like units into content-addressable electronic memory matrices operating somewhat like networks of neurons. Connections formed during storage of data, and data recalled from memory by prompting matrix with approximate or partly erroneous signals. Redundancy in pattern of connections causes matrix to respond with correct stored data.
Simulation of nonlinear strutures with artificial neural networks
Paez, T.L.
1996-03-01
Structural system simulation is important in analysis, design, testing, control, and other areas, but it is particularly difficult when the system under consideration is nonlinear. Artificial neural networks offer a useful tool for the modeling of nonlinear systems, however, such modeling may be inefficient or insufficiently accurate when the system under consideration is complex. This paper shows that there are several transformations that can be used to uncouple and simplify the components of motion of a complex nonlinear system, thereby making its modeling and simulation a much simpler problem. A numerical example is also presented.
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
Brian: A Simulator for Spiking Neural Networks in Python
Goodman, Dan; Brette, Romain
2008-01-01
“Brian” is a new simulator for spiking neural networks, written in Python (http://brian. di.ens.fr). It is an intuitive and highly flexible tool for rapidly developing new models, especially networks of single-compartment neurons. In addition to using standard types of neuron models, users can define models by writing arbitrary differential equations in ordinary mathematical notation. Python scientific libraries can also be used for defining models and analysing data. Vectorisation techniques allow efficient simulations despite the overheads of an interpreted language. Brian will be especially valuable for working on non-standard neuron models not easily covered by existing software, and as an alternative to using Matlab or C for simulations. With its easy and intuitive syntax, Brian is also very well suited for teaching computational neuroscience. PMID:19115011
Leader neurons in leaky integrate and fire neural network simulations.
Zbinden, Cyrille
2011-10-01
In this paper, we highlight the topological properties of leader neurons whose existence is an experimental fact. Several experimental studies show the existence of leader neurons in population bursts of activity in 2D living neural networks (Eytan and Marom, J Neurosci 26(33):8465-8476, 2006; Eckmann et al., New J Phys 10(015011), 2008). A leader neuron is defined as a neuron which fires at the beginning of a burst (respectively network spike) more often than we expect by chance considering its mean firing rate. This means that leader neurons have some burst triggering power beyond a chance-level statistical effect. In this study, we characterize these leader neuron properties. This naturally leads us to simulate neural 2D networks. To build our simulations, we choose the leaky integrate and fire (lIF) neuron model (Gerstner and Kistler 2002; Cessac, J Math Biol 56(3):311-345, 2008), which allows fast simulations (Izhikevich, IEEE Trans Neural Netw 15(5):1063-1070, 2004; Gerstner and Naud, Science 326:379-380, 2009). The dynamics of our lIF model has got stable leader neurons in the burst population that we simulate. These leader neurons are excitatory neurons and have a low membrane potential firing threshold. Except for these two first properties, the conditions required for a neuron to be a leader neuron are difficult to identify and seem to depend on several parameters involved in the simulations themselves. However, a detailed linear analysis shows a trend of the properties required for a neuron to be a leader neuron. Our main finding is: A leader neuron sends signals to many excitatory neurons as well as to few inhibitory neurons and a leader neuron receives only signals from few other excitatory neurons. Our linear analysis exhibits five essential properties of leader neurons each with different relative importance. This means that considering a given neural network with a fixed mean number of connections per neuron, our analysis gives us a way of
Code generation: a strategy for neural network simulators.
Goodman, Dan F M
2010-10-01
We demonstrate a technique for the design of neural network simulation software, runtime code generation. This technique can be used to give the user complete flexibility in specifying the mathematical model for their simulation in a high level way, along with the speed of code written in a low level language such as C+ +. It can also be used to write code only once but target different hardware platforms, including inexpensive high performance graphics processing units (GPUs). Code generation can be naturally combined with computer algebra systems to provide further simplification and optimisation of the generated code. The technique is quite general and could be applied to any simulation package. We demonstrate it with the 'Brian' simulator ( http://www.briansimulator.org ).
Correlated EEG Signals Simulation Based on Artificial Neural Networks.
Tomasevic, Nikola M; Neskovic, Aleksandar M; Neskovic, Natasa J
2016-09-30
In recent years, simulation of the human electroencephalogram (EEG) data found its important role in medical domain and neuropsychology. In this paper, a novel approach to simulation of two cross-correlated EEG signals is proposed. The proposed method is based on the principles of artificial neural networks (ANN). Contrary to the existing EEG data simulators, the ANN-based approach was leveraged solely on the experimentally acquired EEG data. More precisely, measured EEG data were utilized to optimize the simulator which consisted of two ANN models (each model responsible for generation of one EEG sequence). In order to acquire the EEG recordings, the measurement campaign was carried out on a healthy awake adult having no cognitive, physical or mental load. For the evaluation of the proposed approach, comprehensive quantitative and qualitative statistical analysis was performed considering probability distribution, correlation properties and spectral characteristics of generated EEG processes. The obtained results clearly indicated the satisfactory agreement with the measurement data.
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.
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. PMID:23772213
Neural networks for perceptual processing: from simulation tools to theories.
Gurney, Kevin
2007-03-29
Neural networks are modelling tools that are, in principle, able to capture the input-output behaviour of arbitrary systems that may include the dynamics of animal populations or brain circuits. While a neural network model is useful if it captures phenomenologically the behaviour of the target system in this way, its utility is amplified if key mechanisms of the model can be discovered, and identified with those of the underlying system. In this review, we first describe, at a fairly high level with minimal mathematics, some of the tools used in constructing neural network models. We then go on to discuss the implications of network models for our understanding of the system they are supposed to describe, paying special attention to those models that deal with neural circuits and brain systems. We propose that neural nets are useful for brain modelling if they are viewed in a wider computational framework originally devised by Marr. Here, neural networks are viewed as an intermediate mechanistic abstraction between 'algorithm' and 'implementation', which can provide insights into biological neural representations and their putative supporting architectures.
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
Optimal Control Problem of Feeding Adaptations of Daphnia and Neural Network Simulation
NASA Astrophysics Data System (ADS)
Kmet', Tibor; Kmet'ov, Mria
2010-09-01
A neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints and open final time. The optimal control problem is transcribed into nonlinear programming problem, which is implemented with adaptive critic neural network [9] and recurrent neural network for solving nonlinear proprojection equations [10]. The proposed simulation methods is illustrated by the optimal control problem of feeding adaptation of filter feeders of Daphnia. Results show that adaptive critic based systematic approach and neural network solving of nonlinear equations hold promise for obtaining the optimal control with control and state constraints and open final time.
Stevens, R. H.; Najafi, K.
1992-01-01
Artificial neural networks were trained to recognize the test selection patterns of students' successful solutions to seven immunology computer based simulations. When new student's test selections were presented to the trained neural network, their problem solutions were correctly classified as successful or non-successful > 90% of the time. Examination of the neural networks output weights after each test selection revealed a progressive increase for the relevant problem suggesting that a successful solution was represented by the neural network as the accumulation of relevant tests. Unsuccessful problem solutions revealed two patterns of students performances. The first pattern was characterized by low neural network output weights for all seven problems reflecting extensive searching and lack of recognition of relevant information. In the second pattern, the output weights from the neural network were biased towards one of the remaining six incorrect problems suggesting that the student mis-represented the current problem as an instance of a previous problem. PMID:1482863
NASA Astrophysics Data System (ADS)
Dong, Xiao-qiang; Guo, Teng-xiao; Yan, Yu-Ting; Wang, Ji; Zhang, Xu; Li, Jun-ming
2016-03-01
Remote infrared sensing is a good approach to detect Chemical agents which can prevent operator being poisoned. The pattern recognition algorithms such as artificial neural network are the core of the chemical agent spectra identification subsystem. This paper presents a modified artificial neural network that can effectively train and identify chemical agent remote sensing spectra. The C++ language was used to program the identification software. Then many remote sensing spectra DMMP as chemical agent simulants were used to train the artificial neural network. The results show that the adaptive momentum and adaptive learning rate accelerate the artificial neural network convergence, cross-examination avoids neural network over-fitting, and the modified artificial neural network can be used to identify chemical agents remote sensing spectra perfectly.
Use of simulated neural networks of aerial image classification
NASA Technical Reports Server (NTRS)
Medina, Frances I.; Vasquez, Ramon
1991-01-01
The utility of one layer neural network in aerial image classification is examined. The network was trained with the delta rule. This method was shown to be useful as a classifier in aerial images with good resolution. It is fast, it is easy to implement, because it is distribution-free, nothing about statistical distribution of the data is needed, and it is very efficient as a boundary detector.
Use of simulated neural networks of aerial image classification
NASA Technical Reports Server (NTRS)
Medina, Frances I.; Vasquez, Ramon
1991-01-01
The utility of one layer neural network in aerial image classification is examined. The network was trained with the delta rule. This method was shown to be useful as a classifier in aerial images with good resolution. It is fast, it is easy to implement, because it is distribution-free, nothing about statistical distribution of the data is needed, and it is very efficient as a boundary detector.
Simulation of Foam Divot Weight on External Tank Utilizing Least Squares and Neural Network Methods
NASA Technical Reports Server (NTRS)
Chamis, Christos C.; Coroneos, Rula M.
2007-01-01
Simulation of divot weight in the insulating foam, associated with the external tank of the U.S. space shuttle, has been evaluated using least squares and neural network concepts. The simulation required models based on fundamental considerations that can be used to predict under what conditions voids form, the size of the voids, and subsequent divot ejection mechanisms. The quadratic neural networks were found to be satisfactory for the simulation of foam divot weight in various tests associated with the external tank. Both linear least squares method and the nonlinear neural network predicted identical results.
The role of simulation in the design of a neural network chip
NASA Technical Reports Server (NTRS)
Desai, Utpal; Roppel, Thaddeus A.; Padgett, Mary L.
1993-01-01
An iterative, simulation-based design procedure for a neural network chip is introduced. For this design procedure, the goal is to produce a chip layout for a neural network in which the weights are determined by transistor gate width-to-length ratios. In a given iteration, the current layout is simulated using the circuit simulator SPICE, and layout adjustments are made based on conventional gradient-decent methods. After the iteration converges, the chip is fabricated. Monte Carlo analysis is used to predict the effect of statistical fabrication process variations on the overall performance of the neural network chip.
Designing a neural network simulator--the MENS modelling environment for network systems: II.
Schillen, T B
1991-10-01
During recent years, neural network research has been extended to a large number of different fields, increasingly attracting the interest of workers from various disciplines. The computer simulations carried out with this research require an appropriate software environment. The computational similarities of many kinds of simulations allow the design of software components that are largely independent of the specific application. These considerations are reflected, for example, by the general layout of the MENS network simulator, as described in the accompanying first paper. This paper presents the design considerations for the simulator's different software components in more detail. In particular, design and implementation are discussed with respect to computational and memory efficiency. The discussion includes, for example, the representation of a network by the simulator's data structure, the file-driven configuration and initialization of a network, the simulator's stimulus and monitor system, and the simulator's control structures. In addition, the separation and interaction of application-specific and application-independent software components are addressed. Particular performance aspects comprise the implementation of synaptic delays, the dynamic deletion of synaptic links in network learning, and the preprocessing of stimulus films. In addition, some general aspects of simulator performance and testing are considered. The material presented in this paper concerns both the development of new simulation software and the efficient use of existing programs. Therefore, both the general user as well as the software designer may hopefully benefit from this presentation.
Battery Performance Modelling ad Simulation: a Neural Network Based Approach
NASA Astrophysics Data System (ADS)
Ottavianelli, Giuseppe; Donati, Alessandro
2002-01-01
This project has developed on the background of ongoing researches within the Control Technology Unit (TOS-OSC) of the Special Projects Division at the European Space Operations Centre (ESOC) of the European Space Agency. The purpose of this research is to develop and validate an Artificial Neural Network tool (ANN) able to model, simulate and predict the Cluster II battery system's performance degradation. (Cluster II mission is made of four spacecraft flying in tetrahedral formation and aimed to observe and study the interaction between sun and earth by passing in and out of our planet's magnetic field). This prototype tool, named BAPER and developed with a commercial neural network toolbox, could be used to support short and medium term mission planning in order to improve and maximise the batteries lifetime, determining which are the future best charge/discharge cycles for the batteries given their present states, in view of a Cluster II mission extension. This study focuses on the five Silver-Cadmium batteries onboard of Tango, the fourth Cluster II satellite, but time restrains have allowed so far to perform an assessment only on the first battery. In their most basic form, ANNs are hyper-dimensional curve fits for non-linear data. With their remarkable ability to derive meaning from complicated or imprecise history data, ANN can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. ANNs learn by example, and this is why they can be described as an inductive, or data-based models for the simulation of input/target mappings. A trained ANN can be thought of as an "expert" in the category of information it has been given to analyse, and this expert can then be used, as in this project, to provide projections given new situations of interest and answer "what if" questions. The most appropriate algorithm, in terms of training speed and memory storage requirements, is clearly the Levenberg
Designing laboratory wind simulations using artificial neural networks
NASA Astrophysics Data System (ADS)
Križan, Josip; Gašparac, Goran; Kozmar, Hrvoje; Antonić, Oleg; Grisogono, Branko
2015-05-01
While experiments in boundary layer wind tunnels remain to be a major research tool in wind engineering and environmental aerodynamics, designing the modeling hardware required for a proper atmospheric boundary layer (ABL) simulation can be costly and time consuming. Hence, possibilities are sought to speed-up this process and make it more time-efficient. In this study, two artificial neural networks (ANNs) are developed to determine an optimal design of the Counihan hardware, i.e., castellated barrier wall, vortex generators, and surface roughness, in order to simulate the ABL flow developing above urban, suburban, and rural terrains, as previous ANN models were created for one terrain type only. A standard procedure is used in developing those two ANNs in order to further enhance best-practice possibilities rather than to improve existing ANN designing methodology. In total, experimental results obtained using 23 different hardware setups are used when creating ANNs. In those tests, basic barrier height, barrier castellation height, spacing density, and height of surface roughness elements are the parameters that were varied to create satisfactory ABL simulations. The first ANN was used for the estimation of mean wind velocity, turbulent Reynolds stress, turbulence intensity, and length scales, while the second one was used for the estimation of the power spectral density of velocity fluctuations. This extensive set of studied flow and turbulence parameters is unmatched in comparison to the previous relevant studies, as it includes here turbulence intensity and power spectral density of velocity fluctuations in all three directions, as well as the Reynolds stress profiles and turbulence length scales. Modeling results agree well with experiments for all terrain types, particularly in the lower ABL within the height range of the most engineering structures, while exhibiting sensitivity to abrupt changes and data scattering in profiles of wind-tunnel results. The
Applying the Artificial Neural Network to Predict the Soil Responses in the DEM Simulation
NASA Astrophysics Data System (ADS)
Li, Z.; Chow, J. K.; Wang, Y. H.
2017-06-01
This paper aims to bridge the soil properties and the soil response in the discrete element method (DEM) simulation using the artificial neural network (ANN). The network was designed to output the stress-strain-volumetric response from inputting the soil properties. 31 biaxial shearing tests with varying soil parameters were generated using the DEM simulations. Based on these 31 training samples, a three-layer neural network was established. 2 extra samples were generated to examine the validity of the network, and the predicted curves using the ANN were well matched with those from the DEM simulations. Overall, the ANN was found promising in effectively modelling the soil behaviour.
Simulating dynamic plastic continuous neural networks by finite elements.
Joghataie, Abdolreza; Torghabehi, Omid Oliyan
2014-08-01
We introduce dynamic plastic continuous neural network (DPCNN), which is comprised of neurons distributed in a nonlinear plastic medium where wire-like connections of neural networks are replaced with the continuous medium. We use finite element method to model the dynamic phenomenon of information processing within the DPCNNs. During the training, instead of weights, the properties of the continuous material at its different locations and some properties of neurons are modified. Input and output can be vectors and/or continuous functions over lines and/or areas. Delay and feedback from neurons to themselves and from outputs occur in the DPCNNs. We model a simple form of the DPCNN where the medium is a rectangular plate of bilinear material, and the neurons continuously fire a signal, which is a function of the horizontal displacement.
An architecture of the simulation and prediction system of the drainage based on neural network
NASA Astrophysics Data System (ADS)
Luo, Yaqi; Zeng, Bi
2017-08-01
In this paper, the development of the system of the simulation is mainly to establish the prediction model of the pipe network of urban and the real-time simulation system based on neural network. Before the prediction model of pipe network which is based on neural network of city is created, the pump station of pipe network, the parameters needed for modeling and the sample data needed for modeling are needed to choose. The way achieves to get rid of the means of traditional manual participation in calculation and operation, and improves the precision of the selection of drainage path. That way also realize the qualitative leap in efficiency.
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.
Dynamical system modeling via signal reduction and neural network simulation
Paez, T.L.; Hunter, N.F.
1997-11-01
Many dynamical systems tested in the field and the laboratory display significant nonlinear behavior. Accurate characterization of such systems requires modeling in a nonlinear framework. One construct forming a basis for nonlinear modeling is that of the artificial neural network (ANN). However, when system behavior is complex, the amount of data required to perform training can become unreasonable. The authors reduce the complexity of information present in system response measurements using decomposition via canonical variate analysis. They describe a method for decomposing system responses, then modeling the components with ANNs. A numerical example is presented, along with conclusions and recommendations.
Neural network based control schemes for flexible-link manipulators: simulations and experiments.
Talebi, H A.; Khorasani, K; Patel, R V.
1998-10-01
This paper presents simulation and experimental results on the performance of neural network-based controllers for tip position tracking of flexible-link manipulators. The controllers are designed by utilizing the modified output re-definition approach. The modified output re-definition approach requires only a priori knowledge about the linear model of the system and no a priori knowledge about the payload mass. Four different neural network schemes are proposed. The first two schemes are developed by using a modified version of the 'feedback-error-learning' approach to learn the inverse dynamics of the flexible manipulator. Both schemes require only a linear model of the system for defining the new outputs and for designing conventional PD-type controllers. This assumption is relaxed in the third and fourth schemes. In the third scheme, the controller is designed based on tracking the hub position while controlling the elastic deflection at the tip. In the fourth scheme which employs two neural networks, the first network (referred to as the 'output neural network') is responsible for specifying an appropriate output for ensuring minimum phase behavior of the system. The second neural network is responsible for implementing an inverse dynamics controller. The performance of the four proposed neural network controllers is illustrated by simulation results for a two-link planar flexible manipulator and by experimental results for a single flexible-link test-bed. The networks are all trained and employed as online controllers and no off-line training is required.
Artificial Neural Network Metamodels of Stochastic Computer Simulations
1994-08-10
Networks, Vol. 5 (1992), pp. 207-220. 55 Haykin, Op. Cit., pp. 190-191. 56 Gon, M. and Tesi , A., "On the Problem of Local Minima in Backpropagation," IEEE...Simulation Experiments: Taguchi Methods and Response Surface Metamodels, by J. Ramberg, S. Sanchez , P. Sanchez , and L. Hollick" (Piscataway, New Jersey
Simulation of restricted neural networks with reprogrammable neurons
Hartline, D.K. )
1989-05-01
This paper describes a network model composed of reprogrammable neurons. It incorporates the following design features: spikes can be generated by a model representing repetitive firing at axon (and dendritic) trigger zones; active responses (plateau potentials; delaying mechanisms) are simulated with Hodgkin-huxley type kinetics; synaptic interactions both spike-mediated and non-spiking chemical ('chemotonic'), simulate transmitter release and binding to postsynaptic receptors. Facilitation and antifacilitation of spike-mediated postsynaptic potentials (PSP's) are included. Chemical pools are used to simulate second messenger systems, trapping of ions in extracellular spaces, and electrogenic pumps, as well as biochemical reaction chains of quite general character. Modulation of any of the parameters of any compartment can be effected through the pools. Intracellular messengers of three kinds are simulated explicitly: those produced by voltage-gated processes (e.g. Ca); those dependent on transmitter (or hormone) binding; and those dependent on other internal messengers (e.g., internally released Ca; enzymatically activated pathways).
Na, Hyuntae; Lee, Seung-Yub; Üstündag, Ersan; ...
2013-01-01
This paper introduces a recent development and application of a noncommercial artificial neural network (ANN) simulator with graphical user interface (GUI) to assist in rapid data modeling and analysis in the engineering diffraction field. The real-time network training/simulation monitoring tool has been customized for the study of constitutive behavior of engineering materials, and it has improved data mining and forecasting capabilities of neural networks. This software has been used to train and simulate the finite element modeling (FEM) data for a fiber composite system, both forward and inverse. The forward neural network simulation precisely reduplicates FEM results several orders ofmore » magnitude faster than the slow original FEM. The inverse simulation is more challenging; yet, material parameters can be meaningfully determined with the aid of parameter sensitivity information. The simulator GUI also reveals that output node size for materials parameter and input normalization method for strain data are critical train conditions in inverse network. The successful use of ANN modeling and simulator GUI has been validated through engineering neutron diffraction experimental data by determining constitutive laws of the real fiber composite materials via a mathematically rigorous and physically meaningful parameter search process, once the networks are successfully trained from the FEM database.« less
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.
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 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 network simulation of the atmospheric point spread function for the adjacency effect research
NASA Astrophysics Data System (ADS)
Ma, Xiaoshan; Wang, Haidong; Li, Ligang; Yang, Zhen; Meng, Xin
2016-10-01
Adjacency effect could be regarded as the convolution of the atmospheric point spread function (PSF) and the surface leaving radiance. Monte Carlo is a common method to simulate the atmospheric PSF. But it can't obtain analytic expression and the meaningful results can be only acquired by statistical analysis of millions of data. A backward Monte Carlo algorithm was employed to simulate photon emitting and propagating in the atmosphere under different conditions. The PSF was determined by recording the photon-receiving numbers in fixed bin at different position. A multilayer feed-forward neural network with a single hidden layer was designed to learn the relationship between the PSF's and the input condition parameters. The neural network used the back-propagation learning rule for training. Its input parameters involved atmosphere condition, spectrum range, observing geometry. The outputs of the network were photon-receiving numbers in the corresponding bin. Because the output units were too many to be allowed by neural network, the large network was divided into a collection of smaller ones. These small networks could be ran simultaneously on many workstations and/or PCs to speed up the training. It is important to note that the simulated PSF's by Monte Carlo technique in non-nadir viewing angles are more complicated than that in nadir conditions which brings difficulties in the design of the neural network. The results obtained show that the neural network approach could be very useful to compute the atmospheric PSF based on the simulated data generated by Monte Carlo method.
Integration of Continuous-Time Dynamics in a Spiking Neural Network Simulator
Hahne, Jan; Dahmen, David; Schuecker, Jannis; Frommer, Andreas; Bolten, Matthias; Helias, Moritz; Diesmann, Markus
2017-01-01
Contemporary modeling approaches to the dynamics of neural networks include two important classes of models: biologically grounded spiking neuron models and functionally inspired rate-based units. We present a unified simulation framework that supports the combination of the two for multi-scale modeling, enables the quantitative validation of mean-field approaches by spiking network simulations, and provides an increase in reliability by usage of the same simulation code and the same network model specifications for both model classes. While most spiking simulations rely on the communication of discrete events, rate models require time-continuous interactions between neurons. Exploiting the conceptual similarity to the inclusion of gap junctions in spiking network simulations, we arrive at a reference implementation of instantaneous and delayed interactions between rate-based models in a spiking network simulator. The separation of rate dynamics from the general connection and communication infrastructure ensures flexibility of the framework. In addition to the standard implementation we present an iterative approach based on waveform-relaxation techniques to reduce communication and increase performance for large-scale simulations of rate-based models with instantaneous interactions. Finally we demonstrate the broad applicability of the framework by considering various examples from the literature, ranging from random networks to neural-field models. The study provides the prerequisite for interactions between rate-based and spiking models in a joint simulation. PMID:28596730
Integration of Continuous-Time Dynamics in a Spiking Neural Network Simulator.
Hahne, Jan; Dahmen, David; Schuecker, Jannis; Frommer, Andreas; Bolten, Matthias; Helias, Moritz; Diesmann, Markus
2017-01-01
Contemporary modeling approaches to the dynamics of neural networks include two important classes of models: biologically grounded spiking neuron models and functionally inspired rate-based units. We present a unified simulation framework that supports the combination of the two for multi-scale modeling, enables the quantitative validation of mean-field approaches by spiking network simulations, and provides an increase in reliability by usage of the same simulation code and the same network model specifications for both model classes. While most spiking simulations rely on the communication of discrete events, rate models require time-continuous interactions between neurons. Exploiting the conceptual similarity to the inclusion of gap junctions in spiking network simulations, we arrive at a reference implementation of instantaneous and delayed interactions between rate-based models in a spiking network simulator. The separation of rate dynamics from the general connection and communication infrastructure ensures flexibility of the framework. In addition to the standard implementation we present an iterative approach based on waveform-relaxation techniques to reduce communication and increase performance for large-scale simulations of rate-based models with instantaneous interactions. Finally we demonstrate the broad applicability of the framework by considering various examples from the literature, ranging from random networks to neural-field models. The study provides the prerequisite for interactions between rate-based and spiking models in a joint simulation.
Visual NNet: An Educational ANN's Simulation Environment Reusing Matlab Neural Networks Toolbox
ERIC Educational Resources Information Center
Garcia-Roselló, Emilio; González-Dacosta, Jacinto; Lado, Maria J.; Méndez, Arturo J.; Garcia Pérez-Schofield, Baltasar; Ferrer, Fátima
2011-01-01
Artificial Neural Networks (ANN's) are nowadays a common subject in different curricula of graduate and postgraduate studies. Due to the complex algorithms involved and the dynamic nature of ANN's, simulation software has been commonly used to teach this subject. This software has usually been developed specifically for learning purposes, because…
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.
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
Limits to high-speed simulations of spiking neural networks using general-purpose computers.
Zenke, Friedemann; Gerstner, Wulfram
2014-01-01
To understand how the central nervous system performs computations using recurrent neuronal circuitry, simulations have become an indispensable tool for theoretical neuroscience. To study neuronal circuits and their ability to self-organize, increasing attention has been directed toward synaptic plasticity. In particular spike-timing-dependent plasticity (STDP) creates specific demands for simulations of spiking neural networks. On the one hand a high temporal resolution is required to capture the millisecond timescale of typical STDP windows. On the other hand network simulations have to evolve over hours up to days, to capture the timescale of long-term plasticity. To do this efficiently, fast simulation speed is the crucial ingredient rather than large neuron numbers. Using different medium-sized network models consisting of several thousands of neurons and off-the-shelf hardware, we compare the simulation speed of the simulators: Brian, NEST and Neuron as well as our own simulator Auryn. Our results show that real-time simulations of different plastic network models are possible in parallel simulations in which numerical precision is not a primary concern. Even so, the speed-up margin of parallelism is limited and boosting simulation speeds beyond one tenth of real-time is difficult. By profiling simulation code we show that the run times of typical plastic network simulations encounter a hard boundary. This limit is partly due to latencies in the inter-process communications and thus cannot be overcome by increased parallelism. Overall, these results show that to study plasticity in medium-sized spiking neural networks, adequate simulation tools are readily available which run efficiently on small clusters. However, to run simulations substantially faster than real-time, special hardware is a prerequisite.
Limits to high-speed simulations of spiking neural networks using general-purpose computers
Zenke, Friedemann; Gerstner, Wulfram
2014-01-01
To understand how the central nervous system performs computations using recurrent neuronal circuitry, simulations have become an indispensable tool for theoretical neuroscience. To study neuronal circuits and their ability to self-organize, increasing attention has been directed toward synaptic plasticity. In particular spike-timing-dependent plasticity (STDP) creates specific demands for simulations of spiking neural networks. On the one hand a high temporal resolution is required to capture the millisecond timescale of typical STDP windows. On the other hand network simulations have to evolve over hours up to days, to capture the timescale of long-term plasticity. To do this efficiently, fast simulation speed is the crucial ingredient rather than large neuron numbers. Using different medium-sized network models consisting of several thousands of neurons and off-the-shelf hardware, we compare the simulation speed of the simulators: Brian, NEST and Neuron as well as our own simulator Auryn. Our results show that real-time simulations of different plastic network models are possible in parallel simulations in which numerical precision is not a primary concern. Even so, the speed-up margin of parallelism is limited and boosting simulation speeds beyond one tenth of real-time is difficult. By profiling simulation code we show that the run times of typical plastic network simulations encounter a hard boundary. This limit is partly due to latencies in the inter-process communications and thus cannot be overcome by increased parallelism. Overall, these results show that to study plasticity in medium-sized spiking neural networks, adequate simulation tools are readily available which run efficiently on small clusters. However, to run simulations substantially faster than real-time, special hardware is a prerequisite. PMID:25309418
Application of a neural network to simulate analysis in an optimization process
NASA Technical Reports Server (NTRS)
Rogers, James L.; Lamarsh, William J., II
1992-01-01
A new experimental software package called NETS/PROSSS aimed at reducing the computing time required to solve a complex design problem is described. The software combines a neural network for simulating the analysis program with an optimization program. The neural network is applied to approximate results of a finite element analysis program to quickly obtain a near-optimal solution. Results of the NETS/PROSSS optimization process can also be used as an initial design in a normal optimization process and make it possible to converge to an optimum solution with significantly fewer iterations.
