Simple Deterministically Constructed Recurrent Neural Networks
NASA Astrophysics Data System (ADS)
Rodan, Ali; Tiňo, Peter
A large number of models for time series processing, forecasting or modeling follows a state-space formulation. Models in the specific class of state-space approaches, referred to as Reservoir Computing, fix their state-transition function. The state space with the associated state transition structure forms a reservoir, which is supposed to be sufficiently complex so as to capture a large number of features of the input stream that can be potentially exploited by the reservoir-to-output readout mapping. The largely "black box" character of reservoirs prevents us from performing a deeper theoretical investigation of the dynamical properties of successful reservoirs. Reservoir construction is largely driven by a series of (more-or-less) ad-hoc randomized model building stages, with both the researchers and practitioners having to rely on a series of trials and errors. We show that a very simple deterministically constructed reservoir with simple cycle topology gives performances comparable to those of the Echo State Network (ESN) on a number of time series benchmarks. Moreover, we argue that the memory capacity of such a model can be made arbitrarily close to the proved theoretical limit.
A simple chaotic neuron model: stochastic behavior of neural networks.
Aydiner, Ekrem; Vural, Adil M; Ozcelik, Bekir; Kiymac, Kerim; Tan, Uner
2003-05-01
We have briefly reviewed the occurrence of the post-synaptic potentials between neurons, the relationship between EEG and neuron dynamics, as well as methods of signal analysis. We propose a simple stochastic model representing electrical activity of neuronal systems. The model is constructed using the Monte Carlo simulation technique. The results yielded EEG-like signals with their phase portraits in three-dimensional space. The Lyapunov exponent was positive, indicating chaotic behavior. The correlation of the EEG-like signals was.92, smaller than those reported by others. It was concluded that this neuron model may provide valuable clues about the dynamic behavior of neural systems. PMID:12745622
A simple neural network scheduler for real-time machine task scheduling
Gritzo, R.E.
1992-06-01
The recent development of a new generation of automated radionuclide assay equipment in our facility requires embedded software at each machine for the scheduling of sample assay tasks. The execution time requirements of real-time embedded software limit the complexity of the schedular software. By representing the scheduling problem properly, a simple backpropagation neural network performs the scheduling function within the imposed requirements. Operational tests have demonstrated that the neural network schedular has met all development goals and is superior to the previous approaches. This paper describes the design and development of the neural network task scheduler. In addition, several aspects of the practical application of neural networks to real-world problems are discussed.
A simple neural network scheduler for real-time machine task scheduling
Gritzo, R.E.
1992-01-01
The recent development of a new generation of automated radionuclide assay equipment in our facility requires embedded software at each machine for the scheduling of sample assay tasks. The execution time requirements of real-time embedded software limit the complexity of the schedular software. By representing the scheduling problem properly, a simple backpropagation neural network performs the scheduling function within the imposed requirements. Operational tests have demonstrated that the neural network schedular has met all development goals and is superior to the previous approaches. This paper describes the design and development of the neural network task scheduler. In addition, several aspects of the practical application of neural networks to real-world problems are discussed.
A simple neural network scheduler for real-time machine task scheduling
Gritzo, R.E.
1991-01-01
The recent development of a new generation of automated radionuclide assay equipment in our facility requires embedded software at each machine for the scheduling of tasks. The execution time requirements of real-time embedded software limit the complexity of the scheduler design. By representing the scheduling problem properly, a simple backpropagation neural network performs the scheduling function within the imposed requirements. Operational tests have demonstrated that the neural network scheduler has met all development goals and is superior to the previous approaches. 3 refs., 1 tab.
Simple models for excitable and oscillatory neural networks.
Taylor, D; Holmes, P
1998-11-01
Chains of coupled oscillators of simple "rotator" type have been used to model the central pattern generator (CPG) for locomotion in lamprey, among numerous applications in biology and elsewhere. In this paper, motivated by experiments on lamprey CPG with brainstem attached, we investigate a simple oscillator model with internal structure which captures both excitable and bursting dynamics. This model, and that for the coupling functions, is inspired by the Hodgkin-Huxley equations and two-variable simplifications thereof. We analyse pairs of coupled oscillators with both excitatory and inhibitory coupling. We also study traveling wave patterns arising from chains of oscillators, including simulations of "body shapes" generated by a double chain of oscillators providing input to a kinematic musculature model of lamprey. PMID:9836466
Smith, Patrick I.
2003-09-23
information [2]. Each one of these cells acts as a simple processor. When individual cells interact with one another, the complex abilities of the brain are made possible. In neural networks, the input or data are processed by a propagation function that adds up the values of all the incoming data. The ending value is then compared with a threshold or specific value. The resulting value must exceed the activation function value in order to become output. The activation function is a mathematical function that a neuron uses to produce an output referring to its input value. [8] Figure 1 depicts this process. Neural networks usually have three components an input, a hidden, and an output. These layers create the end result of the neural network. A real world example is a child associating the word dog with a picture. The child says dog and simultaneously looks a picture of a dog. The input is the spoken word ''dog'', the hidden is the brain processing, and the output will be the category of the word dog based on the picture. This illustration describes how a neural network functions.
A simple neural network model for the determination of aquifer parameters
NASA Astrophysics Data System (ADS)
Samani, N.; Gohari-Moghadam, M.; Safavi, A. A.
2007-06-01
SummaryA simple artificial neural network (ANN) model is developed for the determination of non-leaky confined aquifer parameters by normalizing and applying the principal component analysis (PCA) on adopted training data pattern from Lin and Chen [Lin, G.F., Chen, G.R., 2006. An improved neural network approach to the determination of aquifer parameters. Journal of Hydrology 316 (1-4), 281-289]. The proposed network uses faster Levenberg-Marquardt training algorithm instead of gradient descent. The application of PCA highly reduced the network topology so that it has only one neuron in the input layer and eight neurons in the hidden layer regardless of the number of drawdown records in the pumping test data. The network trained with 10,205 training sets and tested with 2000 sets of synthetic data. The network generates the coordinates of the match point for any individual pumping test case study and then the aquifer parameters are calculated using Theis' equation. The simple ANN trains faster and determines the coordinate of the match point more accurately because of the simplified topology and LM training algorithm. The accuracy, generalization ability and reliability of the proposed network is verified by two sets of real-time field data and the results are compared with that of Lin and Chen as well as graphical methods of aquifer parameters estimation. The proposed ANN appears to be a simpler and more accurate alternative to the type curve-matching techniques and previous ANN methods.
Song, H Francis; Yang, Guangyu R; Wang, Xiao-Jing
2016-02-01
The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs) that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, "trained" networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale's principle), which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural activity patterns
Wang, Xiao-Jing
2016-01-01
The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs) that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, “trained” networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale’s principle), which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural activity
Digital image classification with the help of artificial neural network by simple histogram
Dey, Pranab; Banerjee, Nirmalya; Kaur, Rajwant
2016-01-01
Background: Visual image classification is a great challenge to the cytopathologist in routine day-to-day work. Artificial neural network (ANN) may be helpful in this matter. Aims and Objectives: In this study, we have tried to classify digital images of malignant and benign cells in effusion cytology smear with the help of simple histogram data and ANN. Materials and Methods: A total of 404 digital images consisting of 168 benign cells and 236 malignant cells were selected for this study. The simple histogram data was extracted from these digital images and an ANN was constructed with the help of Neurointelligence software [Alyuda Neurointelligence 2.2 (577), Cupertino, California, USA]. The network architecture was 6-3-1. The images were classified as training set (281), validation set (63), and test set (60). The on-line backpropagation training algorithm was used for this study. Result: A total of 10,000 iterations were done to train the ANN system with the speed of 609.81/s. After the adequate training of this ANN model, the system was able to identify all 34 malignant cell images and 24 out of 26 benign cells. Conclusion: The ANN model can be used for the identification of the individual malignant cells with the help of simple histogram data. This study will be helpful in the future to identify malignant cells in unknown situations. PMID:27279679
Wan-Mamat, Wan Mohd Fahmi; Isa, Nor Ashidi Mat; Wahab, Habibah A; Wan-Mamat, Wan Mohd Fairuz
2009-01-01
An intelligent prediction system has been developed to discriminate drug-like and non drug-like molecules pattern. The system is constructed by using the application of advanced version of standard multilayer perceptron (MLP) neural network called Hybrid Multilayer Perceptron (HMLP) neural network and trained using Modified Recursive Prediction Error (MRPE) training algorithm. In this work, a well understood and easy excess Rule of Five + Veber filter properties are selected as the topological descriptor. The main idea behind the selection of this simple descriptor is to assure that the system could be used widely, beneficial and more advantageous regardless at all user level within a drug discovery organization. PMID:19964424
NASA Technical Reports Server (NTRS)
Fusaro, Robert L.; Jones, Steven P.; Jansen, Ralph
1996-01-01
A complete evaluation of the tribological characteristics of a given material/mechanical system is a time-consuming operation since the friction and wear process is extremely systems sensitive. As a result, experimental designs (i.e., Latin Square, Taguchi) have been implemented in an attempt to not only reduce the total number of experimental combinations needed to fully characterize a material/mechanical system, but also to acquire life data for a system without having to perform an actual life test. Unfortunately, these experimental designs still require a great deal of experimental testing and the output does not always produce meaningful information. In order to further reduce the amount of experimental testing required, this study employs a computer neural network model to investigate different material/mechanical systems. The work focuses on the modeling of the wear behavior, while showing the feasibility of using neural networks to predict life data. The model is capable of defining which input variables will influence the tribological behavior of the particular material/mechanical system being studied based on the specifications of the overall system.
Xu, Lei; Jeavons, Peter
2015-11-01
Leader election in anonymous rings and complete networks is a very practical problem in distributed computing. Previous algorithms for this problem are generally designed for a classical message passing model where complex messages are exchanged. However, the need to send and receive complex messages makes such algorithms less practical for some real applications. We present some simple synchronous algorithms for distributed leader election in anonymous rings and complete networks that are inspired by the development of the neural system of the fruit fly. Our leader election algorithms all assume that only one-bit messages are broadcast by nodes in the network and processors are only able to distinguish between silence and the arrival of one or more messages. These restrictions allow implementations to use a simpler message-passing architecture. Even with these harsh restrictions our algorithms are shown to achieve good time and message complexity both analytically and experimentally. PMID:26173905
NASA Astrophysics Data System (ADS)
Baldassi, Carlo; Ingrosso, Alessandro; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo
2015-09-01
We show that discrete synaptic weights can be efficiently used for learning in large scale neural systems, and lead to unanticipated computational performance. We focus on the representative case of learning random patterns with binary synapses in single layer networks. The standard statistical analysis shows that this problem is exponentially dominated by isolated solutions that are extremely hard to find algorithmically. Here, we introduce a novel method that allows us to find analytical evidence for the existence of subdominant and extremely dense regions of solutions. Numerical experiments confirm these findings. We also show that the dense regions are surprisingly accessible by simple learning protocols, and that these synaptic configurations are robust to perturbations and generalize better than typical solutions. These outcomes extend to synapses with multiple states and to deeper neural architectures. The large deviation measure also suggests how to design novel algorithmic schemes for optimization based on local entropy maximization.
NASA Astrophysics Data System (ADS)
Karpenka, N. V.; Feroz, F.; Hobson, M. P.
2013-02-01
A method is presented for automated photometric classification of supernovae (SNe) as Type Ia or non-Ia. A two-step approach is adopted in which (i) the SN light curve flux measurements in each observing filter are fitted separately to an analytical parametrized function that is sufficiently flexible to accommodate virtually all types of SNe and (ii) the fitted function parameters and their associated uncertainties, along with the number of flux measurements, the maximum-likelihood value of the fit and Bayesian evidence for the model, are used as the input feature vector to a classification neural network that outputs the probability that the SN under consideration is of Type Ia. The method is trained and tested using data released following the Supernova Photometric Classification Challenge (SNPCC), consisting of light curves for 20 895 SNe in total. We consider several random divisions of the data into training and testing sets: for instance, for our sample D_1 (D_4), a total of 10 (40) per cent of the data are involved in training the algorithm and the remainder used for blind testing of the resulting classifier; we make no selection cuts. Assigning a canonical threshold probability of pth = 0.5 on the network output to class an SN as Type Ia, for the sample D_1 (D_4) we obtain a completeness of 0.78 (0.82), purity of 0.77 (0.82) and SNPCC figure of merit of 0.41 (0.50). Including the SN host-galaxy redshift and its uncertainty as additional inputs to the classification network results in a modest 5-10 per cent increase in these values. We find that the quality of the classification does not vary significantly with SN redshift. Moreover, our probabilistic classification method allows one to calculate the expected completeness, purity and figure of merit (or other measures of classification quality) as a function of the threshold probability pth, without knowing the true classes of the SNe in the testing sample, as is the case in the classification of real SNe
NASA Technical Reports Server (NTRS)
Thakoor, Anil
1990-01-01
Viewgraphs on electronic neural networks for space station are presented. Topics covered include: electronic neural networks; electronic implementations; VLSI/thin film hybrid hardware for neurocomputing; computations with analog parallel processing; features of neuroprocessors; applications of neuroprocessors; neural network hardware for terrain trafficability determination; a dedicated processor for path planning; neural network system interface; neural network for robotic control; error backpropagation algorithm for learning; resource allocation matrix; global optimization neuroprocessor; and electrically programmable read only thin-film synaptic array.
NASA Technical Reports Server (NTRS)
Baram, Yoram
1992-01-01
Report presents analysis of nested neural networks, consisting of interconnected subnetworks. Analysis based on simplified mathematical models more appropriate for artificial electronic neural networks, partly applicable to biological neural networks. Nested structure allows for retrieval of individual subpatterns. Requires fewer wires and connection devices than fully connected networks, and allows for local reconstruction of damaged subnetworks without rewiring entire network.
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.
Ritter, G.X.; Sussner, P.
1996-12-31
The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.
NASA Astrophysics Data System (ADS)
Hoi, K. I.; Yuen, K. V.; Mok, K. M.
2010-05-01
In this study the neural network based air quality prediction model was tested in a typical coastal city, Macau, with Latitude 22° 10'N and Longitude 113° 34'E. By using five years of air quality and meteorological data recorded at an ambient air quality monitoring station between 2001 and 2005, it was found that the performance of the ANN model was generally improved by increasing the number of hidden neurons in the training phase. However, the performance of the ANN model was not sensitive to the change in the number of hidden neurons during the prediction phase. Therefore, the improvement in the error statistics for a complex ANN model in the training phase may be only caused by the overfitting of the data. In addition, the posterior PDF of the parameter vector conditional on the training dataset was investigated for different number of hidden neurons. It was found that the parametric space for a simple ANN model was globally identifiable and the Levenberg-Marquardt backpropagation algorithm was able to locate the optimal parameter vector. However, the parameter vector might contain redundant parameters and the parametric space was not globally identifiable when the model class became complex. In addition, the Levenberg-Marquardt backpropagation algorithm was unable to locate the most optimal parameter vector in this situation. Finally, it was concluded that the a more complex MLP model, that fits the data better, is not necessarily better than a simple one.
Dynamics and kinematics of simple neural systems
Rabinovich, M. |; Selverston, A.; Rubchinsky, L.; Huerta, R.
1996-09-01
The dynamics of simple neural systems is of interest to both biologists and physicists. One of the possible roles of such systems is the production of rhythmic patterns, and their alterations (modification of behavior, processing of sensory information, adaptation, control). In this paper, the neural systems are considered as a subject of modeling by the dynamical systems approach. In particular, we analyze how a stable, ordinary behavior of a small neural system can be described by simple finite automata models, and how more complicated dynamical systems modeling can be used. The approach is illustrated by biological and numerical examples: experiments with and numerical simulations of the stomatogastric central pattern generators network of the California spiny lobster. {copyright} {ital 1996 American Institute of Physics.}
Dynamics and kinematics of simple neural systems
NASA Astrophysics Data System (ADS)
Rabinovich, Mikhail; Selverston, Allen; Rubchinsky, Leonid; Huerta, Ramón
1996-09-01
The dynamics of simple neural systems is of interest to both biologists and physicists. One of the possible roles of such systems is the production of rhythmic patterns, and their alterations (modification of behavior, processing of sensory information, adaptation, control). In this paper, the neural systems are considered as a subject of modeling by the dynamical systems approach. In particular, we analyze how a stable, ordinary behavior of a small neural system can be described by simple finite automata models, and how more complicated dynamical systems modeling can be used. The approach is illustrated by biological and numerical examples: experiments with and numerical simulations of the stomatogastric central pattern generators network of the California spiny lobster.
Samsonovich, Alexei V.; Ascoli, Giorgio A.
2005-01-01
The goal of this work is to extend the theoretical understanding of the relationship between hippocampal spatial and memory functions to the level of neurophysiological mechanisms underlying spatial navigation and episodic memory retrieval. The proposed unifying theory describes both phenomena within a unique framework, as based on one and the same pathfinding function of the hippocampus. We propose a mechanism of reconstruction of the context of experience involving a search for a nearly shortest path in the space of remembered contexts. To analyze this concept in detail, we define a simple connectionist model consistent with available rodent and human neurophysiological data. Numerical study of the model begins with the spatial domain as a simple analogy for more complex phenomena. It is demonstrated how a nearly shortest path is quickly found in a familiar environment. We prove numerically that associative learning during sharp waves can account for the necessary properties of hippocampal place cells. Computational study of the model is extended to other cognitive paradigms, with the main focus on episodic memory retrieval. We show that the ability to find a correct path may be vital for successful retrieval. The model robustly exhibits the pathfinding capacity within a wide range of several factors, including its memory load (up to 30,000 abstract contexts), the number of episodes that become associated with potential target contexts, and the level of dynamical noise. We offer several testable critical predictions in both spatial and memory domains to validate the theory. Our results suggest that (1) the pathfinding function of the hippocampus, in addition to its associative and memory indexing functions, may be vital for retrieval of certain episodic memories, and (2) the hippocampal spatial navigation function could be a precursor of its memory function. PMID:15774943
NASA Technical Reports Server (NTRS)
Benediktsson, J. A.; Ersoy, O. K.; Swain, P. H.
1991-01-01
A neural network architecture called a consensual neural network (CNN) is proposed for the classification of data from multiple sources. Its relation to hierarchical and ensemble neural networks is discussed. CNN is based on the statistical consensus theory and uses nonlinearly transformed input data. The input data are transformed several times, and the different transformed data are applied as if they were independent inputs. The independent inputs are classified using stage neural networks and outputs from the stage networks are then weighted and combined to make a decision. Experimental results based on remote-sensing data and geographic data are given.
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.
Yoo, Tae Keun; Kim, Deok Won; Choi, Soo Beom; Oh, Ein; Park, Jee Soo
2016-01-01
Background Knee osteoarthritis (OA) is the most common joint disease of adults worldwide. Since the treatments for advanced radiographic knee OA are limited, clinicians face a significant challenge of identifying patients who are at high risk of OA in a timely and appropriate way. Therefore, we developed a simple self-assessment scoring system and an improved artificial neural network (ANN) model for knee OA. Methods The Fifth Korea National Health and Nutrition Examination Surveys (KNHANES V-1) data were used to develop a scoring system and ANN for radiographic knee OA. A logistic regression analysis was used to determine the predictors of the scoring system. The ANN was constructed using 1777 participants and validated internally on 888 participants in the KNHANES V-1. The predictors of the scoring system were selected as the inputs of the ANN. External validation was performed using 4731 participants in the Osteoarthritis Initiative (OAI). Area under the curve (AUC) of the receiver operating characteristic was calculated to compare the prediction models. Results The scoring system and ANN were built using the independent predictors including sex, age, body mass index, educational status, hypertension, moderate physical activity, and knee pain. In the internal validation, both scoring system and ANN predicted radiographic knee OA (AUC 0.73 versus 0.81, p<0.001) and symptomatic knee OA (AUC 0.88 versus 0.94, p<0.001) with good discriminative ability. In the external validation, both scoring system and ANN showed lower discriminative ability in predicting radiographic knee OA (AUC 0.62 versus 0.67, p<0.001) and symptomatic knee OA (AUC 0.70 versus 0.76, p<0.001). Conclusions The self-assessment scoring system may be useful for identifying the adults at high risk for knee OA. The performance of the scoring system is improved significantly by the ANN. We provided an ANN calculator to simply predict the knee OA risk. PMID:26859664
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 networks for aircraft control
NASA Technical Reports Server (NTRS)
Linse, Dennis
1990-01-01
Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.