Simulation of concept acquisition according to Posner's theory using artificial neural networks
NASA Astrophysics Data System (ADS)
Grzegorczyk, Dawid; Nieznański, Marek; Mulawka, Jan J.
2011-10-01
The prototype model of classification assumes that categories are stored in human mind as abstracted summary representations formed in the process of experiencing specimens. Classification of new exemplars is based on their similarity to the abstracted prototype. From studies using Michael Posner"s dot-pattern recognition paradigm, we selected several empirical observations, like category size effect, category breadth effect or prototype-exemplar similarity effect, and tested them on artificial neural networks. In this work we show that the properties of human categorization process can be very well simulated and observed on artificial neural networks.
Cheung, Kit; Schultz, Simon R.; Luk, Wayne
2016-01-01
NeuroFlow is a scalable spiking neural network simulation platform for off-the-shelf high performance computing systems using customizable hardware processors such as Field-Programmable Gate Arrays (FPGAs). Unlike multi-core processors and application-specific integrated circuits, the processor architecture of NeuroFlow can be redesigned and reconfigured to suit a particular simulation to deliver optimized performance, such as the degree of parallelism to employ. The compilation process supports using PyNN, a simulator-independent neural network description language, to configure the processor. NeuroFlow supports a number of commonly used current or conductance based neuronal models such as integrate-and-fire and Izhikevich models, and the spike-timing-dependent plasticity (STDP) rule for learning. A 6-FPGA system can simulate a network of up to ~600,000 neurons and can achieve a real-time performance of 400,000 neurons. Using one FPGA, NeuroFlow delivers a speedup of up to 33.6 times the speed of an 8-core processor, or 2.83 times the speed of GPU-based platforms. With high flexibility and throughput, NeuroFlow provides a viable environment for large-scale neural network simulation. PMID:26834542
Cheung, Kit; Schultz, Simon R; Luk, Wayne
2015-01-01
NeuroFlow is a scalable spiking neural network simulation platform for off-the-shelf high performance computing systems using customizable hardware processors such as Field-Programmable Gate Arrays (FPGAs). Unlike multi-core processors and application-specific integrated circuits, the processor architecture of NeuroFlow can be redesigned and reconfigured to suit a particular simulation to deliver optimized performance, such as the degree of parallelism to employ. The compilation process supports using PyNN, a simulator-independent neural network description language, to configure the processor. NeuroFlow supports a number of commonly used current or conductance based neuronal models such as integrate-and-fire and Izhikevich models, and the spike-timing-dependent plasticity (STDP) rule for learning. A 6-FPGA system can simulate a network of up to ~600,000 neurons and can achieve a real-time performance of 400,000 neurons. Using one FPGA, NeuroFlow delivers a speedup of up to 33.6 times the speed of an 8-core processor, or 2.83 times the speed of GPU-based platforms. With high flexibility and throughput, NeuroFlow provides a viable environment for large-scale neural network simulation.
PAX: A mixed hardware/software simulation platform for spiking neural networks.
Renaud, S; Tomas, J; Lewis, N; Bornat, Y; Daouzli, A; Rudolph, M; Destexhe, A; Saïghi, S
2010-09-01
Many hardware-based solutions now exist for the simulation of bio-like neural networks. Less conventional than software-based systems, these types of simulators generally combine digital and analog forms of computation. In this paper we present a mixed hardware-software platform, specifically designed for the simulation of spiking neural networks, using conductance-based models of neurons and synaptic connections with dynamic adaptation rules (Spike-Timing-Dependent Plasticity). The neurons and networks are configurable, and are computed in 'biological real time' by which we mean that the difference between simulated time and simulation time is guaranteed lower than 50 mus. After presenting the issues and context involved in the design and use of hardware-based spiking neural networks, we describe the analog neuromimetic integrated circuits which form the core of the platform. We then explain the organization and computation principles of the modules within the platform, and present experimental results which validate the system. Designed as a tool for computational neuroscience, the platform is exploited in collaborative research projects together with neurobiology and computer science partners. Copyright 2010 Elsevier Ltd. All rights reserved.
Unified-theory-of-reinforcement neural networks do not simulate the blocking effect.
Calvin, Nicholas T; J McDowell, J
2015-11-01
For the last 20 years the unified theory of reinforcement (Donahoe et al., 1993) has been used to develop computer simulations to evaluate its plausibility as an account for behavior. The unified theory of reinforcement states that operant and respondent learning occurs via the same neural mechanisms. As part of a larger project to evaluate the operant behavior predicted by the theory, this project was the first replication of neural network models based on the unified theory of reinforcement. In the process of replicating these neural network models it became apparent that a previously published finding, namely, that the networks simulate the blocking phenomenon (Donahoe et al., 1993), was a misinterpretation of the data. We show that the apparent blocking produced by these networks is an artifact of the inability of these networks to generate the same conditioned response to multiple stimuli. The piecemeal approach to evaluate the unified theory of reinforcement via simulation is critiqued and alternatives are discussed. Copyright © 2015 Elsevier B.V. All rights reserved.
1989-03-01
I. INTRODUCTION A. W HAT IS A NEURAL NETWORK: A neural network is a highly parallel network with many interconnections between analog computational ...optimization problems, using nonlinear analog computation . * Nonlinear Mapping: Many neural networks can map a vector of analog inputs into an output vector...N rNAVAL POSTGRADUATE SCHOOL 0Monterey, California ., THESIS COMPUTER IMPLEMENTATION AND SIMU- LATION OF SOME NEURAL NETWORKS USED IN PATTERN
NASA Astrophysics Data System (ADS)
Narasimha Rao, Gudikandhula; Jagadeeswara Rao, Peddada; Duvvuru, Rajesh
2016-09-01
Wild fires have significant impact on atmosphere and lives. The demand of predicting exact fire area in forest may help fire management team by using drone as a robot. These are flexible, inexpensive and elevated-motion remote sensing systems that use drones as platforms are important for substantial data gaps and supplementing the capabilities of manned aircraft and satellite remote sensing systems. In addition, powerful computational tools are essential for predicting certain burned area in the duration of a forest fire. The reason of this study is to built up a smart system based on semantic neural networking for the forecast of burned areas. The usage of virtual reality simulator is used to support the instruction process of fire fighters and all users for saving of surrounded wild lives by using a naive method Semantic Neural Network System (SNNS). Semantics are valuable initially to have a enhanced representation of the burned area prediction and better alteration of simulation situation to the users. In meticulous, consequences obtained with geometric semantic neural networking is extensively superior to other methods. This learning suggests that deeper investigation of neural networking in the field of forest fires prediction could be productive.
Bernal, Javier; Torres-Jimenez, Jose
2015-01-01
SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller’s scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller’s algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller’s algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller’s algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data. PMID:26958442
NASA Astrophysics Data System (ADS)
Zhou, Wanmeng; Wang, Hua; Tang, Guojin; Guo, Shuai
2016-09-01
The time-consuming experimental method for handling qualities assessment cannot meet the increasing fast design requirements for the manned space flight. As a tool for the aircraft handling qualities research, the model-predictive-control structured inverse simulation (MPC-IS) has potential applications in the aerospace field to guide the astronauts' operations and evaluate the handling qualities more effectively. Therefore, this paper establishes MPC-IS for the manual-controlled rendezvous and docking (RVD) and proposes a novel artificial neural network inverse simulation system (ANN-IS) to further decrease the computational cost. The novel system was obtained by replacing the inverse model of MPC-IS with the artificial neural network. The optimal neural network was trained by the genetic Levenberg-Marquardt algorithm, and finally determined by the Levenberg-Marquardt algorithm. In order to validate MPC-IS and ANN-IS, the manual-controlled RVD experiments on the simulator were carried out. The comparisons between simulation results and experimental data demonstrated the validity of two systems and the high computational efficiency of ANN-IS.
Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator.
Gosmann, Jan; Eliasmith, Chris
2017-01-01
One critical factor limiting the size of neural cognitive models is the time required to simulate such models. To reduce simulation time, specialized hardware is often used. However, such hardware can be costly, not readily available, or require specialized software implementations that are difficult to maintain. Here, we present an algorithm that optimizes the computational graph of the Nengo neural network simulator, allowing simulations to run more quickly on commodity hardware. This is achieved by merging identical operations into single operations and restructuring the accessed data in larger blocks of sequential memory. In this way, a time speed-up of up to 6.8 is obtained. While this does not beat the specialized OpenCL implementation of Nengo, this optimization is available on any platform that can run Python. In contrast, the OpenCL implementation supports fewer platforms and can be difficult to install.
Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator
Gosmann, Jan; Eliasmith, Chris
2017-01-01
One critical factor limiting the size of neural cognitive models is the time required to simulate such models. To reduce simulation time, specialized hardware is often used. However, such hardware can be costly, not readily available, or require specialized software implementations that are difficult to maintain. Here, we present an algorithm that optimizes the computational graph of the Nengo neural network simulator, allowing simulations to run more quickly on commodity hardware. This is achieved by merging identical operations into single operations and restructuring the accessed data in larger blocks of sequential memory. In this way, a time speed-up of up to 6.8 is obtained. While this does not beat the specialized OpenCL implementation of Nengo, this optimization is available on any platform that can run Python. In contrast, the OpenCL implementation supports fewer platforms and can be difficult to install. PMID:28522970
Nageswaran, Jayram Moorkanikara; Dutt, Nikil; Krichmar, Jeffrey L; Nicolau, Alex; Veidenbaum, Alexander V
2009-01-01
Neural network simulators that take into account the spiking behavior of neurons are useful for studying brain mechanisms and for various neural engineering applications. Spiking Neural Network (SNN) simulators have been traditionally simulated on large-scale clusters, super-computers, or on dedicated hardware architectures. Alternatively, Compute Unified Device Architecture (CUDA) Graphics Processing Units (GPUs) can provide a low-cost, programmable, and high-performance computing platform for simulation of SNNs. In this paper we demonstrate an efficient, biologically realistic, large-scale SNN simulator that runs on a single GPU. The SNN model includes Izhikevich spiking neurons, detailed models of synaptic plasticity and variable axonal delay. We allow user-defined configuration of the GPU-SNN model by means of a high-level programming interface written in C++ but similar to the PyNN programming interface specification. PyNN is a common programming interface developed by the neuronal simulation community to allow a single script to run on various simulators. The GPU implementation (on NVIDIA GTX-280 with 1 GB of memory) is up to 26 times faster than a CPU version for the simulation of 100K neurons with 50 Million synaptic connections, firing at an average rate of 7 Hz. For simulation of 10 Million synaptic connections and 100K neurons, the GPU SNN model is only 1.5 times slower than real-time. Further, we present a collection of new techniques related to parallelism extraction, mapping of irregular communication, and network representation for effective simulation of SNNs on GPUs. The fidelity of the simulation results was validated on CPU simulations using firing rate, synaptic weight distribution, and inter-spike interval analysis. Our simulator is publicly available to the modeling community so that researchers will have easy access to large-scale SNN simulations.
Finite-state neural networks. A step toward the simulation of very large systems
Kohring, G.A. )
1991-02-01
Neural networks composed of neurons with Q{sub N} states and synapses with Q{sub J} states are studied analytically and numerically. Analytically it is shown that these finite-state networks are much more efficient at information storage than networks with continuous synapses. In order to take the utmost advantage of networks with finite-state elements, a multineuron and multisynapse coding scheme is introduced which allows the simulation of networks having 1.0 {times} 10{sup 9} couplings at a speed of 7.1 {times} 10{sup 9} coupling evaluations per second on a single processor of the Cray-YMP. A local learning algorithm is also introduced which allows for the efficient training of large networks with finite-state elements.
Neural network simulation on a reduced-mesh-of-trees organization
NASA Astrophysics Data System (ADS)
Misra, Manavendra; Prasanna Kumar, V. K.
1990-07-01
The theory of Artificial Neural Networks (ANN's) shows that ANN's can perform useful image recognition functions. Simulations on uniprocessor sequential machines, however, destroy the parallelism inherent in ANN models and this results in a significant loss of speed. Simulations on parallel machines are therefore essential to fully exploit the advantages of ANN's. We show how to simulate ANN's on an SIMD architecture, the Reduced Mesh of Trees (RMOT). The architecture has p PE's and n2 memory arranged in a p x p array of modules (p is a constant less than or equal to n). This massive memory is used to store connection weights. A fully connected, single layer neural network with n neurons can be mapped easily onto the architecture. An update in this case requires O(n2/p) time steps. A sparse network can also be simulated efficiently on the architecture. The proposed architecture can also be used for the efficient simulation of multilayer networks with a Back Propagation learning scheme. The architecture can easily be implemented within the framework of existing hardware technology.
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
Test of Neural Network Techniques using Simulated Dual-Band Data of LEO Satellites
2010-09-01
expense associated with real data collection from ground-based facilities. Simulation software is used to generate signatures in two visible bands for...external to the framework of the software used to calculate signatures. We examine various pre-processing schemes that combine temporal, spectral and solar...resolved images of satellites are unavailable[1]. Neural networks have been evaluated as a potential automated technique for identifying satellites in
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.
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.
Singh, H P; Sukavanam, N
2012-01-01
This paper proposes a new adaptive neural network based control scheme for switched linear systems with parametric uncertainty and external disturbance. A key feature of this scheme is that the prior information of the possible upper bound of the uncertainty is not required. A feedforward neural network is employed to learn this upper bound. The adaptive learning algorithm is derived from Lyapunov stability analysis so that the system response under arbitrary switching laws is guaranteed uniformly ultimately bounded. A comparative simulation study with robust controller given in [Zhang L, Lu Y, Chen Y, Mastorakis NE. Robust uniformly ultimate boundedness control for uncertain switched linear systems. Computers and Mathematics with Applications 2008; 56: 1709-14] is presented. Copyright © 2011 ISA. Published by Elsevier Ltd. All rights reserved.
NASA Astrophysics Data System (ADS)
Ozasa, Kazunari; Aono, Masashi; Maeda, Mizuo; Hara, Masahiko
In order to develop an adaptive computing system, we investigate microscopic optical feedback to a group of microbes (Euglena gracilis in this study) with a neural network algorithm, expecting that the unique characteristics of microbes, especially their strategies to survive/adapt against unfavorable environmental stimuli, will explicitly determine the temporal evolution of the microbe-based feedback system. The photophobic reactions of Euglena are extracted from experiments, and built in the Monte-Carlo simulation of a microbe-based neurocomputing. The simulation revealed a good performance of Euglena-based neurocomputing. Dynamic transition among the solutions is discussed from the viewpoint of feedback instability.
A neural-network-based method of model reduction for the dynamic simulation of MEMS
NASA Astrophysics Data System (ADS)
Liang, Y. C.; Lin, W. Z.; Lee, H. P.; Lim, S. P.; Lee, K. H.; Feng, D. P.
2001-05-01
This paper proposes a neuro-network-based method for model reduction that combines the generalized Hebbian algorithm (GHA) with the Galerkin procedure to perform the dynamic simulation and analysis of nonlinear microelectromechanical systems (MEMS). An unsupervised neural network is adopted to find the principal eigenvectors of a correlation matrix of snapshots. It has been shown that the extensive computer results of the principal component analysis using the neural network of GHA can extract an empirical basis from numerical or experimental data, which can be used to convert the original system into a lumped low-order macromodel. The macromodel can be employed to carry out the dynamic simulation of the original system resulting in a dramatic reduction of computation time while not losing flexibility and accuracy. Compared with other existing model reduction methods for the dynamic simulation of MEMS, the present method does not need to compute the input correlation matrix in advance. It needs only to find very few required basis functions, which can be learned directly from the input data, and this means that the method possesses potential advantages when the measured data are large. The method is evaluated to simulate the pull-in dynamics of a doubly-clamped microbeam subjected to different input voltage spectra of electrostatic actuation. The efficiency and the flexibility of the proposed method are examined by comparing the results with those of the fully meshed finite-difference method.
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.
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.
[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.
NASA Astrophysics Data System (ADS)
Jokar, Ali; Godarzi, Ali Abbasi; Saber, Mohammad; Shafii, Mohammad Behshad
2016-11-01
In this paper, a novel approach has been presented to simulate and optimize the pulsating heat pipes (PHPs). The used pulsating heat pipe setup was designed and constructed for this study. Due to the lack of a general mathematical model for exact analysis of the PHPs, a method has been applied for simulation and optimization using the natural algorithms. In this way, the simulator consists of a kind of multilayer perceptron neural network, which is trained by experimental results obtained from our PHP setup. The results show that the complex behavior of PHPs can be successfully described by the non-linear structure of this simulator. The input variables of the neural network are input heat flux to evaporator (q″), filling ratio (FR) and inclined angle (IA) and its output is thermal resistance of PHP. Finally, based upon the simulation results and considering the heat pipe's operating constraints, the optimum operating point of the system is obtained by using genetic algorithm (GA). The experimental results show that the optimum FR (38.25 %), input heat flux to evaporator (39.93 W) and IA (55°) that obtained from GA are acceptable.
Weidel, Philipp; Djurfeldt, Mikael; Duarte, Renato C.; Morrison, Abigail
2016-01-01
In order to properly assess the function and computational properties of simulated neural systems, it is necessary to account for the nature of the stimuli that drive the system. However, providing stimuli that are rich and yet both reproducible and amenable to experimental manipulations is technically challenging, and even more so if a closed-loop scenario is required. In this work, we present a novel approach to solve this problem, connecting robotics and neural network simulators. We implement a middleware solution that bridges the Robotic Operating System (ROS) to the Multi-Simulator Coordinator (MUSIC). This enables any robotic and neural simulators that implement the corresponding interfaces to be efficiently coupled, allowing real-time performance for a wide range of configurations. This work extends the toolset available for researchers in both neurorobotics and computational neuroscience, and creates the opportunity to perform closed-loop experiments of arbitrary complexity to address questions in multiple areas, including embodiment, agency, and reinforcement learning. PMID:27536234
Causal measures of structure and plasticity in simulated and living neural networks.
Cadotte, Alex J; DeMarse, Thomas B; He, Ping; Ding, Mingzhou
2008-10-07
A major goal of neuroscience is to understand the relationship between neural structures and their function. Recording of neural activity with arrays of electrodes is a primary tool employed toward this goal. However, the relationships among the neural activity recorded by these arrays are often highly complex making it problematic to accurately quantify a network's structural information and then relate that structure to its function. Current statistical methods including cross correlation and coherence have achieved only modest success in characterizing the structural connectivity. Over the last decade an alternative technique known as Granger causality is emerging within neuroscience. This technique, borrowed from the field of economics, provides a strong mathematical foundation based on linear auto-regression to detect and quantify "causal" relationships among different time series. This paper presents a combination of three Granger based analytical methods that can quickly provide a relatively complete representation of the causal structure within a neural network. These are a simple pairwise Granger causality metric, a conditional metric, and a little known computationally inexpensive subtractive conditional method. Each causal metric is first described and evaluated in a series of biologically plausible neural simulations. We then demonstrate how Granger causality can detect and quantify changes in the strength of those relationships during plasticity using 60 channel spike train data from an in vitro cortical network measured on a microelectrode array. We show that these metrics can not only detect the presence of causal relationships, they also provide crucial information about the strength and direction of that relationship, particularly when that relationship maybe changing during plasticity. Although we focus on the analysis of multichannel spike train data the metrics we describe are applicable to any stationary time series in which causal
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.
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
Vehicle Study with Neural Networks
NASA Astrophysics Data System (ADS)
Ruan, Xiaogang; Dai, Lizhen
The biology is characteristic of biologic phototaxis and negative phototaxis. Can a machine be endowed with such a characteristic? This is the question we study in this paper, so a method of realizing vehicle's phototaxis and negative phototaxis through a neural network is presented. A randomly generated network is used as the main computational unit. Only the weights of the output units of this network are changed during training. It will be shown that this simple type of a biological realistic neural network is able to simulate robot controllers like that incorporated in Braitenberg vehicles. Two experiments are presented illustrating the stage-like study emerging with this neural network.
Simulation tests of the optimization method of Hopfield and Tank using neural networks
NASA Technical Reports Server (NTRS)
Paielli, Russell A.
1988-01-01
The method proposed by Hopfield and Tank for using the Hopfield neural network with continuous valued neurons to solve the traveling salesman problem is tested by simulation. Several researchers have apparently been unable to successfully repeat the numerical simulation documented by Hopfield and Tank. However, as suggested to the author by Adams, it appears that the reason for those difficulties is that a key parameter value is reported erroneously (by four orders of magnitude) in the original paper. When a reasonable value is used for that parameter, the network performs generally as claimed. Additionally, a new method of using feedback to control the input bias currents to the amplifiers is proposed and successfully tested. This eliminates the need to set the input currents by trial and error.
NASA Astrophysics Data System (ADS)
Messina, Luca; Castin, Nicolas; Domain, Christophe; Olsson, Pär
2017-02-01
The quality of kinetic Monte Carlo (KMC) simulations of microstructure evolution in alloys relies on the parametrization of point-defect migration rates, which are complex functions of the local chemical composition and can be calculated accurately with ab initio methods. However, constructing reliable models that ensure the best possible transfer of physical information from ab initio to KMC is a challenging task. This work presents an innovative approach, where the transition rates are predicted by artificial neural networks trained on a database of 2000 migration barriers, obtained with density functional theory (DFT) in place of interatomic potentials. The method is tested on copper precipitation in thermally aged iron alloys, by means of a hybrid atomistic-object KMC model. For the object part of the model, the stability and mobility properties of copper-vacancy clusters are analyzed by means of independent atomistic KMC simulations, driven by the same neural networks. The cluster diffusion coefficients and mean free paths are found to increase with size, confirming the dominant role of coarsening of medium- and large-sized clusters in the precipitation kinetics. The evolution under thermal aging is in better agreement with experiments with respect to a previous interatomic-potential model, especially concerning the experiment time scales. However, the model underestimates the solubility of copper in iron due to the excessively high solution energy predicted by the chosen DFT method. Nevertheless, this work proves the capability of neural networks to transfer complex ab initio physical properties to higher-scale models, and facilitates the extension to systems with increasing chemical complexity, setting the ground for reliable microstructure evolution simulations in a wide range of alloys and applications.
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.
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.
Training Knowledge Bots for Physics-Based Simulations Using Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Samareh, Jamshid A.; Wong, Jay Ming
2014-01-01
Millions of complex physics-based simulations are required for design of an aerospace vehicle. These simulations are usually performed by highly trained and skilled analysts, who execute, monitor, and steer each simulation. Analysts rely heavily on their broad experience that may have taken 20-30 years to accumulate. In addition, the simulation software is complex in nature, requiring significant computational resources. Simulations of system of systems become even more complex and are beyond human capacity to effectively learn their behavior. IBM has developed machines that can learn and compete successfully with a chess grandmaster and most successful jeopardy contestants. These machines are capable of learning some complex problems much faster than humans can learn. In this paper, we propose using artificial neural network to train knowledge bots to identify the idiosyncrasies of simulation software and recognize patterns that can lead to successful simulations. We examine the use of knowledge bots for applications of computational fluid dynamics (CFD), trajectory analysis, commercial finite-element analysis software, and slosh propellant dynamics. We will show that machine learning algorithms can be used to learn the idiosyncrasies of computational simulations and identify regions of instability without including any additional information about their mathematical form or applied discretization approaches.
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 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…
Memory activity of LIP neurons for sequential eye movements simulated with neural networks.
Xing, J; Andersen, R A
2000-08-01
Many neurons in macaque lateral intraparietal cortex (LIP) maintain elevated activity induced by visual or auditory targets during tasks in which monkeys are required to withhold one or more planned eye movements. We studied the mechanisms for such memory activity with neural network modeling. Recurrent connections among simulated LIP neurons were used to model memory responses of LIP neurons. The connection weights were computed using an optimization procedure to produce desired outputs in memory-saccade tasks. One constraint for the training process is the "single-purpose" rule, which mimics the fact that once LIP neurons hold the memory activity of a saccade, they are insensitive to further stimuli until the motor action is completed. After training, excitatory connections were developed between units with similar preferred saccade directions, while inhibitory connections were formed between units with dissimilar directions. This "push-pull" mechanism enables the network to encode the next intended eye movement and is essential for programming sequential saccades. In simulating double saccades, the push-pull connections locked the on-going activity in the network for the first saccade until the saccade was made, then a new population of units became active to prepare for the second saccade. The simulated LIP neurons exhibited sensory responses and memory activities similar to those recorded in LIP neurons. We propose that push-pull recurrent connections might be the basic structure mediating the memory activity of area LIP in planning sequential eye movements.
Guarneri, Paolo; Rocca, Gianpiero; Gobbi, Massimiliano
2008-09-01
This paper deals with the simulation of the tire/suspension dynamics by using recurrent neural networks (RNNs). RNNs are derived from the multilayer feedforward neural networks, by adding feedback connections between output and input layers. The optimal network architecture derives from a parametric analysis based on the optimal tradeoff between network accuracy and size. The neural network can be trained with experimental data obtained in the laboratory from simulated road profiles (cleats). The results obtained from the neural network demonstrate good agreement with the experimental results over a wide range of operation conditions. The NN model can be effectively applied as a part of vehicle system model to accurately predict elastic bushings and tire dynamics behavior. Although the neural network model, as a black-box model, does not provide a good insight of the physical behavior of the tire/suspension system, it is a useful tool for assessing vehicle ride and noise, vibration, harshness (NVH) performance due to its good computational efficiency and accuracy.
Wu, Y; Doi, K; Metz, C E; Asada, N; Giger, M L
1993-05-01
Artificial neural networks are being investigated in the field of medical imaging as a means to facilitate pattern recognition and patient classification. In the work reported here, the effects of internal structure and the nature of input data on the performance of neural networks were investigated systematically using computer-simulated data. Network performance was evaluated quantitatively by means of receiver operating characteristic analysis and compared with the performance of an ideal statistical decision maker. We found that the relatively simple neural networks investigated in this study can perform at the level of an ideal decision maker. These simple networks were also found to learn accurately even when the training data are extremely unbalanced with respect to the prevalence of actually positive cases and to differentiate input data patterns by recognizing their unique characteristics.
Simulation of river stage using artificial neural network and MIKE 11 hydrodynamic model
NASA Astrophysics Data System (ADS)
Panda, Rabindra K.; Pramanik, Niranjan; Bala, Biplab
2010-06-01
Simulation of water levels at different sections of a river using physically based flood routing models is quite cumbersome, because it requires many types of data such as hydrologic time series, river geometry, hydraulics of existing control structures and channel roughness coefficients. Normally in developing countries like India it is not easy to collect these data because of poor monitoring and record keeping. Therefore, an artificial neural network (ANN) technique is used as an effective alternative in hydrologic simulation studies. The present study aims at comparing the performance of the ANN technique with a widely used physically based hydrodynamic model in the MIKE 11 environment. The MIKE 11 hydrodynamic model was calibrated and validated for the monsoon periods (June-September) of the years 2006 and 2001, respectively. Feed forward neural network architecture with Levenberg-Marquardt (LM) back propagation training algorithm was used to train the neural network model using hourly water level data of the period June-September 2006. The trained ANN model was tested using data for the same period of the year 2001. Simulated water levels by the MIKE 11HD were compared with the corresponding water levels predicted by the ANN model. The results obtained from the ANN model were found to be much better than that of the MIKE 11HD results as indicated by the values of the goodness of fit indices used in the study. The Nash-Sutcliffe index ( E) and root mean square error (RMSE) obtained in case of the ANN model were found to be 0.8419 and 0.8939 m, respectively, during model testing, whereas in case of MIKE 11HD, the values of E and RMSE were found to be 0.7836 and 1.00 m, respectively, during model validation. The difference between the observed and simulated peak water levels obtained from the ANN model was found to be much lower than that of MIKE 11HD. The study reveals that the use of Levenberg-Marquardt algorithm with eight hidden neurons in the hidden layer
Chaotic simulated annealing by a neural network with a variable delay: design and application.
Chen, Shyan-Shiou
2011-10-01
In this paper, we have three goals: the first is to delineate the advantages of a variably delayed system, the second is to find a more intuitive Lyapunov function for a delayed neural network, and the third is to design a delayed neural network for a quadratic cost function. For delayed neural networks, most researchers construct a Lyapunov function based on the linear matrix inequality (LMI) approach. However, that approach is not intuitive. We provide a alternative candidate Lyapunov function for a delayed neural network. On the other hand, if we are first given a quadratic cost function, we can construct a delayed neural network by suitably dividing the second-order term into two parts: a self-feedback connection weight and a delayed connection weight. To demonstrate the advantage of a variably delayed neural network, we propose a transiently chaotic neural network with variable delay and show numerically that the model should possess a better searching ability than Chen-Aihara's model, Wang's model, and Zhao's model. We discuss both the chaotic and the convergent phases. During the chaotic phase, we simply present bifurcation diagrams for a single neuron with a constant delay and with a variable delay. We show that the variably delayed model possesses the stochastic property and chaotic wandering. During the convergent phase, we not only provide a novel Lyapunov function for neural networks with a delay (the Lyapunov function is independent of the LMI approach) but also establish a correlation between the Lyapunov function for a delayed neural network and an objective function for the traveling salesman problem.
NASA Astrophysics Data System (ADS)
Hazza, Muataz Hazza F. Al; Adesta, Erry Y. T.; Riza, Muhammad
2013-12-01
High speed milling has many advantages such as higher removal rate and high productivity. However, higher cutting speed increase the flank wear rate and thus reducing the cutting tool life. Therefore estimating and predicting the flank wear length in early stages reduces the risk of unaccepted tooling cost. This research presents a neural network model for predicting and simulating the flank wear in the CNC end milling process. A set of sparse experimental data for finish end milling on AISI H13 at hardness of 48 HRC have been conducted to measure the flank wear length. Then the measured data have been used to train the developed neural network model. Artificial neural network (ANN) was applied to predict the flank wear length. The neural network contains twenty hidden layer with feed forward back propagation hierarchical. The neural network has been designed with MATLAB Neural Network Toolbox. The results show a high correlation between the predicted and the observed flank wear which indicates the validity of the models.
Brain without mind: Computer simulation of neural networks with modifiable neuronal interactions
NASA Astrophysics Data System (ADS)
Clark, John W.; Rafelski, Johann; Winston, Jeffrey V.
1985-07-01
Aspects of brain function are examined in terms of a nonlinear dynamical system of highly interconnected neuron-like binary decision elements. The model neurons operate synchronously in discrete time, according to deterministic or probabilistic equations of motion. Plasticity of the nervous system, which underlies such cognitive collective phenomena as adaptive development, learning, and memory, is represented by temporal modification of interneuronal connection strengths depending on momentary or recent neural activity. A formal basis is presented for the construction of local plasticity algorithms, or connection-modification routines, spanning a large class. To build an intuitive understanding of the behavior of discrete-time network models, extensive computer simulations have been carried out (a) for nets with fixed, quasirandom connectivity and (b) for nets with connections that evolve under one or another choice of plasticity algorithm. From the former experiments, insights are gained concerning the spontaneous emergence of order in the form of cyclic modes of neuronal activity. In the course of the latter experiments, a simple plasticity routine (“brainwashing,” or “anti-learning”) was identified which, applied to nets with initially quasirandom connectivity, creates model networks which provide more felicitous starting points for computer experiments on the engramming of content-addressable memories and on learning more generally. The potential relevance of this algorithm to developmental neurobiology and to sleep states is discussed. The model considered is at the same time a synthesis of earlier synchronous neural-network models and an elaboration upon them; accordingly, the present article offers both a focused review of the dynamical properties of such systems and a selection of new findings derived from computer simulation.
NASA Technical Reports Server (NTRS)
Kapania, Rakesh K.; Liu, Youhua
2000-01-01
At the preliminary design stage of a wing structure, an efficient simulation, one needing little computation but yielding adequately accurate results for various response quantities, is essential in the search of optimal design in a vast design space. In the present paper, methods of using sensitivities up to 2nd order, and direct application of neural networks are explored. The example problem is how to decide the natural frequencies of a wing given the shape variables of the structure. It is shown that when sensitivities cannot be obtained analytically, the finite difference approach is usually more reliable than a semi-analytical approach provided an appropriate step size is used. The use of second order sensitivities is proved of being able to yield much better results than the case where only the first order sensitivities are used. When neural networks are trained to relate the wing natural frequencies to the shape variables, a negligible computation effort is needed to accurately determine the natural frequencies of a new design.
NASA Astrophysics Data System (ADS)
Lv, Zhi-Song; Zhu, Chen-Ping; Nie, Pei; Zhao, Jing; Yang, Hui-Jie; Wang, Yan-Jun; Hu, Chin-Kun
2017-06-01
The distribution of the geometric distances of connected neurons is a practical factor underlying neural networks in the brain. It can affect the brain's dynamic properties at the ground level. Karbowski derived a power-law decay distribution that has not yet been verified by experiment. In this work, we check its validity using simulations with a phenomenological model. Based on the in vitro two-dimensional development of neural networks in culture vessels by Ito, we match the synapse number saturation time to obtain suitable parameters for the development process, then determine the distribution of distances between connected neurons under such conditions. Our simulations obtain a clear exponential distribution instead of a power-law one, which indicates that Karbowski's conclusion is invalid, at least for the case of in vitro neural network development in two-dimensional culture vessels.
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
Exploring neural network technology
Naser, J.; Maulbetsch, J.
1992-12-01
EPRI is funding several projects to explore neural network technology, a form of artificial intelligence that some believe may mimic the way the human brain processes information. This research seeks to provide a better understanding of fundamental neural network characteristics and to identify promising utility industry applications. Results to date indicate that the unique attributes of neural networks could lead to improved monitoring, diagnostic, and control capabilities for a variety of complex utility operations. 2 figs.
Simulated village locations in Thailand: A multi-scale model including a neural network approach
Malanson, George P.; Entwisle, Barbara
2010-01-01
The simulation of rural land use systems, in general, and rural settlement dynamics in particular has developed with synergies of theory and methods for decades. Three current issues are: linking spatial patterns and processes, representing hierarchical relations across scales, and considering nonlinearity to address complex non-stationary settlement dynamics. We present a hierarchical simulation model to investigate complex rural settlement dynamics in Nang Rong, Thailand. This simulation uses sub-models to allocate new villages at three spatial scales. Regional and sub-regional models, which involve a nonlinear space-time autoregressive model implemented in a neural network approach, determine the number of new villages to be established. A dynamic village niche model, establishing pattern-process link, was designed to enable the allocation of villages into specific locations. Spatiotemporal variability in model performance indicates the pattern of village location changes as a settlement frontier advances from rice-growing lowlands to higher elevations. Experiments results demonstrate this simulation model can enhance our understanding of settlement development in Nang Rong and thus gain insight into complex land use systems in this area. PMID:21399748
Simulated village locations in Thailand: A multi-scale model including a neural network approach.
Tang, Wenwu; Malanson, George P; Entwisle, Barbara
2009-04-01
The simulation of rural land use systems, in general, and rural settlement dynamics in particular has developed with synergies of theory and methods for decades. Three current issues are: linking spatial patterns and processes, representing hierarchical relations across scales, and considering nonlinearity to address complex non-stationary settlement dynamics. We present a hierarchical simulation model to investigate complex rural settlement dynamics in Nang Rong, Thailand. This simulation uses sub-models to allocate new villages at three spatial scales. Regional and sub-regional models, which involve a nonlinear space-time autoregressive model implemented in a neural network approach, determine the number of new villages to be established. A dynamic village niche model, establishing pattern-process link, was designed to enable the allocation of villages into specific locations. Spatiotemporal variability in model performance indicates the pattern of village location changes as a settlement frontier advances from rice-growing lowlands to higher elevations. Experiments results demonstrate this simulation model can enhance our understanding of settlement development in Nang Rong and thus gain insight into complex land use systems in this area.
Neural network simulation of habituation and dishabituation in infant speech perception
NASA Astrophysics Data System (ADS)
Gauthier, Bruno; Shi, Rushen; Proulx, Robert
2004-05-01
The habituation techniques used in infant speech perception studies are based on the fact that infants show renewed interest towards novel stimuli. Recent work has shown the possibility of using artificial neural networks to model habituation and dishabituation (e.g., Schafer and Mareschal, 2001). In our study we examine weather the self-organizing-feature-maps (SOM) (Kohonen, 1989) are appropriate for modeling short-term habituation to a repeated speech stimulus. We found that although SOMs are particularly useful for simulating categorization, they can be modified to model habituation and dishabituation, so that they can be applied to direct comparisons with behavioral data on infants' speech discrimination abilities. In particular, we modified the SOMs to include additional parameters that control the relation of input similarity, lateral inhibition, and local and lateral activation between neurons. Preliminary results suggest that these parameters are sufficient for the network to simulate the loss of sensitivity of the auditory system due to the presentation of multiple tokens of a speech stimulus, as well as to model the recovery of sensitivity to a novel stimulus. The implications of this approach to infant speech perception research will be considered.
Neural-Network-Development Program
NASA Technical Reports Server (NTRS)
Phillips, Todd A.
1993-01-01
NETS, software tool for development and evaluation of neural networks, provides simulation of neural-network algorithms plus computing environment for development of such algorithms. Uses back-propagation learning method for all of networks it creates. Enables user to customize patterns of connections between layers of network. Also provides features for saving, during learning process, values of weights, providing more-precise control over learning process. Written in ANSI standard C language. Machine-independent version (MSC-21588) includes only code for command-line-interface version of NETS 3.0.
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
Latent Heat and Sensible Heat Fluxes Simulation in Maize Using Artificial Neural Networks
NASA Astrophysics Data System (ADS)
Safa, B.
2015-12-01
Latent Heat (LE) and Sensible Heat (H) flux are two major components of the energy balance at the earth's surface which play important roles in the water cycle and global warming. There are various methods for their estimation or measurement. Eddy covariance is a direct and accurate technique for their measurement. Some limitations lead to prevention of the extensive use of the eddy covariance technique. Therefore, simulation approaches can be utilized for their estimation. ANNs are the information processing systems, which can inspect the empirical data and investigate the relations (hidden rules) among them, and then make the network structure. In this study, multi-layer perceptron neural network trained by the steepest descent Back-Propagation (BP) algorithm was tested to simulate LE and H flux above two maize sites (rain-fed & irrigated) near Mead, Nebraska. Network training and testing was fulfilled using hourly data of including year, local time of day (DTime), leaf area index (LAI), soil water content (SWC) in 10 and 25 cm depths, soil temperature (Ts) in 10 cm depth, air temperature (Ta), vapor pressure deficit (VPD), wind speed (WS), irrigation and precipitation (P), net radiation (Rn), and the fraction of incoming Photosynthetically Active Radiation (PAR) absorbed by the canopy (fPAR), which were selected from days of year (DOY) 169 to 222 for 2001, 2003, 2005, 2007, and 2009. The results showed high correlation between actual and estimated data; the R² values for LE flux in irrigated and rain-fed sites were 0.9576, and 0.9642; and for H flux 0.8001, and 0.8478, respectively. Furthermore, the RMSE values ranged from 0.0580 to 0.0721 W/m² for LE flux and from 0.0824 to 0.0863 W/m² for H flux. In addition, the sensitivity of the fluxes with respect to each input was analyzed over the growth stages. Thus, the most powerful effects among the inputs for LE flux were identified net radiation, leaf area index, vapor pressure deficit, wind speed, and for H
NASA Astrophysics Data System (ADS)
Besaw, L. E.; Rizzo, D. M.; Boitnoitt, G. N.
2006-12-01
Accurate, yet cost effective, sites characterization and analysis of uncertainty are the first steps in remediation efforts at sites with subsurface contamination. From the time of source identification to the monitoring and assessment of a remediation design, the management objectives change, resulting in increased costs and the need for additional data acquisition. Parameter estimation is a key component in reliable site characterization, contaminant flow and transport predictions, plume delineation and many other data management goals. We implement a data-driven parameter estimation technique using a counterpropagation Artificial Neural Network (ANN) that is able to incorporate multiple types of data. This method is applied to estimates of geophysical properties measured on a slab of Berea sandstone and delineation of the leachate plume migrating from a landfill in upstate N.Y. The estimates generated by the ANN have been found to be statistically similar to estimates generated using conventional geostatistical kriging methods. The associated parameter uncertainty in site characterization, due to sparsely distributed samples (spatial or temporal) and incomplete site knowledge, is of major concern in resource mining and environmental engineering. We also illustrate the ability of the ANN method to perform conditional simulation using the spatial structure of parameters identified with semi-variogram analysis. This method allows for the generation of simulations that respect the observed measurement data, as well as the data's underlying spatial structure. The method of conditional simulation is used in a 3-dimensional application to estimate the uncertainty of soil lithology.
Neural networks to simulate regional ground water levels affected by human activities.
Feng, Shaoyuan; Kang, Shaozhong; Huo, Zailin; Chen, Shaojun; Mao, Xiaomin
2008-01-01
In arid regions, human activities like agriculture and industry often require large ground water extractions. Under these circumstances, appropriate ground water management policies are essential for preventing aquifer overdraft, and thereby protecting critical ecologic and economic objectives. Identification of such policies requires accurate simulation capability of the ground water system in response to hydrological, meteorological, and human factors. In this research, artificial neural networks (ANNs) were developed and applied to investigate the effects of these factors on ground water levels in the Minqin oasis, located in the lower reach of Shiyang River Basin, in Northwest China. Using data spanning 1980 through 1997, two ANNs were developed to model and simulate dynamic ground water levels for the two subregions of Xinhe and Xiqu. The ANN models achieved high predictive accuracy, validating to 0.37 m or less mean absolute error. Sensitivity analyses were conducted with the models demonstrating that agricultural ground water extraction for irrigation is the predominant factor responsible for declining ground water levels exacerbated by a reduction in regional surface water inflows. ANN simulations indicate that it is necessary to reduce the size of the irrigation area to mitigate ground water level declines in the oasis. Unlike previous research, this study demonstrates that ANN modeling can capture important temporally and spatially distributed human factors like agricultural practices and water extraction patterns on a regional basin (or subbasin) scale, providing both high-accuracy prediction capability and enhanced understanding of the critical factors influencing regional ground water conditions.
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
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.
Bulsari, A; Saxén, H
1994-01-01
This work investigated the feasibility of using feed-forward neural networks for estimation of a state variable in a process with highly non-linear characteristics. A biochemical process was considered where the microorganism Saccharomyces cerevisiae, a yeast, grows in a chemostat on a glucose substrate and produces ethanol as a product of primary energy metabolism. Three state variables for the process are the microbial concentration, substrate concentration and product concentration. The Levenberg-Marquardt Method was used to train the neural networks by minimising the sum of squares of the residuals. The inputs to the networks were the measured variable (product concentration) and the control variable (dilution rate). The output of the network was an estimate for the microbial concentration. Earlier work had shown that system identification of this biochemical process could be performed quite well using feed-forward neural networks. This work demonstrated that state estimation can also be performed successfully using feed-forward neural networks. Knowledge of the process model is not required. The method is simple, reliable and accurate enough for engineering purposes. It can save a lot of expense on sensors, their installation and maintenance.
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 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 simulation of soil NO3 dynamic under potato crop system
NASA Astrophysics Data System (ADS)
Goulet-Fortin, Jérôme; Morais, Anne; Anctil, François; Parent, Léon-Étienne; Bolinder, Martin
2013-04-01
Nitrate leaching is a major issue in sandy soils intensively cropped to potato. Modelling could test and improve management practices, particularly as regard to the optimal N application rates. Lack of input data is an important barrier for the application of classical process-based models to predict soil NO3 content (SNOC) and NO3 leaching (NOL). Alternatively, data driven models such as neural networks (NN) could better take into account indicators of spatial soil heterogeneity and plant growth pattern such as the leaf area index (LAI), hence reducing the amount of soil information required. The first objective of this study was to evaluate NN and hybrid models to simulate SNOC in the 0-40 cm soil layer considering inter-annual variations, spatial soil heterogeneity and differential N application rates. The second objective was to evaluate the same methodology to simulate seasonal NOL dynamic at 1 m deep. To this aim, multilayer perceptrons with different combinations of driving meteorological variables, functions of the LAI and state variables of external deterministic models have been trained and evaluated. The state variables from external models were: drainage estimated by the CLASS model and the soil temperature estimated by an ICBM subroutine. Results of SNOC simulations were compared to field data collected between 2004 and 2011 at several experimental plots under potato cropping systems in Québec, Eastern Canada. Results of NOL simulation were compared to data obtained in 2012 from 11 suction lysimeters installed in 2 experimental plots under potato cropping systems in the same region. The most performing model for SNOC simulation was obtained using a 4-input hybrid model composed of 1) cumulative LAI, 2) cumulative drainage, 3) soil temperature and 4) day of year. The most performing model for NOL simulation was obtained using a 5-input NN model composed of 1) N fertilization rate at spring, 2) LAI, 3) cumulative rainfall, 4) the day of year and 5) the
Self-consistent core-pedestal transport simulations with neural network accelerated models
Meneghini, Orso; Smith, Sterling P.; Snyder, Philip B.; ...
2017-07-12
Fusion whole device modeling simulations require comprehensive models that are simultaneously physically accurate, fast, robust, and predictive. In this paper we describe the development of two neural-network (NN) based models as a means to perform a snon-linear multivariate regression of theory-based models for the core turbulent transport fluxes, and the pedestal structure. Specifically, we find that a NN-based approach can be used to consistently reproduce the results of the TGLF and EPED1 theory-based models over a broad range of plasma regimes, and with a computational speedup of several orders of magnitudes. These models are then integrated into a predictive workflowmore » that allows prediction with self-consistent core-pedestal coupling of the kinetic profiles within the last closed flux surface of the plasma. Finally, the NN paradigm is capable of breaking the speed-accuracy trade-off that is expected of traditional numerical physics models, and can provide the missing link towards self-consistent coupled core-pedestal whole device modeling simulations that are physically accurate and yet take only seconds to run.« less
A spatio-temporal hybrid neural network-Kriging model for groundwater level simulation
NASA Astrophysics Data System (ADS)
Tapoglou, Evdokia; Karatzas, George P.; Trichakis, Ioannis C.; Varouchakis, Emmanouil A.
2014-11-01
Artificial Neural Networks (ANNs) and Kriging have both been used for hydraulic head simulation. In this study, the two methodologies were combined in order to simulate the spatial and temporal distribution of hydraulic head in a study area. In order to achieve that, a fuzzy logic inference system can also be used. Different ANN architectures and variogram models were tested, together with the use or not of a fuzzy logic system. The developed algorithm was implemented and applied for predicting, spatially and temporally, the hydraulic head in an area located in Bavaria, Germany. The performance of the algorithm was evaluated using leave one out cross validation and various performance indicators were derived. The best results were achieved by using ANNs with two hidden layers, with the use of the fuzzy logic system and by utilizing the power-law variogram. The results obtained from this procedure can be characterized as favorable, since the RMSE of the method is in the order of magnitude of 10-2 m. Therefore this method can be used successfully in aquifers where geological characteristics are obscure, but a variety of other, easily accessible data, such as meteorological data can be easily found.
Self-consistent core-pedestal transport simulations with neural network accelerated models
NASA Astrophysics Data System (ADS)
Meneghini, O.; Smith, S. P.; Snyder, P. B.; Staebler, G. M.; Candy, J.; Belli, E.; Lao, L.; Kostuk, M.; Luce, T.; Luda, T.; Park, J. M.; Poli, F.
2017-08-01
Fusion whole device modeling simulations require comprehensive models that are simultaneously physically accurate, fast, robust, and predictive. In this paper we describe the development of two neural-network (NN) based models as a means to perform a snon-linear multivariate regression of theory-based models for the core turbulent transport fluxes, and the pedestal structure. Specifically, we find that a NN-based approach can be used to consistently reproduce the results of the TGLF and EPED1 theory-based models over a broad range of plasma regimes, and with a computational speedup of several orders of magnitudes. These models are then integrated into a predictive workflow that allows prediction with self-consistent core-pedestal coupling of the kinetic profiles within the last closed flux surface of the plasma. The NN paradigm is capable of breaking the speed-accuracy trade-off that is expected of traditional numerical physics models, and can provide the missing link towards self-consistent coupled core-pedestal whole device modeling simulations that are physically accurate and yet take only seconds to run.
NASA Astrophysics Data System (ADS)
Kolokythas, Kostantinos; Vasileios, Salamalikis; Athanassios, Argiriou; Kazantzidis, Andreas
2015-04-01
The wind is a result of complex interactions of numerous mechanisms taking place in small or large scales, so, the better knowledge of its behavior is essential in a variety of applications, especially in the field of power production coming from wind turbines. In the literature there is a considerable number of models, either physical or statistical ones, dealing with the problem of simulation and prediction of wind speed. Among others, Artificial Neural Networks (ANNs) are widely used for the purpose of wind forecasting and, in the great majority of cases, outperform other conventional statistical models. In this study, a number of ANNs with different architectures, which have been created and applied in a dataset of wind time series, are compared to Auto Regressive Integrated Moving Average (ARIMA) statistical models. The data consist of mean hourly wind speeds coming from a wind farm on a hilly Greek region and cover a period of one year (2013). The main goal is to evaluate the models ability to simulate successfully the wind speed at a significant point (target). Goodness-of-fit statistics are performed for the comparison of the different methods. In general, the ANN showed the best performance in the estimation of wind speed prevailing over the ARIMA models.
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.
ERIC Educational Resources Information Center
Meghabghab, George
2001-01-01
Discusses the evaluation of search engines and uses neural networks in stochastic simulation of the number of rejected Web pages per search query. Topics include the iterative radial basis functions (RBF) neural network; precision; response time; coverage; Boolean logic; regression models; crawling algorithms; and implications for search engine…
ERIC Educational Resources Information Center
Meghabghab, George
2001-01-01
Discusses the evaluation of search engines and uses neural networks in stochastic simulation of the number of rejected Web pages per search query. Topics include the iterative radial basis functions (RBF) neural network; precision; response time; coverage; Boolean logic; regression models; crawling algorithms; and implications for search engine…
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.
NASA Astrophysics Data System (ADS)
Lotfalizadeh, F.; Faghihi, R.; Bahadorzadeh, B.; Sina, S.
2017-07-01
Neutron spectrometry using a single-sphere containing dosimeters has been developed recently, as an effective replacement for Bonner sphere spectrometry. The aim of this study is unfolding the neutron energy spectra using GRNN artificial neural network, from the response of thermoluminescence dosimeters, TLDs, located inside a polyethylene sphere. The spectrometer was simulated using MCNP5. TLD-600 and TLD-700 dosimeters were simulated at different positions in all directions. Then the GRNN was used for neutron spectra prediction, using the TLDs' readings. Comparison of spectra predicted by the network with the real spectra, show that the single-sphere dosimeter is an effective instrument in unfolding neutron spectra.
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.
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.
NASA Astrophysics Data System (ADS)
Ahmadlou, M.; Delavar, M. R.; Tayyebi, A.; Shafizadeh-Moghadam, H.
2015-12-01
Land use change (LUC) models used for modelling urban growth are different in structure and performance. Local models divide the data into separate subsets and fit distinct models on each of the subsets. Non-parametric models are data driven and usually do not have a fixed model structure or model structure is unknown before the modelling process. On the other hand, global models perform modelling using all the available data. In addition, parametric models have a fixed structure before the modelling process and they are model driven. Since few studies have compared local non-parametric models with global parametric models, this study compares a local non-parametric model called multivariate adaptive regression spline (MARS), and a global parametric model called artificial neural network (ANN) to simulate urbanization in Mumbai, India. Both models determine the relationship between a dependent variable and multiple independent variables. We used receiver operating characteristic (ROC) to compare the power of the both models for simulating urbanization. Landsat images of 1991 (TM) and 2010 (ETM+) were used for modelling the urbanization process. The drivers considered for urbanization in this area were distance to urban areas, urban density, distance to roads, distance to water, distance to forest, distance to railway, distance to central business district, number of agricultural cells in a 7 by 7 neighbourhoods, and slope in 1991. The results showed that the area under the ROC curve for MARS and ANN was 94.77% and 95.36%, respectively. Thus, ANN performed slightly better than MARS to simulate urban areas in Mumbai, India.
Studies of stimulus parameters for seizure disruption using neural network simulations
Kudela, Pawel; Cho, Ryan J.; Bergey, Gregory K.; Franaszczuk, Piotr
2009-01-01
A large scale neural network simulation with realistic cortical architecture has been undertaken to investigate the effects of external electrical stimulation on the propagation and evolution of ongoing seizure activity. This is an effort to explore the parameter space of stimulation variables to uncover promising avenues of research for this therapeutic modality. The model consists of an approximately 800 μm × 800 μm region of simulated cortex, and includes seven neuron classes organized by cortical layer, inhibitory or excitatory properties, and electrophysiological characteristics. The cell dynamics are governed by a modified version of the Hodgkin-Huxley equations in single compartment format. Axonal connections are patterned after histological data and published models of local cortical wiring. Stimulation induced action potentials take place at the axon initial segments, according to threshold requirements on the applied electric field distribution. Stimulation induced action potentials in horizontal axonal branches are also separately simulated. The calculations are performed on a 16 node distributed 32-bit processor system. Clear differences in seizure evolution are presented for stimulated versus the undisturbed rhythmic activity. Data is provided for frequency dependent stimulation effects demonstrating a plateau effect of stimulation efficacy as the applied frequency is increased from 60 Hz to 200 Hz. Timing of the stimulation with respect to the underlying rhythmic activity demonstrates a phase dependent sensitivity. Electrode height and position effects are also presented. Using a dipole stimulation electrode arrangement, clear orientation effects of the dipole with respect to the model connectivity is also demonstrated. A sensitivity analysis of these results as a function of the stimulation threshold is also provided. PMID:17619199
Sen, Baris Ali; Menon, Suresh
2010-01-15
A large eddy simulation (LES) sub-grid model is developed based on the artificial neural network (ANN) approach to calculate the species instantaneous reaction rates for multi-step, multi-species chemical kinetics mechanisms. The proposed methodology depends on training the ANNs off-line on a thermo-chemical database representative of the actual composition and turbulence (but not the actual geometrical problem) of interest, and later using them to replace the stiff ODE solver (direct integration (DI)) to calculate the reaction rates in the sub-grid. The thermo-chemical database is tabulated with respect to the thermodynamic state vector without any reduction in the number of state variables. The thermo-chemistry is evolved by stand-alone linear eddy mixing (LEM) model simulations under both premixed and non-premixed conditions, where the unsteady interaction of turbulence with chemical kinetics is included as a part of the training database. The proposed methodology is tested in LES and in stand-alone LEM studies of three distinct test cases with different reduced mechanisms and conditions. LES of premixed flame-turbulence-vortex interaction provides direct comparison of the proposed ANN method against DI and ANNs trained on thermo-chemical database created using another type of tabulation method. It is shown that the ANN trained on the LEM database can capture the correct flame physics with accuracy comparable to DI, which cannot be achieved by ANN trained on a laminar premix flame database. A priori evaluation of the ANN generality within and outside its training domain is carried out using stand-alone LEM simulations as well. Results in general are satisfactory, and it is shown that the ANN provides considerable amount of memory saving and speed-up with reasonable and reliable accuracy. The speed-up is strongly affected by the stiffness of the reduced mechanism used for the computations, whereas the memory saving is considerable regardless. (author)
Demonstration of Self-Training Autonomous Neural Networks in Space Vehicle Docking Simulations
NASA Technical Reports Server (NTRS)
Patrick, M. Clinton; Thaler, Stephen L.; Stevenson-Chavis, Katherine
2006-01-01
Neural Networks have been under examination for decades in many areas of research, with varying degrees of success and acceptance. Key goals of computer learning, rapid problem solution, and automatic adaptation have been elusive at best. This paper summarizes efforts at NASA's Marshall Space Flight Center harnessing such technology to autonomous space vehicle docking for the purpose of evaluating applicability to future missions.
Neural 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.
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…
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…
Neural-network accelerated fusion simulation with self-consistent core-pedestal coupling
NASA Astrophysics Data System (ADS)
Meneghini, O.; Candy, J.; Snyder, P. B.; Staebler, G.; Belli, E.
2016-10-01
Practical fusion Whole Device Modeling (WDM) simulations require the ability to perform predictions that are fast, but yet account for the sensitivity of the fusion performance to the boundary constraint that is imposed by the pedestal structure of H-mode plasmas due to the stiff core transport models. This poster presents the development of a set of neural-network (NN) models for the pedestal structure (as predicted by the EPED model), and the neoclassical and turbulent transport fluxes (as predicted by the NEO and TGLF codes, respectively), and their self-consistent coupling within the TGYRO transport code. The results are benchmarked with the ones obtained via the coupling scheme described in [Meneghini PoP 2016]. By substituting the most demanding codes with their NN-accelerated versions, the solution can be found at a fraction of the computation cost of the original coupling scheme, thereby combining the accuracy of a high-fidelity model with the fast turnaround time of a reduced model. Work supported by U.S. DOE DE-FC02-04ER54698 and DE-FG02-95ER54309.
Application of artificial neural networks to compact mask models in optical lithography simulation
NASA Astrophysics Data System (ADS)
Agudelo, Viviana; Fühner, Tim; Erdmann, Andreas; Evanschitzky, Peter
2013-04-01
Compact mask models provide an alternative to speed up rigorous mask diffraction computation based on electromagnetic field (EMF) modeling. The high time expense of the rigorous mask models in the simulation process challenges the exploration of innovative modeling techniques to compromise accuracy and speed in the computation of the diffracted field and vectorial imaging in optical lithographic systems. The Artificial Neural Network (ANN) approach is presented as an alternative to retrieve the spectrum of the mask layout in an accurate yet efficient way. The validity of the ANN for different illuminations, feature sizes, pitches and shapes is investigated. The evaluation of the performance of this approach is performed by a process windows analysis, comparison of the spectra, best focus and critical dimension (CD) through pitch. The application of various layouts demonstrated that the ANN can also be trained with different patterns to reproduce various effects such as: shift of the line position, different linewidths and line ends. Comparisons of the ANN approach with other compact models such as boundary layer model, pulses modification, spectrum correction and pupil filtering techniques are presented.