Critical Branching Neural Networks
ERIC Educational Resources Information Center
Kello, Christopher T.
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…
Self-organization of neural networks
NASA Astrophysics Data System (ADS)
Clark, John W.; Winston, Jeffrey V.; Rafelski, Johann
1984-05-01
The plastic development of a neural-network model operating autonomously in discrete time is described by the temporal modification of interneuronal coupling strengths according to momentary neural activity. A simple algorithm (“brainwashing”) is found which, applied to nets with initially quasirandom connectivity, leads to model networks with properties conductive to the simulation of memory and learning phenomena.
Neural network 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.
NASA Technical Reports Server (NTRS)
Padgett, Mary L.; Desai, Utpal; Roppel, T.A.; White, Charles R.
1993-01-01
A design procedure is suggested for neural networks which accommodates the inclusion of such knowledge-based systems techniques as fuzzy logic and pairwise comparisons. The use of these procedures in the design of applications combines qualitative and quantitative factors with empirical data to yield a model with justifiable design and parameter selection procedures. The procedure is especially relevant to areas of back-propagation neural network design which are highly responsive to the use of precisely recorded expert knowledge.
Nonlinear PLS modeling using neural networks
Qin, S.J.; McAvoy, T.J.
1994-12-31
This paper discusses the embedding of neural networks into the framework of the PLS (partial least squares) modeling method resulting in a neural net PLS modeling approach. By using the universal approximation property of neural networks, the PLS modeling method is genealized to a nonlinear framework. The resulting model uses neural networks to capture the nonlinearity and keeps the PLS projection to attain robust generalization property. In this paper, the standard PLS modeling method is briefly reviewed. Then a neural net PLS (NNPLS) modeling approach is proposed which incorporates feedforward networks into the PLS modeling. A multi-input-multi-output nonlinear modeling task is decomposed into linear outer relations and simple nonlinear inner relations which are performed by a number of single-input-single-output networks. Since only a small size network is trained at one time, the over-parametrized problem of the direct neural network approach is circumvented even when the training data are very sparse. A conjugate gradient learning method is employed to train the network. It is shown that, by analyzing the NNPLS algorithm, the global NNPLS model is equivalent to a multilayer feedforward network. Finally, applications of the proposed NNPLS method are presented with comparison to the standard linear PLS method and the direct neural network approach. The proposed neural net PLS method gives better prediction results than the PLS modeling method and the direct neural network approach.
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. PMID:24808287
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.
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.
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.
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.
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.
Parallel processing neural networks
Zargham, M.
1988-09-01
A model for Neural Network which is based on a particular kind of Petri Net has been introduced. The model has been implemented in C and runs on the Sequent Balance 8000 multiprocessor, however it can be directly ported to different multiprocessor environments. The potential advantages of using Petri Nets include: (1) the overall system is often easier to understand due to the graphical and precise nature of the representation scheme, (2) the behavior of the system can be analyzed using Petri Net theory. Though, the Petri Net is an obvious choice as a basis for the model, the basic Petri Net definition is not adequate to represent the neuronal system. To eliminate certain inadequacies more information has been added to the Petri Net model. In the model, a token represents either a processor or a post synaptic potential. Progress through a particular Neural Network is thus graphically depicted in the movement of the processor tokens through the Petri Net.
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.
Uniformly sparse neural networks
NASA Astrophysics Data System (ADS)
Haghighi, Siamack
1992-07-01
Application of neural networks to problems with a large number of sensory inputs is severely limited when the processing elements (PEs) need to be fully connected. This paper presents a new network model in which a trade off between the number of connections to a node and the number of processing layers can be made. This trade off is an important issue in the VLSI implementation of neural networks. The performance and capability of a hierarchical pyramidal network architecture of limited fan-in PE layers is analyzed. Analysis of this architecture requires the development of a new learning rule, since each PE has access to limited information about the entire network input. A spatially local unsupervised training rule is developed in which each PE optimizes the fraction of its output variance contributed by input correlations, resulting in PEs behaving as adaptive local correlation detectors. It is also shown that the output of a PE optimally represents the mutual information among the inputs to that PE. Applications of the developed model in image compression and motion detection are presented.
Neural-Network Modeling Of Arc Welding
NASA Technical Reports Server (NTRS)
Anderson, Kristinn; Barnett, Robert J.; Springfield, James F.; Cook, George E.; Strauss, Alvin M.; Bjorgvinsson, Jon B.
1994-01-01
Artificial neural networks considered for use in monitoring and controlling gas/tungsten arc-welding processes. Relatively simple network, using 4 welding equipment parameters as inputs, estimates 2 critical weld-bead paramaters within 5 percent. Advantage is computational efficiency.
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.
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.
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.
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.
Kepler, T.B.
1989-01-01
After a brief introduction to the techniques and philosophy of neural network modeling by spin glass inspired system, the author investigates several properties of these discrete models for autoassociative memory. Memories are represented as patterns of neural activity; their traces are stored in a distributed manner in the matrix of synaptic coupling strengths. Recall is dynamic, an initial state containing partial information about one of the memories evolves toward that memory. Activity in each neuron creates fields at every other neuron, the sum total of which determines its activity. By averaging over the space of interaction matrices with memory constraints enforced by the choice of measure, we show that the exist universality classes defined by families of field distributions and the associated network capacities. He demonstrates the dominant role played by the field distribution in determining the size of the domains of attraction and present, in two independent ways, an expression for this size. He presents a class of convergent learning algorithms which improve upon known algorithms for producing such interaction matrices. He demonstrates that spurious states, or unexperienced memories, may be practically suppressed by the inducement of n-cycles and chaos. He investigates aspects of chaos in these systems, and then leave discrete modeling to implement the analysis of chaotic behavior on a continuous valued network realized in electronic hardware. In each section he combine analytical calculation and computer simulations.
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.
Neural network training with global optimization techniques.
Yamazaki, Akio; Ludermir, Teresa B
2003-04-01
This paper presents an approach of using Simulated Annealing and Tabu Search for the simultaneous optimization of neural network architectures and weights. The problem considered is the odor recognition in an artificial nose. Both methods have produced networks with high classification performance and low complexity. Generalization has been improved by using the backpropagation algorithm for fine tuning. The combination of simple and traditional search methods has shown to be very suitable for generating compact and efficient networks. PMID:12923920
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. PMID:11088736
Sarotti, Ariel M
2013-08-01
GIAO NMR chemical shift calculations coupled with trained artificial neural networks (ANNs) have been shown to provide a powerful strategy for simple, rapid and reliable identification of structural misassignments of organic compounds using only one set of both computational and experimental data. The geometry optimization, usually the most time-consuming step in the overall procedure, was carried out using computationally inexpensive methods (MM+, AM1 or HF/3-21G) and the NMR shielding constants at the affordable mPW1PW91/6-31G(d) level of theory. As low quality NMR prediction is typically obtained with such protocols, the decision making was foreseen as a problem of pattern recognition. Thus, given a set of statistical parameters computed after correlation between experimental and calculated chemical shifts the classification was done using the knowledge derived from trained ANNs. The training process was carried out with a set of 200 molecules chosen to provide a wide array of chemical functionalities and molecular complexity, and the results were validated with a set of 26 natural products that had been incorrectly assigned along with their 26 revised structures. The high prediction effectiveness observed makes this method a suitable test for rapid identification of structural misassignments, preventing not only the publication of wrong structures but also avoiding the consequences of such a mistake. PMID:23779148
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 network applications in telecommunications
NASA Technical Reports Server (NTRS)
Alspector, Joshua
1994-01-01
Neural network capabilities include automatic and organized handling of complex information, quick adaptation to continuously changing environments, nonlinear modeling, and parallel implementation. This viewgraph presentation presents Bellcore work on applications, learning chip computational function, learning system block diagram, neural network equalization, broadband access control, calling-card fraud detection, software reliability prediction, and conclusions.
Neural Networks for the Beginner.
ERIC Educational Resources Information Center
Snyder, Robin M.
Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…
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.
McDonnell, Mark D.; Tissera, Migel D.; Vladusich, Tony; van Schaik, André; Tapson, Jonathan
2015-01-01
Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the ‘Extreme Learning Machine’ (ELM) approach, which also enables a very rapid training time (∼ 10 minutes). Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random ‘receptive field’ sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems. PMID:26262687
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.
Deinterlacing using modular neural network
NASA Astrophysics Data System (ADS)
Woo, Dong H.; Eom, Il K.; Kim, Yoo S.
2004-05-01
Deinterlacing is the conversion process from the interlaced scan to progressive one. While many previous algorithms that are based on weighted-sum cause blurring in edge region, deinterlacing using neural network can reduce the blurring through recovering of high frequency component by learning process, and is found robust to noise. In proposed algorithm, input image is divided into edge and smooth region, and then, to each region, one neural network is assigned. Through this process, each neural network learns only patterns that are similar, therefore it makes learning more effective and estimation more accurate. But even within each region, there are various patterns such as long edge and texture in edge region. To solve this problem, modular neural network is proposed. In proposed modular neural network, two modules are combined in output node. One is for low frequency feature of local area of input image, and the other is for high frequency feature. With this structure, each modular neural network can learn different patterns with compensating for drawback of counterpart. Therefore it can adapt to various patterns within each region effectively. In simulation, the proposed algorithm shows better performance compared with conventional deinterlacing methods and single neural network method.
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.
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 snapshots"…
Neural Networks Of VLSI Components
NASA Technical Reports Server (NTRS)
Eberhardt, Silvio P.
1991-01-01
Concept for design of electronic neural network calls for assembly of very-large-scale integrated (VLSI) circuits of few standard types. Each VLSI chip, which contains both analog and digital circuitry, used in modular or "building-block" fashion by interconnecting it in any of variety of ways with other chips. Feedforward neural network in typical situation operates under control of host computer and receives inputs from, and sends outputs to, other equipment.
Correlational Neural Networks.
Chandar, Sarath; Khapra, Mitesh M; Larochelle, Hugo; Ravindran, Balaraman
2016-02-01
Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)-based approaches and autoencoder (AE)-based approaches. CCA-based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE-based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA-based approaches outperform AE-based approaches for the task of transfer learning, they are not as scalable as the latter. In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than AE and CCA with respect to its ability to learn correlated common representations. We employ CorrNet for several cross-language tasks and show that the representations learned using it perform better than the ones learned using other state-of-the-art approaches. PMID:26654210
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.
Neural network and letter recognition
Lee, Hue Yeon.
1989-01-01
Neural net architectures and learning algorithms that recognize hand written 36 alphanumeric characters are studied. The thin line input patterns written in 32 x 32 binary array are used. The system is comprised of two major components, viz. a preprocessing unit and a Recognition unit. The preprocessing unit in turn consists of three layers of neurons; the U-layer, the V-layer, and the C-layer. The functions of the U-layer is to extract local features by template matching. The correlation between the detected local features are considered. Through correlating neurons in a plane with their neighboring neurons, the V-layer would thicken the on-cells or lines that are groups of on-cells of the previous layer. These two correlations would yield some deformation tolerance and some of the rotational tolerance of the system. The C-layer then compresses data through the Gabor transform. Pattern dependent choice of center and wavelengths of Gabor filters is the cause of shift and scale tolerance of the system. Three different learning schemes had been investigated in the recognition unit, namely; the error back propagation learning with hidden units, a simple perceptron learning, and a competitive learning. Their performances were analyzed and compared. Since sometimes the network fails to distinguish between two letters that are inherently similar, additional ambiguity resolving neural nets are introduced on top of the above main neural net. The two dimensional Fourier transform is used as the preprocessing and the perceptron is used as the recognition unit of the ambiguity resolver. One hundred different person's handwriting sets are collected. Some of these are used as the training sets and the remainders are used as the test sets.
Pruning Neural Networks with Distribution Estimation Algorithms
Cantu-Paz, E
2003-01-15
This paper describes the application of four evolutionary algorithms to the pruning of neural networks used in classification problems. Besides of a simple genetic algorithm (GA), the paper considers three distribution estimation algorithms (DEAs): a compact GA, an extended compact GA, and the Bayesian Optimization Algorithm. The objective is to determine if the DEAs present advantages over the simple GA in terms of accuracy or speed in this problem. The experiments used a feed forward neural network trained with standard back propagation and public-domain and artificial data sets. The pruned networks seemed to have better or equal accuracy than the original fully-connected networks. Only in a few cases, pruning resulted in less accurate networks. We found few differences in the accuracy of the networks pruned by the four EAs, but found important differences in the execution time. The results suggest that a simple GA with a small population might be the best algorithm for pruning networks on the data sets we tested.
An introduction to neural networks: A tutorial
Walker, J.L.; Hill, E.V.K.
1994-12-31
Neural networks are a powerful set of mathematical techniques used for solving linear and nonlinear classification and prediction (function approximation) problems. Inspired by studies of the brain, these series and parallel combinations of simple functional units called artificial neurons have the ability to learn or be trained to solve very complex problems. Fundamental aspects of artificial neurons are discussed, including their activation functions, their combination into multilayer feedforward networks with hidden layers, and the use of bias neurons to reduce training time. The back propagation (of errors) paradigm for supervised training of feedforward networks is explained. Then, the architecture and mathematics of a Kohonen self organizing map for unsupervised learning are discussed. Two example problems are given. The first is for the application of a back propagation neural network to learn the correct response to an input vector using supervised training. The second is a classification problem using a self organizing map and unsupervised training.
Multiscale Modeling of Cortical Neural Networks
NASA Astrophysics Data System (ADS)
Torben-Nielsen, Benjamin; Stiefel, Klaus M.
2009-09-01
In this study, we describe efforts at modeling the electrophysiological dynamics of cortical networks in a multi-scale manner. Specifically, we describe the implementation of a network model composed of simple single-compartmental neuron models, in which a single complex multi-compartmental model of a pyramidal neuron is embedded. The network is capable of generating Δ (2 Hz, observed during deep sleep states) and γ (40 Hz, observed during wakefulness) oscillations, which are then imposed onto the multi-compartmental model, thus providing realistic, dynamic boundary conditions. We furthermore discuss the challenges and chances involved in multi-scale modeling of neural function.
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.
Dynamic Artificial Neural Networks with Affective Systems
Schuman, Catherine D.; Birdwell, J. Douglas
2013-01-01
Artificial neural networks (ANNs) are processors that are trained to perform particular tasks. We couple a computational ANN with a simulated affective system in order to explore the interaction between the two. In particular, we design a simple affective system that adjusts the threshold values in the neurons of our ANN. The aim of this paper is to demonstrate that this simple affective system can control the firing rate of the ensemble of neurons in the ANN, as well as to explore the coupling between the affective system and the processes of long term potentiation (LTP) and long term depression (LTD), and the effect of the parameters of the affective system on its performance. We apply our networks with affective systems to a simple pole balancing example and briefly discuss the effect of affective systems on network performance. PMID:24303015
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. PMID:26152990
Neural network ultrasound image analysis
NASA Astrophysics Data System (ADS)
Schneider, Alexander C.; Brown, David G.; Pastel, Mary S.
1993-09-01
Neural network based analysis of ultrasound image data was carried out on liver scans of normal subjects and those diagnosed with diffuse liver disease. In a previous study, ultrasound images from a group of normal volunteers, Gaucher's disease patients, and hepatitis patients were obtained by Garra et al., who used classical statistical methods to distinguish from among these three classes. In the present work, neural network classifiers were employed with the same image features found useful in the previous study for this task. Both standard backpropagation neural networks and a recently developed biologically-inspired network called Dystal were used. Classification performance as measured by the area under a receiver operating characteristic curve was generally excellent for the back propagation networks and was roughly comparable to that of classical statistical discriminators tested on the same data set and documented in the earlier study. Performance of the Dystal network was significantly inferior; however, this may be due to the choice of network parameter. Potential methods for enhancing network performance was identified.
Negative transfer problem in neural networks
NASA Astrophysics Data System (ADS)
Abunawass, Adel M.
1992-07-01
Harlow, 1949, observed that when human subjects were trained to perform simple discrimination tasks over a sequence of successive training sessions (trials), their performance improved as a function of the successive sessions. Harlow called this phenomena `learning-to- learn.' The subjects acquired knowledge and improved their ability to learn in future training sessions. It seems that previous training sessions contribute positively to the current one. Abunawass & Maki, 1989, observed that when a neural network (using the back-propagation model) is trained over successive sessions, the performance and learning ability of the network degrade as a function of the training sessions. In some cases this leads to a complete paralysis of the network. Abunawass & Maki called this phenomena the `negative transfer' problem, since previous training sessions contribute negatively to the current one. The effect of the negative transfer problem is in clear contradiction to that reported by Harlow on human subjects. Since the ability to model human cognition and learning is one of the most important goals (and claims) of neural networks, the negative transfer problem represents a clear limitation to this ability. This paper describes a new neural network sequential learning model known as Adaptive Memory Consolidation. In this model the network uses its past learning experience to enhance its future learning ability. Adaptive Memory Consolidation has led to the elimination and reversal of the effect of the negative transfer problem. Thus producing a `positive transfer' effect similar to Harlow's learning-to-learn phenomena.
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.
Centroid calculation using neural networks
NASA Astrophysics Data System (ADS)
Himes, Glenn S.; Inigo, Rafael M.
1992-01-01
Centroid calculation provides a means of eliminating translation problems, which is useful for automatic target recognition. a neural network implementation of centroid calculation is described that used a spatial filter and a Hopfield network to determine the centroid location of an object. spatial filtering of a segmented window creates a result whose peak vale occurs at the centroid of the input data set. A Hopfield network then finds the location of this peak and hence gives the location of the centroid. Hardware implementations of the networks are described and simulation results are provided.
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.
Parameter extraction with neural networks
NASA Astrophysics Data System (ADS)
Cazzanti, Luca; Khan, Mumit; Cerrina, Franco
1998-06-01
In semiconductor processing, the modeling of the process is becoming more and more important. While the ultimate goal is that of developing a set of tools for designing a complete process (Technology CAD), it is also necessary to have modules to simulate the various technologies and, in particular, to optimize specific steps. This need is particularly acute in lithography, where the continuous decrease in CD forces the technologies to operate near their limits. In the development of a 'model' for a physical process, we face several levels of challenges. First, it is necessary to develop a 'physical model,' i.e. a rational description of the process itself on the basis of know physical laws. Second, we need an 'algorithmic model' to represent in a virtual environment the behavior of the 'physical model.' After a 'complete' model has been developed and verified, it becomes possible to do performance analysis. In many cases the input parameters are poorly known or not accessible directly to experiment. It would be extremely useful to obtain the values of these 'hidden' parameters from experimental results by comparing model to data. This is particularly severe, because the complexity and costs associated with semiconductor processing make a simple 'trial-and-error' approach infeasible and cost- inefficient. Even when computer models of the process already exists, obtaining data through simulations may be time consuming. Neural networks (NN) are powerful computational tools to predict the behavior of a system from an existing data set. They are able to adaptively 'learn' input/output mappings and to act as universal function approximators. In this paper we use artificial neural networks to build a mapping from the input parameters of the process to output parameters which are indicative of the performance of the process. Once the NN has been 'trained,' it is also possible to observe the process 'in reverse,' and to extract the values of the inputs which yield outputs
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.
Investigation of efficient features for image recognition by neural networks.
Goltsev, Alexander; Gritsenko, Vladimir
2012-04-01
In the paper, effective and simple features for image recognition (named LiRA-features) are investigated in the task of handwritten digit recognition. Two neural network classifiers are considered-a modified 3-layer perceptron LiRA and a modular assembly neural network. A method of feature selection is proposed that analyses connection weights formed in the preliminary learning process of a neural network classifier. In the experiments using the MNIST database of handwritten digits, the feature selection procedure allows reduction of feature number (from 60 000 to 7000) preserving comparable recognition capability while accelerating computations. Experimental comparison between the LiRA perceptron and the modular assembly neural network is accomplished, which shows that recognition capability of the modular assembly neural network is somewhat better. PMID:22391231
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.