Barkaoui, Abdelwahed; Tlili, Brahim; Vercher-Martínez, Ana; Hambli, Ridha
2016-10-01
Bone is a living material with a complex hierarchical structure which entails exceptional mechanical properties, including high fracture toughness, specific stiffness and strength. Bone tissue is essentially composed by two phases distributed in approximately 30-70%: an organic phase (mainly type I collagen and cells) and an inorganic phase (hydroxyapatite-HA-and water). The nanostructure of bone can be represented throughout three scale levels where different repetitive structural units or building blocks are found: at the first level, collagen molecules are arranged in a pentameric structure where mineral crystals grow in specific sites. This primary bone structure constitutes the mineralized collagen microfibril. A structural organization of inter-digitating microfibrils forms the mineralized collagen fibril which represents the second scale level. The third scale level corresponds to the mineralized collagen fibre which is composed by the binding of fibrils. The hierarchical nature of the bone tissue is largely responsible of their significant mechanical properties; consequently, this is a current outstanding research topic. Scarce works in literature correlates the elastic properties in the three scale levels at the bone nanoscale. The main goal of this work is to estimate the elastic properties of the bone tissue in a multiscale approach including a sensitivity analysis of the elastic behaviour at each length scale. This proposal is achieved by means of a novel hybrid multiscale modelling that involves neural network (NN) computations and finite elements method (FEM) analysis. The elastic properties are estimated using a neural network simulation that previously has been trained with the database results of the finite element models. In the results of this work, parametric analysis and averaged elastic constants for each length scale are provided. Likewise, the influence of the elastic constants of the tissue constituents is also depicted. Results highlight
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
Sen, Baris Ali; Menon, Suresh; Hawkes, Evatt R.
2010-03-15
Large eddy simulation (LES) of a non-premixed, temporally evolving, syngas/air flame is performed with special emphasis on speeding-up the sub-grid chemistry computations using an artificial neural networks (ANN) approach. The numerical setup for the LES is identical to a previous direct numerical simulation (DNS) study, which reported considerable local extinction and reignition physics, and hence, offers a challenging test case. The chemical kinetics modeling with ANN is based on a recent approach, and replaces the stiff ODE solver (DI) to predict the species reaction rates in the subgrid linear eddy mixing (LEM) model based LES (LEMLES). In order to provide a comprehensive evaluation of the current approach, additional information on conditional statistics of some of the key species and temperature are extracted from the previous DNS study and are compared with the LEMLES using ANN (ANN-LEMLES, hereafter). The results show that the current approach can detect the correct extinction and reignition physics with reasonable accuracy compared to the DNS. The syngas flame structure and the scalar dissipation rate statistics obtained by the current ANN-LEMLES are provided to further probe the flame physics. It is observed that, in contrast to H{sub 2}, CO exhibits a smooth variation within the region enclosed by the stoichiometric mixture fraction. The probability density functions (PDFs) of the scalar dissipation rates calculated based on the mixture fraction and CO demonstrate that the mean value of the PDF is insensitive to extinction and reignition. However, this is not the case for the scalar dissipation rate calculated by the OH mass fraction. Overall, ANN provides considerable computational speed-up and memory saving compared to DI, and can be used to investigate turbulent flames in a computationally affordable manner. (author)
NASA Technical Reports Server (NTRS)
Buch, A. M.; Narain, A.; Pandey, P. C.
1994-01-01
The simulation of runoff from a Himalayan Glacier basin using an Artificial Neural Network (ANN) is presented. The performance of the ANN model is found to be superior to the Energy Balance Model and the Multiple Regression model. The RMS Error is used as the figure of merit for judging the performance of the three models, and the RMS Error for the ANN model is the latest of the three models. The ANN is faster in learning and exhibits excellent system generalization characteristics.
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
NASA Astrophysics Data System (ADS)
Narayanareddy, V. V.; Chandrasekhar, N.; Vasudevan, M.; Muthukumaran, S.; Vasantharaja, P.
2016-02-01
In the present study, artificial neural network modeling has been employed for predicting welding-induced angular distortions in autogenous butt-welded 304L stainless steel plates. The input data for the neural network have been obtained from a series of three-dimensional finite element simulations of TIG welding for a wide range of plate dimensions. Thermo-elasto-plastic analysis was carried out for 304L stainless steel plates during autogenous TIG welding employing double ellipsoidal heat source. The simulated thermal cycles were validated by measuring thermal cycles using thermocouples at predetermined positions, and the simulated distortion values were validated by measuring distortion using vertical height gauge for three cases. There was a good agreement between the model predictions and the measured values. Then, a multilayer feed-forward back propagation neural network has been developed using the numerically simulated data. Artificial neural network model developed in the present study predicted the angular distortion accurately.
NASA Astrophysics Data System (ADS)
Luo, Bingyang; Chi, Shangjie; Fang, Man; Li, Mengchao
2017-03-01
Permanent magnet synchronous motor is used widely in industry, the performance requirements wouldn't be met by adopting traditional PID control in some of the occasions with high requirements. In this paper, a hybrid control strategy - nonlinear neural network PID and traditional PID parallel control are adopted. The high stability and reliability of traditional PID was combined with the strong adaptive ability and robustness of neural network. The permanent magnet synchronous motor will get better control performance when switch different working modes according to different controlled object conditions. As the results showed, the speed response adopting the composite control strategy in this paper was faster than the single control strategy. And in the case of sudden disturbance, the recovery time adopting the composite control strategy designed in this paper was shorter, the recovery ability and the robustness were stronger.
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.
Neural networks in seismic discrimination
Dowla, F.U.
1995-01-01
Neural networks are powerful and elegant computational tools that can be used in the analysis of geophysical signals. At Lawrence Livermore National Laboratory, we have developed neural networks to solve problems in seismic discrimination, event classification, and seismic and hydrodynamic yield estimation. Other researchers have used neural networks for seismic phase identification. We are currently developing neural networks to estimate depths of seismic events using regional seismograms. In this paper different types of network architecture and representation techniques are discussed. We address the important problem of designing neural networks with good generalization capabilities. Examples of neural networks for treaty verification applications are also described.
Dynamic Analysis of Feedforward Neural Networks Using Simulated and Measured Data
1988-12-01
principle behind the single and multilayer feedforward (MFB, model neural network. 2.9 The Single Layer Perceptron While the Kohonen model uses...the work of Sun (Sun, 1986) and others (Lippman, 1987) have shown that the Single Layer Perceptron can only make correct classifications in very simple...decision regions. A number of complications can affect the performance of a single layer perceptron . Different classes of data being meshed in a small
NASA Astrophysics Data System (ADS)
İstif, İlyas
2005-11-01
This paper studies a servo-valve controlled hydraulic cylinder system which is mostly used in industrial applications such as robotics, computer numerical control (CNC) machines and transportations. The system model consists of combination of two models: The first model involves nonlinear flow equations of the servo-valve, which are widely available in the literature. The second model employed in the system is a tailored asymmetric cylinder model. A fourth order nonlinear system model is then obtained by combining these two models. Two different neural network control algorithms are applied to the system. The first algorithm is "Neural Network Predictive Control (NNPC)," which employs identified neural network model to predict the future output of the system. The second algorithm is "Nonlinear Autoregressive Moving Average (NARMA-L2)" control, which transforms nonlinear system dynamics into linear system dynamics by eliminating the nonlinearities. On the simulation, NNPC and NARMA-L2 control are applied to the system model by using Matlab's Simulik simulation package and position control of the system is realized. A discussion regarding the advantages and disadvantages of the two control algorithms are also provided in the paper.
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.
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.
Advanced telerobotic control using neural networks
NASA Technical Reports Server (NTRS)
Pap, Robert M.; Atkins, Mark; Cox, Chadwick; Glover, Charles; Kissel, Ralph; Saeks, Richard
1993-01-01
Accurate Automation is designing and developing adaptive decentralized joint controllers using neural networks. We are then implementing these in hardware for the Marshall Space Flight Center PFMA as well as to be usable for the Remote Manipulator System (RMS) robot arm. Our design is being realized in hardware after completion of the software simulation. This is implemented using a Functional-Link neural network.
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.
Advanced telerobotic control using neural networks
NASA Technical Reports Server (NTRS)
Pap, Robert M.; Atkins, Mark; Cox, Chadwick; Glover, Charles; Kissel, Ralph; Saeks, Richard
1993-01-01
Accurate Automation is designing and developing adaptive decentralized joint controllers using neural networks. We are then implementing these in hardware for the Marshall Space Flight Center PFMA as well as to be usable for the Remote Manipulator System (RMS) robot arm. Our design is being realized in hardware after completion of the software simulation. This is implemented using a Functional-Link neural network.
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.
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.
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.
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.
Kudela, Pawel; Franaszczuk, Piotr J; Bergey, Gregory K
2003-04-01
The development of synchronous bursting in neuronal ensembles represents an important change in network behavior. To determine the influences on development of such synchronous bursting behavior we study the dynamics of small networks of sparsely connected excitatory and inhibitory neurons using numerical simulations. The synchronized bursting activities in networks evoked by background spikes are investigated. Specifically, patterns of bursting activity are examined when the balance between excitation and inhibition on neuronal inputs is varied and the fraction of inhibitory neurons in the network is changed. For quantitative comparison of bursting activities in networks, measures of the degree of synchrony are used. We demonstrate how changes in the strength of excitation on inputs of neurons can be compensated by changes in the strength of inhibition without changing the degree of synchrony in the network. The effects of changing several network parameters on the network activity are analyzed and discussed. These changes may underlie the transition of network activity from normal to potentially pathologic (e.g., epileptic) states.
Drewes, Rich; Zou, Quan; Goodman, Philip H.
2008-01-01
Neuroscience modeling experiments often involve multiple complex neural network and cell model variants, complex input stimuli and input protocols, followed by complex data analysis. Coordinating all this complexity becomes a central difficulty for the experimenter. The Python programming language, along with its extensive library packages, has emerged as a leading “glue” tool for managing all sorts of complex programmatic tasks. This paper describes a toolkit called Brainlab, written in Python, that leverages Python's strengths for the task of managing the general complexity of neuroscience modeling experiments. Brainlab was also designed to overcome the major difficulties of working with the NCS (NeoCortical Simulator) environment in particular. Brainlab is an integrated model-building, experimentation, and data analysis environment for the powerful parallel spiking neural network simulator system NCS. PMID:19506707
Drewes, Rich; Zou, Quan; Goodman, Philip H
2009-01-01
Neuroscience modeling experiments often involve multiple complex neural network and cell model variants, complex input stimuli and input protocols, followed by complex data analysis. Coordinating all this complexity becomes a central difficulty for the experimenter. The Python programming language, along with its extensive library packages, has emerged as a leading "glue" tool for managing all sorts of complex programmatic tasks. This paper describes a toolkit called Brainlab, written in Python, that leverages Python's strengths for the task of managing the general complexity of neuroscience modeling experiments. Brainlab was also designed to overcome the major difficulties of working with the NCS (NeoCortical Simulator) environment in particular. Brainlab is an integrated model-building, experimentation, and data analysis environment for the powerful parallel spiking neural network simulator system NCS.
Neural Networks and Micromechanics
NASA Astrophysics Data System (ADS)
Kussul, Ernst; Baidyk, Tatiana; Wunsch, Donald C.
The title of the book, "Neural Networks and Micromechanics," seems artificial. However, the scientific and technological developments in recent decades demonstrate a very close connection between the two different areas of neural networks and micromechanics. The purpose of this book is to demonstrate this connection. Some artificial intelligence (AI) methods, including neural networks, could be used to improve automation system performance in manufacturing processes. However, the implementation of these AI methods within industry is rather slow because of the high cost of conducting experiments using conventional manufacturing and AI systems. To lower the cost, we have developed special micromechanical equipment that is similar to conventional mechanical equipment but of much smaller size and therefore of lower cost. This equipment could be used to evaluate different AI methods in an easy and inexpensive way. The proved methods could be transferred to industry through appropriate scaling. In this book, we describe the prototypes of low cost microequipment for manufacturing processes and the implementation of some AI methods to increase precision, such as computer vision systems based on neural networks for microdevice assembly and genetic algorithms for microequipment characterization and the increase of microequipment precision.
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.
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.
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.
Chaotic Neural Networks and Beyond
NASA Astrophysics Data System (ADS)
Aihara, Kazuyuki; Yamada, Taiji; Oku, Makito
2013-01-01
A chaotic neuron model which is closely related to deterministic chaos observed experimentally with squid giant axons is explained, and used to construct a chaotic neural network model. Further, such a chaotic neural network is extended to different chaotic models such as a largescale memory relation network, a locally connected network, a vector-valued network, and a quaternionic-valued neuron.
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.
Hannula, Manne; Huttunen, Kerttu; Koskelo, Jukka; Laitinen, Tomi; Leino, Tuomo
2008-01-01
In this study, the performances of artificial neural network (ANN) analysis and multilinear regression (MLR) model-based estimation of heart rate were compared in an evaluation of individual cognitive workload. The data comprised electrocardiography (ECG) measurements and an evaluation of cognitive load that induces psychophysiological stress (PPS), collected from 14 interceptor fighter pilots during complex simulated F/A-18 Hornet air battles. In our data, the mean absolute error of the ANN estimate was 11.4 as a visual analog scale score, being 13-23% better than the mean absolute error of the MLR model in the estimation of cognitive workload.
Li, Yan-Long; Chen, Zhao-Yang; Ma, Jun; Chen, Yu-Hong
2008-02-01
Adopting small-world neural networks of the Hodgkin-Huxley (HH) model, the stimulation parameters in desynchronisation and its possible implications for vagus nerve stimulation (VNS) are numerically investigated. With the synchronisation status of networks to represent epilepsy, then, adding pulse to stimulations to 10% of neurons to simulate the VNS, we obtain the desynchronisation status of networks (representing antiepileptic effects). The simulations show that synchronisation evolves into desynchronisation in the HH neural networks when a part (10%) of neurons are stimulated with a pulse current signal. The network desynchronisation appears to be sensitive to the stimulation parameters. For the case of the same stimulation intensity, weakly coupled networks reach desynchronisation more easily than strongly coupled networks. The network desynchronisation reduced by short-stimulation interval is more distinct than that of induced by long stimulation interval. We find that there exist the optimal stimulation interval and optimal stimulation intensity when the other stimulation parameters remain certain.
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.
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.
Interval probabilistic neural network.
Kowalski, Piotr A; Kulczycki, Piotr
2017-01-01
Automated classification systems have allowed for the rapid development of exploratory data analysis. Such systems increase the independence of human intervention in obtaining the analysis results, especially when inaccurate information is under consideration. The aim of this paper is to present a novel approach, a neural networking, for use in classifying interval information. As presented, neural methodology is a generalization of probabilistic neural network for interval data processing. The simple structure of this neural classification algorithm makes it applicable for research purposes. The procedure is based on the Bayes approach, ensuring minimal potential losses with regard to that which comes about through classification errors. In this article, the topological structure of the network and the learning process are described in detail. Of note, the correctness of the procedure proposed here has been verified by way of numerical tests. These tests include examples of both synthetic data, as well as benchmark instances. The results of numerical verification, carried out for different shapes of data sets, as well as a comparative analysis with other methods of similar conditioning, have validated both the concept presented here and its positive features.
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.
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.
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.
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.
A realistic neural-network simulation of both slow and quick phase components of the guinea pig VOR.
Cartwright, Andrew D; Gilchrist, Darrin P D; Burgess, Ann M; Curthoys, Ian S
2003-04-01
A realistic neural-network model was constructed to simulate production of both the slow-phase and quick-phase components of vestibular nystagmus by incorporating a quick-phase pathway into a previous model of the slow phase. The neurons in the network were modelled by multicompartmental Hodgkin-Huxley-style spiking neurons based on known responses and projections of physiologically identified vestibular neurons. The modelling used the GENESIS software package. The slow-phase network consisted of ganglion and medial vestibular nucleus (MVN) neurons; the latter were constructed using biophysical models of MVN type A and B neurons. The quick-phase network contained several types of bursting cells which have been shown to have major roles in the generation of the quick phase: burster-driver neurons, long-lead burst neurons, pause neurons, excitatory burst neurons and inhibitory burst neurons. Comparison of the output neural responses from the model with guinea pig behavioural responses from the companion paper showed consistency between model and animal data for neuron firing patterns, maximal firing rates, and timing, duration and number of quick phases. Comparisons were made for stable head input and for sinusoidal angular stimuli at a range of frequencies from 0.1 to 2 Hz. Except for data at 0.1 Hz, where the simulation produced one more quick phase per half cycle than the animal data, the number of quick phases was consistent between the model and the animal data. The model was also used to simulate the effects both of unilateral vestibular deafferentation (UVD) and of vestibular compensation after UVD, and the responses in the modelled MVN neurons were affected in a way similar to those measured in guinea pig MVN neurons: the number of quick phases and their timing changed in a similar fashion to that observed in behavioural data.
Dornay, M; Sanger, T D
1993-01-01
A planar 17 muscle model of the monkey's arm based on realistic biomechanical measurements was simulated on a Symbolics Lisp Machine. The simulator implements the equilibrium point hypothesis for the control of arm movements. Given initial and final desired positions, it generates a minimum-jerk desired trajectory of the hand and uses the backdriving algorithm to determine an appropriate sequence of motor commands to the muscles (Flash 1987; Mussa-Ivaldi et al. 1991; Dornay 1991b). These motor commands specify a temporal sequence of stable (attractive) equilibrium positions which lead to the desired hand movement. A strong disadvantage of the simulator is that it has no memory of previous computations. Determining the desired trajectory using the minimum-jerk model is instantaneous, but the laborious backdriving algorithm is slow, and can take up to one hour for some trajectories. The complexity of the required computations makes it a poor model for biological motor control. We propose a computationally simpler and more biologically plausible method for control which achieves the benefits of the backdriving algorithm. A fast learning, tree-structured network (Sanger 1991c) was trained to remember the knowledge obtained by the backdriving algorithm. The neural network learned the nonlinear mapping from a 2-dimensional cartesian planar hand position (x,y) to a 17-dimensional motor command space (u1, . . ., u17). Learning 20 training trajectories, each composed of 26 sample points [[x,y], [u1, . . ., u17] took only 20 min on a Sun-4 Sparc workstation. After the learning stage, new, untrained test trajectories as well as the original trajectories of the hand were given to the neural network as input. The network calculated the required motor commands for these movements. The resulting movements were close to the desired ones for both the training and test cases.
Hinaut, Xavier; Lance, Florian; Droin, Colas; Petit, Maxime; Pointeau, Gregoire; Dominey, Peter Ford
2015-11-01
Language production requires selection of the appropriate sentence structure to accommodate the communication goal of the speaker - the transmission of a particular meaning. Here we consider event meanings, in terms of predicates and thematic roles, and we address the problem that a given event can be described from multiple perspectives, which poses a problem of response selection. We present a model of response selection in sentence production that is inspired by the primate corticostriatal system. The model is implemented in the context of reservoir computing where the reservoir - a recurrent neural network with fixed connections - corresponds to cortex, and the readout corresponds to the striatum. We demonstrate robust learning, and generalization properties of the model, and demonstrate its cross linguistic capabilities in English and Japanese. The results contribute to the argument that the corticostriatal system plays a role in response selection in language production, and to the stance that reservoir computing is a valid potential model of corticostriatal processing.
Henker, Stephan; Partzsch, Johannes; Schüffny, René
2012-04-01
With the various simulators for spiking neural networks developed in recent years, a variety of numerical solution methods for the underlying differential equations are available. In this article, we introduce an approach to systematically assess the accuracy of these methods. In contrast to previous investigations, our approach focuses on a completely deterministic comparison and uses an analytically solved model as a reference. This enables the identification of typical sources of numerical inaccuracies in state-of-the-art simulation methods. In particular, with our approach we can separate the error of the numerical integration from the timing error of spike detection and propagation, the latter being prominent in simulations with fixed timestep. To verify the correctness of the testing procedure, we relate the numerical deviations to theoretical predictions for the employed numerical methods. Finally, we give an example of the influence of simulation artefacts on network behaviour and spike-timing-dependent plasticity (STDP), underlining the importance of spike-time accuracy for the simulation of STDP.
Horcholle-Bossavit, Ginette; Quenet, Brigitte; Foucart, Olivier
2007-01-01
For the analysis of coding mechanisms in the insect olfactory system, a fully connected network of synchronously updated McCulloch and Pitts neurons (MC-P type) was developed [Quenet, B., Horn, D., 2003. The dynamic neural filter: a binary model of spatio-temporal coding. Neural Comput. 15 (2), 309-329]. Considering the update time as an intrinsic clock, this "Dynamic Neural Filter" (DNF), which maps regions of input space into spatio-temporal sequences of neuronal activity, is able to produce exact binary codes extracted from the synchronized activities recorded at the level of projection neurons (PN) in the locust antennal lobe (AL) in response to different odors [Wehr, M., Laurent, G., 1996. Odor encoding by temporal sequences of firing in oscillating neural assemblies. Nature 384, 162-166]. Here, in a first step, we separate the populations of PN and local inhibitory neurons (LN) and use the DNF as a guide for simulations based on biological plausible neurons (Hodgkin-Huxley: H-H type). We show that a parsimonious network of 10 H-H neurons generates action potentials whose timing represents the required codes. In a second step, we construct a new type of DNF in order to study the population dynamics when different delays are taken into account. We find synaptic matrices which lead to both the emergence of robust oscillations and spatio-temporal patterns, using a formal criterion, based on a Normalized Euclidian Distance (NED), in order to measure the use of the temporal dimension as a coding dimension by the DNF. Similarly to biological PN, the activity of excitatory neurons in the model can be both phase-locked to different cycles of oscillations which remind local field potential (LFP), and nevertheless exhibit dynamic behavior complex enough to be the basis of spatio-temporal codes.
Structured Pyramidal Neural Networks.
Soares, Alessandra M; Fernandes, Bruno J T; Bastos-Filho, Carmelo J A
2017-02-09
The Pyramidal Neural Networks (PNN) are an example of a successful recently proposed model inspired by the human visual system and deep learning theory. PNNs are applied to computer vision and based on the concept of receptive fields. This paper proposes a variation of PNN, named here as Structured Pyramidal Neural Network (SPNN). SPNN has self-adaptive variable receptive fields, while the original PNNs rely on the same size for the fields of all neurons, which limits the model since it is not possible to put more computing resources in a particular region of the image. Another limitation of the original approach is the need to define values for a reasonable number of parameters, which can turn difficult the application of PNNs in contexts in which the user does not have experience. On the other hand, SPNN has a fewer number of parameters. Its structure is determined using a novel method with Delaunay Triangulation and k-means clustering. SPNN achieved better results than PNNs and similar performance when compared to Convolutional Neural Network (CNN) and Support Vector Machine (SVM), but using lower memory capacity and processing time.
NASA Astrophysics Data System (ADS)
Agrawal, Paras M.; Samadh, Abdul N. A.; Raff, Lionel M.; Hagan, Martin T.; Bukkapatnam, Satish T.; Komanduri, Ranga
2005-12-01
A new approach involving neural networks combined with molecular dynamics has been used for the determination of reaction probabilities as a function of various input parameters for the reactions associated with the chemical-vapor deposition of carbon dimers on a diamond (100) surface. The data generated by the simulations have been used to train and test neural networks. The probabilities of chemisorption, scattering, and desorption as a function of input parameters, such as rotational energy, translational energy, and direction of the incident velocity vector of the carbon dimer, have been considered. The very good agreement obtained between the predictions of neural networks and those provided by molecular dynamics and the fact that, after training the network, the determination of the interpolated probabilities as a function of various input parameters involves only the evaluation of simple analytical expressions rather than computationally intensive algorithms show that neural networks are extremely powerful tools for interpolating the probabilities and rates of chemical reactions. We also find that a neural network fits the underlying trends in the data rather than the statistical variations present in the molecular-dynamics results. Consequently, neural networks can also provide a computationally convenient means of averaging the statistical variations inherent in molecular-dynamics calculations. In the present case the application of this method is found to reduce the statistical uncertainty in the molecular-dynamics results by about a factor of 3.5.
Buyukada, Musa
2016-09-01
Co-combustion of coal and peanut hull (PH) were investigated using artificial neural networks (ANN), particle swarm optimization, and Monte Carlo simulation as a function of blend ratio, heating rate, and temperature. The best prediction was reached by ANN61 multi-layer perception model with a R(2) of 0.99994. Blend ratio of 90 to 10 (PH to coal, wt%), temperature of 305°C, and heating rate of 49°Cmin(-1) were determined as the optimum input values and yield of 87.4% was obtained under PSO optimized conditions. The validation experiments resulted in yields of 87.5%±0.2 after three replications. Monte Carlo simulations were used for the probabilistic assessments of stochastic variability and uncertainty associated with explanatory variables of co-combustion process.
Padhi, Radhakant; Bhardhwaj, Jayender R
2009-06-01
An adaptive drug delivery design is presented in this paper using neural networks for effective treatment of infectious diseases. The generic mathematical model used describes the coupled evolution of concentration of pathogens, plasma cells, antibodies and a numerical value that indicates the relative characteristic of a damaged organ due to the disease under the influence of external drugs. From a system theoretic point of view, the external drugs can be interpreted as control inputs, which can be designed based on control theoretic concepts. In this study, assuming a set of nominal parameters in the mathematical model, first a nonlinear controller (drug administration) is designed based on the principle of dynamic inversion. This nominal drug administration plan was found to be effective in curing "nominal model patients" (patients whose immunological dynamics conform to the mathematical model used for the control design exactly. However, it was found to be ineffective in curing "realistic model patients" (patients whose immunological dynamics may have off-nominal parameter values and possibly unwanted inputs) in general. Hence, to make the drug delivery dosage design more effective for realistic model patients, a model-following adaptive control design is carried out next by taking the help of neural networks, that are trained online. Simulation studies indicate that the adaptive controller proposed in this paper holds promise in killing the invading pathogens and healing the damaged organ even in the presence of parameter uncertainties and continued pathogen attack. Note that the computational requirements for computing the control are very minimal and all associated computations (including the training of neural networks) can be carried out online. However it assumes that the required diagnosis process can be carried out at a sufficient faster rate so that all the states are available for control computation.
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.
Discontinuities in recurrent neural networks.
Gavaldá, R; Siegelmann, H T
1999-04-01
This article studies the computational power of various discontinuous real computational models that are based on the classical analog recurrent neural network (ARNN). This ARNN consists of finite number of neurons; each neuron computes a polynomial net function and a sigmoid-like continuous activation function. We introduce arithmetic networks as ARNN augmented with a few simple discontinuous (e.g., threshold or zero test) neurons. We argue that even with weights restricted to polynomial time computable reals, arithmetic networks are able to compute arbitrarily complex recursive functions. We identify many types of neural networks that are at least as powerful as arithmetic nets, some of which are not in fact discontinuous, but they boost other arithmetic operations in the net function (e.g., neurons that can use divisions and polynomial net functions inside sigmoid-like continuous activation functions). These arithmetic networks are equivalent to the Blum-Shub-Smale model, when the latter is restricted to a bounded number of registers. With respect to implementation on digital computers, we show that arithmetic networks with rational weights can be simulated with exponential precision, but even with polynomial-time computable real weights, arithmetic networks are not subject to any fixed precision bounds. This is in contrast with the ARNN that are known to demand precision that is linear in the computation time. When nontrivial periodic functions (e.g., fractional part, sine, tangent) are added to arithmetic networks, the resulting networks are computationally equivalent to a massively parallel machine. Thus, these highly discontinuous networks can solve the presumably intractable class of PSPACE-complete problems in polynomial time.
Opposition logic and neural network models in artificial grammar learning.
Vokey, John R; Higham, Philip A
2004-09-01
Following neural network simulations of the two experiments of, argued that the opposition logic advocated by was incapable of distinguishing between single and multiple influences on performance of artificial grammar learning and more generally. We show that their simulations do not support their conclusions. We also provide different neural network simulations that do simulate the essential results of Higham et al. (2000).
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.
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.
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.
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Shelton, Robert O.
1992-01-01
Concept of space-time neural network affords distributed temporal memory enabling such network to model complicated dynamical systems mathematically and to recognize temporally varying spatial patterns. Digital filters replace synaptic-connection weights of conventional back-error-propagation neural network.
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
Ioannidis, Dimitris; Papadopoulos, Georgios E; Anastassopoulos, Georgios; Kortsaris, Alexandros; Anagnostopoulos, Konstantinos
2015-06-01
In order to elucidate some basic principles for protein-ligand interactions, a subset of 87 structures of human proteins with their ligands was obtained from the PDB databank. After a short molecular dynamics simulation (to ensure structure stability), a variety of interaction energies and structural parameters were extracted. Linear regression was performed to determine which of these parameters have a potentially significant contribution to the protein-ligand interaction. The parameters exhibiting relatively high correlation coefficients were selected. Important factors seem to be the number of ligand atoms, the ratio of N, O and S atoms to total ligand atoms, the hydrophobic/polar aminoacid ratio and the ratio of cavity size to the sum of ligand plus water atoms in the cavity. An important factor also seems to be the immobile water molecules in the cavity. Nine of these parameters were used as known inputs to train a neural network in the prediction of seven other. Eight structures were left out of the training to test the quality of the predictions. After optimization of the neural network, the predictions were fairly accurate given the relatively small number of structures, especially in the prediction of the number of nitrogen and sulfur atoms of the ligand. Copyright © 2015 Elsevier Ltd. All rights reserved.
NASA Astrophysics Data System (ADS)
Stamenkovic, Dragan D.; Popovic, Vladimir M.
2015-02-01
Warranty is a powerful marketing tool, but it always involves additional costs to the manufacturer. In order to reduce these costs and make use of warranty's marketing potential, the manufacturer needs to master the techniques for warranty cost prediction according to the reliability characteristics of the product. In this paper a combination free replacement and pro rata warranty policy is analysed as warranty model for one type of light bulbs. Since operating conditions have a great impact on product reliability, they need to be considered in such analysis. A neural network model is used to predict light bulb reliability characteristics based on the data from the tests of light bulbs in various operating conditions. Compared with a linear regression model used in the literature for similar tasks, the neural network model proved to be a more accurate method for such prediction. Reliability parameters obtained in this way are later used in Monte Carlo simulation for the prediction of times to failure needed for warranty cost calculation. The results of the analysis make possible for the manufacturer to choose the optimal warranty policy based on expected product operating conditions. In such a way, the manufacturer can lower the costs and increase the profit.
Pappu, J Sharon Mano; Gummadi, Sathyanarayana N
2016-11-01
This study examines the use of unstructured kinetic model and artificial neural networks as predictive tools for xylitol production by Debaryomyces nepalensis NCYC 3413 in bioreactor. An unstructured kinetic model was proposed in order to assess the influence of pH (4, 5 and 6), temperature (25°C, 30°C and 35°C) and volumetric oxygen transfer coefficient kLa (0.14h(-1), 0.28h(-1) and 0.56h(-1)) on growth and xylitol production. A feed-forward back-propagation artificial neural network (ANN) has been developed to investigate the effect of process condition on xylitol production. ANN configuration of 6-10-3 layers was selected and trained with 339 experimental data points from bioreactor studies. Results showed that simulation and prediction accuracy of ANN was apparently higher when compared to unstructured mechanistic model under varying operational conditions. ANN was found to be an efficient data-driven tool to predict the optimal harvest time in xylitol production. Copyright © 2016 Elsevier Ltd. All rights reserved.
NASA Astrophysics Data System (ADS)
Kasiviswanathan, K. S.; Cibin, R.; Sudheer, K. P.; Chaubey, I.
2013-08-01
This paper presents a method of constructing prediction interval for artificial neural network (ANN) rainfall runoff models during calibration with a consideration of generating ensemble predictions. A two stage optimization procedure is envisaged in this study for construction of prediction interval for the ANN output. In Stage 1, ANN model is trained with genetic algorithm (GA) to obtain optimal set of weights and biases vector. In Stage 2, possible variability of ANN parameters (obtained in Stage 1) is optimized so as to create an ensemble of models with the consideration of minimum residual variance for the ensemble mean, while ensuring a maximum of the measured data to fall within the estimated prediction interval. The width of the prediction interval is also minimized simultaneously. The method is demonstrated using a real world case study of rainfall runoff data for an Indian basin. The method was able to produce ensembles with a prediction interval (average width) of 26.49 m3/s with 97.17% of the total observed data points lying within the interval in validation. One specific advantage of the method is that when ensemble mean value is considered as a forecast, the peak flows are predicted with improved accuracy by this method compared to traditional single point forecasted ANNs.
Neural-network simulation of tonal categorization based on F0 velocity profiles
NASA Astrophysics Data System (ADS)
Gauthier, Bruno; Shi, Rushen; Xu, Yi; Proulx, Robert
2005-04-01
Perception studies have shown that by the age of six months, infants show particular response patterns to tones in their native language. The present study focuses on how infants might develop lexical tones in Man- darin. F0 is generally considered the main cue in tone perception. However, F0 patterns in connected speech display extensive contextual variability. Since speech input to infants consists mainly of multi-word utterances, tone learning must involve processes that can effectively resolve variability. In this study we explore the Target Approximation model (Xu and Wang, 2001) which characterizes surface F0 as asymptotic movements toward underlying pitch targets defined as simple linear functions. The model predicts that it is possible to infer underlying pitch targets from the manners of F0 movements. Using production data of three of the speakers from Xu (1997), we trained a self-organizing neural network with both F0 profiles and F0 velocity profiles as input. In the testing phase, velocity profiles yielded far superior categorization than F0 profiles. The results confirm that velocity profiles can effectively abstract away from surface variability and directly reflect underlying articulatory goals. The finding thus points to one way through which infants can successfully derive at phonetic categories from adult speech.
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
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
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.
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.
Christo, F.C.; Masri, A.R.; Nebot, E.M.
1996-09-01
A novel approach using artificial neural networks for representing chemical reactions is developed and successfully implemented with a modeled velocity-scalar joint pdf transport equation for H{sub 2}CO{sub 2} turbulent jet diffusion flames. The chemical kinetics are represented using a three-step reduced mechanism, and the transport equation is solved by a Monte Carlo method. A detailed analysis of computational performance and a comparison between the neural network approach and other methods used to represent the chemistry, namely the look-up table, or the direct integration procedures, are presented. A multilayer perceptron architecture is chosen for the neural network. The training algorithm is based on a back-propagation supervised learning procedure with individual momentum terms and adaptive learning rate adjustment for the weights matrix. A new procedure for the selection of training samples using dynamic randomization is developed and is aimed at reducing the possibility of the network being trapped in a local minimum. This algorithm achieved an impressive acceleration in convergence compared with the use of a fixed set of selected training samples. The optimization process of the neural network is discussed in detail. The feasibility of using neural network models to represent highly nonlinear chemical reactions is successfully illustrated. The prediction of the flow field and flame characteristics using the neural network approach is in good agreement with those obtained using other methods, and is also in reasonable agreement with the experimental data. The computational benefits of the neural network approach over the look-up table and the direct integration methods, both in CPU time and RAM storage requirements are not great for a chemical mechanisms of less than three reactions. The neural network approach becomes superior, however, for more complex reaction schemes.
2016-09-15
27 5 Taxonomy of neural net architectures. [50...171 41 Multilayer perceptron artificial neural network with bias . . . . . . . . . . . . 172 xiii List of Tables Table Page 1 Taxonomy of...effort was followed by Wilson & Rubinstein in 1984 with two comprehensive VRT reviews [130] and [129] where he introduces a VRT taxonomy to better classify
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.
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.
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.
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.
Belov, Oleg V; Batmunkh, Munkhbaatar; Incerti, Sébastien; Lkhagva, Oidov
2016-12-01
Radiation damage to the central nervous system (CNS) has been an on-going challenge for the last decades primarily due to the issues of brain radiotherapy and radiation protection for astronauts during space travel. Although recent findings revealed a number of molecular mechanisms associated with radiation-induced impairments in behaviour and cognition, some uncertainties exist in the initial neuronal cell injury leading to the further development of CNS malfunction. The present study is focused on the investigation of early biological damage induced by ionizing radiations in a sample neural network by means of modelling physico-chemical processes occurring in the medium after exposure. For this purpose, the stochastic simulation of incident particle tracks and water radiation chemistry was performed in realistic neuron phantoms constructed using experimental data on cell morphology. The applied simulation technique is based on using Monte-Carlo processes of the Geant4-DNA toolkit. The calculations were made for proton, (12)C, and (56)Fe particles of different energy within a relatively wide range of linear energy transfer values from a few to hundreds of keV/μm. The results indicate that the neuron morphology is an important factor determining the accumulation of microscopic radiation dose and water radiolysis products in neurons. The estimation of the radiolytic yields in neuronal cells suggests that the observed enhancement in the levels of reactive oxygen species may potentially lead to oxidative damage to neuronal components disrupting the normal communication between cells of the neural network. Copyright © 2016 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.
NASA Astrophysics Data System (ADS)
Wang, Fei; Wang, Xuan; Chen, Bin; Zhao, Ying; Yang, Zhifeng
2013-05-01
Accurate and reliable forecasting is important for the sustainable management of ecosystems. Chlorophyll a (Chl a) simulation and forecasting can provide early warning information and enable managers to make appropriate decisions for protecting lake ecosystems. In this study, we proposed a method for Chl a simulation in a lake that coupled the wavelet analysis and the artificial neural networks (WA-ANN). The proposed method had the advantage of data preprocessing, which reduced noise and managed nonstationary data. Fourteen variables were included in the developed and validated model, relating to hydrologic, ecological and meteorologic time series data from January 2000 to December 2009 at the Lake Baiyangdian study area, North China. The performance of the proposed WA-ANN model for monthly Chl a simulation in the lake ecosystem was compared with a multiple stepwise linear regression (MSLR) model, an autoregressive integrated moving average (ARIMA) model and a regular ANN model. The results showed that the WA-ANN model was suitable for Chl a simulation providing a more accurate performance than the MSLR, ARIMA, and ANN models. We recommend that the proposed method be widely applied to further facilitate the development and implementation of lake ecosystem management.
Wang, Fei; Wang, Xuan; Chen, Bin; Zhao, Ying; Yang, Zhifeng
2013-05-01
Accurate and reliable forecasting is important for the sustainable management of ecosystems. Chlorophyll a (Chl a) simulation and forecasting can provide early warning information and enable managers to make appropriate decisions for protecting lake ecosystems. In this study, we proposed a method for Chl a simulation in a lake that coupled the wavelet analysis and the artificial neural networks (WA-ANN). The proposed method had the advantage of data preprocessing, which reduced noise and managed nonstationary data. Fourteen variables were included in the developed and validated model, relating to hydrologic, ecological and meteorologic time series data from January 2000 to December 2009 at the Lake Baiyangdian study area, North China. The performance of the proposed WA-ANN model for monthly Chl a simulation in the lake ecosystem was compared with a multiple stepwise linear regression (MSLR) model, an autoregressive integrated moving average (ARIMA) model and a regular ANN model. The results showed that the WA-ANN model was suitable for Chl a simulation providing a more accurate performance than the MSLR, ARIMA, and ANN models. We recommend that the proposed method be widely applied to further facilitate the development and implementation of lake ecosystem management.
NASA Astrophysics Data System (ADS)
H. Kashani, Mahsa; Ghorbani, Mohammad Ali; Dinpashoh, Yagob; Shahmorad, Sedaghat
2016-09-01
Rainfall-runoff simulation is an important task in water resources management. In this study, an integrated Volterra model with artificial neural networks (IVANN) was presented to simulate the rainfall-runoff process. The proposed integrated model includes the semi-distributed forms of the Volterra and ANN models which can explore spatial variation in rainfall-runoff process without requiring physical characteristic parameters of the catchments, while taking advantage of the potential of Volterra and ANNs models in nonlinear mapping. The IVANN model was developed using hourly rainfall and runoff data pertaining to thirteen storms to study short-term responses of a forest catchment in northern Iran; and its performance was compared with that of semi-distributed integrated ANN (IANN) model and lumped Volterra model. The Volterra model was applied as a nonlinear model (second-order Volterra (SOV) model) and solved using the ordinary least square (OLS) method. The models performance were evaluated and compared using five performance criteria namely coefficient of efficiency, root mean square error, error of total volume, relative error of peak discharge and error of time for peak to arrive. Results showed that the IVANN model performs well than the other semi-distributed and lumped models to simulate the rainfall-runoff process. Comparing to the integrated models, the lumped SOV model has lower precision to simulate the rainfall-runoff process.
NASA Astrophysics Data System (ADS)
Kashani, Mahsa H.; Ghorbani, Mohammad Ali; Dinpashoh, Yagob; Shahmorad, Sedaghat
2016-09-01
Rainfall-runoff simulation is an important task in water resources management. In this study, an integrated Volterra model with artificial neural networks (IVANN) was presented to simulate the rainfall-runoff process. The proposed integrated model includes the semi-distributed forms of the Volterra and ANN models which can explore spatial variation in rainfall-runoff process without requiring physical characteristic parameters of the catchments, while taking advantage of the potential of Volterra and ANNs models in nonlinear mapping. The IVANN model was developed using hourly rainfall and runoff data pertaining to thirteen storms to study short-term responses of a forest catchment in northern Iran; and its performance was compared with that of semi-distributed integrated ANN (IANN) model and lumped Volterra model. The Volterra model was applied as a nonlinear model (second-order Volterra (SOV) model) and solved using the ordinary least square (OLS) method. The models performance were evaluated and compared using five performance criteria namely coefficient of efficiency, root mean square error, error of total volume, relative error of peak discharge and error of time for peak to arrive. Results showed that the IVANN model performs well than the other semi-distributed and lumped models to simulate the rainfall-runoff process. Comparing to the integrated models, the lumped SOV model has lower precision to simulate the rainfall-runoff process.
Igarashi, Jun; Shouno, Osamu; Fukai, Tomoki; Tsujino, Hiroshi
2011-11-01
Real-time simulation of a biologically realistic spiking neural network is necessary for evaluation of its capacity to interact with real environments. However, the real-time simulation of such a neural network is difficult due to its high computational costs that arise from two factors: (1) vast network size and (2) the complicated dynamics of biologically realistic neurons. In order to address these problems, mainly the latter, we chose to use general purpose computing on graphics processing units (GPGPUs) for simulation of such a neural network, taking advantage of the powerful computational capability of a graphics processing unit (GPU). As a target for real-time simulation, we used a model of the basal ganglia that has been developed according to electrophysiological and anatomical knowledge. The model consists of heterogeneous populations of 370 spiking model neurons, including computationally heavy conductance-based models, connected by 11,002 synapses. Simulation of the model has not yet been performed in real-time using a general computing server. By parallelization of the model on the NVIDIA Geforce GTX 280 GPU in data-parallel and task-parallel fashion, faster-than-real-time simulation was robustly realized with only one-third of the GPU's total computational resources. Furthermore, we used the GPU's full computational resources to perform faster-than-real-time simulation of three instances of the basal ganglia model; these instances consisted of 1100 neurons and 33,006 synapses and were synchronized at each calculation step. Finally, we developed software for simultaneous visualization of faster-than-real-time simulation output. These results suggest the potential power of GPGPU techniques in real-time simulation of realistic neural networks.
Han, Zong-wei; Huang, Wei; Luo, Yun; Zhang, Chun-di; Qi, Da-cheng
2015-03-01
Taking the soil organic matter in eastern Zhongxiang County, Hubei Province, as a research object, thirteen sample sets from different regions were arranged surrounding the road network, the spatial configuration of which was optimized by the simulated annealing approach. The topographic factors of these thirteen sample sets, including slope, plane curvature, profile curvature, topographic wetness index, stream power index and sediment transport index, were extracted by the terrain analysis. Based on the results of optimization, a multiple linear regression model with topographic factors as independent variables was built. At the same time, a multilayer perception model on the basis of neural network approach was implemented. The comparison between these two models was carried out then. The results revealed that the proposed approach was practicable in optimizing soil sampling scheme. The optimal configuration was capable of gaining soil-landscape knowledge exactly, and the accuracy of optimal configuration was better than that of original samples. This study designed a sampling configuration to study the soil attribute distribution by referring to the spatial layout of road network, historical samples, and digital elevation data, which provided an effective means as well as a theoretical basis for determining the sampling configuration and displaying spatial distribution of soil organic matter with low cost and high efficiency.
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.
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.
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…
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.
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
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.
Tóth-Nagy, Csaba; Conley, John J; Jarrett, Ronald P; Clark, Nigel N
2006-07-01
With the advent of hybrid electric vehicles, computer-based vehicle simulation becomes more useful to the engineer and designer trying to optimize the complex combination of control strategy, power plant, drive train, vehicle, and driving conditions. With the desire to incorporate emissions as a design criterion, researchers at West Virginia University have developed artificial neural network (ANN) models for predicting emissions from heavy-duty vehicles. The ANN models were trained on engine and exhaust emissions data collected from transient dynamometer tests of heavy-duty diesel engines then used to predict emissions based on engine speed and torque data from simulated operation of a tractor truck and hybrid electric bus. Simulated vehicle operation was performed with the ADVISOR software package. Predicted emissions (carbon dioxide [CO2] and oxides of nitrogen [NO(x)]) were then compared with actual emissions data collected from chassis dynamometer tests of similar vehicles. This paper expands on previous research to include different driving cycles for the hybrid electric bus and varying weights of the conventional truck. Results showed that different hybrid control strategies had a significant effect on engine behavior (and, thus, emissions) and may affect emissions during different driving cycles. The ANN models underpredicted emissions of CO2 and NO(x) in the case of a class-8 truck but were more accurate as the truck weight increased.
NASA Astrophysics Data System (ADS)
Kim, Jeoung Han; Reddy, N. S.; Yeom, Jong Taek; Hong, Jae Keun; Lee, Chong Soo; Park, Nho-Kwang
2009-06-01
The microstructural evolution of titanium alloy under isothermal and non-isothermal hot forging conditions was predicted using artificial neural networks (ANN) and finite element (FE) simulation. In the present work, the change in phase volume fraction, grain size, and the volume fraction of dynamic globularization were modelled considering hot working conditions. Initially, an ANN model was developed for steady-state phase volume fraction. The input parameters were the alloy chemical composition (Al, V, Fe, O, and N) and the holding temperature, and the output parameter was the alpha/beta phase volume fraction at steady state. The non-steady state phase volume fraction under non-isothermal conditions was subsequently modelled on the basis of 4 input parameters such as initial specimen temperature, die (or environment) temperature, steady-state phase volume fraction at die (or environment) temperature, and elapsed time during forging. Resulting ANN models were coupled with the FE simulation (DEFORM-3D) in order to predict the variation of phase volume fraction during isothermal and non-isothermal forging. In addition, a grain size variation and a globularization model were developed for hot forging. To validate the predicted results from the models, Ti-6Al-4V alloy was hot-worked at various conditions and then the resulting microstructures were compared with simulated data. Comparisons between model predictions and experimental data indicated that the ANN model holds promise for microstructure evolution in two phase Ti-6Al-4V alloy.
NASA Astrophysics Data System (ADS)
Ebrahimi, Hadi; Rajaee, Taher
2017-01-01
Simulation of groundwater level (GWL) fluctuations is an important task in management of groundwater resources. In this study, the effect of wavelet analysis on the training of the artificial neural network (ANN), multi linear regression (MLR) and support vector regression (SVR) approaches was investigated, and the ANN, MLR and SVR along with the wavelet-ANN (WNN), wavelet-MLR (WLR) and wavelet-SVR (WSVR) models were compared in simulating one-month-ahead of GWL. The only variable used to develop the models was the monthly GWL data recorded over a period of 11 years from two wells in the Qom plain, Iran. The results showed that decomposing GWL time series into several sub-time series, extremely improved the training of the models. For both wells 1 and 2, the Meyer and Db5 wavelets produced better results compared to the other wavelets; which indicated wavelet types had similar behavior in similar case studies. The optimal number of delays was 6 months, which seems to be due to natural phenomena. The best WNN model, using Meyer mother wavelet with two decomposition levels, simulated one-month-ahead with RMSE values being equal to 0.069 m and 0.154 m for wells 1 and 2, respectively. The RMSE values for the WLR model were 0.058 m and 0.111 m, and for WSVR model were 0.136 m and 0.060 m for wells 1 and 2, respectively.
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).
ERIC Educational Resources Information Center
Hewett, Thomas T.
There are a number of areas in psychology where an electronic spreadsheet simulator can be used to study and explore functional relationships among a number of parameters. For example, when dealing with sensation, perception, and pattern recognition, it is sometimes desirable for students to understand both the basic neurophysiology and the…
ERIC Educational Resources Information Center
Hewett, Thomas T.
There are a number of areas in psychology where an electronic spreadsheet simulator can be used to study and explore functional relationships among a number of parameters. For example, when dealing with sensation, perception, and pattern recognition, it is sometimes desirable for students to understand both the basic neurophysiology and the…
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.
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.
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.
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.
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.
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.
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.
Mustafa, Yasmen A; Jaid, Ghydaa M; Alwared, Abeer I; Ebrahim, Mothana
2014-06-01
The application of advanced oxidation process (AOP) in the treatment of wastewater contaminated with oil was investigated in this study. The AOP investigated is the homogeneous photo-Fenton (UV/H2O2/Fe(+2)) process. The reaction is influenced by the input concentration of hydrogen peroxide H2O2, amount of the iron catalyst Fe(+2), pH, temperature, irradiation time, and concentration of oil in the wastewater. The removal efficiency for the used system at the optimal operational parameters (H2O2 = 400 mg/L, Fe(+2) = 40 mg/L, pH = 3, irradiation time = 150 min, and temperature = 30 °C) for 1,000 mg/L oil load was found to be 72%. The study examined the implementation of artificial neural network (ANN) for the prediction and simulation of oil degradation in aqueous solution by photo-Fenton process. The multilayered feed-forward networks were trained by using a backpropagation algorithm; a three-layer network with 22 neurons in the hidden layer gave optimal results. The results show that the ANN model can predict the experimental results with high correlation coefficient (R (2) = 0.9949). The sensitivity analysis showed that all studied variables (H2O2, Fe(+2), pH, irradiation time, temperature, and oil concentration) have strong effect on the oil degradation. The pH was found to be the most influential parameter with relative importance of 20.6%.
NASA Astrophysics Data System (ADS)
Tapoglou, Evdokia; Karatzas, George P.; Trichakis, Ioannis C.; Varouchakis, Emmanouil A.
2015-04-01
The purpose of this study is to evaluate the uncertainty, using various methodologies, in a combined Artificial Neural Network (ANN) - Fuzzy logic - Kriging system, which can simulate spatially and temporally the hydraulic head in an aquifer. This system uses ANNs for the temporal prediction of hydraulic head in various locations, one ANN for every location with available data, and Kriging for the spatial interpolation of ANN's results. A fuzzy logic is used for the interconnection of these two methodologies. The full description of the initial system and its functionality can be found in Tapoglou et al. (2014). Two methodologies were used for the calculation of uncertainty for the implementation of the algorithm in a study area. First, the uncertainty of Kriging parameters was examined using a Bayesian bootstrap methodology. In this case the variogram is calculated first using the traditional methodology of Ordinary Kriging. Using the parameters derived and the covariance function of the model, the covariance matrix is constructed. A common method for testing a statistical model is the use of artificial data. Normal random numbers generation is the first step in this procedure and by multiplying them by the decomposed covariance matrix, correlated random numbers (sample set) can be calculated. These random values are then fitted into a variogram and the value in an unknown location is estimated using Kriging. The distribution of the simulated values using the Kriging of different correlated random values can be used in order to derive the prediction intervals of the process. In this study 500 variograms were constructed for every time step and prediction point, using the method described above, and their results are presented as the 95th and 5th percentile of the predictions. The second methodology involved the uncertainty of ANNs training. In this case, for all the data points 300 different trainings were implemented having different training datasets each time
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
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.
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
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.
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.
Patil, R.B.
1995-05-01
Traditional neural networks like multi-layered perceptrons (MLP) use example patterns, i.e., pairs of real-valued observation vectors, ({rvec x},{rvec y}), to approximate function {cflx f}({rvec x}) = {rvec y}. To determine the parameters of the approximation, a special version of the gradient descent method called back-propagation is widely used. In many situations, observations of the input and output variables are not precise; instead, we usually have intervals of possible values. The imprecision could be due to the limited accuracy of the measuring instrument or could reflect genuine uncertainty in the observed variables. In such situation input and output data consist of mixed data types; intervals and precise numbers. Function approximation in interval domains is considered in this paper. We discuss a modification of the classical backpropagation learning algorithm to interval domains. Results are presented with simple examples demonstrating few properties of nonlinear interval mapping as noise resistance and finding set of solutions to the function approximation problem.
De, Suvranu; Deo, Dhannanjay; Sankaranarayanan, Ganesh; Arikatla, Venkata S
2011-08-01
BACKGROUND: While an update rate of 30 Hz is considered adequate for real time graphics, a much higher update rate of about 1 kHz is necessary for haptics. Physics-based modeling of deformable objects, especially when large nonlinear deformations and complex nonlinear material properties are involved, at these very high rates is one of the most challenging tasks in the development of real time simulation systems. While some specialized solutions exist, there is no general solution for arbitrary nonlinearities. METHODS: In this work we present PhyNNeSS - a Physics-driven Neural Networks-based Simulation System - to address this long-standing technical challenge. The first step is an off-line pre-computation step in which a database is generated by applying carefully prescribed displacements to each node of the finite element models of the deformable objects. In the next step, the data is condensed into a set of coefficients describing neurons of a Radial Basis Function network (RBFN). During real-time computation, these neural networks are used to reconstruct the deformation fields as well as the interaction forces. RESULTS: We present realistic simulation examples from interactive surgical simulation with real time force feedback. As an example, we have developed a deformable human stomach model and a Penrose-drain model used in the Fundamentals of Laparoscopic Surgery (FLS) training tool box. CONCLUSIONS: A unique computational modeling system has been developed that is capable of simulating the response of nonlinear deformable objects in real time. The method distinguishes itself from previous efforts in that a systematic physics-based pre-computational step allows training of neural networks which may be used in real time simulations. We show, through careful error analysis, that the scheme is scalable, with the accuracy being controlled by the number of neurons used in the simulation. PhyNNeSS has been integrated into SoFMIS (Software Framework for Multimodal
Caldara, Roberto; Hervé, Abdi
2006-01-01
Other-race (OR) faces are less accurately recognized than same-race (SR) faces, but faster classified by race. This phenomenon has often been reported as the 'other-race' effect (ORE). Valentine (1991 Quarterly Journal of Experimental Psychology A: Human Experimental Psychology 43 161-204) proposed a theoretical multidimensional face-space model that explained both of these results, in terms of variations in exemplar density between races. According to this model, SR faces are more widely distributed across the dimensions of the space than OR faces. However, this model does not quantify nor state the dimensions coded within this face space. The aim of the present study was to test the face-space explanation of the ORE with neural network simulations by quantifying its dimensions. We found the predicted density properties of Valentine's framework in the face-projection spaces of the autoassociative memories. This was supported by an interaction for exemplar density between the race of the learned face set and the race of the faces. In addition, the elaborated face representations showed optimal responses for SR but not for OR faces within SR face spaces when explored at the individual level, as gender errors occurred significantly more often in OR than in SR face-space representations. Altogether, our results add further evidence in favor of a statistical exemplar density explanation of the ORE as suggested by Valentine, and question the plausibility of such coding for faces in the framework of recent neuroimaging studies.
Hattab, Nour; Hambli, Ridha; Motelica-Heino, Mikael; Mench, Michel
2013-11-15
The statistical variation of soil properties and their stochastic combinations may affect the extent of soil contamination by metals. This paper describes a method for the stochastic analysis of the effects of the variation in some selected soil factors (pH, DOC and EC) on the concentration of copper in dwarf bean leaves (phytoavailability) grown in the laboratory on contaminated soils treated with different amendments. The method is based on a hybrid modeling technique that combines an artificial neural network (ANN) and Monte Carlo Simulations (MCS). Because the repeated analyses required by MCS are time-consuming, the ANN is employed to predict the copper concentration in dwarf bean leaves in response to stochastic (random) combinations of soil inputs. The input data for the ANN are a set of selected soil parameters generated randomly according to a Gaussian distribution to represent the parameter variabilities. The output is the copper concentration in bean leaves. The results obtained by the stochastic (hybrid) ANN-MCS method show that the proposed approach may be applied (i) to perform a sensitivity analysis of soil factors in order to quantify the most important soil parameters including soil properties and amendments on a given metal concentration, (ii) to contribute toward the development of decision-making processes at a large field scale such as the delineation of contaminated sites. Copyright © 2013 Elsevier Ltd. All rights reserved.
NASA Astrophysics Data System (ADS)
Krasilenko, Vladimir G.; Nikolsky, Alexander I.; Lazarev, Alexander A.; Lazareva, Maria V.