Neural networks for handwriting recognition
NASA Astrophysics Data System (ADS)
Kelly, David A.
1992-09-01
The market for a product that can read handwritten forms, such as insurance applications, re- order forms, or checks, is enormous. Companies could save millions of dollars each year if they had an effective and efficient way to read handwritten forms into a computer without human intervention. Urged on by the potential gold mine that an adequate solution would yield, a number of companies and researchers have developed, and are developing, neural network-based solutions to this long-standing problem. This paper briefly outlines the current state-of-the-art in neural network-based handwriting recognition research and products. The first section of the paper examines the potential market for this technology. The next section outlines the steps in the recognition process, followed by a number of the basic issues that need to be dealt with to solve the recognition problem in a real-world setting. Next, an overview of current commercial solutions and research projects shows the different ways that neural networks are applied to the problem. This is followed by a breakdown of the current commercial market and the future outlook for neural network-based handwriting recognition technology.
FPGA-based artificial neural network using CORDIC modules
NASA Astrophysics Data System (ADS)
Liddicoat, Albert A.; Slivovsky, Lynne A.; McLenegan, Tim; Heyer, Don
2006-08-01
Artificial neural networks have been used in applications that require complex procedural algorithms and in systems which lack an analytical mathematic model. By designing a large network of computing nodes based on the artificial neuron model, new solutions can be developed for computational problems in fields such as image processing and speech recognition. Neural networks are inherently parallel since each neuron, or node, acts as an autonomous computational element. Artificial neural networks use a mathematical model for each node that processes information from other nodes in the same region. The information processing entails computing a weighted average computation followed by a nonlinear mathematical transformation. Some typical artificial neural network applications use the exponential function or trigonometric functions for the nonlinear transformation. Various simple artificial neural networks have been implemented using a processor to compute the output for each node sequentially. This approach uses sequential processing and does not take advantage of the parallelism of a complex artificial neural network. In this work a hardware-based approach is investigated for artificial neural network applications. A Field Programmable Gate Arrays (FPGAs) is used to implement an artificial neuron using hardware multipliers, adders and CORDIC functional units. In order to create a large scale artificial neural network, area efficient hardware units such as CORDIC units are needed. High performance and low cost bit serial CORDIC implementations are presented. Finally, the FPGA resources and the performance of a hardware-based artificial neuron are presented.
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.
Image texture segmentation using a neural network
NASA Astrophysics Data System (ADS)
Sayeh, Mohammed R.; Athinarayanan, Ragu; Dhali, Pushpuak
1992-09-01
In this paper we use a neural network called the Lyapunov associative memory (LYAM) system to segment image texture into different categories or clusters. The LYAM system is constructed by a set of ordinary differential equations which are simulated on a digital computer. The clustering can be achieved by using a single tuning parameter in the simplest model. Pattern classes are represented by the stable equilibrium states of the system. Design of the system is based on synthesizing two local energy functions, namely, the learning and recall energy functions. Before the implementation of the segmentation process, a Gauss-Markov random field (GMRF) model is applied to the raw image. This application suitably reduces the image data and prepares the texture information for the neural network process. We give a simple image example illustrating the capability of the technique. The GMRF-generated features are also used for a clustering, based on the Euclidean distance.
Training neural networks with heterogeneous data.
Drakopoulos, John A; Abdulkader, Ahmad
2005-01-01
Data pruning and ordered training are two methods and the results of a small theory that attempts to formalize neural network training with heterogeneous data. Data pruning is a simple process that attempts to remove noisy data. Ordered training is a more complex method that partitions the data into a number of categories and assigns training times to those assuming that data size and training time have a polynomial relation. Both methods derive from a set of premises that form the 'axiomatic' basis of our theory. Both methods have been applied to a time-delay neural network-which is one of the main learners in Microsoft's Tablet PC handwriting recognition system. Their effect is presented in this paper along with a rough estimate of their effect on the overall multi-learner system. The handwriting data and the chosen language are Italian. PMID:16095874
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.
Overview of artificial neural networks.
Zou, Jinming; Han, Yi; So, Sung-Sau
2008-01-01
The artificial neural network (ANN), or simply neural network, is a machine learning method evolved from the idea of simulating the human brain. The data explosion in modem drug discovery research requires sophisticated analysis methods to uncover the hidden causal relationships between single or multiple responses and a large set of properties. The ANN is one of many versatile tools to meet the demand in drug discovery modeling. Compared to a traditional regression approach, the ANN is capable of modeling complex nonlinear relationships. The ANN also has excellent fault tolerance and is fast and highly scalable with parallel processing. This chapter introduces the background of ANN development and outlines the basic concepts crucially important for understanding more sophisticated ANN. Several commonly used learning methods and network setups are discussed briefly at the end of the chapter. PMID:19065803
Neural Networks For Visual Telephony
NASA Astrophysics Data System (ADS)
Gottlieb, A. M.; Alspector, J.; Huang, P.; Hsing, T. R.
1988-10-01
By considering how an image is processed by the eye and brain, we may find ways to simplify the task of transmitting complex video images over a telecommunication channel. Just as the retina and visual cortex reduce the amount of information sent to other areas of the brain, electronic systems can be designed to compress visual data, encode features, and adapt to new scenes for video transmission. In this talk, we describe a system inspired by models of neural computation that may, in the future, augment standard digital processing techniques for image compression. In the next few years it is expected that a compact low-cost full motion video telephone operating over an ISDN basic access line (144 KBits/sec) will be shown to be feasible. These systems will likely be based on a standard digital signal processing approach. In this talk, we discuss an alternative method that does not use standard digital signal processing but instead uses eletronic neural networks to realize the large compression necessary for a low bit-rate video telephone. This neural network approach is not being advocated as a near term solution for visual telephony. However, low bit rate visual telephony is an area where neural network technology may, in the future, find a significant application.
Validation and regulation of medical neural networks.
Rodvold, D M
2001-01-01
Using artificial neural networks (ANNs) in medical applications can be challenging because of the often-experimental nature of ANN construction and the "black box" label that is frequently attached to them. In the US, medical neural networks are regulated by the Food and Drug Administration. This article briefly discusses the documented FDA policy on neural networks and the various levels of formal acceptance that neural network development groups might pursue. To assist medical neural network developers in creating robust and verifiable software, this paper provides a development process model targeted specifically to ANNs for critical applications. PMID:11790274
Cost estimation of timber bridges using neural networks
Creese, R.C.; Li. L.
1995-05-01
Neural network models, or more simply {open_quotes}neural nets,{close_quotes} have great potential application in speech and image recognition. They also have great potential for cost estimating. Neural networks are particularly effective for complex estimation where the relationship between the output and the input cannot be expressed by simple mathematic relationships. A neural network method was applied to the cost estimation of timber bridges to illustrate the technique. The results of the neural network method were evaluated by the coefficient of determination, The R square value for the key input variables. A comparison of the neural network results and the standard linear regression results was performed upon the timber bridge data. A step-by-step validation is presented to make it easy to understand the application of neural networks to this estimation process. The input is propagated from the input through each layer until an output is generated. The output is compared with the desired output and the error is distributed for each node in the outer layer. The error is transmitted backward (thus the phase {open_quotes}back propagation{close_quotes}) from the output layer to the intermediate layers and then to the input layer. Based upon the errors, the weights are adjusted and the procedure is repeated. The number of training cycles is 15,000 to 50,000 for simple networks, but this usually takes only a few minutes on a personal computer. 7 refs., 4 figs., 11 tabs.
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.
Analysis of IMS spectra using neural networks
Bell, S.E.
1992-09-01
Ion mobility spectrometry (IMS) has been used for over 20 years, and IMS coupled to gas chromatography (GC/IMS) has been used for over 10 years. There still is no systematic approach to IMS spectral interpretation such as exists for mass spectrometry and infrared spectrometry. Neural networks, a form of adaptive pattern recognition, were examined as a method of data reduction for IMS and GC/IMS. A wide variety of volatile organics were analyzed using IMS and GC/IMS and submitted to different networks for identification. Several different networks and data preprocessing algorithms were studied. A network was linked to a simple rule-based expert system and analyzed. The expert system was used to filter out false positive identifications made by the network using retention indices. The various network configurations were compared to other pattern recognition techniques, including human experts. The network performance was comparable to human experts, but responded much faster. Preliminary comparison of the network to other pattern recognition showed comparable performance. Linkage of the network output to the rule-based retention index system yielded the best performance.
Analysis of IMS spectra using neural networks
Bell, S.E.
1992-01-01
Ion mobility spectrometry (IMS) has been used for over 20 years, and IMS coupled to gas chromatography (GC/IMS) has been used for over 10 years. There still is no systematic approach to IMS spectral interpretation such as exists for mass spectrometry and infrared spectrometry. Neural networks, a form of adaptive pattern recognition, were examined as a method of data reduction for IMS and GC/IMS. A wide variety of volatile organics were analyzed using IMS and GC/IMS and submitted to different networks for identification. Several different networks and data preprocessing algorithms were studied. A network was linked to a simple rule-based expert system and analyzed. The expert system was used to filter out false positive identifications made by the network using retention indices. The various network configurations were compared to other pattern recognition techniques, including human experts. The network performance was comparable to human experts, but responded much faster. Preliminary comparison of the network to other pattern recognition showed comparable performance. Linkage of the network output to the rule-based retention index system yielded the best performance.
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.
The hysteretic Hopfield neural network.
Bharitkar, S; Mendel, J M
2000-01-01
A new neuron activation function based on a property found in physical systems--hysteresis--is proposed. We incorporate this neuron activation in a fully connected dynamical system to form the hysteretic Hopfield neural network (HHNN). We then present an analog implementation of this architecture and its associated dynamical equation and energy function.We proceed to prove Lyapunov stability for this new model, and then solve a combinatorial optimization problem (i.e., the N-queen problem) using this network. We demonstrate the advantages of hysteresis by showing increased frequency of convergence to a solution, when the parameters associated with the activation function are varied. PMID:18249816
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. PMID:8832491
File access prediction using neural networks.
Patra, Prashanta Kumar; Sahu, Muktikanta; Mohapatra, Subasish; Samantray, Ronak Kumar
2010-06-01
One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors. PMID:20421183
Inverse kinematics problem in robotics using neural networks
NASA Technical Reports Server (NTRS)
Choi, Benjamin B.; Lawrence, Charles
1992-01-01
In this paper, Multilayer Feedforward Networks are applied to the robot inverse kinematic problem. The networks are trained with endeffector position and joint angles. After training, performance is measured by having the network generate joint angles for arbitrary endeffector trajectories. A 3-degree-of-freedom (DOF) spatial manipulator is used for the study. It is found that neural networks provide a simple and effective way to both model the manipulator inverse kinematics and circumvent the problems associated with algorithmic solution methods.
Analog neural network-based helicopter gearbox health monitoring system.
Monsen, P T; Dzwonczyk, M; Manolakos, E S
1995-12-01
The development of a reliable helicopter gearbox health monitoring system (HMS) has been the subject of considerable research over the past 15 years. The deployment of such a system could lead to a significant saving in lives and vehicles as well as dramatically reduce the cost of helicopter maintenance. Recent research results indicate that a neural network-based system could provide a viable solution to the problem. This paper presents two neural network-based realizations of an HMS system. A hybrid (digital/analog) neural system is proposed as an extremely accurate off-line monitoring tool used to reduce helicopter gearbox maintenance costs. In addition, an all analog neural network is proposed as a real-time helicopter gearbox fault monitor that can exploit the ability of an analog neural network to directly compute the discrete Fourier transform (DFT) as a sum of weighted samples. Hardware performance results are obtained using the Integrated Neural Computing Architecture (INCA/1) analog neural network platform that was designed and developed at The Charles Stark Draper Laboratory. The results indicate that it is possible to achieve a 100% fault detection rate with 0% false alarm rate by performing a DFT directly on the first layer of INCA/1 followed by a small-size two-layer feed-forward neural network and a simple post-processing majority voting stage. PMID:8550948
Load forecasting using artificial neural networks
Pham, K.D.
1995-12-31
Artificial neural networks, modeled after their biological counterpart, have been successfully applied in many diverse areas including speech and pattern recognition, remote sensing, electrical power engineering, robotics and stock market forecasting. The most commonly used neural networks are those that gained knowledge from experience. Experience is presented to the network in form of the training data. Once trained, the neural network can recognized data that it has not seen before. This paper will present a fundamental introduction to the manner in which neural networks work and how to use them in load forecasting.
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.
Neural networks for aircraft system identification
NASA Technical Reports Server (NTRS)
Linse, Dennis J.
1991-01-01
Artificial neural networks offer some interesting possibilities for use in control. Our current research is on the use of neural networks on an aircraft model. The model can then be used in a nonlinear control scheme. The effectiveness of network training is demonstrated.
Neural networks and MIMD-multiprocessors
NASA Technical Reports Server (NTRS)
Vanhala, Jukka; Kaski, Kimmo
1990-01-01
Two artificial neural network models are compared. They are the Hopfield Neural Network Model and the Sparse Distributed Memory model. Distributed algorithms for both of them are designed and implemented. The run time characteristics of the algorithms are analyzed theoretically and tested in practice. The storage capacities of the networks are compared. Implementations are done using a distributed multiprocessor system.
Neural 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.
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.
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.
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.
Complexity matching in neural networks
NASA Astrophysics Data System (ADS)
Usefie Mafahim, Javad; Lambert, David; Zare, Marzieh; Grigolini, Paolo
2015-01-01
In the wide literature on the brain and neural network dynamics the notion of criticality is being adopted by an increasing number of researchers, with no general agreement on its theoretical definition, but with consensus that criticality makes the brain very sensitive to external stimuli. We adopt the complexity matching principle that the maximal efficiency of communication between two complex networks is realized when both of them are at criticality. We use this principle to establish the value of the neuronal interaction strength at which criticality occurs, yielding a perfect agreement with the adoption of temporal complexity as criticality indicator. The emergence of a scale-free distribution of avalanche size is proved to occur in a supercritical regime. We use an integrate-and-fire model where the randomness of each neuron is only due to the random choice of a new initial condition after firing. The new model shares with that proposed by Izikevich the property of generating excessive periodicity, and with it the annihilation of temporal complexity at supercritical values of the interaction strength. We find that the concentration of inhibitory links can be used as a control parameter and that for a sufficiently large concentration of inhibitory links criticality is recovered again. Finally, we show that the response of a neural network at criticality to a harmonic stimulus is very weak, in accordance with the complexity matching principle.
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. PMID:19632811
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.
Neural network modeling of distillation columns
Baratti, R.; Vacca, G.; Servida, A.
1995-06-01
Neural network modeling (NNM) was implemented for monitoring and control applications on two actual distillation columns: the butane splitter tower and the gasoline stabilizer. The two distillation columns are in operation at the SARAS refinery. Results show that with proper implementation techniques NNM can significantly improve column operation. The common belief that neural networks can be used as black-box process models is not completely true. Effective implementation always requires a minimum degree of process knowledge to identify the relevant inputs to the net. After background and generalities on neural network modeling, the paper describes efforts on the development of neural networks for the two distillation units.
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.
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 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.
Neural network for photoplethysmographic respiratory rate monitoring
NASA Astrophysics Data System (ADS)
Johansson, Anders
2001-10-01
The photoplethysmographic signal (PPG) includes respiratory components seen as frequency modulation of the heart rate (respiratory sinus arrhythmia, RSA), amplitude modulation of the cardiac pulse, and respiratory induced intensity variations (RIIV) in the PPG baseline. The aim of this study was to evaluate the accuracy of these components in determining respiratory rate, and to combine the components in a neural network for improved accuracy. The primary goal is to design a PPG ventilation monitoring system. PPG signals were recorded from 15 healthy subjects. From these signals, the systolic waveform, diastolic waveform, respiratory sinus arrhythmia, pulse amplitude and RIIV were extracted. By using simple algorithms, the rates of false positive and false negative detection of breaths were calculated for each of the five components in a separate analysis. Furthermore, a simple neural network (NN) was tried out in a combined pattern recognition approach. In the separate analysis, the error rates (sum of false positives and false negatives) ranged from 9.7% (pulse amplitude) to 14.5% (systolic waveform). The corresponding value of the NN analysis was 9.5-9.6%.
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
Ozone Modeling Using Neural Networks.
NASA Astrophysics Data System (ADS)
Narasimhan, Ramesh; Keller, Joleen; Subramaniam, Ganesh; Raasch, Eric; Croley, Brandon; Duncan, Kathleen; Potter, William T.
2000-03-01
Ozone models for the city of Tulsa were developed using neural network modeling techniques. The neural models were developed using meteorological data from the Oklahoma Mesonet and ozone, nitric oxide, and nitrogen dioxide (NO2) data from Environmental Protection Agency monitoring sites in the Tulsa area. An initial model trained with only eight surface meteorological input variables and NO2 was able to simulate ozone concentrations with a correlation coefficient of 0.77. The trained model was then used to evaluate the sensitivity to the primary variables that affect ozone concentrations. The most important variables (NO2, temperature, solar radiation, and relative humidity) showed response curves with strong nonlinear codependencies. Incorporation of ozone concentrations from the previous 3 days into the model increased the correlation coefficient to 0.82. As expected, the ozone concentrations correlated best with the most recent (1-day previous) values. The model's correlation coefficient was increased to 0.88 by the incorporation of upper-air data from the National Weather Service's Nested Grid Model. Sensitivity analysis for the upper-air variables indicated unusual positive correlations between ozone and the relative humidity from 500 hPa to the tropopause in addition to the other expected correlations with upper-air temperatures, vertical wind velocity, and 1000-500-hPa layer thickness. The neural model results are encouraging for the further use of these systems to evaluate complex parameter cosensitivities, and for the use of these systems in automated ozone forecast systems.
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.
Not Available
1991-01-01
The present conference discusses such topics as the self-organization of nonnumeric data sets, higher-order data compression with neural networks, approaches to connectionist pattern synthesis, a time-varying recurrent neural system for convex programming, a fuzzy associative memory for conceptual design, sensor failure detection and recovery via neural networks, genetic optimization of self-organizing feature maps, a maximum neural network for the max-cut problem, a neural-network LSI chip with on-chip learning, an optoelectronic adaptive resonance unit, an adaptive fuzzy system for transform image coding, a neural model of image velocity encoding, and incremental learning with rule-based neural networks. Also discussed are the induction of neural networks for parallel binary operations, hybrid learning in expert networks, self-organizing modular neural networks, connectionist category formation, period-doublings to chaos in a simple neural network, the optimal adaptive classifier design criterion, fuzzy neuron models, associative memory networks, adaptive transfer functions, spatiotemporal correlation in the cerebellum, prejuditial searches and the pole balancer, linear quadratic regulation via neural networks, the global optimization of a neural network, neural network analysis of DNA sequences, map learning using an associative-memory neural network, a pairing strategy in an associative memory classifier, neural networks for music composition, and a neural network for motion computation.
Geophysical phenomena classification by artificial neural networks
NASA Technical Reports Server (NTRS)
Gough, M. P.; Bruckner, J. R.
1995-01-01
Space science information systems involve accessing vast data bases. There is a need for an automatic process by which properties of the whole data set can be assimilated and presented to the user. Where data are in the form of spectrograms, phenomena can be detected by pattern recognition techniques. Presented are the first results obtained by applying unsupervised Artificial Neural Networks (ANN's) to the classification of magnetospheric wave spectra. The networks used here were a simple unsupervised Hamming network run on a PC and a more sophisticated CALM network run on a Sparc workstation. The ANN's were compared in their geophysical data recognition performance. CALM networks offer such qualities as fast learning, superiority in generalizing, the ability to continuously adapt to changes in the pattern set, and the possibility to modularize the network to allow the inter-relation between phenomena and data sets. This work is the first step toward an information system interface being developed at Sussex, the Whole Information System Expert (WISE). Phenomena in the data are automatically identified and provided to the user in the form of a data occurrence morphology, the Whole Information System Data Occurrence Morphology (WISDOM), along with relationships to other parameters and phenomena.
Geophysical phenomena classification by artificial neural networks
Gough, M.P.; Bruckner, J.R.
1995-01-01
Space science information systems involve accessing vast data bases. There is a need for an automatic process by which properties of the whole data set can be assimilated and presented to the user. Where data are in the form of spectrograms, phenomena can be detected by pattern recognition techniques. Presented are the first results obtained by applying unsupervised Artificial Neural Networks (ANN`s) to the classification of magnetospheric wave spectra. The networks used here were a simple unsupervised Hamming network run on a PC and a more sophisticated CALM network run on a Sparc workstation. The ANN`s were compared in their geophysical data recognition performance. CALM networks offer such qualities as fast learning, superiority in generalizing, the ability to continuously adapt to changes in the pattern set, and the possibility to modularize the network to allow the inter-relation between phenomena and data sets. This work is the first step toward an information system interface being developed at Sussex, the Whole Information System Expert (WISE). Phenomena in the data are automatically identified and provided to the user in the form of a data occurrence morphology, the Whole Information System Data Occurrence Morphology (WISDOM), along with relationships to other parameters and phenomena.
Neural network model for extracting optic flow.
Tohyama, Kazuya; Fukushima, Kunihiko
2005-01-01
When we travel in an environment, we have an optic flow on the retina. Neurons in the area MST of macaque monkeys are reported to have a very large receptive field and analyze optic flows on the retina. Many MST-cells respond selectively to rotation, expansion/contraction and planar motion of the optic flow. Many of them show position-invariant responses to optic flow, that is, their responses are maintained during the shift of the center of the optic flow. It has long been suggested mathematically that vector-field calculus is useful for analyzing optic flow field. Biologically, plausible neural network models based on this idea, however, have little been proposed so far. This paper, based on vector-field hypothesis, proposes a neural network model for extracting optic flows. Our model consists of hierarchically connected layers: retina, V1, MT and MST. V1-cells measure local velocity. There are two kinds of MT-cell: one is for extracting absolute velocities, the other for extracting relative velocities with their antagonistic inputs. Collecting signals from MT-cells, MST-cells respond selectively to various types of optic flows. We demonstrate through a computer simulation that this simple network is enough to explain a variety of results of neurophysiological experiments. PMID:16112546
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. PMID:24987050
Computational acceleration using neural networks
NASA Astrophysics Data System (ADS)
Cadaret, Paul
2008-04-01
The author's recent participation in the Small Business Innovative Research (SBIR) program has resulted in the development of a patent pending technology that enables the construction of very large and fast artificial neural networks. Through the use of UNICON's CogniMax pattern recognition technology we believe that systems can be constructed that exploit the power of "exhaustive learning" for the benefit of certain types of complex and slow computational problems. This paper presents a theoretical study that describes one potentially beneficial application of exhaustive learning. It describes how a very large and fast Radial Basis Function (RBF) artificial Neural Network (NN) can be used to implement a useful computational system. Viewed another way, it presents an unusual method of transforming a complex, always-precise, and slow computational problem into a fuzzy pattern recognition problem where other methods are available to effectively improve computational performance. The method described recognizes that the need for computational precision in a problem domain sometimes varies throughout the domain's Feature Space (FS) and high precision may only be needed in limited areas. These observations can then be exploited to the benefit of overall computational performance. Addressing computational reliability, we describe how existing always-precise computational methods can be used to reliably train the NN to perform the computational interpolation function. The author recognizes that the method described is not applicable to every situation, but over the last 8 months we have been surprised at how often this method can be applied to enable interesting and effective solutions.
Real-Time Adaptive Color Segmentation by Neural Networks
NASA Technical Reports Server (NTRS)
Duong, Tuan A.
2004-01-01
Artificial neural networks that would utilize the cascade error projection (CEP) algorithm have been proposed as means of autonomous, real-time, adaptive color segmentation of images that change with time. In the original intended application, such a neural network would be used to analyze digitized color video images of terrain on a remote planet as viewed from an uninhabited spacecraft approaching the planet. During descent toward the surface of the planet, information on the segmentation of the images into differently colored areas would be updated adaptively in real time to capture changes in contrast, brightness, and resolution, all in an effort to identify a safe and scientifically productive landing site and provide control feedback to steer the spacecraft toward that site. Potential terrestrial applications include monitoring images of crops to detect insect invasions and monitoring of buildings and other facilities to detect intruders. The CEP algorithm is reliable and is well suited to implementation in very-large-scale integrated (VLSI) circuitry. It was chosen over other neural-network learning algorithms because it is better suited to realtime learning: It provides a self-evolving neural-network structure, requires fewer iterations to converge and is more tolerant to low resolution (that is, fewer bits) in the quantization of neural-network synaptic weights. Consequently, a CEP neural network learns relatively quickly, and the circuitry needed to implement it is relatively simple. Like other neural networks, a CEP neural network includes an input layer, hidden units, and output units (see figure). As in other neural networks, a CEP network is presented with a succession of input training patterns, giving rise to a set of outputs that are compared with the desired outputs. Also as in other neural networks, the synaptic weights are updated iteratively in an effort to bring the outputs closer to target values. A distinctive feature of the CEP neural
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. PMID:21859600
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.
Coherence resonance in bursting neural networks
NASA Astrophysics Data System (ADS)
Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J.
2015-10-01
Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal—a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.
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.
From Classical Neural Networks to Quantum Neural Networks
NASA Astrophysics Data System (ADS)
Tirozzi, B.
2013-09-01
First I give a brief description of the classical Hopfield model introducing the fundamental concepts of patterns, retrieval, pattern recognition, neural dynamics, capacity and describe the fundamental results obtained in this field by Amit, Gutfreund and Sompolinsky,1 using the non rigorous method of replica and the rigorous version given by Pastur, Shcherbina, Tirozzi2 using the cavity method. Then I give a formulation of the theory of Quantum Neural Networks (QNN) in terms of the XY model with Hebbian interaction. The problem of retrieval and storage is discussed. The retrieval states are the states of the minimum energy. I apply the estimates found by Lieb3 which give lower and upper bound of the free-energy and expectation of the observables of the quantum model. I discuss also some experiment and the search of ground state using Monte Carlo Dynamics applied to the equivalent classical two dimensional Ising model constructed by Suzuki et al.6 At the end there is a list of open problems.
Simple model for directed networks
NASA Astrophysics Data System (ADS)
Morelli, Luis G.
2003-06-01
We study a model for directed networks based on the Watts-Stogatz model for small-world phenomena. We focus on some topological aspects of directed networks inspired in food web theory, namely, the fraction of basal and top nodes in the network and node level distributions. We argue that in directed networks basal nodes play an important role, collecting information or resources from the environment. We give analytical expressions for the fraction of basal and top nodes for the model, and study the node level distributions with numerical simulations.
Neural Network Algorithm for Particle Loading
J. L. V. Lewandowski
2003-04-25
An artificial neural network algorithm for continuous minimization is developed and applied to the case of numerical particle loading. It is shown that higher-order moments of the probability distribution function can be efficiently renormalized using this technique. A general neural network for the renormalization of an arbitrary number of moments is given.
Adaptive Neurons For Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Tawel, Raoul
1990-01-01
Training time decreases dramatically. In improved mathematical model of neural-network processor, temperature of neurons (in addition to connection strengths, also called weights, of synapses) varied during supervised-learning phase of operation according to mathematical formalism and not heuristic rule. Evidence that biological neural networks also process information at neuronal level.
Radiation Behavior of Analog Neural Network Chip
NASA Technical Reports Server (NTRS)
Langenbacher, H.; Zee, F.; Daud, T.; Thakoor, A.
1996-01-01
A neural network experiment conducted for the Space Technology Research Vehicle (STRV-1) 1-b launched in June 1994. Identical sets of analog feed-forward neural network chips was used to study and compare the effects of space and ground radiation on the chips. Three failure mechanisms are noted.
Medical image analysis with artificial neural networks.
Jiang, J; Trundle, P; Ren, J
2010-12-01
Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing, with the aims of increasing awareness of how neural networks can be applied to these areas and to provide a foundation for further research and practical development. Representative techniques and algorithms are explained in detail to provide inspiring examples illustrating: (i) how a known neural network with fixed structure and training procedure could be applied to resolve a medical imaging problem; (ii) how medical images could be analysed, processed, and characterised by neural networks; and (iii) how neural networks could be expanded further to resolve problems relevant to medical imaging. In the concluding section, a highlight of comparisons among many neural network applications is included to provide a global view on computational intelligence with neural networks in medical imaging. PMID:20713305
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.
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.
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)
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…
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.
Multiple neural network approaches to clinical expert systems
NASA Astrophysics Data System (ADS)
Stubbs, Derek F.
1990-08-01
We briefly review the concept of computer aided medical diagnosis and more extensively review the the existing literature on neural network applications in the field. Neural networks can function as simple expert systems for diagnosis or prognosis. Using a public database we develop a neural network for the diagnosis of a major presenting symptom while discussing the development process and possible approaches. MEDICAL EXPERTS SYSTEMS COMPUTER AIDED DIAGNOSIS Biomedicine is an incredibly diverse and multidisciplinary field and it is not surprising that neural networks with their many applications are finding more and more applications in the highly non-linear field of biomedicine. I want to concentrate on neural networks as medical expert systems for clinical diagnosis or prognosis. Expert Systems started out as a set of computerized " ifthen" rules. Everything was reduced to boolean logic and the promised land of computer experts was said to be in sight. It never came. Why? First the computer code explodes as the number of " ifs" increases. All the " ifs" have to interact. Second experts are not very good at reducing expertise to language. It turns out that experts recognize patterns and have non-verbal left-brain intuition decision processes. Third learning by example rather than learning by rule is the way natural brains works and making computers work by rule-learning is hideously labor intensive. Neural networks can learn from example. They learn the 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. PMID:21517565
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.
Linear circuits for neural networks and affective computing.
Frenger, P
1999-01-01
Biological phenomena are often modeled with software on digital computers, even though the events may be analog in nature. The author describes the use of linear circuitry in two areas of biological simulation: artificial neural networks and affective computing. The operational amplifier, with the assistance of some new analog chips and simple digital microcontrollers, is featured prominently in these linear designs. PMID:11143356
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.
Moon, S W; Kong, S G
2001-01-01
This paper presents a novel block-based neural network (BBNN) model and the optimization of its structure and weights based on a genetic algorithm. The architecture of the BBNN consists of a 2D array of fundamental blocks with four variable input/output nodes and connection weights. Each block can have one of four different internal configurations depending on the structure settings, The BBNN model includes some restrictions such as 2D array and integer weights in order to allow easier implementation with reconfigurable hardware such as field programmable logic arrays (FPGA). The structure and weights of the BBNN are encoded with bit strings which correspond to the configuration bits of FPGA. The configuration bits are optimized globally using a genetic algorithm with 2D encoding and modified genetic operators. Simulations show that the optimized BBNN can solve engineering problems such as pattern classification and mobile robot control. PMID:18244385
Neural networks: a biased overview
Domany, E.
1988-06-01
An overview of recent activity in the field of neural networks is presented. The long-range aim of this research is to understand how the brain works. First some of the problems are stated and terminology defined; then an attempt is made to explain why physicists are drawn to the field, and their main potential contribution. In particular, in recent years some interesting models have been introduced by physicists. A small subset of these models is described, with particular emphasis on those that are analytically soluble. Finally a brief review of the history and recent developments of single- and multilayer perceptrons is given, bringing the situation up to date regarding the central immediate problem of the field: search for a learning algorithm that has an associated convergence theorem.
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. PMID:19674951
Introduction to artificial neural networks.
Grossi, Enzo; Buscema, Massimo
2007-12-01
The coupling of computer science and theoretical bases such as nonlinear dynamics and chaos theory allows the creation of 'intelligent' agents, such as artificial neural networks (ANNs), able to adapt themselves dynamically to problems of high complexity. ANNs are able to reproduce the dynamic interaction of multiple factors simultaneously, allowing the study of complexity; they can also draw conclusions on individual basis and not as average trends. These tools can offer specific advantages with respect to classical statistical techniques. This article is designed to acquaint gastroenterologists with concepts and paradigms related to ANNs. The family of ANNs, when appropriately selected and used, permits the maximization of what can be derived from available data and from complex, dynamic, and multidimensional phenomena, which are often poorly predictable in the traditional 'cause and effect' philosophy. PMID:17998827
Parameter incremental learning algorithm for neural networks.
Wan, Sheng; Banta, Larry E
2006-11-01
In this paper, a novel stochastic (or online) training algorithm for neural networks, named parameter incremental learning (PIL) algorithm, is proposed and developed. The main idea of the PIL strategy is that the learning algorithm should not only adapt to the newly presented input-output training pattern by adjusting parameters, but also preserve the prior results. A general PIL algorithm for feedforward neural networks is accordingly presented as the first-order approximate solution to an optimization problem, where the performance index is the combination of proper measures of preservation and adaptation. The PIL algorithms for the multilayer perceptron (MLP) are subsequently derived. Numerical studies show that for all the three benchmark problems used in this paper the PIL algorithm for MLP is measurably superior to the standard online backpropagation (BP) algorithm and the stochastic diagonal Levenberg-Marquardt (SDLM) algorithm in terms of the convergence speed and accuracy. Other appealing features of the PIL algorithm are that it is computationally as simple as the BP algorithm, and as easy to use as the BP algorithm. It, therefore, can be applied, with better performance, to any situations where the standard online BP algorithm is applicable. PMID:17131658
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
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
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
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
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.
Neural networks and orbit control in accelerators
Bozoki, E.; Friedman, A.
1994-07-01
An overview of the architecture, workings and training of Neural Networks is given. We stress the aspects which are important for the use of Neural Networks for orbit control in accelerators and storage rings, especially its ability to cope with the nonlinear behavior of the orbit response to `kicks` and the slow drift in the orbit response during long-term operation. Results obtained for the two NSLS storage rings with several network architectures and various training methods for each architecture are given.
Stochastic cellular automata model of neural networks.
Goltsev, A V; de Abreu, F V; Dorogovtsev, S N; Mendes, J F F
2010-06-01
We propose a stochastic dynamical model of noisy neural networks with complex architectures and discuss activation of neural networks by a stimulus, pacemakers, and spontaneous activity. This model has a complex phase diagram with self-organized active neural states, hybrid phase transitions, and a rich array of behaviors. We show that if spontaneous activity (noise) reaches a threshold level then global neural oscillations emerge. Stochastic resonance is a precursor of this dynamical phase transition. These oscillations are an intrinsic property of even small groups of 50 neurons. PMID:20866454
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.
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.
Hopf bifurcation stability in Hopfield neural networks.
Marichal, R L; González, E J; Marichal, G N
2012-12-01
In this paper we consider a simple discrete Hopfield neural network model and analyze local stability using the associated characteristic model. In order to study the dynamic behavior of the quasi-periodic orbit, the Hopf bifurcation must be determined. For the case of two neurons, we find one necessary condition that yields the Hopf bifurcation. In addition, we determine the stability and direction of the Hopf bifurcation by applying normal form theory and the center manifold theorem. An example is given and a numerical simulation is performed to illustrate the results. We analyze the influence of bias weights on the stability of the quasi-periodic orbit and study the phase-locking phenomena for certain experimental results with Arnold Tongues in a particular weight configuration. PMID:23037776
Data compression using artificial neural networks
Watkins, B.E.
1991-09-01
This thesis investigates the application of artificial neural networks for the compression of image data. An algorithm is developed using the competitive learning paradigm which takes advantage of the parallel processing and classification capability of neural networks to produce an efficient implementation of vector quantization. Multi-Stage, tree searched, and classification vector quantization codebook design are adapted to the neural network design to reduce the computational cost and hardware requirements. The results show that the new algorithm provides a substantial reduction in computational costs and an improvement in performance.
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 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.
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.
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.
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.
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
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 characteristics…
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.
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.
Associative memory realized by a reconfigurable memristive Hopfield neural network
NASA Astrophysics Data System (ADS)
Hu, S. G.; Liu, Y.; Liu, Z.; Chen, T. P.; Wang, J. J.; Yu, Q.; Deng, L. J.; Yin, Y.; Hosaka, Sumio
2015-06-01
Although synaptic behaviours of memristors have been widely demonstrated, implementation of an even simple artificial neural network is still a great challenge. In this work, we demonstrate the associative memory on the basis of a memristive Hopfield network. Different patterns can be stored into the memristive Hopfield network by tuning the resistance of the memristors, and the pre-stored patterns can be successfully retrieved directly or through some associative intermediate states, being analogous to the associative memory behaviour. Both single-associative memory and multi-associative memories can be realized with the memristive Hopfield network.
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.
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.
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
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.
Applications of neural networks in chemical engineering: Hybrid systems
Ferrada, J.J.; Osborne-Lee, I.W. ); Grizzaffi, P.A. )
1990-01-01
Expert systems are known to be useful in capturing expertise and applying knowledge to chemical engineering problems such as diagnosis, process control, process simulation, and process advisory. However, expert system applications are traditionally limited to knowledge domains that are heuristic and involve only simple mathematics. Neural networks, on the other hand, represent an emerging technology capable of rapid recognition of patterned behavior without regard to mathematical complexity. Although useful in problem identification, neural networks are not very efficient in providing in-depth solutions and typically do not promote full understanding of the problem or the reasoning behind its solutions. Hence, applications of neural networks have certain limitations. This paper explores the potential for expanding the scope of chemical engineering areas where neural networks might be utilized by incorporating expert systems and neural networks into the same application, a process called hybridization. In addition, hybrid applications are compared with those using more traditional approaches, the results of the different applications are analyzed, and the feasibility of converting the preliminary prototypes described herein into useful final products is evaluated. 12 refs., 8 figs.
Using neural networks in software repositories
NASA Technical Reports Server (NTRS)
Eichmann, David (Editor); Srinivas, Kankanahalli; Boetticher, G.
1992-01-01
The first topic is an exploration of the use of neural network techniques to improve the effectiveness of retrieval in software repositories. The second topic relates to a series of experiments conducted to evaluate the feasibility of using adaptive neural networks as a means of deriving (or more specifically, learning) measures on software. Taken together, these two efforts illuminate a very promising mechanism supporting software infrastructures - one based upon a flexible and responsive technology.
Limitations of opto-electronic neural networks
NASA Technical Reports Server (NTRS)
Yu, Jeffrey; Johnston, Alan; Psaltis, Demetri; Brady, David
1989-01-01
Consideration is given to the limitations of implementing neurons, weights, and connections in neural networks for electronics and optics. It is shown that the advantages of each technology are utilized when electronically fabricated neurons are included and a combination of optics and electronics are employed for the weights and connections. The relationship between the types of neural networks being constructed and the choice of technologies to implement the weights and connections is examined.
Neural network simulations of the nervous system.
van Leeuwen, J L
1990-01-01
Present knowledge of brain mechanisms is mainly based on anatomical and physiological studies. Such studies are however insufficient to understand the information processing of the brain. The present new focus on neural network studies is the most likely candidate to fill this gap. The present paper reviews some of the history and current status of neural network studies. It signals some of the essential problems for which answers have to be found before substantial progress in the field can be made. PMID:2245130
Neural-Network Controller For Vibration Suppression
NASA Technical Reports Server (NTRS)
Boussalis, Dhemetrios; Wang, Shyh Jong
1995-01-01
Neural-network-based adaptive-control system proposed for vibration suppression of flexible space structures. Controller features three-layer neural network and utilizes output feedback. Measurements generated by various sensors on structure. Feed forward path also included to speed up response in case plant exhibits predominantly linear dynamic behavior. System applicable to single-input single-output systems. Work extended to multiple-input multiple-output systems as well.
Optimization neural network for solving flow problems.