2010-05-01
In the paper we show that the biologically motivated conception of time-pulse encoding usage gives a set of advantages (single methodological basis, universality, tuning simplicity, learning and programming et al) at creation and design of sensor systems with parallel input-output and processing for 2D structures hybrid and next generations neuro-fuzzy neurocomputers. We show design principles of programmable relational optoelectronic time-pulse encoded processors on the base of continuous logic, order logic and temporal waves processes. We consider a structure that execute analog signal extraction, analog and time-pulse coded variables sorting. We offer optoelectronic realization of such base relational order logic element, that consists of time-pulse coded photoconverters (pulse-width and pulse-phase modulators) with direct and complementary outputs, sorting network on logical elements and programmable commutation blocks. We make technical parameters estimations of devices and processors on such base elements by simulation and experimental research: optical input signals power 0.2 - 20 uW, processing time 1 - 10 us, supply voltage 1 - 3 V, consumption power 10 - 100 uW, extended functional possibilities, learning possibilities. We discuss some aspects of possible rules and principles of learning and programmable tuning on required function, relational operation and realization of hardware blocks for modifications of such processors. We show that it is possible to create sorting machines, neural networks and hybrid data-processing systems with untraditional numerical systems and pictures operands on the basis of such quasiuniversal hardware simple blocks with flexible programmable tuning.
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.
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.
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.
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.
Lagari, Pola Lydia; Sobes, Vladimir; Alamaniotis, Miltiadis; ...
2016-10-01
Detection and identification of special nuclear materials (SNMs) are an essential part of the US nonproliferation effort. Modern cutting-edge SNM detection methodologies rely more and more on modeling and simulation techniques. Experiments with radiological samples in realistic configurations, is the ultimate tool that establishes the minimum detection limits of SNMs in a host of different geometries. Modern modeling and simulation approaches have the potential to significantly reduce the number of experiments with radioactive sources needed to determine these detection limits and reduce the financial barrier to SNM detection. Unreliable nuclear data is one of the principal causes of uncertainty inmore » modeling and simulating nuclear systems. In particular, nuclear cross sections introduce a significant uncertainty in the nuclear data. The goal of this research is to develop a methodology that will autonomously extract the correct nuclear resonance characteristics of experimental data in a reliable way, a task previously left to expert judgement. Accurate nuclear data will in turn allow contemporary modeling and simulation to become far more reliable, de-escalating the extent of experimental testing. Modeling and simulation techniques reduce the use and distribution of radiological sources, while at the same time increase the reliability of the currently used methods for the detection and identification of SNMs.« less
Lagari, Pola Lydia; Sobes, Vladimir; Alamaniotis, Miltiadis; Tsoukalas, Lefteri H.
2016-10-01
Detection and identification of special nuclear materials (SNMs) are an essential part of the US nonproliferation effort. Modern cutting-edge SNM detection methodologies rely more and more on modeling and simulation techniques. Experiments with radiological samples in realistic configurations, is the ultimate tool that establishes the minimum detection limits of SNMs in a host of different geometries. Modern modeling and simulation approaches have the potential to significantly reduce the number of experiments with radioactive sources needed to determine these detection limits and reduce the financial barrier to SNM detection. Unreliable nuclear data is one of the principal causes of uncertainty in modeling and simulating nuclear systems. In particular, nuclear cross sections introduce a significant uncertainty in the nuclear data. The goal of this research is to develop a methodology that will autonomously extract the correct nuclear resonance characteristics of experimental data in a reliable way, a task previously left to expert judgement. Accurate nuclear data will in turn allow contemporary modeling and simulation to become far more reliable, de-escalating the extent of experimental testing. Modeling and simulation techniques reduce the use and distribution of radiological sources, while at the same time increase the reliability of the currently used methods for the detection and identification of SNMs.
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.
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.
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.
Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks.
Pu, Yi-Fei; Yi, Zhang; Zhou, Ji-Liu
2017-10-01
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.
Representations in neural network based empirical potentials
NASA Astrophysics Data System (ADS)
Cubuk, Ekin D.; Malone, Brad D.; Onat, Berk; Waterland, Amos; Kaxiras, Efthimios
2017-07-01
Many structural and mechanical properties of crystals, glasses, and biological macromolecules can be modeled from the local interactions between atoms. These interactions ultimately derive from the quantum nature of electrons, which can be prohibitively expensive to simulate. Machine learning has the potential to revolutionize materials modeling due to its ability to efficiently approximate complex functions. For example, neural networks can be trained to reproduce results of density functional theory calculations at a much lower cost. However, how neural networks reach their predictions is not well understood, which has led to them being used as a "black box" tool. This lack of understanding is not desirable especially for applications of neural networks in scientific inquiry. We argue that machine learning models trained on physical systems can be used as more than just approximations since they had to "learn" physical concepts in order to reproduce the labels they were trained on. We use dimensionality reduction techniques to study in detail the representation of silicon atoms at different stages in a neural network, which provides insight into how a neural network learns to model atomic interactions.
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.
Stimulated photorefractive optical neural networks
NASA Astrophysics Data System (ADS)
Owechko, Y.; Dunning, G.; Nordin, G.; Soffer, B. H.
1992-12-01
This final report describes research in optical neural networks performed under DARPA sponsorship at Hughes Aircraft Company during the period 1989-1992. The objective of demonstrating a programmable optical computer for flexible implementation of multi-layer neural network models was successfully achieved. The advantages of optics for neural network implementations include large storage capacity, high connectivity, and massive parallelism which result in high computation rates. The optical neurocomputer developed on this program is based on a new type of holography, cascaded grating holography (CGH), in which the neural network weights are distributed among angularly- and spatially-multiplexed gratings generated by stimulated processes 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, 2x10(7) weights, and processing rates of 2x10(7) connection updates per second were achieved. Packaging concepts for future versions of the neurocomputer were also studied.
Optical disk based neural network
NASA Astrophysics Data System (ADS)
Lu, Taiwei; Choi, Kyusun; Wu, Shudong; Xu, Xin; Yu, Francis T. S.
1989-11-01
An optical disk (OD)-based optical neural network architecture for high-speed and large-capacity associative processing is proposed. The information storage by the OD is described, and an optical neural network using an OD for large-capacity storage of interconnection weight matrices (IWMs) is shown and discussed. The ways that optical interconnections are established between the IWM and the input pattern is shown, as is the way that the loop is closed. The operation of the OD in the network is examined.
A Neural-Network Model-Based Simulation Tool for Blast Wall Protection of Structures (PREPRINT)
2010-05-01
modeling with software such as LS-DYNA [11], AUTODYN [12], FEFLO [13], Air3D [14], SHAMRC [15, 16], CTH [17], and DYSMAS [18]. The downside to this...approach, but used simulation models (based on AUTODYN ), rather than live experiments, to generate a database of pressure-time histories over the height...GCI for LS-DYNA, CTH, and AUTODYN [30]. Results from the two studies showed that LS-DYNA, CTH, and DYSMAS appear to be good options in regard to the
NASA Astrophysics Data System (ADS)
Monfared, Vahid
2017-03-01
The present work presents a new approach based on neural network prediction for simple and fast estimation of the creep plastic behaviour of the short fiber composites. Also, this approach is proposed to reduce the solution procedure. Moreover, as a significant application of the method, shuttles and spaceships, turbine blades and discs are generally subjected to the creep effects. Consequently, analysis of the creep phenomenon is required and vital in different industries. Analysis of the creep behaviour is required for failure, fracture, fatigue, and creep resistance of the optoelectronic/photonic composites, and sensors. One of the main applications of the present work is in designing the composites with optical fibers and devices. At last, a good agreement is seen among the present prediction by neural network approach, finite element method (FEM), and the experimental results.
Jang, Hong-Seok; Xing, Shuli; Lee, Malrey; Lee, Young-Keun; So, Seung-Young
2016-05-01
In this study, an artificial neural networks study was carried out to predict the quantity of radon of Granulated Blast Furnace Slag (GBFS) cement mortar. A data set of a laboratory work, in which a total of 3 mortars were produced, was utilized in the Artificial Neural Networks (ANNs) study. The mortar mixture parameters were three different GBFS ratios (0%, 20%, 40%). Measurement radon of moist cured specimens was measured at 3, 10, 30, 100, 365 days by sensing technology for continuous monitoring of indoor air quality (IAQ). ANN model is constructed, trained and tested using these data. The data used in the ANN model are arranged in a format of two input parameters that cover the cement, GBFS and age of samples and, an output parameter which is concentrations of radon emission of mortar. The results showed that ANN can be an alternative approach for the predicting the radon concentration of GBFS mortar using mortar ingredients as input parameters.
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.
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.
Spiking neural network simulation: numerical integration with the Parker-Sochacki method.
Stewart, Robert D; Bair, Wyeth
2009-08-01
Mathematical neuronal models are normally expressed using differential equations. The Parker-Sochacki method is a new technique for the numerical integration of differential equations applicable to many neuronal models. Using this method, the solution order can be adapted according to the local conditions at each time step, enabling adaptive error control without changing the integration timestep. The method has been limited to polynomial equations, but we present division and power operations that expand its scope. We apply the Parker-Sochacki method to the Izhikevich 'simple' model and a Hodgkin-Huxley type neuron, comparing the results with those obtained using the Runge-Kutta and Bulirsch-Stoer methods. Benchmark simulations demonstrate an improved speed/accuracy trade-off for the method relative to these established techniques.
Neuronify: An Educational Simulator for Neural Circuits
Hafreager, Anders; Malthe-Sørenssen, Anders; Fyhn, Marianne
2017-01-01
Abstract Educational software (apps) can improve science education by providing an interactive way of learning about complicated topics that are hard to explain with text and static illustrations. However, few educational apps are available for simulation of neural networks. Here, we describe an educational app, Neuronify, allowing the user to easily create and explore neural networks in a plug-and-play simulation environment. The user can pick network elements with adjustable parameters from a menu, i.e., synaptically connected neurons modelled as integrate-and-fire neurons and various stimulators (current sources, spike generators, visual, and touch) and recording devices (voltmeter, spike detector, and loudspeaker). We aim to provide a low entry point to simulation-based neuroscience by allowing students with no programming experience to create and simulate neural networks. To facilitate the use of Neuronify in teaching, a set of premade common network motifs is provided, performing functions such as input summation, gain control by inhibition, and detection of direction of stimulus movement. Neuronify is developed in C++ and QML using the cross-platform application framework Qt and runs on smart phones (Android, iOS) and tablet computers as well personal computers (Windows, Mac, Linux). PMID:28321440
Neuronify: An Educational Simulator for Neural Circuits.
Dragly, Svenn-Arne; Hobbi Mobarhan, Milad; Våvang Solbrå, Andreas; Tennøe, Simen; Hafreager, Anders; Malthe-Sørenssen, Anders; Fyhn, Marianne; Hafting, Torkel; Einevoll, Gaute T
2017-01-01
Educational software (apps) can improve science education by providing an interactive way of learning about complicated topics that are hard to explain with text and static illustrations. However, few educational apps are available for simulation of neural networks. Here, we describe an educational app, Neuronify, allowing the user to easily create and explore neural networks in a plug-and-play simulation environment. The user can pick network elements with adjustable parameters from a menu, i.e., synaptically connected neurons modelled as integrate-and-fire neurons and various stimulators (current sources, spike generators, visual, and touch) and recording devices (voltmeter, spike detector, and loudspeaker). We aim to provide a low entry point to simulation-based neuroscience by allowing students with no programming experience to create and simulate neural networks. To facilitate the use of Neuronify in teaching, a set of premade common network motifs is provided, performing functions such as input summation, gain control by inhibition, and detection of direction of stimulus movement. Neuronify is developed in C++ and QML using the cross-platform application framework Qt and runs on smart phones (Android, iOS) and tablet computers as well personal computers (Windows, Mac, Linux).
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.
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.
Analog neural network for support vector machine learning.
Perfetti, Renzo; Ricci, Elisa
2006-07-01
An analog neural network for support vector machine learning is proposed, based on a partially dual formulation of the quadratic programming problem. It results in a simpler circuit implementation with respect to existing neural solutions for the same application. The effectiveness of the proposed network is shown through some computer simulations concerning benchmark problems.
Multiprocessor Neural Network in Healthcare.
Godó, Zoltán Attila; Kiss, Gábor; Kocsis, Dénes
2015-01-01
A possible way of creating a multiprocessor artificial neural network is by the use of microcontrollers. The RISC processors' high performance and the large number of I/O ports mean they are greatly suitable for creating such a system. During our research, we wanted to see if it is possible to efficiently create interaction between the artifical neural network and the natural nervous system. To achieve as much analogy to the living nervous system as possible, we created a frequency-modulated analog connection between the units. Our system is connected to the living nervous system through 128 microelectrodes. Two-way communication is provided through A/D transformation, which is even capable of testing psychopharmacons. The microcontroller-based analog artificial neural network can play a great role in medical singal processing, such as ECG, EEG etc.
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.
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
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.
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.
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.
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.
Adaptive Neural Networks for Automatic Negotiation
Sakas, D. P.; Vlachos, D. S.; Simos, T. E.
2007-12-26
The use of fuzzy logic and fuzzy neural networks has been found effective for the modelling of the uncertain relations between the parameters of a negotiation procedure. The problem with these configurations is that they are static, that is, any new knowledge from theory or experiment lead to the construction of entirely new models. To overcome this difficulty, we apply in this work, an adaptive neural topology to model the negotiation process. Finally a simple simulation is carried in order to test the new method.
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
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
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.
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
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…
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…
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.
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.
Are artificial neural networks white boxes?
Kolman, Eyal; Margaliot, Michael
2005-07-01
In this paper, we introduce a novel Mamdani-type fuzzy model, referred to as the all-permutations fuzzy rule base (APFRB), and show that it is mathematically equivalent to a standard feedforward neural network. We describe several applications of this equivalence between a neural network and our fuzzy rule base (FRB), including knowledge extraction from and knowledge insertion into neural networks.
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.
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.
Neural network explanation using inversion.
Saad, Emad W; Wunsch, Donald C
2007-01-01
An important drawback of many artificial neural networks (ANN) is their lack of explanation capability [Andrews, R., Diederich, J., & Tickle, A. B. (1996). A survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems, 8, 373-389]. This paper starts with a survey of algorithms which attempt to explain the ANN output. We then present HYPINV, a new explanation algorithm which relies on network inversion; i.e. calculating the ANN input which produces a desired output. HYPINV is a pedagogical algorithm, that extracts rules, in the form of hyperplanes. It is able to generate rules with arbitrarily desired fidelity, maintaining a fidelity-complexity tradeoff. To our knowledge, HYPINV is the only pedagogical rule extraction method, which extracts hyperplane rules from continuous or binary attribute neural networks. Different network inversion techniques, involving gradient descent as well as an evolutionary algorithm, are presented. An information theoretic treatment of rule extraction is presented. HYPINV is applied to example synthetic problems, to a real aerospace problem, and compared with similar algorithms using benchmark problems.
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.
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.
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.
Tests of track segment and vertex finding with neural networks
Denby, B.; Lessner, E. ); Lindsey, C.S. )
1990-04-01
Feed forward neural networks have been trained, using back-propagation, to find the slopes of simulated track segments in a straw chamber and to find the vertex of tracks from both simulated and real events in a more conventional drift chamber geometry. Network architectures, training, and performance are presented. 12 refs., 7 figs.
Artificial neural networks: theoretical background and pharmaceutical applications: a review.
Wesolowski, Marek; Suchacz, Bogdan
2012-01-01
In recent times, there has been a growing interest in artificial neural networks, which are a rough simulation of the information processing ability of the human brain, as modern and vastly sophisticated computational techniques. This interest has also been reflected in the pharmaceutical sciences. This paper presents a review of articles on the subject of the application of neural networks as effective tools assisting the solution of various problems in science and the pharmaceutical industry, especially those characterized by multivariate and nonlinear dependencies. After a short description of theoretical background and practical basics concerning the computations performed by means of neural networks, the most important pharmaceutical applications of neural networks, with suitable references, are demonstrated. The huge role played by neural networks in pharmaceutical analysis, pharmaceutical technology, and searching for the relationships between the chemical structure and the properties of newly synthesized compounds as candidates for drugs is discussed.
A Novel Neural Network for Generally Constrained Variational Inequalities.
Gao, Xingbao; Liao, Li-Zhi
2016-06-13
This paper presents a novel neural network for solving generally constrained variational inequality problems by constructing a system of double projection equations. By defining proper convex energy functions, the proposed neural network is proved to be stable in the sense of Lyapunov and converges to an exact solution of the original problem for any starting point under the weaker cocoercivity condition or the monotonicity condition of the gradient mapping on the linear equation set. Furthermore, two sufficient conditions are provided to ensure the stability of the proposed neural network for a special case. The proposed model overcomes some shortcomings of existing continuous-time neural networks for constrained variational inequality, and its stability only requires some monotonicity conditions of the underlying mapping and the concavity of nonlinear inequality constraints on the equation set. The validity and transient behavior of the proposed neural network are demonstrated by some simulation results.
A novel neural network for nonlinear convex programming.
Gao, Xing-Bao
2004-05-01
In this paper, we present a neural network for solving the nonlinear convex programming problem in real time by means of the projection method. The main idea is to convert the convex programming problem into a variational inequality problem. Then a dynamical system and a convex energy function are constructed for resulting variational inequality problem. It is shown that the proposed neural network is stable in the sense of Lyapunov and can converge to an exact optimal solution of the original problem. Compared with the existing neural networks for solving the nonlinear convex programming problem, the proposed neural network has no Lipschitz condition, no adjustable parameter, and its structure is simple. The validity and transient behavior of the proposed neural network are demonstrated by some simulation results.
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
El-Nagar, Ahmad M; El-Bardini, Mohammad
2014-05-01
This manuscript describes the use of a hardware-in-the-loop simulation to simulate the control of a multivariable anesthesia system based on an interval type-2 fuzzy neural network (IT2FNN) controller. The IT2FNN controller consists of an interval type-2 fuzzy linguistic process as the antecedent part and an interval neural network as the consequent part. It has been proposed that the IT2FNN controller can be used for the control of a multivariable anesthesia system to minimize the effects of surgical stimulation and to overcome the uncertainty problem introduced by the large inter-individual variability of the patient parameters. The parameters of the IT2FNN controller were trained online using a back-propagation algorithm. Three experimental cases are presented. All of the experimental results show good performance for the proposed controller over a wide range of patient parameters. Additionally, the results show better performance than the type-1 fuzzy neural network (T1FNN) controller under the effect of surgical stimulation. The response of the proposed controller has a smaller settling time and a smaller overshoot compared with the T1FNN controller and the adaptive interval type-2 fuzzy logic controller (AIT2FLC). The values of the performance indices for the proposed controller are lower than those obtained for the T1FNN controller and the AIT2FLC. The IT2FNN controller is superior to the T1FNN controller for the handling of uncertain information due to the structure of type-2 fuzzy logic systems (FLSs), which are able to model and minimize the numerical and linguistic uncertainties associated with the inputs and outputs of the FLSs. Copyright © 2014 Elsevier B.V. All rights reserved.
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.
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.
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.
Artificial neural networks reveal efficiency in genetic value prediction.
Peixoto, L A; Bhering, L L; Cruz, C D
2015-06-18
The objective of this study was to evaluate the efficiency of artificial neural networks (ANNs) for predicting genetic value in experiments carried out in randomized blocks. Sixteen scenarios were simulated with different values of heritability (10, 20, 30, and 40%), coefficient of variation (5 and 10%), and the number of genotypes per block (150 and 200 for validation, and 5000 for neural network training). One hundred validation populations were used in each scenario. Accuracy of ANNs was evaluated by comparing the correlation of network value with genetic value, and of phenotypic value with genetic value. Neural networks were efficient in predicting genetic value with a 0.64 to 10.3% gain compared to the phenotypic value, regardless the simulated population size, heritability, or coefficient of variation. Thus, the artificial neural network is a promising technique for predicting genetic value in balanced experiments.
Inversion of surface parameters using fast learning neural networks
NASA Technical Reports Server (NTRS)
Dawson, M. S.; Olvera, J.; Fung, A. K.; Manry, M. T.
1992-01-01
A neural network approach to the inversion of surface scattering parameters is presented. Simulated data sets based on a surface scattering model are used so that the data may be viewed as taken from a completely known randomly rough surface. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) are tested on the simulated backscattering data. The RMS error of training the FL network is found to be less than one half the error of the BP network while requiring one to two orders of magnitude less CPU time. When applied to inversion of parameters from a statistically rough surface, the FL method is successful at recovering the surface permittivity, the surface correlation length, and the RMS surface height in less time and with less error than the BP network. Further applications of the FL neural network to the inversion of parameters from backscatter measurements of an inhomogeneous layer above a half space are shown.
Inversion of surface parameters using fast learning neural networks
NASA Technical Reports Server (NTRS)
Dawson, M. S.; Olvera, J.; Fung, A. K.; Manry, M. T.
1992-01-01
A neural network approach to the inversion of surface scattering parameters is presented. Simulated data sets based on a surface scattering model are used so that the data may be viewed as taken from a completely known randomly rough surface. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) are tested on the simulated backscattering data. The RMS error of training the FL network is found to be less than one half the error of the BP network while requiring one to two orders of magnitude less CPU time. When applied to inversion of parameters from a statistically rough surface, the FL method is successful at recovering the surface permittivity, the surface correlation length, and the RMS surface height in less time and with less error than the BP network. Further applications of the FL neural network to the inversion of parameters from backscatter measurements of an inhomogeneous layer above a half space are shown.
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 Flows in Hopfield Network Approach
NASA Astrophysics Data System (ADS)
Ionescu, Carmen; Panaitescu, Emilian; Stoicescu, Mihai
2013-12-01
In most of the applications involving neural networks, the main problem consists in finding an optimal procedure to reduce the real neuron to simpler models which still express the biological complexity but allow highlighting the main characteristics of the system. We effectively investigate a simple reduction procedure which leads from complex models of Hodgkin-Huxley type to very convenient binary models of Hopfield type. The reduction will allow to describe the neuron interconnections in a quite large network and to obtain information concerning its symmetry and stability. Both cases, on homogeneous voltage across the membrane and inhomogeneous voltage along the axon will be tackled out. Few numerical simulations of the neural flow based on the cable-equation will be also presented.
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.
Application of a neural network for reflectance spectrum classification
NASA Astrophysics Data System (ADS)
Yang, Gefei; Gartley, Michael
2017-05-01
Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.
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.
NASA Astrophysics Data System (ADS)
Karimi, Gholamreza; Banitalebi, Roza; Babaei Sedaghat, Sedigheh
2013-07-01
In this article, the small-signal equivalent circuit model of SiGe:C heterojunction bipolar transistors (HBTs) has directly been extracted from S-parameter data. Moreover, in this article, we present a new modelling approach using ANFIS (adaptive neuro-fuzzy inference system), which in general has a high degree of accuracy, simplicity and novelty (independent approach). Then measured and model-calculated data show an excellent agreement with less than 1.68 × 10-5% discrepancy in the frequency range of higher than 300 GHz over a wide range of bias points in ANFIS. The results show ANFIS model is better than ANN (artificial neural network) for redeveloping the model and increasing the input parameters.
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-Based Hyperspectral Algorithms
2016-06-07
Neural Network -Based Hyperspectral Algorithms Walter F. Smith, Jr. and Juanita Sandidge Naval Research Laboratory Code 7340, Bldg 1105 Stennis Space...combination of in-situ and model data of water column variables (IOP’s, depth, bottom type, upwelling radiance, etc.) a neural network non-linear... network (Lippman, 1987). Neural network -based algorithms have been demonstrated by the investigators for retrieval of water depth from Airborne Visible
Neural network subtyping of depression.
Florio, T M; Parker, G; Austin, M P; Hickie, I; Mitchell, P; Wilhelm, K
1998-10-01
To examine the applicability of a neural network classification strategy to examine the independent contribution of psychomotor disturbance (PMD) and endogeneity symptoms to the DSM-III-R definition of melancholia. We studied 407 depressed patients with the clinical dataset comprising 17 endogeneity symptoms and the 18-item CORE measure of behaviourally rated PMD. A multilayer perception neural network was used to fit non-linear models of varying complexity. A linear discriminant function analysis was also used to generate a model for comparison with the non-linear models. Models (linear and non-linear) using PMD items only and endogeneity symptoms only had similar rates of successful classification, while non-linear models combining both PMD and symptoms scores achieved the best classifications. Our current non-linear model was superior to a linear analysis, a finding which may have wider application to psychiatric classification. Our non-linear analysis of depressive subtypes supports the binary view that melancholic and non-melancholic depression are separate clinical disorders rather than different forms of the same entity. This study illustrates how non-linear modelling with neural networks is a potentially fruitful approach to the study of the diagnostic taxonomy of psychiatric disorders and to clinical decision-making.
2016-01-01
The aim of this study was to determine how representative wear scars of simulator-tested polyethylene (PE) inserts compare with retrieved PE inserts from total knee replacement (TKR). By means of a nonparametric self-organizing feature map (SOFM), wear scar images of 21 postmortem- and 54 revision-retrieved components were compared with six simulator-tested components that were tested either in displacement or in load control according to ISO protocols. The SOFM network was then trained with the wear scar images of postmortem-retrieved components since those are considered well-functioning at the time of retrieval. Based on this training process, eleven clusters were established, suggesting considerable variability among wear scars despite an uncomplicated loading history inside their hosts. The remaining components (revision-retrieved and simulator-tested) were then assigned to these established clusters. Six out of five simulator components were clustered together, suggesting that the network was able to identify similarities in loading history. However, the simulator-tested components ended up in a cluster at the fringe of the map containing only 10.8% of retrieved components. This may suggest that current ISO testing protocols were not fully representative of this TKR population, and protocols that better resemble patients' gait after TKR containing activities other than walking may be warranted. PMID:27597955
Orozco Villaseñor, Diego A; Wimmer, Markus A
2016-01-01
The aim of this study was to determine how representative wear scars of simulator-tested polyethylene (PE) inserts compare with retrieved PE inserts from total knee replacement (TKR). By means of a nonparametric self-organizing feature map (SOFM), wear scar images of 21 postmortem- and 54 revision-retrieved components were compared with six simulator-tested components that were tested either in displacement or in load control according to ISO protocols. The SOFM network was then trained with the wear scar images of postmortem-retrieved components since those are considered well-functioning at the time of retrieval. Based on this training process, eleven clusters were established, suggesting considerable variability among wear scars despite an uncomplicated loading history inside their hosts. The remaining components (revision-retrieved and simulator-tested) were then assigned to these established clusters. Six out of five simulator components were clustered together, suggesting that the network was able to identify similarities in loading history. However, the simulator-tested components ended up in a cluster at the fringe of the map containing only 10.8% of retrieved components. This may suggest that current ISO testing protocols were not fully representative of this TKR population, and protocols that better resemble patients' gait after TKR containing activities other than walking may be warranted.
Fault detection and diagnosis using neural network approaches
NASA Technical Reports Server (NTRS)
Kramer, Mark A.
1992-01-01
Neural networks can be used to detect and identify abnormalities in real-time process data. Two basic approaches can be used, the first based on training networks using data representing both normal and abnormal modes of process behavior, and the second based on statistical characterization of the normal mode only. Given data representative of process faults, radial basis function networks can effectively identify failures. This approach is often limited by the lack of fault data, but can be facilitated by process simulation. The second approach employs elliptical and radial basis function neural networks and other models to learn the statistical distributions of process observables under normal conditions. Analytical models of failure modes can then be applied in combination with the neural network models to identify faults. Special methods can be applied to compensate for sensor failures, to produce real-time estimation of missing or failed sensors based on the correlations codified in the neural network.
2008-03-01
artificial neural networks , to overcome problems of computationally expensive simulations. Neural networks have the potential to make predictions of...optimal solution. Artificial neural networks appear to be well suited to this application, performing well for problems that are strongly non-linear and
Dynamic Neural Networks Supporting Memory Retrieval
St. Jacques, Peggy L.; Kragel, Philip A.; Rubin, David C.
2011-01-01
How do separate neural networks interact to support complex cognitive processes such as remembrance of the personal past? Autobiographical memory (AM) retrieval recruits a consistent pattern of activation that potentially comprises multiple neural networks. However, it is unclear how such large-scale neural networks interact and are modulated by properties of the memory retrieval process. In the present functional MRI (fMRI) study, we combined independent component analysis (ICA) and dynamic causal modeling (DCM) to understand the neural networks supporting AM retrieval. ICA revealed four task-related components consistent with the previous literature: 1) Medial Prefrontal Cortex (PFC) Network, associated with self-referential processes, 2) Medial Temporal Lobe (MTL) Network, associated with memory, 3) Frontoparietal Network, associated with strategic search, and 4) Cingulooperculum Network, associated with goal maintenance. DCM analysis revealed that the medial PFC network drove activation within the system, consistent with the importance of this network to AM retrieval. Additionally, memory accessibility and recollection uniquely altered connectivity between these neural networks. Recollection modulated the influence of the medial PFC on the MTL network during elaboration, suggesting that greater connectivity among subsystems of the default network supports greater re-experience. In contrast, memory accessibility modulated the influence of frontoparietal and MTL networks on the medial PFC network, suggesting that ease of retrieval involves greater fluency among the multiple networks contributing to AM. These results show the integration between neural networks supporting AM retrieval and the modulation of network connectivity by behavior. PMID:21550407
Motion model identification of rescue robot based on optimized Jordan neural network
NASA Astrophysics Data System (ADS)
Zhang, Guangbin; Zhang, Runmei; Wang, Guangyin; Wu, Yulu
2017-06-01
Considering the influence of various factors, such as speed, angle, depth of water, weight, and water flow, on the underwater rescue robot, a method based on neural network is proposed. According to the characteristics of Elman and Jordan neural network, a new dynamic neural network is constructed. The network can be used to remember the state of the hidden layer and increase the feedback of the output node. The improved Jordan network is optimized by chaos particle swarm optimization algorithm. The optimized neural network is applied to identify the dynamic model of the underwater rescue robot. The simulation results show that the neural network has good convergence speed and accuracy.