Perfetti, R
1995-01-01
This paper describes a neural network for solving flow problems, which are of interest in many areas of application as in fuel, hydro, and electric power scheduling. The neural network consist of two layers: a hidden layer and an output layer. The hidden units correspond to the nodes of the flow graph. The output units represent the branch variables. The network has a linear order of complexity, it is easily programmable, and it is suited for analog very large scale integration (VLSI) realization. The functionality of the proposed network is illustrated by a simulation example concerning the maximal flow problem. PMID:18263420
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.
Speech synthesis with artificial neural networks
NASA Astrophysics Data System (ADS)
Weijters, Ton; Thole, Johan
1992-10-01
The application of neural nets to speech synthesis is considered. In speech synthesis, the main efforts so far have been to master the grapheme to phoneme conversion. During this conversion symbols (graphemes) are converted into other symbols (phonemes). Neural networks, however, are especially competitive for tasks in which complex nonlinear transformations are needed and sufficient domain specific knowledge is not available. The conversion of text into speech parameters appropriate as input for a speech generator seems such a task. Results of a pilot study in which an attempt is made to train a neural network for this conversion are presented.
NASA Astrophysics Data System (ADS)
de Vos, N. J.
2013-01-01
Despite theoretical benefits of recurrent artificial neural networks over their feedforward counterparts, it is still unclear whether the former offer practical advantages as rainfall-runoff models. The main drawback of recurrent networks is the increased complexity of the training procedure due to their architecture. This work uses the recently introduced and conceptually simple echo state networks for streamflow forecasts on twelve river basins in the Eastern United States, and compares them to a variety of traditional feedforward and recurrent approaches. Two modifications on the echo state network models are made that increase the hydrologically relevant information content of their internal state. The results show that the echo state networks outperform feedforward networks and are competitive with state-of-the-art recurrent networks, across a range of performance measures. This, along with their simplicity and ease of training, suggests that they can be considered promising alternatives to traditional artificial neural networks in rainfall-runoff modelling.
A neural network for visual pattern recognition
Fukushima, K.
1988-03-01
A modeling approach, which is a synthetic approach using neural network models, continues to gain importance. In the modeling approach, the authors study how to interconnect neurons to synthesize a brain model, which is a network with the same functions and abilities as the brain. The relationship between modeling neutral networks and neurophysiology resembles that between theoretical physics and experimental physics. Modeling takes synthetic approach, while neurophysiology or psychology takes an analytical approach. Modeling neural networks is useful in explaining the brain and also in engineering applications. It brings the results of neurophysiological and psychological research to engineering applications in the most direct way possible. This article discusses a neural network model thus obtained, a model with selective attention in visual pattern recognition.
Object Recognition by a Hopfield Neural Network
NASA Astrophysics Data System (ADS)
Li, Wei; Nasrabadi, Nasser M.
1990-03-01
A model-based object recognition technique is introduced in this paper to identify and locate an object in any position and orientation. The test scenes could consist of an isolated object or several partially overlapping objects. A cooperative feature matching technique is proposed which is implemented by a Hopfield neural network. The proposed matching technique uses the parallelism of the neural network to globally match all the objects (they may be overlapping or touching) in the input scene against all the object models in the model-database at the same time. For each model, distinct features such as curvature points (corners) are extracted and a graph consisting of a number of nodes connected by arcs is constructed. Each node in the graph represents a feature which has a numerical feature value and is connected to other nodes by an arc representing the relationship or compatibility between them. Object recognition is formulated as matching a global model graph, representing all the object models, with an input scene graph representing a single object or several overlapping objects. A 2-dimensional Hopfield binary neural network is implemented to perform a subgraph isomorphism to obtain the optimal compatible matching features between the two graphs. The synaptic interconnection weights between neurons are designed such that matched features belonging to the same model receive excitatory supports, and matched features belonging to different models receive an inhibitory support or a mutual support depending on whether the input scene is an isolated object or several overlapping objects. The coordinate transformation for mapping each pair of matched nodes from the model onto the input scene is calculated, followed by a simple clustering technique to eliminate any false matches. The orientation and the position of objects in the scene are then calculated by averaging the transformation of correct matched nodes. Some simulation results are shown to illustrate the
The H1 neural network trigger project
NASA Astrophysics Data System (ADS)
Kiesling, C.; Denby, B.; Fent, J.; Fröchtenicht, W.; Garda, P.; Granado, B.; Grindhammer, G.; Haberer, W.; Janauschek, L.; Kobler, T.; Koblitz, B.; Nellen, G.; Prevotet, J.-C.; Schmidt, S.; Tzamariudaki, E.; Udluft, S.
2001-08-01
We present a short overview of neuromorphic hardware and some of the physics projects making use of such devices. As a concrete example we describe an innovative project within the H1-Experiment at the electron-proton collider HERA, instrumenting hardwired neural networks as pattern recognition machines to discriminate between wanted physics and uninteresting background at the trigger level. The decision time of the system is less than 20 microseconds, typical for a modern second level trigger. The neural trigger has been successfully running for the past four years and has turned out new physics results from H1 unobtainable so far with other triggering schemes. We describe the concepts and the technical realization of the neural network trigger system, present the most important physics results, and motivate an upgrade of the system for the future high luminosity running at HERA. The upgrade concentrates on "intelligent preprocessing" of the neural inputs which help to strongly improve the networks' discrimination power.
Optical neural stimulation modeling on degenerative neocortical neural networks
NASA Astrophysics Data System (ADS)
Zverev, M.; Fanjul-Vélez, F.; Salas-García, I.; Arce-Diego, J. L.
2015-07-01
Neurodegenerative diseases usually appear at advanced age. Medical advances make people live longer and as a consequence, the number of neurodegenerative diseases continuously grows. There is still no cure for these diseases, but several brain stimulation techniques have been proposed to improve patients' condition. One of them is Optical Neural Stimulation (ONS), which is based on the application of optical radiation over specific brain regions. The outer cerebral zones can be noninvasively stimulated, without the common drawbacks associated to surgical procedures. This work focuses on the analysis of ONS effects in stimulated neurons to determine their influence in neuronal activity. For this purpose a neural network model has been employed. The results show the neural network behavior when the stimulation is provided by means of different optical radiation sources and constitute a first approach to adjust the optical light source parameters to stimulate specific neocortical areas.
A neural network approach to job-shop scheduling.
Zhou, D N; Cherkassky, V; Baldwin, T R; Olson, D E
1991-01-01
A novel analog computational network is presented for solving NP-complete constraint satisfaction problems, i.e. job-shop scheduling. In contrast to most neural approaches to combinatorial optimization based on quadratic energy cost function, the authors propose to use linear cost functions. As a result, the network complexity (number of neurons and the number of resistive interconnections) grows only linearly with problem size, and large-scale implementations become possible. The proposed approach is related to the linear programming network described by D.W. Tank and J.J. Hopfield (1985), which also uses a linear cost function for a simple optimization problem. It is shown how to map a difficult constraint-satisfaction problem onto a simple neural net in which the number of neural processors equals the number of subjobs (operations) and the number of interconnections grows linearly with the total number of operations. Simulations show that the authors' approach produces better solutions than existing neural approaches to job-shop scheduling, i.e. the traveling salesman problem-type Hopfield approach and integer linear programming approach of J.P.S. Foo and Y. Takefuji (1988), in terms of the quality of the solution and the network complexity. PMID:18276371
Artificial Astrocytes Improve Neural Network Performance
Porto-Pazos, Ana B.; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso
2011-01-01
Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function. PMID:21526157
Artificial astrocytes improve neural network performance.
Porto-Pazos, Ana B; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso
2011-01-01
Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function. PMID:21526157
Predicting permeability from porosity using artificial neural networks
Rogers, S.J.; Fang, J.H.; Chen, H.C. Kopaska-Merkel, D.C.
1995-12-01
Permeability values in a borehole are predicted by an artificial neural network from the porosity values at the same depths. THe network used in this study employs an architecture called backpropagation that is good at making predictions. The traditional approach for permeability prediction is regression analysis, the relationship between porosity and permeability is assumed to be known. In reality, the functional form of this relationship, i.e., the model equation, is unknown. In contrast, the neural-network approach assumes no functional relationship. Six wells from Big Escambia Creek (Jurassic Smackover carbonate) field in southern Alabama were used to test predicting permeability from porosity using a neural network. Porosity and spatial data alone were used to predict permeability because these data are readily available from any hydrocarbon field. Three scenarios were performed; in each one, a subset of the six wells was used for a training set, one well for calibration, and one or two wells were used for prediction. For each scenario, simple linear regression was also used to predict permeability from porosity. The neural net predicted permeability much better than did regression in one scenario; in the other two scenarios the two methods performed equally well. The neural net predicted permeability accurately using minimal data, but other kinds of information (e.g., log- or core-derived lithologic information) are easily incorporated if available. In addition, compartmentalization of carbonate reservoirs may be recognizable by this approach.
Fuzzy logic and neural networks
Loos, J.R.
1994-11-01
Combine fuzzy logic`s fuzzy sets, fuzzy operators, fuzzy inference, and fuzzy rules - like defuzzification - with neural networks and you can arrive at very unfuzzy real-time control. Fuzzy logic, cursed with a very whimsical title, simply means multivalued logic, which includes not only the conventional two-valued (true/false) crisp logic, but also the logic of three or more values. This means one can assign logic values of true, false, and somewhere in between. This is where fuzziness comes in. Multi-valued logic avoids the black-and-white, all-or-nothing assignment of true or false to an assertion. Instead, it permits the assignment of shades of gray. When assigning a value of true or false to an assertion, the numbers typically used are {open_quotes}1{close_quotes} or {open_quotes}0{close_quotes}. This is the case for programmed systems. If {open_quotes}0{close_quotes} means {open_quotes}false{close_quotes} and {open_quotes}1{close_quotes} means {open_quotes}true,{close_quotes} then {open_quotes}shades of gray{close_quotes} are any numbers between 0 and 1. Therefore, {open_quotes}nearly true{close_quotes} may be represented by 0.8 or 0.9, {open_quotes}nearly false{close_quotes} may be represented by 0.1 or 0.2, and {close_quotes}your guess is as good as mine{close_quotes} may be represented by 0.5. The flexibility available to one is limitless. One can associate any meaning, such as {open_quotes}nearly true{close_quotes}, to any value of any granularity, such as 0.9999. 2 figs.
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.
Wu, Si; Wong, K Y Michael; Fung, C C Alan; Mi, Yuanyuan; Zhang, Wenhao
2016-01-01
Owing to its many computationally desirable properties, the model of continuous attractor neural networks (CANNs) has been successfully applied to describe the encoding of simple continuous features in neural systems, such as orientation, moving direction, head direction, and spatial location of objects. Recent experimental and computational studies revealed that complex features of external inputs may also be encoded by low-dimensional CANNs embedded in the high-dimensional space of neural population activity. The new experimental data also confirmed the existence of the M-shaped correlation between neuronal responses, which is a correlation structure associated with the unique dynamics of CANNs. This body of evidence, which is reviewed in this report, suggests that CANNs may serve as a canonical model for neural information representation. PMID:26937278
On sparsely connected optimal neural networks
Beiu, V.; Draghici, S.
1997-10-01
This paper uses two different approaches to show that VLSI- and size-optimal discrete neural networks are obtained for small fan-in values. These have applications to hardware implementations of neural networks, but also reveal an intrinsic limitation of digital VLSI technology: its inability to cope with highly connected structures. The first approach is based on implementing F{sub n,m} functions. The authors show that this class of functions can be implemented in VLSI-optimal (i.e., minimizing AT{sup 2}) neural networks of small constant fan-ins. In order to estimate the area (A) and the delay (T) of such networks, the following cost functions will be used: (i) the connectivity and the number-of-bits for representing the weights and thresholds--for good estimates of the area; and (ii) the fan-ins and the length of the wires--for good approximates of the delay. The second approach is based on implementing Boolean functions for which the classical Shannon`s decomposition can be used. Such a solution has already been used to prove bounds on the size of fan-in 2 neural networks. They will generalize the result presented there to arbitrary fan-in, and prove that the size is minimized by small fan-in values. Finally, a size-optimal neural network of small constant fan-ins will be suggested for F{sub n,m} functions.
Artificial Neural Networks and Instructional Technology.
ERIC Educational Resources Information Center
Carlson, Patricia A.
1991-01-01
Artificial neural networks (ANN), part of artificial intelligence, are discussed. Such networks are fed sample cases (training sets), learn how to recognize patterns in the sample data, and use this experience in handling new cases. Two cognitive roles for ANNs (intelligent filters and spreading, associative memories) are examined. Prototypes…
Higher-Order Neural Networks Recognize Patterns
NASA Technical Reports Server (NTRS)
Reid, Max B.; Spirkovska, Lilly; Ochoa, Ellen
1996-01-01
Networks of higher order have enhanced capabilities to distinguish between different two-dimensional patterns and to recognize those patterns. Also enhanced capabilities to "learn" patterns to be recognized: "trained" with far fewer examples and, therefore, in less time than necessary to train comparable first-order neural networks.
Orthogonal Patterns In A Binary Neural Network
NASA Technical Reports Server (NTRS)
Baram, Yoram
1991-01-01
Report presents some recent developments in theory of binary neural networks. Subject matter relevant to associate (content-addressable) memories and to recognition of patterns - both of considerable importance in advancement of robotics and artificial intelligence. When probed by any pattern, network converges to one of stored patterns.
Target detection using multilayer feedforward neural networks
NASA Astrophysics Data System (ADS)
Scherf, Alan V.; Scott, Peter A.
1991-08-01
Multilayer feedforward neural networks have been integrated with conventional image processing techniques to form a hybrid target detection algorithm for use in the F/A-18 FLIR pod advanced air-to-air track-while-scan mode. The network has been trained to detect and localize small targets in infrared imagery. Comparative performance between this target detection technique is evaluated.
Comparing artificial and biological dynamical neural networks
NASA Astrophysics Data System (ADS)
McAulay, Alastair D.
2006-05-01
Modern computers can be made more friendly and otherwise improved by making them behave more like humans. Perhaps we can learn how to do this from biology in which human brains evolved over a long period of time. Therefore, we first explain a commonly used biological neural network (BNN) model, the Wilson-Cowan neural oscillator, that has cross-coupled excitatory (positive) and inhibitory (negative) neurons. The two types of neurons are used for frequency modulation communication between neurons which provides immunity to electromagnetic interference. We then evolve, for the first time, an artificial neural network (ANN) to perform the same task. Two dynamical feed-forward artificial neural networks use cross-coupling feedback (like that in a flip-flop) to form an ANN nonlinear dynamic neural oscillator with the same equations as the Wilson-Cowan neural oscillator. Finally we show, through simulation, that the equations perform the basic neural threshold function, switching between stable zero output and a stable oscillation, that is a stable limit cycle. Optical implementation with an injected laser diode and future research are discussed.
IR wireless cluster synapses of HYDRA very large neural networks
NASA Astrophysics Data System (ADS)
Jannson, Tomasz; Forrester, Thomas
2008-04-01
RF/IR wireless (virtual) synapses are critical components of HYDRA (Hyper-Distributed Robotic Autonomy) neural networks, already discussed in two earlier papers. The HYDRA network has the potential to be very large, up to 10 11-neurons and 10 18-synapses, based on already established technologies (cellular RF telephony and IR-wireless LANs). It is organized into almost fully connected IR-wireless clusters. The HYDRA neurons and synapses are very flexible, simple, and low-cost. They can be modified into a broad variety of biologically-inspired brain-like computing capabilities. In this third paper, we focus on neural hardware in general, and on IR-wireless synapses in particular. Such synapses, based on LED/LD-connections, dominate the HYDRA neural cluster.
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.
Improving neural network performance on SIMD architectures
NASA Astrophysics Data System (ADS)
Limonova, Elena; Ilin, Dmitry; Nikolaev, Dmitry
2015-12-01
Neural network calculations for the image recognition problems can be very time consuming. In this paper we propose three methods of increasing neural network performance on SIMD architectures. The usage of SIMD extensions is a way to speed up neural network processing available for a number of modern CPUs. In our experiments, we use ARM NEON as SIMD architecture example. The first method deals with half float data type for matrix computations. The second method describes fixed-point data type for the same purpose. The third method considers vectorized activation functions implementation. For each method we set up a series of experiments for convolutional and fully connected networks designed for image recognition task.
Neural networks and logical reasoning systems: a translation table.
Martins, J; Mendes, R V
2001-04-01
A correspondence is established between the basic elements of logic reasoning systems (knowledge bases, rules, inference and queries) and the structure and dynamical evolution laws of neural networks. The correspondence is pictured as a translation dictionary which might allow to go back and forth between symbolic and network formulations, a desirable step in learning-oriented systems and multicomputer networks. In the framework of Horn clause logics, it is found that atomic propositions with n arguments correspond to nodes with nth order synapses, rules to synaptic intensity constraints, forward chaining to synaptic dynamics and queries either to simple node activation or to a query tensor dynamics. PMID:14632170
Mathematically Reduced Chemical Reaction Mechanism Using Neural Networks
Ziaul Huque
2007-08-31
This is the final technical report for the project titled 'Mathematically Reduced Chemical Reaction Mechanism Using Neural Networks'. The aim of the project was to develop an efficient chemistry model for combustion simulations. The reduced chemistry model was developed mathematically without the need of having extensive knowledge of the chemistry involved. To aid in the development of the model, Neural Networks (NN) was used via a new network topology known as Non-linear Principal Components Analysis (NPCA). A commonly used Multilayer Perceptron Neural Network (MLP-NN) was modified to implement NPCA-NN. The training rate of NPCA-NN was improved with the GEneralized Regression Neural Network (GRNN) based on kernel smoothing techniques. Kernel smoothing provides a simple way of finding structure in data set without the imposition of a parametric model. The trajectory data of the reaction mechanism was generated based on the optimization techniques of genetic algorithm (GA). The NPCA-NN algorithm was then used for the reduction of Dimethyl Ether (DME) mechanism. DME is a recently discovered fuel made from natural gas, (and other feedstock such as coal, biomass, and urban wastes) which can be used in compression ignition engines as a substitute for diesel. An in-house two-dimensional Computational Fluid Dynamics (CFD) code was developed based on Meshfree technique and time marching solution algorithm. The project also provided valuable research experience to two graduate students.
DCS-Neural-Network Program for Aircraft Control and Testing
NASA Technical Reports Server (NTRS)
Jorgensen, Charles C.
2006-01-01
A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.
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.
Constructing general partial differential equations using polynomial and neural networks.
Zjavka, Ladislav; Pedrycz, Witold
2016-01-01
Sum fraction terms can approximate multi-variable functions on the basis of discrete observations, replacing a partial differential equation definition with polynomial elementary data relation descriptions. Artificial neural networks commonly transform the weighted sum of inputs to describe overall similarity relationships of trained and new testing input patterns. Differential polynomial neural networks form a new class of neural networks, which construct and solve an unknown general partial differential equation of a function of interest with selected substitution relative terms using non-linear multi-variable composite polynomials. The layers of the network generate simple and composite relative substitution terms whose convergent series combinations can describe partial dependent derivative changes of the input variables. This regression is based on trained generalized partial derivative data relations, decomposed into a multi-layer polynomial network structure. The sigmoidal function, commonly used as a nonlinear activation of artificial neurons, may transform some polynomial items together with the parameters with the aim to improve the polynomial derivative term series ability to approximate complicated periodic functions, as simple low order polynomials are not able to fully make up for the complete cycles. The similarity analysis facilitates substitutions for differential equations or can form dimensional units from data samples to describe real-world problems. PMID:26547244
Artificial neural network ensembles and their application in pooled flood frequency analysis
NASA Astrophysics Data System (ADS)
Shu, Chang; Burn, Donald H.