Prediction of Aerodynamic Coefficients using Neural Networks for Sparse Data
NASA Technical Reports Server (NTRS)
Rajkumar, T.; Bardina, Jorge; Clancy, Daniel (Technical Monitor)
2002-01-01
Basic aerodynamic coefficients are modeled as functions of angles of attack and sideslip with vehicle lateral symmetry and compressibility effects. Most of the aerodynamic parameters can be well-fitted using polynomial functions. In this paper a fast, reliable way of predicting aerodynamic coefficients is produced using a neural network. The training data for the neural network is derived from wind tunnel test and numerical simulations. The coefficients of lift, drag, pitching moment are expressed as a function of alpha (angle of attack) and Mach number. The results produced from preliminary neural network analysis are very good.
Sea ice classification using fast learning neural networks
NASA Technical Reports Server (NTRS)
Dawson, M. S.; Fung, A. K.; Manry, M. T.
1992-01-01
A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks.
Sea ice classification using fast learning neural networks
NASA Technical Reports Server (NTRS)
Dawson, M. S.; Fung, A. K.; Manry, M. T.
1992-01-01
A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks.
Constructive neural network learning algorithms
Parekh, R.; Yang, Jihoon; Honavar, V.
1996-12-31
Constructive Algorithms offer an approach for incremental construction of potentially minimal neural network architectures for pattern classification tasks. These algorithms obviate the need for an ad-hoc a-priori choice of the network topology. The constructive algorithm design involves alternately augmenting the existing network topology by adding one or more threshold logic units and training the newly added threshold neuron(s) using a stable variant of the perception learning algorithm (e.g., pocket algorithm, thermal perception, and barycentric correction procedure). Several constructive algorithms including tower, pyramid, tiling, upstart, and perception cascade have been proposed for 2-category pattern classification. These algorithms differ in terms of their topological and connectivity constraints as well as the training strategies used for individual neurons.
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 in Nonlinear Aircraft Control
NASA Technical Reports Server (NTRS)
Linse, Dennis J.
1990-01-01
Recent research indicates that artificial neural networks offer interesting learning or adaptive capabilities. The current research focuses on the potential for application of neural networks in a nonlinear aircraft control law. The current work has been to determine which networks are suitable for such an application and how they will fit into a nonlinear control law.
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.
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.
Efficiently modeling neural networks on massively parallel computers
NASA Technical Reports Server (NTRS)
Farber, Robert M.
1993-01-01
Neural networks are a very useful tool for analyzing and modeling complex real world systems. Applying neural network simulations to real world problems generally involves large amounts of data and massive amounts of computation. To efficiently handle the computational requirements of large problems, we have implemented at Los Alamos a highly efficient neural network compiler for serial computers, vector computers, vector parallel computers, and fine grain SIMD computers such as the CM-2 connection machine. This paper describes the mapping used by the compiler to implement feed-forward backpropagation neural networks for a SIMD (Single Instruction Multiple Data) architecture parallel computer. Thinking Machines Corporation has benchmarked our code at 1.3 billion interconnects per second (approximately 3 gigaflops) on a 64,000 processor CM-2 connection machine (Singer 1990). This mapping is applicable to other SIMD computers and can be implemented on MIMD computers such as the CM-5 connection machine. Our mapping has virtually no communications overhead with the exception of the communications required for a global summation across the processors (which has a sub-linear runtime growth on the order of O(log(number of processors)). We can efficiently model very large neural networks which have many neurons and interconnects and our mapping can extend to arbitrarily large networks (within memory limitations) by merging the memory space of separate processors with fast adjacent processor interprocessor communications. This paper will consider the simulation of only feed forward neural network although this method is extendable to recurrent networks.
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
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
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.
The Neural Network Method of Corrosion Diagnosis for Grounding Grid
Hou Zaien; Duan Fujian; Zhang Kecun
2008-11-06
Safety of persons, protection of equipment and continuity of power supply are the main objectives of the grounding system of a large electrical installation. For its accurate working status, it is essential to determine every branch resistance in the system. In this paper, we present a neural network method of corrosion diagnosis for the grounding grid based on the neural network theory. The feasibility of this method is discussed by means of its application to a simulant grounding grid.
An efficient annealing in Boltzmann machine in Hopfield neural network
NASA Astrophysics Data System (ADS)
Kin, Teoh Yeong; Hasan, Suzanawati Abu; Bulot, Norhisam; Ismail, Mohammad Hafiz
2012-09-01
This paper proposes and implements Boltzmann machine in Hopfield neural network doing logic programming based on the energy minimization system. The temperature scheduling in Boltzmann machine enhancing the performance of doing logic programming in Hopfield neural network. The finest temperature is determined by observing the ratio of global solution and final hamming distance using computer simulations. The study shows that Boltzmann Machine model is more stable and competent in term of representing and solving difficult combinatory problems.
2014-04-01
Damselfly is a model-based parallel network simulator. It can simulate communication patterns of High Performance Computing applications on different network topologies. It outputs steady-state network traffic for a communication pattern, which can help in studying network congestion and its impact on performance.
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.
A flexible annealing chaotic neural network to maximum clique problem.
Yang, Gang; Tang, Zheng; Zhang, Zhiqiang; Zhu, Yunyi
2007-06-01
Based on the analysis and comparison of several annealing strategies, we present a flexible annealing chaotic neural network which has flexible controlling ability and quick convergence rate to optimization problem. The proposed network has rich and adjustable chaotic dynamics at the beginning, and then can converge quickly to stable states. We test the network on the maximum clique problem by some graphs of the DIMACS clique instances, p-random and k random graphs. The simulations show that the flexible annealing chaotic neural network can get satisfactory solutions at very little time and few steps. The comparison between our proposed network and other chaotic neural networks denotes that the proposed network has superior executive efficiency and better ability to get optimal or near-optimal solution.
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.
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.
NASA Astrophysics Data System (ADS)
Dafonte, C.; Fustes, D.; Manteiga, M.; Garabato, D.; Álvarez, M. A.; Ulla, A.; Allende Prieto, C.
2016-10-01
Aims: We present an innovative artificial neural network (ANN) architecture, called Generative ANN (GANN), that computes the forward model, that is it learns the function that relates the unknown outputs (stellar atmospheric parameters, in this case) to the given inputs (spectra). Such a model can be integrated in a Bayesian framework to estimate the posterior distribution of the outputs. Methods: The architecture of the GANN follows the same scheme as a normal ANN, but with the inputs and outputs inverted. We train the network with the set of atmospheric parameters (Teff, log g, [Fe/H] and [α/ Fe]), obtaining the stellar spectra for such inputs. The residuals between the spectra in the grid and the estimated spectra are minimized using a validation dataset to keep solutions as general as possible. Results: The performance of both conventional ANNs and GANNs to estimate the stellar parameters as a function of the star brightness is presented and compared for different Galactic populations. GANNs provide significantly improved parameterizations for early and intermediate spectral types with rich and intermediate metallicities. The behaviour of both algorithms is very similar for our sample of late-type stars, obtaining residuals in the derivation of [Fe/H] and [α/ Fe] below 0.1 dex for stars with Gaia magnitude Grvs < 12, which accounts for a number in the order of four million stars to be observed by the Radial Velocity Spectrograph of the Gaia satellite. Conclusions: Uncertainty estimation of computed astrophysical parameters is crucial for the validation of the parameterization itself and for the subsequent exploitation by the astronomical community. GANNs produce not only the parameters for a given spectrum, but a goodness-of-fit between the observed spectrum and the predicted one for a given set of parameters. Moreover, they allow us to obtain the full posterior distribution over the astrophysical parameters space once a noise model is assumed. This can be
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.
The Laplacian spectrum of neural networks
de Lange, Siemon C.; de Reus, Marcel A.; van den Heuvel, Martijn P.
2014-01-01
The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these “conventional” graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network's structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks. PMID:24454286
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.
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.
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.
VCSEL operational requirements for optoelectronic neural networks
NASA Astrophysics Data System (ADS)
Waddie, Andrew J.; Taghizadeh, Mohammad R.
2003-04-01
In this paper we shall describe the design and successful operation of an optoelectronic Hopfield network demonstrator system. This demonstrator system, based around a free-space diffractive optical interconnect, was designed to perform a range of optimisation tasks, in particular those associated with the scheduling of packets through different switching topologies. Experimental optimisation of the neural network throughput, for both a crossbar and Banyan switch topology, allows the neural network parameters (e.g. neuron bias, neuron weighting) to be tuned to ensure optimal operation of the network for a particular switch topology. The weighted interconnections in this optoelectronic system are provided by a diffractive optical element/lens combination whilst the neurons are implemented electronically. The transition between the electronic and optical domains is handled by an 8×8 VCSEL array for the electronic-optic interface, and an 8×8 Si photodetector array for the optic-electronic interface. The VCSEL array, supplied by Avalon Photonics, is an oxide-confined near-infrared GaAs device capable of 250MHz modulation at a wavelength of 960nm. The diffractive optical interconnect is designed using simulated annealing optimization and fabricated using VLSI photolithography. Using these techniques it is possible to create interconnects with a total efficiency of ~70% and a uniformity of < 1%.
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.
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.
Neural Network Modeling of Developmental Effects in Discrimination Shifts.
ERIC Educational Resources Information Center
Sirois, Sylvain; Shultz, Thomas R.
1998-01-01
Presents a theoretical account of human shift learning with the use of neural network tools. Details how simulations using the cascade-correlation algorithm which show that networks can capture the regularities of the discrimination shift literature better than existing psychological theories. Suggests that human developmental differences in shift…
function. Key Words and Phrases: Parametric estimation , exponential families, nonlinear models, nonlinear least squares, neural networks, Monte Carlo simulation, computer intensive statistical methods.
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.
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.
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.
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.
Lashkari, Negin; Poshtan, Javad; Azgomi, Hamid Fekri
2015-11-01
The three-phase shift between line current and phase voltage of induction motors can be used as an efficient fault indicator to detect and locate inter-turn stator short-circuit (ITSC) fault. However, unbalanced supply voltage is one of the contributing factors that inevitably affect stator currents and therefore the three-phase shift. Thus, it is necessary to propose a method that is able to identify whether the unbalance of three currents is caused by ITSC or supply voltage fault. This paper presents a feedforward multilayer-perceptron Neural Network (NN) trained by back propagation, based on monitoring negative sequence voltage and the three-phase shift. The data which are required for training and test NN are generated using simulated model of stator. The experimental results are presented to verify the superior accuracy of the proposed method. Copyright © 2015. Published by Elsevier Ltd.
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
Blur identification by multilayer neural network based on multivalued neurons.
Aizenberg, Igor; Paliy, Dmitriy V; Zurada, Jacek M; Astola, Jaakko T
2008-05-01
A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of specific different features. Its backpropagation learning algorithm is derivative-free. The functionality of MLMVN is superior to that of the traditional feedforward neural networks and of a variety kernel-based networks. Its higher flexibility and faster adaptation to the target mapping enables to model complex problems using simpler networks. In this paper, the MLMVN is used to identify both type and parameters of the point spread function, whose precise identification is of crucial importance for the image deblurring. The simulation results show the high efficiency of the proposed approach. It is confirmed that the MLMVN is a powerful tool for solving classification problems, especially multiclass ones.
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. Copyright © 2013 Elsevier Ltd. All rights reserved.
NASA Astrophysics Data System (ADS)
Magalhães, R. S.; Fontes, C. H. O.; Almeida, L. A. L.; Embiruçu, M.
2011-10-01
Acoustic noise in industrial areas, typically generated by compressors and vacuum pumps, may be mitigated by the combined use of passive and active noise control strategies. Despite its widespread use, the traditional Active Noise Control (ANC) technique requires error feedback and has been proven to be effective only within a small spatial region. When the movement of human ears is required within a large region and error feedback is difficult to be accomplished, new cancelling strategies have to be devised to achieve acceptable levels of spatial coverage. In the pursuit of this goal, this paper proposes a vibroacustic model to predict noise radiated from machinery. The model output is the sound signal of the noise at a given point inside a closed room. The two model inputs are the vibration signal at the noise source and the spatial coordinates of the intended point. Experimental output data were measured at several points inside a region defined by a solid rectangle. A fixed-order ARX model was chosen (AutoRegressive with eXogenous input), and for each spatial point and its corresponding pair of input-output signals, a set of parameter values was estimated. To integrate all these models into a single one, a neural network was employed to associate or approximate each set of parameters to its spatial coordinates. With this approach, the total number of parameters is expected to be greatly reduced, when considering the original separated models. Experimental results are presented and comparisons with other models are established on the basis of least-square error metrics and parsimony of parameters. A qualitative perspective for employing the proposed model in the design of large-region ANC strategies is also offered.
Creativity in design and artificial neural networks
Neocleous, C.C.; Esat, I.I.; Schizas, C.N.
1996-12-31
The creativity phase is identified as an integral part of the design phase. The characteristics of creative persons which are relevant to designing artificial neural networks manifesting aspects of creativity, are identified. Based on these identifications, a general framework of artificial neural network characteristics to implement such a goal are proposed.
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.
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.
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.
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.
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.
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.
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.
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
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.
The neural network approach to parton fitting
Rojo, Joan; Latorre, Jose I.; Del Debbio, Luigi; Forte, Stefano; Piccione, Andrea
2005-10-06
We introduce the neural network approach to global fits of parton distribution functions. First we review previous work on unbiased parametrizations of deep-inelastic structure functions with faithful estimation of their uncertainties, and then we summarize the current status of neural network parton distribution fits.
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. Copyright © 2010 Elsevier Ltd. All rights reserved.
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.
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…
Calculation of precise firing statistics in a neural network model
NASA Astrophysics Data System (ADS)
Cho, Myoung Won
2017-08-01
A precise prediction of neural firing dynamics is requisite to understand the function of and the learning process in a biological neural network which works depending on exact spike timings. Basically, the prediction of firing statistics is a delicate manybody problem because the firing probability of a neuron at a time is determined by the summation over all effects from past firing states. A neural network model with the Feynman path integral formulation is recently introduced. In this paper, we present several methods to calculate firing statistics in the model. We apply the methods to some cases and compare the theoretical predictions with simulation results.
NASA Astrophysics Data System (ADS)
Musca, Serban C.; Vadillo, Miguel A.; Blanco, Fernando; Matute, Helena
2010-06-01
Although normatively irrelevant to the relationship between a cue and an outcome, outcome density (i.e. its base-rate probability) affects people's estimation of causality. By what process causality is incorrectly estimated is of importance to an integrative theory of causal learning. A potential explanation may be that this happens because outcome density induces a judgement bias. An alternative explanation is explored here, following which the incorrect estimation of causality is grounded in the processing of cue-outcome information during learning. A first neural network simulation shows that, in the absence of a deep processing of cue information, cue-outcome relationships are acquired but causality is correctly estimated. The second simulation shows how an incorrect estimation of causality may emerge from the active processing of both cue and outcome information. In an experiment inspired by the simulations, the role of a deep processing of cue information was put to test. In addition to an outcome density manipulation, a shallow cue manipulation was introduced: cue information was either still displayed (concurrent) or no longer displayed (delayed) when outcome information was given. Behavioural and simulation results agree: the outcome-density effect was maximal in the concurrent condition. The results are discussed with respect to the extant explanations of the outcome-density effect within the causal learning framework.
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.
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.
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
USDA-ARS?s Scientific Manuscript database
A general regression neural network and Monte Carlo simulation model for predicting survival and growth of Salmonella on raw chicken skin as a function of serotype (Typhimurium, Kentucky, Hadar), temperature (5 to 50C) and time (0 to 8 h) was developed. Poultry isolates of Salmonella with natural r...
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.
CAISSON: Interconnect Network Simulator
NASA Technical Reports Server (NTRS)
Springer, Paul L.
2006-01-01
Cray response to HPCS initiative. Model future petaflop computer interconnect. Parallel discrete event simulation techniques for large scale network simulation. Built on WarpIV engine. Run on laptop and Altix 3000. Can be sized up to 1000 simulated nodes per host node. Good parallel scaling characteristics. Flexible: multiple injectors, arbitration strategies, queue iterators, network topologies.
Zhang, Songchuan; Xia, Youshen; Wang, Jun
2015-12-01
In this paper, we present a complex-valued projection neural network for solving constrained convex optimization problems of real functions with complex variables, as an extension of real-valued projection neural networks. Theoretically, by developing results on complex-valued optimization techniques, we prove that the complex-valued projection neural network is globally stable and convergent to the optimal solution. Obtained results are completely established in the complex domain and thus significantly generalize existing results of the real-valued projection neural networks. Numerical simulations are presented to confirm the obtained results and effectiveness of the proposed complex-valued projection neural network.
NASA Astrophysics Data System (ADS)
Li, Hong; Ding, Xue
2017-03-01
This paper combines wavelet analysis and wavelet transform theory with artificial neural network, through the pretreatment on point feature attributes before in intrusion detection, to make them suitable for improvement of wavelet neural network. The whole intrusion classification model gets the better adaptability, self-learning ability, greatly enhances the wavelet neural network for solving the problem of field detection invasion, reduces storage space, contributes to improve the performance of the constructed neural network, and reduces the training time. Finally the results of the KDDCup99 data set simulation experiment shows that, this method reduces the complexity of constructing wavelet neural network, but also ensures the accuracy of the intrusion classification.
The use of artificial neural networks in experimental data acquisition and aerodynamic design
NASA Technical Reports Server (NTRS)
Meade, Andrew J., Jr.
1991-01-01
It is proposed that an artificial neural network be used to construct an intelligent data acquisition system. The artificial neural networks (ANN) model has a potential for replacing traditional procedures as well as for use in computational fluid dynamics validation. Potential advantages of the ANN model are listed. As a proof of concept, the author modeled a NACA 0012 airfoil at specific conditions, using the neural network simulator NETS, developed by James Baffes of the NASA Johnson Space Center. The neural network predictions were compared to the actual data. It is concluded that artificial neural networks can provide an elegant and valuable class of mathematical tools for data analysis.
Lu, Hongtao; Amari, Shun-ichi
2006-09-01
In this paper, we study the global exponential stability of a multitime scale competitive neural network model with nonsmooth functions, which models a literally inhibited neural network with unsupervised Hebbian learning. The network has two types of state variables, one corresponds to the fast neural activity and another to the slow unsupervised modification of connection weights. Based on the nonsmooth analysis techniques, we prove the existence and uniqueness of equilibrium for the system and establish some new theoretical conditions ensuring global exponential stability of the unique equilibrium of the neural network. Numerical simulations are conducted to illustrate the effectiveness of the derived conditions in characterizing stability regions of the neural network.
A new one-layer neural network for linear and quadratic programming.
Gao, Xingbao; Liao, Li-Zhi
2010-06-01
In this paper, we present a new neural network for solving linear and quadratic programming problems in real time by introducing some new vectors. The proposed neural network is stable in the sense of Lyapunov and can converge to an exact optimal solution of the original problem when the objective function is convex on the set defined by equality constraints. Compared with existing one-layer neural networks for quadratic programming problems, the proposed neural network has the least neurons and requires weak stability conditions. The validity and transient behavior of the proposed neural network are demonstrated by some simulation results.
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.
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.
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.
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.
Energy complexity of recurrent neural networks.
Síma, Jiří
2014-05-01
Recently a new so-called energy complexity measure has been introduced and studied for feedforward perceptron networks. This measure is inspired by the fact that biological neurons require more energy to transmit a spike than not to fire, and the activity of neurons in the brain is quite sparse, with only about 1% of neurons firing. In this letter, we investigate the energy complexity of recurrent networks, which counts the number of active neurons at any time instant of a computation. We prove that any deterministic finite automaton with m states can be simulated by a neural network of optimal size [Formula: see text] with the time overhead of [Formula: see text] per one input bit, using the energy O(e), for any e such that [Formula: see text] and e=O(s), which shows the time-energy trade-off in recurrent networks. In addition, for the time overhead [Formula: see text] satisfying [Formula: see text], we obtain the lower bound of [Formula: see text] on the energy of such a simulation for some constant c>0 and for infinitely many s.
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
Artificial neural networks in neurosurgery.
Azimi, Parisa; Mohammadi, Hasan Reza; Benzel, Edward C; Shahzadi, Sohrab; Azhari, Shirzad; Montazeri, Ali
2015-03-01
Artificial neural networks (ANNs) effectively analyze non-linear data sets. The aimed was A review of the relevant published articles that focused on the application of ANNs as a tool for assisting clinical decision-making in neurosurgery. A literature review of all full publications in English biomedical journals (1993-2013) was undertaken. The strategy included a combination of key words 'artificial neural networks', 'prognostic', 'brain', 'tumor tracking', 'head', 'tumor', 'spine', 'classification' and 'back pain' in the title and abstract of the manuscripts using the PubMed search engine. The major findings are summarized, with a focus on the application of ANNs for diagnostic and prognostic purposes. Finally, the future of ANNs in neurosurgery is explored. A total of 1093 citations were identified and screened. In all, 57 citations were found to be relevant. Of these, 50 articles were eligible for inclusion in this review. The synthesis of the data showed several applications of ANN in neurosurgery, including: (1) diagnosis and assessment of disease progression in low back pain, brain tumours and primary epilepsy; (2) enhancing clinically relevant information extraction from radiographic images, intracranial pressure processing, low back pain and real-time tumour tracking; (3) outcome prediction in epilepsy, brain metastases, lumbar spinal stenosis, lumbar disc herniation, childhood hydrocephalus, trauma mortality, and the occurrence of symptomatic cerebral vasospasm in patients with aneurysmal subarachnoid haemorrhage; (4) the use in the biomechanical assessments of spinal disease. ANNs can be effectively employed for diagnosis, prognosis and outcome prediction in neurosurgery. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions.
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.
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
Local Dynamics in Trained Recurrent Neural Networks
NASA Astrophysics Data System (ADS)
Rivkind, Alexander; Barak, Omri
2017-06-01
Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.
NASA Astrophysics Data System (ADS)
Song, Lanlan
2017-04-01
Nitrous oxide is much more potent greenhouse gas than carbon dioxide. However, the estimation of N2O flux is usually clouded with uncertainty, mainly due to high spatial and temporal variations. This hampers the development of general mechanistic models for N2O emission as well, as most previously developed models were empirical or exhibited low predictability with numerous assumptions. In this study, we tested General Regression Neural Networks (GRNN) as an alternative to classic empirical models for simulating N2O emission in riparian zones of Reservoirs. GRNN and nonlinear regression (NLR) were applied to estimate the N2O flux of 1-year observations in riparian zones of Three Gorge Reservoir. NLR resulted in lower prediction power and higher residuals compared to GRNN. Although nonlinear regression model estimated similar average values of N2O, it could not capture the fluctuation patterns accurately. In contrast, GRNN model achieved a fairly high predictability, with an R2 of 0.59 for model validation, 0.77 for model calibration (training), and a low root mean square error (RMSE), indicating a high capacity to simulate the dynamics of N2O flux. According to a sensitivity analysis of the GRNN, nonlinear relationships between input variables and N2O flux were well explained. Our results suggest that the GRNN developed in this study has a greater performance in simulating variations in N2O flux than nonlinear regressions.
Neutron spectrum unfolding using radial basis function neural networks.
Alvar, Amin Asgharzadeh; Deevband, Mohammad Reza; Ashtiyani, Meghdad
2017-07-26
Neutron energy spectrum unfolding has been the subject of research for several years. The Bayesian theory, Monte Carlo simulation, and iterative methods are some of the methods that have been used for neutron spectrum unfolding. In this study, the radial basis function (RBF), multilayer perceptron, and artificial neural networks (ANNs) were used for the unfolding of neutron spectrum, and a comparison was made between the networks' results. Both neural network architectures were trained and tested using the same data set for neutron spectrum unfolding from the response of LiI detectors with Eu impurity. Advantages of each ANN method in the unfolding of neutron energy spectrum were investigated, and the performance of the networks was compared. The results obtained showed that RBF neural network can be applied as an effective method for unfolding neutron spectrum, especially when the main target is the neutron dosimetry. Copyright © 2017 Elsevier Ltd. All rights reserved.
Ideomotor feedback control in a recurrent neural network.
Galtier, Mathieu
2015-06-01
The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and action are simultaneously read and fed back. There are two concurrent learning rules implementing a sort of ideomotor control: (i) perception is learned along the principle that the network should predict reliably its incoming stimuli; (ii) action is learned along the principle that the prediction of the network should match a target time series. The coherent behavior of the neural network in its environment is a consequence of the interaction between the two principles. Numerical simulations show a promising performance of the approach, which can be turned into a local and better "biologically plausible" algorithm.
Efficient Training of Recurrent Neural Network with Time Delays.
Marom, Emanuel; Saad, David; Cohen, Barak
1997-01-01
Training recurrent neural networks to perform certain tasks is known to be difficult. The possibility of adding synaptic delays to the network properties makes the training task more difficult. However, the disadvantage of tough training procedure is diminished by the improved network performance. During our research of training neural networks with time delays we encountered a robust method for accomplishing the training task. The method is based on adaptive simulated annealing algorithm (ASA) which was found to be superior to other training algorithms. It requires no tuning and is fast enough to enable training to be held on low end platforms such as personal computers. The implementation of the algorithm is presented over a set of typical benchmark tests of training recurrent neural networks with time delays. Copyright 1996 Elsevier Science Ltd.
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.
Deterministic chaos control in neural networks on various topologies
NASA Astrophysics Data System (ADS)
Neto, A. J. F.; Lima, F. W. S.
2017-01-01
Using numerical simulations, we study the control of deterministic chaos in neural networks on various topologies like Voronoi-Delaunay, Barabási-Albert, Small-World networks and Erdös-Rényi random graphs by "pinning" the state of a "special" neuron. We show that the chaotic activity of the networks or graphs, when control is on, can become constant or periodic.
Artificial neural network for multifunctional areas.
Riccioli, Francesco; El Asmar, Toufic; El Asmar, Jean-Pierre; Fagarazzi, Claudio; Casini, Leonardo
2016-01-01
The issues related to the appropriate planning of the territory are particularly pronounced in highly inhabited areas (urban areas), where in addition to protecting the environment, it is important to consider an anthropogenic (urban) development placed in the context of sustainable growth. This work aims at mathematically simulating the changes in the land use, by implementing an artificial neural network (ANN) model. More specifically, it will analyze how the increase of urban areas will develop and whether this development would impact on areas with particular socioeconomic and environmental value, defined as multifunctional areas. The simulation is applied to the Chianti Area, located in the province of Florence, in Italy. Chianti is an area with a unique landscape, and its territorial planning requires a careful examination of the territory in which it is inserted.
Šiljić, Aleksandra; Antanasijević, Davor; Perić-Grujić, Aleksandra; Ristić, Mirjana; Pocajt, Viktor
2015-03-01
Biological oxygen demand (BOD) is the most significant water quality parameter and indicates water pollution with respect to the present biodegradable organic matter content. European countries are therefore obliged to report annual BOD values to Eurostat; however, BOD data at the national level is only available for 28 of 35 listed European countries for the period prior to 2008, among which 46% of data is missing. This paper describes the development of an artificial neural network model for the forecasting of annual BOD values at the national level, using widely available sustainability and economical/industrial parameters as inputs. The initial general regression neural network (GRNN) model was trained, validated and tested utilizing 20 inputs. The number of inputs was reduced to 15 using the Monte Carlo simulation technique as the input selection method. The best results were achieved with the GRNN model utilizing 25% less inputs than the initial model and a comparison with a multiple linear regression model trained and tested using the same input variables using multiple statistical performance indicators confirmed the advantage of the GRNN model. Sensitivity analysis has shown that inputs with the greatest effect on the GRNN model were (in descending order) precipitation, rural population with access to improved water sources, treatment capacity of wastewater treatment plants (urban) and treatment of municipal waste, with the last two having an equal effect. Finally, it was concluded that the developed GRNN model can be useful as a tool to support the decision-making process on sustainable development at a regional, national and international level.
Adaptive Neural Network Based Control of Noncanonical Nonlinear Systems.
Zhang, Yanjun; Tao, Gang; Chen, Mou
2016-09-01
This paper presents a new study on the adaptive neural network-based control of a class of noncanonical nonlinear systems with large parametric uncertainties. Unlike commonly studied canonical form nonlinear systems whose neural network approximation system models have explicit relative degree structures, which can directly be used to derive parameterized controllers for adaptation, noncanonical form nonlinear systems usually do not have explicit relative degrees, and thus their approximation system models are also in noncanonical forms. It is well-known that the adaptive control of noncanonical form nonlinear systems involves the parameterization of system dynamics. As demonstrated in this paper, it is also the case for noncanonical neural network approximation system models. Effective control of such systems is an open research problem, especially in the presence of uncertain parameters. This paper shows that it is necessary to reparameterize such neural network system models for adaptive control design, and that such reparameterization can be realized using a relative degree formulation, a concept yet to be studied for general neural network system models. This paper then derives the parameterized controllers that guarantee closed-loop stability and asymptotic output tracking for noncanonical form neural network system models. An illustrative example is presented with the simulation results to demonstrate the control design procedure, and to verify the effectiveness of such a new design method.