2004-09-01
Recent theoretical and empirical studies show that the generalization ability of artificial neural networks can be improved by combining several artificial neural networks in redundant ensembles. In this paper, a review is given of popular ensemble methods. Six approaches for creating artificial neural network ensembles are applied in pooled flood frequency analysis for estimating the index flood and the 10-year flood quantile. The results show that artificial neural network ensembles generate improved flood estimates and are less sensitive to the choice of initial parameters when compared with a single artificial neural network. Factors that may affect the generalization of an artificial neural network ensemble are analyzed. In terms of the methods for creating ensemble members, the model diversity introduced by varying the initial conditions of the base artificial neural networks to reduce the prediction error is comparable with more sophisticated methods, such as bagging and boosting. When the same method for creating ensemble members is used, combining member networks using stacking is generally better than using simple averaging. An ensemble size of at least 10 artificial neural networks is suggested to achieve sufficient generalization ability. In comparison with parametric regression methods, properly designed artificial neural network ensembles can significantly reduce the prediction error.
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.
A neural network approach to cloud classification
NASA Technical Reports Server (NTRS)
Lee, Jonathan; Weger, Ronald C.; Sengupta, Sailes K.; Welch, Ronald M.
1990-01-01
It is shown that, using high-spatial-resolution data, very high cloud classification accuracies can be obtained with a neural network approach. A texture-based neural network classifier using only single-channel visible Landsat MSS imagery achieves an overall cloud identification accuracy of 93 percent. Cirrus can be distinguished from boundary layer cloudiness with an accuracy of 96 percent, without the use of an infrared channel. Stratocumulus is retrieved with an accuracy of 92 percent, cumulus at 90 percent. The use of the neural network does not improve cirrus classification accuracy. Rather, its main effect is in the improved separation between stratocumulus and cumulus cloudiness. While most cloud classification algorithms rely on linear parametric schemes, the present study is based on a nonlinear, nonparametric four-layer neural network approach. A three-layer neural network architecture, the nonparametric K-nearest neighbor approach, and the linear stepwise discriminant analysis procedure are compared. A significant finding is that significantly higher accuracies are attained with the nonparametric approaches using only 20 percent of the database as training data, compared to 67 percent of the database in the linear approach.
Neural network technologies for image classification
NASA Astrophysics Data System (ADS)
Korikov, A. M.; Tungusova, A. V.
2015-11-01
We analyze the classes of problems with an objective necessity to use neural network technologies, i.e. representation and resolution problems in the neural network logical basis. Among these problems, image recognition takes an important place, in particular the classification of multi-dimensional data based on information about textural characteristics. These problems occur in aerospace and seismic monitoring, materials science, medicine and other. We reviewed different approaches for the texture description: statistical, structural, and spectral. We developed a neural network technology for resolving a practical problem of cloud image classification for satellite snapshots from the spectroradiometer MODIS. The cloud texture is described by the statistical characteristics of the GLCM (Gray Level Co- Occurrence Matrix) method. From the range of neural network models that might be applied for image classification, we chose the probabilistic neural network model (PNN) and developed an implementation which performs the classification of the main types and subtypes of clouds. Also, we chose experimentally the optimal architecture and parameters for the PNN model which is used for image classification.
Using Neural Networks to Describe Tracer Correlations
NASA Technical Reports Server (NTRS)
Lary, D. J.; Mueller, M. D.; Mussa, H. Y.
2003-01-01
Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). In this study a neural network using Quickprop learning and one hidden layer with eight nodes was able to reproduce the CH4-N2O correlation with a correlation co- efficient of 0.9995. Such an accurate representation of tracer-tracer correlations allows more use to be made of long-term datasets to constrain chemical models. Such as the dataset from the Halogen Occultation Experiment (HALOE) which has continuously observed CH4, (but not N2O) from 1991 till the present. The neural network Fortran code used is available for download.
Using neural networks for process planning
NASA Astrophysics Data System (ADS)
Huang, Samuel H.; Zhang, HongChao
1995-08-01
Process planning has been recognized as an interface between computer-aided design and computer-aided manufacturing. Since the late 1960s, computer techniques have been used to automate process planning activities. AI-based techniques are designed for capturing, representing, organizing, and utilizing knowledge by computers, and are extremely useful for automated process planning. To date, most of the AI-based approaches used in automated process planning are some variations of knowledge-based expert systems. Due to their knowledge acquisition bottleneck, expert systems are not sufficient in solving process planning problems. Fortunately, AI has developed other techniques that are useful for knowledge acquisition, e.g., neural networks. Neural networks have several advantages over expert systems that are desired in today's manufacturing practice. However, very few neural network applications in process planning have been reported. We present this paper in order to stimulate the research on using neural networks for process planning. This paper also identifies the problems with neural networks and suggests some possible solutions, which will provide some guidelines for research and implementation.
Fuzzy neural network with fast backpropagation learning
NASA Astrophysics Data System (ADS)
Wang, Zhiling; De Sario, Marco; Guerriero, Andrea; Mugnuolo, Raffaele
1995-03-01
Neural filters with multilayer backpropagation network have been proved to be able to define mostly all linear or non-linear filters. Because of the slowness of the networks' convergency, however, the applicable fields have been limited. In this paper, fuzzy logic is introduced to adjust learning rate and momentum parameter depending upon output errors and training times. This makes the convergency of the network greatly improved. Test curves are shown to prove the fast filters' performance.
Stability of Stochastic Neutral Cellular Neural Networks
NASA Astrophysics Data System (ADS)
Chen, Ling; Zhao, Hongyong
In this paper, we study a class of stochastic neutral cellular neural networks. By constructing a suitable Lyapunov functional and employing the nonnegative semi-martingale convergence theorem we give some sufficient conditions ensuring the almost sure exponential stability of the networks. The results obtained are helpful to design stability of networks when stochastic noise is taken into consideration. Finally, two examples are provided to show the correctness of our analysis.
Flexible body control using neural networks
NASA Technical Reports Server (NTRS)
Mccullough, Claire L.
1992-01-01
Progress is reported on the control of Control Structures Interaction suitcase demonstrator (a flexible structure) using neural networks and fuzzy logic. It is concluded that while control by neural nets alone (i.e., allowing the net to design a controller with no human intervention) has yielded less than optimal results, the neural net trained to emulate the existing fuzzy logic controller does produce acceptible system responses for the initial conditions examined. Also, a neural net was found to be very successful in performing the emulation step necessary for the anticipatory fuzzy controller for the CSI suitcase demonstrator. The fuzzy neural hybrid, which exhibits good robustness and noise rejection properties, shows promise as a controller for practical flexible systems, and should be further evaluated.
A 12-transistor PFM demodulator for analog neural networks communication.
Mortara, A; Vittoz, E A
1995-01-01
Pulse frequency modulation (PFM) provides robust long-distance communication and event-driven access to the communication channel. A PFM demodulator small and simple enough to equip every cell of a large analog neural network is analyzed. The circuit can demodulate PFM signals with pulse rates as low as 1 kHz using the switched-capacitor technique. Measurement results from integrated demodulators are presented. PMID:18263418
Can neural networks compete with process calculations
Blaesi, J.; Jensen, B.
1992-12-01
Neural networks have been called a real alternative to rigorous theoretical models. A theoretical model for the calculation of refinery coker naphtha end point and coker furnace oil 90% point already was in place on the combination tower of a coking unit. Considerable data had been collected on the theoretical model during the commissioning phase and benefit analysis of the project. A neural net developed for the coker fractionator has equalled the accuracy of theoretical models, and shown the capability to handle normal operating conditions. One disadvantage of a neural network is the amount of data needed to create a good model. Anywhere from 100 to thousands of cases are needed to create a neural network model. Overall, the correlation between theoretical and neural net models for both the coker naphtha end point and the coker furnace oil 90% point was about .80; the average deviation was about 4 degrees. This indicates that the neural net model was at least as capable as the theoretical model in calculating inferred properties. 3 figs.
Artificial neural networks for small dataset analysis.
Pasini, Antonello
2015-05-01
Artificial neural networks (ANNs) are usually considered as tools which can help to analyze cause-effect relationships in complex systems within a big-data framework. On the other hand, health sciences undergo complexity more than any other scientific discipline, and in this field large datasets are seldom available. In this situation, I show how a particular neural network tool, which is able to handle small datasets of experimental or observational data, can help in identifying the main causal factors leading to changes in some variable which summarizes the behaviour of a complex system, for instance the onset of a disease. A detailed description of the neural network tool is given and its application to a specific case study is shown. Recommendations for a correct use of this tool are also supplied. PMID:26101654
Kannada character recognition system using neural network
NASA Astrophysics Data System (ADS)
Kumar, Suresh D. S.; Kamalapuram, Srinivasa K.; Kumar, Ajay B. R.
2013-03-01
Handwriting recognition has been one of the active and challenging research areas in the field of pattern recognition. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. As there is no sufficient number of works on Indian language character recognition especially Kannada script among 15 major scripts in India. In this paper an attempt is made to recognize handwritten Kannada characters using Feed Forward neural networks. A handwritten Kannada character is resized into 20x30 Pixel. The resized character is used for training the neural network. Once the training process is completed the same character is given as input to the neural network with different set of neurons in hidden layer and their recognition accuracy rate for different Kannada characters has been calculated and compared. The results show that the proposed system yields good recognition accuracy rates comparable to that of other handwritten character recognition systems.
Classification of radar clutter using neural networks.
Haykin, S; Deng, C
1991-01-01
A classifier that incorporates both preprocessing and postprocessing procedures as well as a multilayer feedforward network (based on the back-propagation algorithm) in its design to distinguish between several major classes of radar returns including weather, birds, and aircraft is described. The classifier achieves an average classification accuracy of 89% on generalization for data collected during a single scan of the radar antenna. The procedures of feature selection for neural network training, the classifier design considerations, the learning algorithm development, the implementation, and the experimental results of the neural clutter classifier, which is simulated on a Warp systolic computer, are discussed. A comparative evaluation of the multilayer neural network with a traditional Bayes classifier is presented. PMID:18282874
Critical and resonance phenomena in neural networks
NASA Astrophysics Data System (ADS)
Goltsev, A. V.; Lopes, M. A.; Lee, K.-E.; Mendes, J. F. F.
2013-01-01
Brain rhythms contribute to every aspect of brain function. Here, we study critical and resonance phenomena that precede the emergence of brain rhythms. Using an analytical approach and simulations of a cortical circuit model of neural networks with stochastic neurons in the presence of noise, we show that spontaneous appearance of network oscillations occurs as a dynamical (non-equilibrium) phase transition at a critical point determined by the noise level, network structure, the balance between excitatory and inhibitory neurons, and other parameters. We find that the relaxation time of neural activity to a steady state, response to periodic stimuli at the frequency of the oscillations, amplitude of damped oscillations, and stochastic fluctuations of neural activity are dramatically increased when approaching the critical point of the transition.
Web traffic prediction with artificial neural networks
NASA Astrophysics Data System (ADS)
Gluszek, Adam; Kekez, Michal; Rudzinski, Filip
2005-02-01
The main aim of the paper is to present application of the artificial neural network in the web traffic prediction. First, the general problem of time series modelling and forecasting is shortly described. Next, the details of building of dynamic processes models with the neural networks are discussed. At this point determination of the model structure in terms of its inputs and outputs is the most important question because this structure is a rough approximation of the dynamics of the modelled process. The following section of the paper presents the results obtained applying artificial neural network (classical multilayer perceptron trained with backpropagation algorithm) to the real-world web traffic prediction. Finally, we discuss the results, describe weak points of presented method and propose some alternative approaches.
Artificial neural networks for small dataset analysis
2015-01-01
Artificial neural networks (ANNs) are usually considered as tools which can help to analyze cause-effect relationships in complex systems within a big-data framework. On the other hand, health sciences undergo complexity more than any other scientific discipline, and in this field large datasets are seldom available. In this situation, I show how a particular neural network tool, which is able to handle small datasets of experimental or observational data, can help in identifying the main causal factors leading to changes in some variable which summarizes the behaviour of a complex system, for instance the onset of a disease. A detailed description of the neural network tool is given and its application to a specific case study is shown. Recommendations for a correct use of this tool are also supplied. PMID:26101654
Effects of Fast Simple Numerical Calculation Training on Neural Systems
Takeuchi, Hikaru; Nagase, Tomomi; Taki, Yasuyuki; Sassa, Yuko; Hashizume, Hiroshi; Nouchi, Rui; Kawashima, Ryuta
2016-01-01
Cognitive training, including fast simple numerical calculation (FSNC), has been shown to improve performance on untrained processing speed and executive function tasks in the elderly. However, the effects of FSNC training on cognitive functions in the young and on neural mechanisms remain unknown. We investigated the effects of 1-week intensive FSNC training on cognitive function, regional gray matter volume (rGMV), and regional cerebral blood flow at rest (resting rCBF) in healthy young adults. FSNC training was associated with improvements in performance on simple processing speed, speeded executive functioning, and simple and complex arithmetic tasks. FSNC training was associated with a reduction in rGMV and an increase in resting rCBF in the frontopolar areas and a weak but widespread increase in resting rCBF in an anatomical cluster in the posterior region. These results provide direct evidence that FSNC training alone can improve performance on processing speed and executive function tasks as well as plasticity of brain structures and perfusion. Our results also indicate that changes in neural systems in the frontopolar areas may underlie these cognitive improvements. PMID:26881117
On the Local-Field Distribution in Attractor Neural Networks
NASA Astrophysics Data System (ADS)
Korutcheva, E.; Koroutchev, K.
In this paper a simple two-layer neural network's model, similar to that studied by D. Amit and N. Brunel,11 is investigated in the frames of the mean-field approximation. The distributions of the local fields are analytically derived and compared to those obtained in Ref. 11. The dynamic properties are discussed and the basin of attraction in some parametric space is found. A procedure for driving the system into a basin of attraction by using a regulation imposed on the network is proposed. The effect of outer stimulus is shown to have a destructive influence on the attractor, forcing the latter to disappear if the distribution of the stimulus has high enough variance or if the stimulus has a spatial structure with sufficient contrast. The techniques, used in this paper, for obtaining the analytical results can be applied to more complex topologies of linked recurrent neural networks.
A simple model for studying interacting networks
NASA Astrophysics Data System (ADS)
Liu, Wenjia; Jolad, Shivakumar; Schmittmann, Beate; Zia, R. K. P.
2011-03-01
Many specific physical networks (e.g., internet, power grid, interstates), have been characterized in considerable detail, but in isolation from each other. Yet, each of these networks supports the functions of the others, and so far, little is known about how their interactions affect their structure and functionality. To address this issue, we consider two coupled model networks. Each network is relatively simple, with a fixed set of nodes, but dynamically generated set of links which has a preferred degree, κ . In the stationary state, the degree distribution has exponential tails (far from κ), an attribute which we can explain. Next, we consider two such networks with different κ 's, reminiscent of two social groups, e.g., extroverts and introverts. Finally, we let these networks interact by establishing a controllable fraction of cross links. The resulting distribution of links, both within and across the two model networks, is investigated and discussed, along with some potential consequences for real networks. Supported in part by NSF-DMR-0705152 and 1005417.
Proceedings of the Neural Network Workshop for the Hanford Community
Keller, P.E.
1994-01-01
These proceedings were generated from a series of presentations made at the Neural Network Workshop for the Hanford Community. The abstracts and viewgraphs of each presentation are reproduced in these proceedings. This workshop was sponsored by the Computing and Information Sciences Department in the Molecular Science Research Center (MSRC) at the Pacific Northwest Laboratory (PNL). Artificial neural networks constitute a new information processing technology that is destined within the next few years, to provide the world with a vast array of new products. A major reason for this is that artificial neural networks are able to provide solutions to a wide variety of complex problems in a much simpler fashion than is possible using existing techniques. In recognition of these capabilities, many scientists and engineers are exploring the potential application of this new technology to their fields of study. An artificial neural network (ANN) can be a software simulation, an electronic circuit, optical system, or even an electro-chemical system designed to emulate some of the brain`s rudimentary structure as well as some of the learning processes that are believed to take place in the brain. For a very wide range of applications in science, engineering, and information technology, ANNs offer a complementary and potentially superior approach to that provided by conventional computing and conventional artificial intelligence. This is because, unlike conventional computers, which have to be programmed, ANNs essentially learn from experience and can be trained in a straightforward fashion to carry out tasks ranging from the simple to the highly complex.
Application of artificial neural networks to eating disorders.
Buscema, M; Mazzetti di Pietralata, M; Salvemini, V; Intraligi, M; Indrimi, M
1998-02-01
An experimental application of Artificial Neural Networks to Eating Disorders is presented. The sample, composed of 172 cases (all women) collected at the Centre for the Diagnosis and Treatment of Eating Disorders of the 1st Medical Division of the St. Eugenio Hospital of Rome, was subdivided, on the basis of the diagnosis made by the specialist of the St. Eugenio, into four classes: Anorexia Nervosa (AN), Nervous Bulimia (NB), Binge Eating Disorders (BED) and Psychogenic Eating Disorders that are Not Otherwise Specified (PED-NOS). The data base was composed of 124 different variables: generic information, alimentary behavior, eventual treatment and hospitalization, substance use, menstrual cycles, weight and height, hematochemical and instrumental examinations, psychodiagnostic tests, etc. The goal of this experiment was to verify the accuracy of the Neural Networks in recognising anorexic and bulimic patients. This article describes 6 experiments, using a Feed Forward Neural Network, each one using different variables. Starting from only the generic variables (life styles, family environment, etc.) and hematoclinical and instrumental examinations, a Neural Networks provided 86.94% of the prediction precision. This work is meant to be a first contribution to creating diagnostic procedures for Eating Disorders, that would be simple and easy-to-use by professionals who are neither psychologists nor psychiatrists nor psychotherapists but who are, however, among the first to meet these patients and who are therefore called upon to give such patients the very first pieces of advice on seeking proper treatment. PMID:9533740
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.
Autonomous robot behavior based on neural networks
NASA Astrophysics Data System (ADS)
Grolinger, Katarina; Jerbic, Bojan; Vranjes, Bozo
1997-04-01
The purpose of autonomous robot is to solve various tasks while adapting its behavior to the variable environment, expecting it is able to navigate much like a human would, including handling uncertain and unexpected obstacles. To achieve this the robot has to be able to find solution to unknown situations, to learn experienced knowledge, that means action procedure together with corresponding knowledge on the work space structure, and to recognize working environment. The planning of the intelligent robot behavior presented in this paper implements the reinforcement learning based on strategic and random attempts for finding solution and neural network approach for memorizing and recognizing work space structure (structural assignment problem). Some of the well known neural networks based on unsupervised learning are considered with regard to the structural assignment problem. The adaptive fuzzy shadowed neural network is developed. It has the additional shadowed hidden layer, specific learning rule and initialization phase. The developed neural network combines advantages of networks based on the Adaptive Resonance Theory and using shadowed hidden layer provides ability to recognize lightly translated or rotated obstacles in any direction.
Experimental analysis of a Lotka-Volterra neural network for classification
NASA Astrophysics Data System (ADS)
Sukhu, Christopher L.; Stanton, Joseph; Aylesworth, Marc
2015-06-01
An experimental study of a neural network modeled by an adaptive Lotka-Volterra system follows. With totally inhibitory connections, this system can be embedded in a simple classification network. This network is able to classify and monitor its inputs in a spontaneous nonlinear fashion without prior training. We describe a framework for leveraging this behavior through an example involving breast cancer diagnosis.
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.
Fuzzy logic, neural networks, and soft computing
NASA Technical Reports Server (NTRS)
Zadeh, Lofti A.
1994-01-01
The past few years have witnessed a rapid growth of interest in a cluster of modes of modeling and computation which may be described collectively as soft computing. The distinguishing characteristic of soft computing is that its primary aims are to achieve tractability, robustness, low cost, and high MIQ (machine intelligence quotient) through an exploitation of the tolerance for imprecision and uncertainty. Thus, in soft computing what is usually sought is an approximate solution to a precisely formulated problem or, more typically, an approximate solution to an imprecisely formulated problem. A simple case in point is the problem of parking a car. Generally, humans can park a car rather easily because the final position of the car is not specified exactly. If it were specified to within, say, a few millimeters and a fraction of a degree, it would take hours or days of maneuvering and precise measurements of distance and angular position to solve the problem. What this simple example points to is the fact that, in general, high precision carries a high cost. The challenge, then, is to exploit the tolerance for imprecision by devising methods of computation which lead to an acceptable solution at low cost. By its nature, soft computing is much closer to human reasoning than the traditional modes of computation. At this juncture, the major components of soft computing are fuzzy logic (FL), neural network theory (NN), and probabilistic reasoning techniques (PR), including genetic algorithms, chaos theory, and part of learning theory. Increasingly, these techniques are used in combination to achieve significant improvement in performance and adaptability. Among the important application areas for soft computing are control systems, expert systems, data compression techniques, image processing, and decision support systems. It may be argued that it is soft computing, rather than the traditional hard computing, that should be viewed as the foundation for artificial
A neural network with modular hierarchical learning
NASA Technical Reports Server (NTRS)
Baldi, Pierre F. (Inventor); Toomarian, Nikzad (Inventor)
1994-01-01
This invention provides a new hierarchical approach for supervised neural learning of time dependent trajectories. The modular hierarchical methodology leads to architectures which are more structured than fully interconnected networks. The networks utilize a general feedforward flow of information and sparse recurrent connections to achieve dynamic effects. The advantages include the sparsity of units and connections, the modular organization. A further advantage is that the learning is much more circumscribed learning than in fully interconnected systems. The present invention is embodied by a neural network including a plurality of neural modules each having a pre-established performance capability wherein each neural module has an output outputting present results of the performance capability and an input for changing the present results of the performance capabilitiy. For pattern recognition applications, the performance capability may be an oscillation capability producing a repeating wave pattern as the present results. In the preferred embodiment, each of the plurality of neural modules includes a pre-established capability portion and a performance adjustment portion connected to control the pre-established capability portion.
Neural network tomography: network replication from output surface geometry.
Minnett, Rupert C J; Smith, Andrew T; Lennon, William C; Hecht-Nielsen, Robert
2011-06-01
Multilayer perceptron networks whose outputs consist of affine combinations of hidden units using the tanh activation function are universal function approximators and are used for regression, typically by reducing the MSE with backpropagation. We present a neural network weight learning algorithm that directly positions the hidden units within input space by numerically analyzing the curvature of the output surface. Our results show that under some sampling requirements, this method can reliably recover the parameters of a neural network used to generate a data set. PMID:21377326
Development of programmable artificial neural networks
NASA Technical Reports Server (NTRS)
Meade, Andrew J.
1993-01-01
Conventionally programmed digital computers can process numbers with great speed and precision, but do not easily recognize patterns or imprecise or contradictory data. Instead of being programmed in the conventional sense, artificial neural networks are capable of self-learning through exposure to repeated examples. However, the training of an ANN can be a time consuming and unpredictable process. A general method is being developed to mate the adaptability of the ANN with the speed and precision of the digital computer. This method was successful in building feedforward networks that can approximate functions and their partial derivatives from examples in a single iteration. The general method also allows the formation of feedforward networks that can approximate the solution to nonlinear ordinary and partial differential equations to desired accuracy without the need of examples. It is believed that continued research will produce artificial neural networks that can be used with confidence in practical scientific computing and engineering applications.
Field-theoretic approach to fluctuation effects in neural networks
Buice, Michael A.; Cowan, Jack D.
2007-05-15
A well-defined stochastic theory for neural activity, which permits the calculation of arbitrary statistical moments and equations governing them, is a potentially valuable tool for theoretical neuroscience. We produce such a theory by analyzing the dynamics of neural activity using field theoretic methods for nonequilibrium statistical processes. Assuming that neural network activity is Markovian, we construct the effective spike model, which describes both neural fluctuations and response. This analysis leads to a systematic expansion of corrections to mean field theory, which for the effective spike model is a simple version of the Wilson-Cowan equation. We argue that neural activity governed by this model exhibits a dynamical phase transition which is in the universality class of directed percolation. More general models (which may incorporate refractoriness) can exhibit other universality classes, such as dynamic isotropic percolation. Because of the extremely high connectivity in typical networks, it is expected that higher-order terms in the systematic expansion are small for experimentally accessible measurements, and thus, consistent with measurements in neocortical slice preparations, we expect mean field exponents for the transition. We provide a quantitative criterion for the relative magnitude of each term in the systematic expansion, analogous to the Ginsburg criterion. Experimental identification of dynamic universality classes in vivo is an outstanding and important question for neuroscience.
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.
Constructive approximate interpolation by neural networks
NASA Astrophysics Data System (ADS)
Llanas, B.; Sainz, F. J.
2006-04-01
We present a type of single-hidden layer feedforward neural networks with sigmoidal nondecreasing activation function. We call them ai-nets. They can approximately interpolate, with arbitrary precision, any set of distinct data in one or several dimensions. They can uniformly approximate any continuous function of one variable and can be used for constructing uniform approximants of continuous functions of several variables. All these capabilities are based on a closed expression of the networks.
Digital Neural Networks for New Media
NASA Astrophysics Data System (ADS)
Spaanenburg, Lambert; Malki, Suleyman
Neural Networks perform computationally intensive tasks offering smart solutions for many new media applications. A number of analog and mixed digital/analog implementations have been proposed to smooth the algorithmic gap. But gradually, the digital implementation has become feasible, and the dedicated neural processor is on the horizon. A notable example is the Cellular Neural Network (CNN). The analog direction has matured for low-power, smart vision sensors; the digital direction is gradually being shaped into an IP-core for algorithm acceleration, especially for use in FPGA-based high-performance systems. The chapter discusses the next step towards a flexible and scalable multi-core engine using Application-Specific Integrated Processors (ASIP). This topographic engine can serve many new media tasks, as illustrated by novel applications in Homeland Security. We conclude with a view on the CNN kaleidoscope for the year 2020.
NASA Astrophysics Data System (ADS)
Gan, Qintao; Lv, Tianshi; Fu, Zhenhua
2016-04-01
In this paper, the synchronization problem for a class of generalized neural networks with time-varying delays and reaction-diffusion terms is investigated concerning Neumann boundary conditions in terms of p-norm. The proposed generalized neural networks model includes reaction-diffusion local field neural networks and reaction-diffusion static neural networks as its special cases. By establishing a new inequality, some simple and useful conditions are obtained analytically to guarantee the global exponential synchronization of the addressed neural networks under the periodically intermittent control. According to the theoretical results, the influences of diffusion coefficients, diffusion space, and control rate on synchronization are analyzed. Finally, the feasibility and effectiveness of the proposed methods are shown by simulation examples, and by choosing different diffusion coefficients, diffusion spaces, and control rates, different controlled synchronization states can be obtained.
A neural network architecture for implementation of expert systems for real time monitoring
NASA Technical Reports Server (NTRS)
Ramamoorthy, P. A.
1991-01-01
Since neural networks have the advantages of massive parallelism and simple architecture, they are good tools for implementing real time expert systems. In a rule based expert system, the antecedents of rules are in the conjunctive or disjunctive form. We constructed a multilayer feedforward type network in which neurons represent AND or OR operations of rules. Further, we developed a translator which can automatically map a given rule base into the network. Also, we proposed a new and powerful yet flexible architecture that combines the advantages of both fuzzy expert systems and neural networks. This architecture uses the fuzzy logic concepts to separate input data domains into several smaller and overlapped regions. Rule-based expert systems for time critical applications using neural networks, the automated implementation of rule-based expert systems with neural nets, and fuzzy expert systems vs. neural nets are covered.
Tutorial: Neural networks and their potential application in nuclear power plants
Uhrig, R.E. . Dept. of Nuclear Engineering Oak Ridge National Lab., TN )
1989-01-01
A neural network is a data processing system consisting of a number of simple, highly interconnected processing elements in an architecture inspired by the structure of the cerebral cortex portion of the brain. Hence, neural networks are often capable of doing things which humans or animals do well but which conventional computers often do poorly. Neural networks have emerged in the past few years as an area of unusual opportunity for research, development and application to a variety of real world problems. Indeed, neural networks exhibit characteristics and capabilities not provided by any other technology. Examples include reading Japanese Kanji characters and human handwriting, reading a typewritten manuscript aloud, compensating for alignment errors in robots, interpreting very noise'' signals (e.g. electroencephalograms), modeling complex systems that cannot be modelled mathematically, and predicting whether proposed loans will be good or fail. This paper presents a brief tutorial on neural networks and describes research on the potential applications to nuclear power plants.
Gan, Qintao; Lv, Tianshi; Fu, Zhenhua
2016-04-01
In this paper, the synchronization problem for a class of generalized neural networks with time-varying delays and reaction-diffusion terms is investigated concerning Neumann boundary conditions in terms of p-norm. The proposed generalized neural networks model includes reaction-diffusion local field neural networks and reaction-diffusion static neural networks as its special cases. By establishing a new inequality, some simple and useful conditions are obtained analytically to guarantee the global exponential synchronization of the addressed neural networks under the periodically intermittent control. According to the theoretical results, the influences of diffusion coefficients, diffusion space, and control rate on synchronization are analyzed. Finally, the feasibility and effectiveness of the proposed methods are shown by simulation examples, and by choosing different diffusion coefficients, diffusion spaces, and control rates, different controlled synchronization states can be obtained. PMID:27131492
Optoelectronic Integrated Circuits For Neural Networks
NASA Technical Reports Server (NTRS)
Psaltis, D.; Katz, J.; Kim, Jae-Hoon; Lin, S. H.; Nouhi, A.
1990-01-01
Many threshold devices placed on single substrate. Integrated circuits containing optoelectronic threshold elements developed for use as planar arrays of artificial neurons in research on neural-network computers. Mounted with volume holograms recorded in photorefractive crystals serving as dense arrays of variable interconnections between neurons.
Psychometric Measurement Models and Artificial Neural Networks
ERIC Educational Resources Information Center
Sese, Albert; Palmer, Alfonso L.; Montano, Juan J.
2004-01-01
The study of measurement models in psychometrics by means of dimensionality reduction techniques such as Principal Components Analysis (PCA) is a very common practice. In recent times, an upsurge of interest in the study of artificial neural networks apt to computing a principal component extraction has been observed. Despite this interest, the…
Active Sampling in Evolving Neural Networks.
ERIC Educational Resources Information Center
Parisi, Domenico
1997-01-01
Comments on Raftopoulos article (PS 528 649) on facilitative effect of cognitive limitation in development and connectionist models. Argues that the use of neural networks within an "Artificial Life" perspective can more effectively contribute to the study of the role of cognitive limitations in development and their genetic basis than can using…
Localizing Tortoise Nests by Neural Networks
2016-01-01
The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating). Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS) which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN). We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours), the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition. PMID:26985660
Neural network application to comprehensive engine diagnostics
NASA Technical Reports Server (NTRS)
Marko, Kenneth A.
1994-01-01
We have previously reported on the use of neural networks for detection and identification of faults in complex microprocessor controlled powertrain systems. The data analyzed in those studies consisted of the full spectrum of signals passing between the engine and the real-time microprocessor controller. The specific task of the classification system was to classify system operation as nominal or abnormal and to identify the fault present. The primary concern in earlier work was the identification of faults, in sensors or actuators in the powertrain system as it was exercised over its full operating range. The use of data from a variety of sources, each contributing some potentially useful information to the classification task, is commonly referred to as sensor fusion and typifies the type of problems successfully addressed using neural networks. In this work we explore the application of neural networks to a different diagnostic problem, the diagnosis of faults in newly manufactured engines and the utility of neural networks for process control.
Localizing Tortoise Nests by Neural Networks.
Barbuti, Roberto; Chessa, Stefano; Micheli, Alessio; Pucci, Rita
2016-01-01
The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating). Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS) which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN). We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours), the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition. PMID:26985660
Nonlinear Time Series Analysis via Neural Networks
NASA Astrophysics Data System (ADS)
Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin
This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.
Foetal ECG recovery using dynamic neural networks.
Camps-Valls, Gustavo; Martínez-Sober, Marcelino; Soria-Olivas, Emilio; Magdalena-Benedito, Rafael; Calpe-Maravilla, Javier; Guerrero-Martínez, Juan
2004-07-01
Non-invasive electrocardiography has proven to be a very interesting method for obtaining information about the foetus state and thus to assure its well-being during pregnancy. One of the main applications in this field is foetal electrocardiogram (ECG) recovery by means of automatic methods. Evident problems found in the literature are the limited number of available registers, the lack of performance indicators, and the limited use of non-linear adaptive methods. In order to circumvent these problems, we first introduce the generation of synthetic registers and discuss the influence of different kinds of noise to the modelling. Second, a method which is based on numerical (correlation coefficient) and statistical (analysis of variance, ANOVA) measures allows us to select the best recovery model. Finally, finite impulse response (FIR) and gamma neural networks are included in the adaptive noise cancellation (ANC) scheme in order to provide highly non-linear, dynamic capabilities to the recovery model. Neural networks are benchmarked with classical adaptive methods such as the least mean squares (LMS) and the normalized LMS (NLMS) algorithms in simulated and real registers and some conclusions are drawn. For synthetic registers, the most determinant factor in the identification of the models is the foetal-maternal signal-to-noise ratio (SNR). In addition, as the electromyogram contribution becomes more relevant, neural networks clearly outperform the LMS-based algorithm. From the ANOVA test, we found statistical differences between LMS-based models and neural models when complex situations (high foetal-maternal and foetal-noise SNRs) were present. These conclusions were confirmed after doing robustness tests on synthetic registers, visual inspection of the recovered signals and calculation of the recognition rates of foetal R-peaks for real situations. Finally, the best compromise between model complexity and outcomes was provided by the FIR neural network. Both
Optimal input sizes for neural network de-interlacing
NASA Astrophysics Data System (ADS)
Choi, Hyunsoo; Seo, Guiwon; Lee, Chulhee
2009-02-01
Neural network de-interlacing has shown promising results among various de-interlacing methods. In this paper, we investigate the effects of input size for neural networks for various video formats when the neural networks are used for de-interlacing. In particular, we investigate optimal input sizes for CIF, VGA and HD video formats.
[Application of artificial neural networks in infectious diseases].
Xu, Jun-fang; Zhou, Xiao-nong
2011-02-28
With the development of information technology, artificial neural networks has been applied to many research fields. Due to the special features such as nonlinearity, self-adaptation, and parallel processing, artificial neural networks are applied in medicine and biology. This review summarizes the application of artificial neural networks in the relative factors, prediction and diagnosis of infectious diseases in recent years. PMID:21823326
Algorithm For A Self-Growing Neural Network
NASA Technical Reports Server (NTRS)
Cios, Krzysztof J.
1996-01-01
CID3 algorithm simulates self-growing neural network. Constructs decision trees equivalent to hidden layers of neural network. Based on ID3 algorithm, which dynamically generates decision tree while minimizing entropy of information. CID3 algorithm generates feedforward neural network by use of either crisp or fuzzy measure of entropy.
Super-linear Precision in Simple Neural Population Codes
NASA Astrophysics Data System (ADS)
Schwab, David; Fiete, Ila
2015-03-01
A widely used tool for quantifying the precision with which a population of noisy sensory neurons encodes the value of an external stimulus is the Fisher Information (FI). Maximizing the FI is also a commonly used objective for constructing optimal neural codes. The primary utility and importance of the FI arises because it gives, through the Cramer-Rao bound, the smallest mean-squared error achievable by any unbiased stimulus estimator. However, it is well-known that when neural firing is sparse, optimizing the FI can result in codes that perform very poorly when considering the resulting mean-squared error, a measure with direct biological relevance. Here we construct optimal population codes by minimizing mean-squared error directly and study the scaling properties of the resulting network, focusing on the optimal tuning curve width. We then extend our results to continuous attractor networks that maintain short-term memory of external stimuli in their dynamics. Here we find similar scaling properties in the structure of the interactions that minimize diffusive information loss.
Learning Contextual Dependence With Convolutional Hierarchical Recurrent Neural Networks
NASA Astrophysics Data System (ADS)
Zuo, Zhen; Shuai, Bing; Wang, Gang; Liu, Xiao; Wang, Xingxing; Wang, Bing; Chen, Yushi
2016-07-01
Existing deep convolutional neural networks (CNNs) have shown their great success on image classification. CNNs mainly consist of convolutional and pooling layers, both of which are performed on local image areas without considering the dependencies among different image regions. However, such dependencies are very important for generating explicit image representation. In contrast, recurrent neural networks (RNNs) are well known for their ability of encoding contextual information among sequential data, and they only require a limited number of network parameters. General RNNs can hardly be directly applied on non-sequential data. Thus, we proposed the hierarchical RNNs (HRNNs). In HRNNs, each RNN layer focuses on modeling spatial dependencies among image regions from the same scale but different locations. While the cross RNN scale connections target on modeling scale dependencies among regions from the same location but different scales. Specifically, we propose two recurrent neural network models: 1) hierarchical simple recurrent network (HSRN), which is fast and has low computational cost; and 2) hierarchical long-short term memory recurrent network (HLSTM), which performs better than HSRN with the price of more computational cost. In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs). C-HRNNs not only make use of the representation power of CNNs, but also efficiently encodes spatial and scale dependencies among different image regions. On four of the most challenging object/scene image classification benchmarks, our C-HRNNs achieve state-of-the-art results on Places 205, SUN 397, MIT indoor, and competitive results on ILSVRC 2012.
Neural network modelling of non-linear hydrological relationships
NASA Astrophysics Data System (ADS)
Abrahart, R. J.; See, L. M.
2007-09-01
Two recent studies have suggested that neural network modelling offers no worthwhile improvements in comparison to the application of weighted linear transfer functions for capturing the non-linear nature of hydrological relationships. The potential of an artificial neural network to perform simple non-linear hydrological transformations under controlled conditions is examined in this paper. Eight neural network models were developed: four full or partial emulations of a recognised non-linear hydrological rainfall-runoff model; four solutions developed on an identical set of inputs and a calculated runoff coefficient output. The use of different input combinations enabled the competencies of solutions developed on a reduced number of parameters to be assessed. The selected hydrological model had a limited number of inputs and contained no temporal component. The modelling process was based on a set of random inputs that had a uniform distribution and spanned a modest range of possibilities. The initial cloning operations permitted a direct comparison to be performed with the equation-based relationship. It also provided more general information about the power of a neural network to replicate mathematical equations and model modest non-linear relationships. The second group of experiments explored a different relationship that is of hydrological interest; the target surface contained a stronger set of non-linear properties and was more challenging. Linear modelling comparisons were performed against traditional least squares multiple linear regression solutions developed on identical datasets. The reported results demonstrate that neural networks are capable of modelling non-linear hydrological processes and are therefore appropriate tools for hydrological modelling.
Intrinsic adaptation in autonomous recurrent neural networks.
Marković, Dimitrije; Gros, Claudius
2012-02-01
A massively recurrent neural network responds on one side to input stimuli and is autonomously active, on the other side, in the absence of sensory inputs. Stimuli and information processing depend crucially on the quality of the autonomous-state dynamics of the ongoing neural activity. This default neural activity may be dynamically structured in time and space, showing regular, synchronized, bursting, or chaotic activity patterns. We study the influence of nonsynaptic plasticity on the default dynamical state of recurrent neural networks. The nonsynaptic adaption considered acts on intrinsic neural parameters, such as the threshold and the gain, and is driven by the optimization of the information entropy. We observe, in the presence of the intrinsic adaptation processes, three distinct and globally attracting dynamical regimes: a regular synchronized, an overall chaotic, and an intermittent bursting regime. The intermittent bursting regime is characterized by intervals of regular flows, which are quite insensitive to external stimuli, interceded by chaotic bursts that respond sensitively to input signals. We discuss these findings in the context of self-organized information processing and critical brain dynamics. PMID:22091667
Finite element neural networks for electromagnetic inverse problems
NASA Astrophysics Data System (ADS)
Ramuhalli, P.; Udpa, L.; Udpa, S.
2002-05-01
Iterative approaches using numerical forward models are commonly used for solving inverse problems in nondestructive evaluation. The drawbacks of these approaches include their high computational cost and the difficulty in computing gradients for updating defect profiles. This paper proposes a finite element neural network (FENN) that embeds finite element models into a neural network format. This approach enables fast and accurate solution of the forward problem. The FENN can then be used as the forward model in an iterative approach to solve the inverse problem. Gradient-based optimization methods are easily applied since the FENN provides an explicit functional mapping between the defect profile and the measured signal. Results of applying the FENN to several simple electromagnetic forward and inverse problems are presented.