Neural network chips for trigger purposes in high energy physics
Gemmeke, H.; Eppler, W.; Fischer, T.
1996-12-31
Two novel neural chips SAND (Simple Applicable Neural Device) and SIOP (Serial Input - Operating Parallel) are described. Both are highly usable for hardware triggers in particle physics. The chips are optimized for a high input data rate at a very low cost basis. The performance of a single SAND chip is 200 MOPS due to four parallel 16 bit multipliers and 40 bit adders working in one clock cycle. The chip is able to implement feedforward neural networks, Kohonen feature maps and radial basis function networks. Four chips will be implemented on a PCI-board for simulation and on a VUE board for trigger and on- and off-line analysis. For small sized feedforward neural networks the bit-serial neuro-chip SIOP may lead to even smaller latencies because each synaptic connection is implemented by its own bit serial multiplier and adder.
Coronary Artery Diagnosis Aided by Neural Network
NASA Astrophysics Data System (ADS)
Stefko, Kamil
2007-01-01
Coronary artery disease is due to atheromatous narrowing and subsequent occlusion of the coronary vessel. Application of optimised feed forward multi-layer back propagation neural network (MLBP) for detection of narrowing in coronary artery vessels is presented in this paper. The research was performed using 580 data records from traditional ECG exercise test confirmed by coronary arteriography results. Each record of training database included description of the state of a patient providing input data for the neural network. Level and slope of ST segment of a 12 lead ECG signal recorded at rest and after effort (48 floating point values) was the main component of input data for neural network was. Coronary arteriography results (verified the existence or absence of more than 50% stenosis of the particular coronary vessels) were used as a correct neural network training output pattern. More than 96% of cases were correctly recognised by especially optimised and a thoroughly verified neural network. Leave one out method was used for neural network verification so 580 data records could be used for training as well as for verification of neural network.
Acute appendicitis diagnosis using artificial neural networks.
Park, Sung Yun; Kim, Sung Min
2015-01-01
Artificial neural networks is one of pattern analyzer method which are rapidly applied on a bio-medical field. The aim of this research was to propose an appendicitis diagnosis system using artificial neural networks (ANNs). Data from 801 patients of the university hospital in Dongguk were used to construct artificial neural networks for diagnosing appendicitis and acute appendicitis. A radial basis function neural network structure (RBF), a multilayer neural network structure (MLNN), and a probabilistic neural network structure (PNN) were used for artificial neural network models. The Alvarado clinical scoring system was used for comparison with the ANNs. The accuracy of the RBF, PNN, MLNN, and Alvarado was 99.80%, 99.41%, 97.84%, and 72.19%, respectively. The area under ROC (receiver operating characteristic) curve of RBF, PNN, MLNN, and Alvarado was 0.998, 0.993, 0.985, and 0.633, respectively. The proposed models using ANNs for diagnosing appendicitis showed good performances, and were significantly better than the Alvarado clinical scoring system (p < 0.001). With cooperation among facilities, the accuracy for diagnosing this serious health condition can be improved.
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 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.
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.
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
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.
Deep Neural Networks for Identifying Cough Sounds.
Amoh, Justice; Odame, Kofi
2016-10-01
In this paper, we consider two different approaches of using deep neural networks for cough detection. The cough detection task is cast as a visual recognition problem and as a sequence-to-sequence labeling problem. A convolutional neural network and a recurrent neural network are implemented to address these problems, respectively. We evaluate the performance of the two networks and compare them to other conventional approaches for identifying cough sounds. In addition, we also explore the effect of the network size parameters and the impact of long-term signal dependencies in cough classifier performance. Experimental results show both network architectures outperform traditional methods. Between the two, our convolutional network yields a higher specificity 92.7% whereas the recurrent attains a higher sensitivity of 87.7%.
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«.
Attitude control of spacecraft using neural networks
NASA Technical Reports Server (NTRS)
Vadali, Srinivas R.; Krishnan, S.; Singh, T.
1993-01-01
This paper investigates the use of radial basis function neural networks for adaptive attitude control and momentum management of spacecraft. In the first part of the paper, neural networks are trained to learn from a family of open-loop optimal controls parameterized by the initial states and times-to-go. The trained is then used for closed-loop control. In the second part of the paper, neural networks are used for direct adaptive control in the presence of unmodeled effects and parameter uncertainty. The control and learning laws are derived using the method of Lyapunov.
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.
Neural networks in auroral data assimilation
NASA Astrophysics Data System (ADS)
Härter, Fabrício P.; de Campos Velho, Haroldo F.; Rempel, Erico L.; Chian, Abraham C.-L.
2008-07-01
Data assimilation is an essential step for improving space weather forecasting by means of a weighted combination between observational data and data from a mathematical model. In the present work data assimilation methods based on Kalman filter (KF) and artificial neural networks are applied to a three-wave model of auroral radio emissions. A novel data assimilation method is presented, whereby a multilayer perceptron neural network is trained to emulate a KF for data assimilation by using cross-validation. The results obtained render support for the use of neural networks as an assimilation technique for space weather prediction.
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.
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.
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.
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 for Signal Processing and Control
NASA Astrophysics Data System (ADS)
Hesselroth, Ted Daniel
Neural networks are developed for controlling a robot-arm and camera system and for processing images. The networks are based upon computational schemes that may be found in the brain. In the first network, a neural map algorithm is employed to control a five-joint pneumatic robot arm and gripper through feedback from two video cameras. The pneumatically driven robot arm employed shares essential mechanical characteristics with skeletal muscle systems. To control the position of the arm, 200 neurons formed a network representing the three-dimensional workspace embedded in a four-dimensional system of coordinates from the two cameras, and learned a set of pressures corresponding to the end effector positions, as well as a set of Jacobian matrices for interpolating between these positions. Because of the properties of the rubber-tube actuators of the arm, the position as a function of supplied pressure is nonlinear, nonseparable, and exhibits hysteresis. Nevertheless, through the neural network learning algorithm the position could be controlled to an accuracy of about one pixel (~3 mm) after two hundred learning steps. Applications of repeated corrections in each step via the Jacobian matrices leads to a very robust control algorithm since the Jacobians learned by the network have to satisfy the weak requirement that they yield a reduction of the distance between gripper and target. The second network is proposed as a model for the mammalian vision system in which backward connections from the primary visual cortex (V1) to the lateral geniculate nucleus play a key role. The application of hebbian learning to the forward and backward connections causes the formation of receptive fields which are sensitive to edges, bars, and spatial frequencies of preferred orientations. The receptive fields are learned in such a way as to maximize the rate of transfer of information from the LGN to V1. Orientational preferences are organized into a feature map in the primary visual
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.
Synchronization in a noise-driven developing neural network
NASA Astrophysics Data System (ADS)
Lin, I.-H.; Wu, R.-K.; Chen, C.-M.
2011-11-01
We use computer simulations to investigate the structural and dynamical properties of a developing neural network whose activity is driven by noise. Structurally, the constructed neural networks in our simulations exhibit the small-world properties that have been observed in several neural networks. The dynamical change of neuronal membrane potential is described by the Hodgkin-Huxley model, and two types of learning rules, including spike-timing-dependent plasticity (STDP) and inverse STDP, are considered to restructure the synaptic strength between neurons. Clustered synchronized firing (SF) of the network is observed when the network connectivity (number of connections/maximal connections) is about 0.75, in which the firing rate of neurons is only half of the network frequency. At the connectivity of 0.86, all neurons fire synchronously at the network frequency. The network SF frequency increases logarithmically with the culturing time of a growing network and decreases exponentially with the delay time in signal transmission. These conclusions are consistent with experimental observations. The phase diagrams of SF in a developing network are investigated for both learning rules.
A gentle introduction to artificial neural networks.
Zhang, Zhongheng
2016-10-01
Artificial neural network (ANN) is a flexible and powerful machine learning technique. However, it is under utilized in clinical medicine because of its technical challenges. The article introduces some basic ideas behind ANN and shows how to build ANN using R in a step-by-step framework. In topology and function, ANN is in analogue to the human brain. There are input and output signals transmitting from input to output nodes. Input signals are weighted before reaching output nodes according to their respective importance. Then the combined signal is processed by activation function. I simulated a simple example to illustrate how to build a simple ANN model using nnet() function. This function allows for one hidden layer with varying number of units in that layer. The basic structure of ANN can be visualized with plug-in plot.nnet() function. The plot function is powerful that it allows for varieties of adjustment to the appearance of the neural networks. Prediction with ANN can be performed with predict() function, similar to that of conventional generalized linear models. Finally, the prediction power of ANN is examined using confusion matrix and average accuracy. It appears that ANN is slightly better than conventional linear model.
Neural networks for convex hull computation.
Leung, Y; Zhang, J S; Xu, Z B
1997-01-01
Computing convex hull is one of the central problems in various applications of computational geometry. In this paper, a convex hull computing neural network (CHCNN) is developed to solve the related problems in the N-dimensional spaces. The algorithm is based on a two-layered neural network, topologically similar to ART, with a newly developed adaptive training strategy called excited learning. The CHCNN provides a parallel online and real-time processing of data which, after training, yields two closely related approximations, one from within and one from outside, of the desired convex hull. It is shown that accuracy of the approximate convex hulls obtained is around O[K(-1)(N-1/)], where K is the number of neurons in the output layer of the CHCNN. When K is taken to be sufficiently large, the CHCNN can generate any accurate approximate convex hull. We also show that an upper bound exists such that the CHCNN will yield the precise convex hull when K is larger than or equal to this bound. A series of simulations and applications is provided to demonstrate the feasibility, effectiveness, and high efficiency of the proposed algorithm.
A neural network model of harmonic detection
NASA Astrophysics Data System (ADS)
Lewis, Clifford F.
2003-04-01
Harmonic detection theories postulate that a virtual pitch is perceived when a sufficient number of harmonics is present. The harmonics need not be consecutive, but higher harmonics contribute less than lower harmonics [J. Raatgever and F. A. Bilsen, in Auditory Physiology and Perception, edited by Y. Cazals, K. Horner, and L. Demany (Pergamon, Oxford, 1992), pp. 215-222 M. K. McBeath and J. F. Wayand, Abstracts of the Psychonom. Soc. 3, 55 (1998)]. A neural network model is presented that has the potential to simulate this operation. Harmonics are first passed through a bank of rounded exponential filters with lateral inhibition. The results are used as inputs for an autoassociator neural network. The model is trained using harmonic data for symphonic musical instruments, in order to test whether it can self-organize by learning associations between co-occurring harmonics. It is shown that the trained model can complete the pattern for missing-fundamental sounds. The Performance of the model in harmonic detection will be compared with experimental results for humans.
An artificial neural network controller for intelligent transportation systems applications
Vitela, J.E.; Hanebutte, U.R.; Reifman, J.
1996-04-01
An Autonomous Intelligent Cruise Control (AICC) has been designed using a feedforward artificial neural network, as an example for utilizing artificial neural networks for nonlinear control problems arising in intelligent transportation systems applications. The AICC is based on a simple nonlinear model of the vehicle dynamics. A Neural Network Controller (NNC) code developed at Argonne National Laboratory to control discrete dynamical systems was used for this purpose. In order to test the NNC, an AICC-simulator containing graphical displays was developed for a system of two vehicles driving in a single lane. Two simulation cases are shown, one involving a lead vehicle with constant velocity and the other a lead vehicle with varying acceleration. More realistic vehicle dynamic models will be considered in future work.
Gradient calculations for dynamic recurrent neural networks: a survey.
Pearlmutter, B A
1995-01-01
Surveys learning algorithms for recurrent neural networks with hidden units and puts the various techniques into a common framework. The authors discuss fixed point learning algorithms, namely recurrent backpropagation and deterministic Boltzmann machines, and nonfixed point algorithms, namely backpropagation through time, Elman's history cutoff, and Jordan's output feedback architecture. Forward propagation, an on-line technique that uses adjoint equations, and variations thereof, are also discussed. In many cases, the unified presentation leads to generalizations of various sorts. The author discusses advantages and disadvantages of temporally continuous neural networks in contrast to clocked ones continues with some "tricks of the trade" for training, using, and simulating continuous time and recurrent neural networks. The author presents some simulations, and at the end, addresses issues of computational complexity and learning speed.
A one-layer recurrent neural network for support vector machine learning.
Xia, Youshen; Wang, Jun
2004-04-01
This paper presents a one-layer recurrent neural network for support vector machine (SVM) learning in pattern classification and regression. The SVM learning problem is first converted into an equivalent formulation, and then a one-layer recurrent neural network for SVM learning is proposed. The proposed neural network is guaranteed to obtain the optimal solution of support vector classification and regression. Compared with the existing two-layer neural network for the SVM classification, the proposed neural network has a low complexity for implementation. Moreover, the proposed neural network can converge exponentially to the optimal solution of SVM learning. The rate of the exponential convergence can be made arbitrarily high by simply turning up a scaling parameter. Simulation examples based on benchmark problems are discussed to show the good performance of the proposed neural network for SVM learning.
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.
Nonequilibrium landscape theory of neural networks
Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin
2013-01-01
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. PMID:24145451
Borst, Alexander; Weber, Franz
2011-01-01
Optic flow based navigation is a fundamental way of visual course control described in many different species including man. In the fly, an essential part of optic flow analysis is performed in the lobula plate, a retinotopic map of motion in the environment. There, the so-called lobula plate tangential cells possess large receptive fields with different preferred directions in different parts of the visual field. Previous studies demonstrated an extensive connectivity between different tangential cells, providing, in principle, the structural basis for their large and complex receptive fields. We present a network simulation of the tangential cells, comprising most of the neurons studied so far (22 on each hemisphere) with all the known connectivity between them. On their dendrite, model neurons receive input from a retinotopic array of Reichardt-type motion detectors. Model neurons exhibit receptive fields much like their natural counterparts, demonstrating that the connectivity between the lobula plate tangential cells indeed can account for their complex receptive field structure. We describe the tuning of a model neuron to particular types of ego-motion (rotation as well as translation around/along a given body axis) by its ‘action field’. As we show for model neurons of the vertical system (VS-cells), each of them displays a different type of action field, i.e., responds maximally when the fly is rotating around a particular body axis. However, the tuning width of the rotational action fields is relatively broad, comparable to the one with dendritic input only. The additional intra-lobula-plate connectivity mainly reduces their translational action field amplitude, i.e., their sensitivity to translational movements along any body axis of the fly. PMID:21305019
Ndesendo, Valence M K; Pillay, Viness; Choonara, Yahya E; du Toit, Lisa C; Kumar, Pradeep; Buchmann, Eckhart; Meyer, Leith C R; Khan, Riaz A
2012-01-01
This study aimed at elucidating an optimal synergistic polymer composite for achieving a desirable molecular bioadhesivity and Matrix Erosion of a bioactive-loaded Intravaginal Bioadhesive Polymeric Device (IBPD) employing Molecular Mechanic Simulations and Artificial Neural Networks (ANN). Fifteen lead caplet-shaped devices were formulated by direct compression with the model bioactives zidovudine and polystyrene sulfonate. The Matrix Erosion was analyzed in simulated vaginal fluid to assess the critical integrity. Blueprinting the molecular mechanics of bioadhesion between vaginal epithelial glycoprotein (EGP), mucin (MUC) and the IBPD were performed on HyperChem 8.0.8 software (MM+ and AMBER force fields) for the quantification and characterization of correlative molecular interactions during molecular bioadhesion. Results proved that the IBPD bioadhesivity was pivoted on the conformation, orientation, and poly(acrylic acid) (PAA) composition that interacted with EGP and MUC present on the vaginal epithelium due to heterogeneous surface residue distributions (free energy= -46.33 kcalmol(-1)). ANN sensitivity testing as a connectionist model enabled strategic polymer selection for developing an IBPD with an optimally prolonged Matrix Erosion and superior molecular bioadhesivity (ME = 1.21-7.68%; BHN = 2.687-4.981 N/mm(2)). Molecular modeling aptly supported the EGP-MUC-PAA molecular interaction at the vaginal epithelium confirming the role of PAA in bioadhesion of the IBPD once inserted into the posterior fornix of the vagina.
Castin, N; Malerba, L
2010-02-21
In this paper we take a few steps further in the development of an approach based on the use of an artificial neural network (ANN) to introduce long-range chemical effects and zero temperature relaxation (elastic strain) effects in a rigid lattice atomistic kinetic Monte Carlo (AKMC) model. The ANN is trained to predict the vacancy migration energies as calculated given an interatomic potential with the nudged elastic band method, as functions of the local atomic environment. The kinetics of a single-vacancy migration is thus predicted as accurately as possible, within the limits of the given interatomic potential. The detailed procedure to apply this method is described and analyzed in detail. A novel ANN training algorithm is proposed to deal with the necessarily large number of input variables to be taken into account in the mathematical regression of the migration energies. The application of the ANN-based AKMC method to the simulation of a thermal annealing experiment in Fe-20%Cr alloy is reported. The results obtained are found to be in better agreement with experiments, as compared to already published simulations, where no atomic relaxation was taken into account and chemical effects were only heuristically allowed for.
McCreddin, A; Alam, M S; McNabola, A
2015-01-01
An experimental assessment of personal exposure to PM10 in 59 office workers was carried out in Dublin, Ireland. 255 samples of 24-h personal exposure were collected in real time over a 28 month period. A series of modelling techniques were subsequently assessed for their ability to predict 24-h personal exposure to PM10. Artificial neural network modelling, Monte Carlo simulation and time-activity based models were developed and compared. The results of the investigation showed that using the Monte Carlo technique to randomly select concentrations from statistical distributions of exposure concentrations in typical microenvironments encountered by office workers produced the most accurate results, based on 3 statistical measures of model performance. The Monte Carlo simulation technique was also shown to have the greatest potential utility over the other techniques, in terms of predicting personal exposure without the need for further monitoring data. Over the 28 month period only a very weak correlation was found between background air quality and personal exposure measurements, highlighting the need for accurate models of personal exposure in epidemiological studies.
Simulation of an array-based neural net model
NASA Technical Reports Server (NTRS)
Barnden, John A.
1987-01-01
Research in cognitive science suggests that much of cognition involves the rapid manipulation of complex data structures. However, it is very unclear how this could be realized in neural networks or connectionist systems. A core question is: how could the interconnectivity of items in an abstract-level data structure be neurally encoded? The answer appeals mainly to positional relationships between activity patterns within neural arrays, rather than directly to neural connections in the traditional way. The new method was initially devised to account for abstract symbolic data structures, but it also supports cognitively useful spatial analogue, image-like representations. As the neural model is based on massive, uniform, parallel computations over 2D arrays, the massively parallel processor is a convenient tool for simulation work, although there are complications in using the machine to the fullest advantage. An MPP Pascal simulation program for a small pilot version of the model is running.
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.
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.
Vein matching using artificial neural network in vein authentication systems
NASA Astrophysics Data System (ADS)
Noori Hoshyar, Azadeh; Sulaiman, Riza
2011-10-01
Personal identification technology as security systems is developing rapidly. Traditional authentication modes like key; password; card are not safe enough because they could be stolen or easily forgotten. Biometric as developed technology has been applied to a wide range of systems. According to different researchers, vein biometric is a good candidate among other biometric traits such as fingerprint, hand geometry, voice, DNA and etc for authentication systems. Vein authentication systems can be designed by different methodologies. All the methodologies consist of matching stage which is too important for final verification of the system. Neural Network is an effective methodology for matching and recognizing individuals in authentication systems. Therefore, this paper explains and implements the Neural Network methodology for finger vein authentication system. Neural Network is trained in Matlab to match the vein features of authentication system. The Network simulation shows the quality of matching as 95% which is a good performance for authentication system matching.
Sensor failure detection and recovery by neural networks
NASA Technical Reports Server (NTRS)
Guo, Ten-Huei; Nurre, J.
1991-01-01
A new method of sensor failure detection, isolation, and accommodation is described using a neural network approach. In a propulsion system such as the Space Shuttle Main Engine, the dynamics are usually much higher than the order of the system. This built-in redundancy of the sensors can be utilized to detect and correct sensor failure problems. The goal of the proposed scheme is to train a neural network to identify the sensor whose measurement is not consistent with other sensor outputs. Another neural network is trained to recover the value of critical variables when their measurements fail. Techniques for training the network with a limited amount of data are developed. The proposed scheme is tested using the simulated data of the Space Shuttle Main Engine (SSME) inflight sensor group.
Speech transmission index from running speech: A neural network approach
NASA Astrophysics Data System (ADS)
Li, F. F.; Cox, T. J.
2003-04-01
Speech transmission index (STI) is an important objective parameter concerning speech intelligibility for sound transmission channels. It is normally measured with specific test signals to ensure high accuracy and good repeatability. Measurement with running speech was previously proposed, but accuracy is compromised and hence applications limited. A new approach that uses artificial neural networks to accurately extract the STI from received running speech is developed in this paper. Neural networks are trained on a large set of transmitted speech examples with prior knowledge of the transmission channels' STIs. The networks perform complicated nonlinear function mappings and spectral feature memorization to enable accurate objective parameter extraction from transmitted speech. Validations via simulations demonstrate the feasibility of this new method on a one-net-one-speech extract basis. In this case, accuracy is comparable with normal measurement methods. This provides an alternative to standard measurement techniques, and it is intended that the neural network method can facilitate occupied room acoustic measurements.
Decision-making differences: novices, experts, and a neural network
NASA Astrophysics Data System (ADS)
Manning, David; Bunting, Sam; Leach, John
2000-04-01
We investigated the decision making performance of trained radiographers, novice radiographers and a neural network in the detection of fractures. Ground truth was established by the independent agreement of experienced radiologists for 740 single view digitized radiographs of the wrist. The images were categorized into negatives and positives; 520 of these were used to train the back propagation, three layer neural network in a supervised mode, and the remainder were used to create a test bank. The test was presented to 20 novice observers, 12 experienced radiographers trained in the detection of skeletal trauma and then to the trained neural network. ROC Az values for all the decision makers were not significantly different (p > 0.1) but there were significant differences in the values of True Positive and True Negative Fractions. The neural network showed a greater aptitude for distinguishing the normals. By filtering the neural net decisions through the human data we simulated the effect of assisted reporting. Results suggest that if fracture prevalence is very low in a population, a neural network demonstrating high specificity may have utility in reducing the number of images which must be reviewed by human experts.
Artificial neural network modeling of dissolved oxygen in reservoir.
Chen, Wei-Bo; Liu, Wen-Cheng
2014-02-01
The water quality of reservoirs is one of the key factors in the operation and water quality management of reservoirs. Dissolved oxygen (DO) in water column is essential for microorganisms and a significant indicator of the state of aquatic ecosystems. In this study, two artificial neural network (ANN) models including back propagation neural network (BPNN) and adaptive neural-based fuzzy inference system (ANFIS) approaches and multilinear regression (MLR) model were developed to estimate the DO concentration in the Feitsui Reservoir of northern Taiwan. The input variables of the neural network are determined as water temperature, pH, conductivity, turbidity, suspended solids, total hardness, total alkalinity, and ammonium nitrogen. The performance of the ANN models and MLR model was assessed through the mean absolute error, root mean square error, and correlation coefficient computed from the measured and model-simulated DO values. The results reveal that ANN estimation performances were superior to those of MLR. Comparing to the BPNN and ANFIS models through the performance criteria, the ANFIS model is better than the BPNN model for predicting the DO values. Study results show that the neural network particularly using ANFIS model is able to predict the DO concentrations with reasonable accuracy, suggesting that the neural network is a valuable tool for reservoir management in Taiwan.
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.
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…
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…
Dynamic security contingency screening and ranking using neural networks.
Mansour, Y; Vaahedi, E; El-Sharkawi, M A
1997-01-01
This paper summarizes BC Hydro's experience in applying neural networks to dynamic security contingency screening and ranking. The idea is to use the information on the prevailing operating condition and directly provide contingency screening and ranking using a trained neural network. To train the two neural networks for the large scale systems of BC Hydro and Hydro Quebec, in total 1691 detailed transient stability simulation were conducted, 1158 for BC Hydro system and 533 for the Hydro Quebec system. The simulation program was equipped with the energy margin calculation module (second kick) to measure the energy margin in each run. The first set of results showed poor performance for the neural networks in assessing the dynamic security. However a number of corrective measures improved the results significantly. These corrective measures included: 1) the effectiveness of output; 2) the number of outputs; 3) the type of features (static versus dynamic); 4) the number of features; 5) system partitioning; and 6) the ratio of training samples to features. The final results obtained using the large scale systems of BC Hydro and Hydro Quebec demonstrates a good potential for neural network in dynamic security assessment contingency screening and ranking.
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
Control of autonomous robot using neural networks
NASA Astrophysics Data System (ADS)
Barton, Adam; Volna, Eva
2017-07-01
The aim of the article is to design a method of control of an autonomous robot using artificial neural networks. The introductory part describes control issues from the perspective of autonomous robot navigation and the current mobile robots controlled by neural networks. The core of the article is the design of the controlling neural network, and generation and filtration of the training set using ART1 (Adaptive Resonance Theory). The outcome of the practical part is an assembled Lego Mindstorms EV3 robot solving the problem of avoiding obstacles in space. To verify models of an autonomous robot behavior, a set of experiments was created as well as evaluation criteria. The speed of each motor was adjusted by the controlling neural network with respect to the situation in which the robot was found.
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.
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.
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.
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
Firing rate dynamics in recurrent spiking neural networks with intrinsic and network heterogeneity.
Ly, Cheng
2015-12-01
Heterogeneity of neural attributes has recently gained a lot of attention and is increasing recognized as a crucial feature in neural processing. Despite its importance, this physiological feature has traditionally been neglected in theoretical studies of cortical neural networks. Thus, there is still a lot unknown about the consequences of cellular and circuit heterogeneity in spiking neural networks. In particular, combining network or synaptic heterogeneity and intrinsic heterogeneity has yet to be considered systematically despite the fact that both are known to exist and likely have significant roles in neural network dynamics. In a canonical recurrent spiking neural network model, we study how these two forms of heterogeneity lead to different distributions of excitatory firing rates. To analytically characterize how these types of heterogeneities affect the network, we employ a dimension reduction method that relies on a combination of Monte Carlo simulations and probability density function equations. We find that the relationship between intrinsic and network heterogeneity has a strong effect on the overall level of heterogeneity of the firing rates. Specifically, this relationship can lead to amplification or attenuation of firing rate heterogeneity, and these effects depend on whether the recurrent network is firing asynchronously or rhythmically firing. These observations are captured with the aforementioned reduction method, and furthermore simpler analytic descriptions based on this dimension reduction method are developed. The final analytic descriptions provide compact and descriptive formulas for how the relationship between intrinsic and network heterogeneity determines the firing rate heterogeneity dynamics in various settings.
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.
Tensor-Factorized Neural Networks.
Chien, Jen-Tzung; Bao, Yi-Ting
2017-04-17
The growing interests in multiway data analysis and deep learning have drawn tensor factorization (TF) and neural network (NN) as the crucial topics. Conventionally, the NN model is estimated from a set of one-way observations. Such a vectorized NN is not generalized for learning the representation from multiway observations. The classification performance using vectorized NN is constrained, because the temporal or spatial information in neighboring ways is disregarded. More parameters are required to learn the complicated data structure. This paper presents a new tensor-factorized NN (TFNN), which tightly integrates TF and NN for multiway feature extraction and classification under a unified discriminative objective. This TFNN is seen as a generalized NN, where the affine transformation in an NN is replaced by the multilinear and multiway factorization for tensor-based NN. The multiway information is preserved through layerwise factorization. Tucker decomposition and nonlinear activation are performed in each hidden layer. The tensor-factorized error backpropagation is developed to train TFNN with the limited parameter size and computation time. This TFNN can be further extended to realize the convolutional TFNN (CTFNN) by looking at small subtensors through the factorized convolution. Experiments on real-world classification tasks demonstrate that TFNN and CTFNN attain substantial improvement when compared with an NN and a convolutional NN, respectively.
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.
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.
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
Cellular neuron and large wireless neural network
NASA Astrophysics Data System (ADS)
Jannson, Tomasz; Forrester, Thomas; Ambrose, Barry; Kazantzidis, Matheos; Lin, Freddie
2006-05-01
A new approach to neural networks is proposed, based on wireless interconnects (synapses) and cellular neurons, both software and hardware; with the capacity of 10 10 neurons, almost fully connected. The core of the system is Spatio-Temporal-Variant (STV) kernel and cellular axon with synaptic plasticity variable in time and space. The novel large neural network hardware is based on two established wireless technologies: RF-cellular and IR-wireless.