Application of Artificial Neural Networks for estimating index floods
NASA Astrophysics Data System (ADS)
Šimor, Viliam; Hlavčová, Kamila; Kohnová, Silvia; Szolgay, Ján
2012-12-01
This article presents an application of Artificial Neural Networks (ANNs) and multiple regression models for estimating mean annual maximum discharge (index flood) at ungauged sites. Both approaches were tested for 145 small basins in Slovakia in areas ranging from 20 to 300 km2. Using the objective clustering method, the catchments were divided into ten homogeneous pooling groups; for each pooling group, mutually independent predictors (catchment characteristics) were selected for both models. The neural network was applied as a simple multilayer perceptron with one hidden layer and with a back propagation learning algorithm. Hyperbolic tangents were used as an activation function in the hidden layer. Estimating index floods by the multiple regression models were based on deriving relationships between the index floods and catchment predictors. The efficiencies of both approaches were tested by the Nash-Sutcliffe and a correlation coefficients. The results showed the comparative applicability of both models with slightly better results for the index floods achieved using the ANNs methodology.
Classifying multispectral data by neural networks
NASA Technical Reports Server (NTRS)
Telfer, Brian A.; Szu, Harold H.; Kiang, Richard K.
1993-01-01
Several energy functions for synthesizing neural networks are tested on 2-D synthetic data and on Landsat-4 Thematic Mapper data. These new energy functions, designed specifically for minimizing misclassification error, in some cases yield significant improvements in classification accuracy over the standard least mean squares energy function. In addition to operating on networks with one output unit per class, a new energy function is tested for binary encoded outputs, which result in smaller network sizes. The Thematic Mapper data (four bands were used) is classified on a single pixel basis, to provide a starting benchmark against which further improvements will be measured. Improvements are underway to make use of both subpixel and superpixel (i.e. contextual or neighborhood) information in tile processing. For single pixel classification, the best neural network result is 78.7 percent, compared with 71.7 percent for a classical nearest neighbor classifier. The 78.7 percent result also improves on several earlier neural network results on this data.
Color control of printers by neural networks
NASA Astrophysics Data System (ADS)
Tominaga, Shoji
1998-07-01
A method is proposed for solving the mapping problem from the 3D color space to the 4D CMYK space of printer ink signals by means of a neural network. The CIE-L*a*b* color system is used as the device-independent color space. The color reproduction problem is considered as the problem of controlling an unknown static system with four inputs and three outputs. A controller determines the CMYK signals necessary to produce the desired L*a*b* values with a given printer. Our solution method for this control problem is based on a two-phase procedure which eliminates the need for UCR and GCR. The first phase determines a neural network as a model of the given printer, and the second phase determines the combined neural network system by combining the printer model and the controller in such a way that it represents an identity mapping in the L*a*b* color space. Then the network of the controller part realizes the mapping from the L*a*b* space to the CMYK space. Practical algorithms are presented in the form of multilayer feedforward networks. The feasibility of the proposed method is shown in experiments using a dye sublimation printer and an ink jet printer.
A Topological Perspective of Neural Network Structure
NASA Astrophysics Data System (ADS)
Sizemore, Ann; Giusti, Chad; Cieslak, Matthew; Grafton, Scott; Bassett, Danielle
The wiring patterns of white matter tracts between brain regions inform functional capabilities of the neural network. Indeed, densely connected and cyclically arranged cognitive systems may communicate and thus perform distinctly. However, previously employed graph theoretical statistics are local in nature and thus insensitive to such global structure. Here we present an investigation of the structural neural network in eight healthy individuals using persistent homology. An extension of homology to weighted networks, persistent homology records both circuits and cliques (all-to-all connected subgraphs) through a repetitive thresholding process, thus perceiving structural motifs. We report structural features found across patients and discuss brain regions responsible for these patterns, finally considering the implications of such motifs in relation to cognitive function.
Fuzzy logic and neural network technologies
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Lea, Robert N.; Savely, Robert T.
1992-01-01
Applications of fuzzy logic technologies in NASA projects are reviewed to examine their advantages in the development of neural networks for aerospace and commercial expert systems and control. Examples of fuzzy-logic applications include a 6-DOF spacecraft controller, collision-avoidance systems, and reinforcement-learning techniques. The commercial applications examined include a fuzzy autofocusing system, an air conditioning system, and an automobile transmission application. The practical use of fuzzy logic is set in the theoretical context of artificial neural systems (ANSs) to give the background for an overview of ANS research programs at NASA. The research and application programs include the Network Execution and Training Simulator and faster training algorithms such as the Difference Optimized Training Scheme. The networks are well suited for pattern-recognition applications such as predicting sunspots, controlling posture maintenance, and conducting adaptive diagnoses.
a Heterosynaptic Learning Rule for Neural Networks
NASA Astrophysics Data System (ADS)
Emmert-Streib, Frank
In this article we introduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.
Neural networks: Application to medical imaging
NASA Technical Reports Server (NTRS)
Clarke, Laurence P.
1994-01-01
The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.
Controlling neural network responsiveness: tradeoffs and constraints
Keren, Hanna; Marom, Shimon
2014-01-01
In recent years much effort is invested in means to control neural population responses at the whole brain level, within the context of developing advanced medical applications. The tradeoffs and constraints involved, however, remain elusive due to obvious complications entailed by studying whole brain dynamics. Here, we present effective control of response features (probability and latency) of cortical networks in vitro over many hours, and offer this approach as an experimental toy for studying controllability of neural networks in the wider context. Exercising this approach we show that enforcement of stable high activity rates by means of closed loop control may enhance alteration of underlying global input–output relations and activity dependent dispersion of neuronal pair-wise correlations across the network. PMID:24808860
Computationally Efficient Neural Network Intrusion Security Awareness
Todd Vollmer; Milos Manic
2009-08-01
An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.
Neural network construction via back-propagation
Burwick, T.T.
1994-06-01
A method is presented that combines back-propagation with multi-layer neural network construction. Back-propagation is used not only to adjust the weights but also the signal functions. Going from one network to an equivalent one that has additional linear units, the non-linearity of these units and thus their effective presence is then introduced via back-propagation (weight-splitting). The back-propagated error causes the network to include new units in order to minimize the error function. We also show how this formalism allows to escape local minima.
Tumor Diagnosis Using Backpropagation Neural Network Method
NASA Astrophysics Data System (ADS)
Ma, Lixing; Looney, Carl; Sukuta, Sydney; Bruch, Reinhard; Afanasyeva, Natalia
1998-05-01
For characterization of skin cancer, an artificial neural network (ANN) method has been developed to diagnose normal tissue, benign tumor and melanoma. The pattern recognition is based on a three-layer neural network fuzzy learning system. In this study, the input neuron data set is the Fourier Transform infrared (FT-IR)spectrum obtained by a new Fiberoptic Evanescent Wave Fourier Transform Infrared (FEW-FTIR) spectroscopy method in the range of 1480 to 1850 cm-1. Ten input features are extracted from the absorbency values in this region. A single hidden layer of neural nodes with sigmoids activation functions clusters the feature space into small subclasses and the output nodes are separated in different nonconvex classes to permit nonlinear discrimination of disease states. The output is classified as three classes: normal tissue, benign tumor and melanoma. The results obtained from the neural network pattern recognition are shown to be consistent with traditional medical diagnosis. Input features have also been extracted from the absorbency spectra using chemical factor analysis. These abstract features or factors are also used in the classification.
Neural networks in the process industries
Ben, L.R.; Heavner, L.
1996-12-01
Neural networks, or more precisely, artificial neural networks (ANNs), are rapidly gaining in popularity. They first began to appear on the process-control scene in the early 1990s, but have been a research focus for more than 30 years. Neural networks are really empirical models that approximate the way man thinks neurons in the human brain work. Neural-net technology is not trying to produce computerized clones, but to model nature in an effort to mimic some of the brain`s capabilities. Modeling, for the purposes of this article, means developing a mathematical description of physical phenomena. The physics and chemistry of industrial processes are usually quite complex and sometimes poorly understood. Our process understanding, and our imperfect ability to describe complexity in mathematical terms, limit fidelity of first-principle models. Computational requirements for executing these complex models are a further limitation. It is often not possible to execute first-principle model algorithms at the high rate required for online control. Nevertheless, rigorous first principle models are commonplace design tools. Process control is another matter. Important model inputs are often not available as process measurements, making real-time application difficult. In fact, engineers often use models to infer unavailable measurements. 5 figs.
Membership generation using multilayer neural network
NASA Technical Reports Server (NTRS)
Kim, Jaeseok
1992-01-01
There has been intensive research in neural network applications to pattern recognition problems. Particularly, the back-propagation network has attracted many researchers because of its outstanding performance in pattern recognition applications. In this section, we describe a new method to generate membership functions from training data using a multilayer neural network. The basic idea behind the approach is as follows. The output values of a sigmoid activation function of a neuron bear remarkable resemblance to membership values. Therefore, we can regard the sigmoid activation values as the membership values in fuzzy set theory. Thus, in order to generate class membership values, we first train a suitable multilayer network using a training algorithm such as the back-propagation algorithm. After the training procedure converges, the resulting network can be treated as a membership generation network, where the inputs are feature values and the outputs are membership values in the different classes. This method allows fairly complex membership functions to be generated because the network is highly nonlinear in general. Also, it is to be noted that the membership functions are generated from a classification point of view. For pattern recognition applications, this is highly desirable, although the membership values may not be indicative of the degree of typicality of a feature value in a particular class.
Neural Network Approach To Sensory Fusion
NASA Astrophysics Data System (ADS)
Pearson, John C.; Gelfand, Jack J.; Sullivan, W. E.; Peterson, Richard M.; Spence, Clay D.
1988-08-01
We present a neural network model for sensory fusion based on the design of the visual/acoustic target localiza-tion system of the barn owl. This system adaptively fuses its separate visual and acoustic representations of object position into a single joint representation used for head orientation. The building block in this system, as in much of the brain, is the neuronal map. Neuronal maps are large arrays of locally interconnected neurons that represent information in a map-like form, that is, parameter values are systematically encoded by the position of neural activation in the array. The computational load is distributed to a hierarchy of maps, and the computation is performed in stages by transforming the representation from map to map via the geometry of the projections between the maps and the local interactions within the maps. For example, azimuthal position is computed from the frequency and binaural phase information encoded in the signals of the acoustic sensors, while elevation is computed in a separate stream using binaural intensity information. These separate streams are merged in their joint projection onto the external nucleus of the inferior colliculus, a two dimensional array of cells which contains a map of acoustic space. This acoustic map, and the visual map of the retina, jointly project onto the optic tectum, creating a fused visual/acoustic representation of position in space that is used for object localization. In this paper we describe our mathematical model of the stage of visual/acoustic fusion in the optic tectum. The model assumes that the acoustic projection from the external nucleus onto the tectum is roughly topographic and one-to-many, while the visual projection from the retina onto the tectum is topographic and one-to-one. A simple process of self-organization alters the strengths of the acoustic connections, effectively forming a focused beam of strong acoustic connections whose inputs are coincident with the visual inputs
Computational capabilities of recurrent NARX neural networks.
Siegelmann, H T; Horne, B G; Giles, C L
1997-01-01
Recently, fully connected recurrent neural networks have been proven to be computationally rich-at least as powerful as Turing machines. This work focuses on another network which is popular in control applications and has been found to be very effective at learning a variety of problems. These networks are based upon Nonlinear AutoRegressive models with eXogenous Inputs (NARX models), and are therefore called NARX networks. As opposed to other recurrent networks, NARX networks have a limited feedback which comes only from the output neuron rather than from hidden states. They are formalized by y(t)=Psi(u(t-n(u)), ..., u(t-1), u(t), y(t-n(y)), ..., y(t-1)) where u(t) and y(t) represent input and output of the network at time t, n(u) and n(y) are the input and output order, and the function Psi is the mapping performed by a Multilayer Perceptron. We constructively prove that the NARX networks with a finite number of parameters are computationally as strong as fully connected recurrent networks and thus Turing machines. We conclude that in theory one can use the NARX models, rather than conventional recurrent networks without any computational loss even though their feedback is limited. Furthermore, these results raise the issue of what amount of feedback or recurrence is necessary for any network to be Turing equivalent and what restrictions on feedback limit computational power. PMID:18255858
Generalization of features in the assembly neural networks.
Goltsev, Alexander; Wunsch, Donald C
2004-02-01
The purpose of the paper is an experimental study of the formation of class descriptions, taking place during learning, in assembly neural networks. The assembly neural network is artificially partitioned into several sub-networks according to the number of classes that the network has to recognize. The features extracted from input data are represented in neural column structures of the sub-networks. Hebbian neural assemblies are formed in the column structure of the sub-networks by weight adaptation. A specific class description is formed in each sub-network of the assembly neural network due to intersections between the neural assemblies. The process of formation of class descriptions in the sub-networks is interpreted as feature generalization. A set of special experiments is performed to study this process, on a task of character recognition using the MNIST database. PMID:15034946
VLSI implementable neural networks for target tracking
NASA Astrophysics Data System (ADS)
Himes, Glenn S.; Inigo, Rafael M.; Narathong, Chiewcharn
1991-08-01
This paper describes part of an integrated system for target tracking. The image is acquired, edge detected, and segmented by a subsystem not discussed in this paper. Algorithms to determine the centroid of a windowed target using neural networks are developed. Further, once the target centroid is determined, it is continuously updated in order to track the trajectory, since the centroid location is not dependent on scaling or rotation on the optical axis. The image is then mapped to a log-spiral grid. A conformal transformation is used to map the log-spiral grid to a computation plane in which rotations and scalings are transformed to displacements along the vertical and horizonal axes, respectively. The images in this plane are used for recognition. The recognition algorithms are the subject of another paper. A second neural network, also described in this paper, is then used to determine object rotation and scaling. The algorithm used by this network is an original line correlator tracker which, as the name indicates, uses linear instead of 2D correlations. Simulation results using ICBM images are presented for both the centroid neural net and the rotation-scaling detection network.
Functional expansion representations of artificial neural networks
NASA Technical Reports Server (NTRS)
Gray, W. Steven
1992-01-01
In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.
Correcting wave predictions with artificial neural networks
NASA Astrophysics Data System (ADS)
Makarynskyy, O.; Makarynska, D.
2003-04-01
The predictions of wind waves with different lead times are necessary in a large scope of coastal and open ocean activities. Numerical wave models, which usually provide this information, are based on deterministic equations that do not entirely account for the complexity and uncertainty of the wave generation and dissipation processes. An attempt to improve wave parameters short-term forecasts based on artificial neural networks is reported. In recent years, artificial neural networks have been used in a number of coastal engineering applications due to their ability to approximate the nonlinear mathematical behavior without a priori knowledge of interrelations among the elements within a system. The common multilayer feed-forward networks, with a nonlinear transfer functions in the hidden layers, were developed and employed to forecast the wave characteristics over one hour intervals starting from one up to 24 hours, and to correct these predictions. Three non-overlapping data sets of wave characteristics, both from a buoy, moored roughly 60 miles west of the Aran Islands, west coast of Ireland, were used to train and validate the neural nets involved. The networks were trained with error back propagation algorithm. Time series plots and scatterplots of the wave characteristics as well as tables with statistics show an improvement of the results achieved due to the correction procedure employed.
Convolutional Neural Network Based dem Super Resolution
NASA Astrophysics Data System (ADS)
Chen, Zixuan; Wang, Xuewen; Xu, Zekai; Hou, Wenguang
2016-06-01
DEM super resolution is proposed in our previous publication to improve the resolution for a DEM on basis of some learning examples. Meanwhile, the nonlocal algorithm is introduced to deal with it and lots of experiments show that the strategy is feasible. In our publication, the learning examples are defined as the partial original DEM and their related high measurements due to this way can avoid the incompatibility between the data to be processed and the learning examples. To further extent the applications of this new strategy, the learning examples should be diverse and easy to obtain. Yet, it may cause the problem of incompatibility and unrobustness. To overcome it, we intend to investigate a convolutional neural network based method. The input of the convolutional neural network is a low resolution DEM and the output is expected to be its high resolution one. A three layers model will be adopted. The first layer is used to detect some features from the input, the second integrates the detected features to some compressed ones and the final step transforms the compressed features as a new DEM. According to this designed structure, some learning DEMs will be taken to train it. Specifically, the designed network will be optimized by minimizing the error of the output and its expected high resolution DEM. In practical applications, a testing DEM will be input to the convolutional neural network and a super resolution will be obtained. Many experiments show that the CNN based method can obtain better reconstructions than many classic interpolation methods.
The relevance of network micro-structure for neural dynamics.
Pernice, Volker; Deger, Moritz; Cardanobile, Stefano; Rotter, Stefan
2013-01-01
The activity of cortical neurons is determined by the input they receive from presynaptic neurons. Many previous studies have investigated how specific aspects of the statistics of the input affect the spike trains of single neurons and neurons in recurrent networks. However, typically very simple random network models are considered in such studies. Here we use a recently developed algorithm to construct networks based on a quasi-fractal probability measure which are much more variable than commonly used network models, and which therefore promise to sample the space of recurrent networks in a more exhaustive fashion than previously possible. We use the generated graphs as the underlying network topology in simulations of networks of integrate-and-fire neurons in an asynchronous and irregular state. Based on an extensive dataset of networks and neuronal simulations we assess statistical relations between features of the network structure and the spiking activity. Our results highlight the strong influence that some details of the network structure have on the activity dynamics of both single neurons and populations, even if some global network parameters are kept fixed. We observe specific and consistent relations between activity characteristics like spike-train irregularity or correlations and network properties, for example the distributions of the numbers of in- and outgoing connections or clustering. Exploiting these relations, we demonstrate that it is possible to estimate structural characteristics of the network from activity data. We also assess higher order correlations of spiking activity in the various networks considered here, and find that their occurrence strongly depends on the network structure. These results provide directions for further theoretical studies on recurrent networks, as well as new ways to interpret spike train recordings from neural circuits. PMID:23761758
Character Recognition Using Genetically Trained Neural Networks
Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.
1998-10-01
Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the amount of
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.
Neural network for tsunami and runup forecast
NASA Astrophysics Data System (ADS)
Namekar, Shailesh; Yamazaki, Yoshiki; Cheung, Kwok Fai
2009-04-01
This paper examines the use of neural network to model nonlinear tsunami processes for forecasting of coastal waveforms and runup. The three-layer network utilizes a radial basis function in the hidden, middle layer for nonlinear transformation of input waveforms near the tsunami source. Events based on the 2006 Kuril Islands tsunami demonstrate the implementation and capability of the network. Division of the Kamchatka-Kuril subduction zone into a number of subfaults facilitates development of a representative tsunami dataset using a nonlinear long-wave model. The computed waveforms near the tsunami source serve as the input and the far-field waveforms and runup provide the target output for training of the network through a back-propagation algorithm. The trained network reproduces the resonance of tsunami waves and the topography-dominated runup patterns at Hawaii's coastlines from input water-level data off the Aleutian Islands.
A neural networks-based hybrid routing protocol for wireless mesh networks.
Kojić, Nenad; Reljin, Irini; Reljin, Branimir
2012-01-01
The networking infrastructure of wireless mesh networks (WMNs) is decentralized and relatively simple, but they can display reliable functioning performance while having good redundancy. WMNs provide Internet access for fixed and mobile wireless devices. Both in urban and rural areas they provide users with high-bandwidth networks over a specific coverage area. The main problems affecting these networks are changes in network topology and link quality. In order to provide regular functioning, the routing protocol has the main influence in WMN implementations. In this paper we suggest a new routing protocol for WMN, based on good results of a proactive and reactive routing protocol, and for that reason it can be classified as a hybrid routing protocol. The proposed solution should avoid flooding and creating the new routing metric. We suggest the use of artificial logic-i.e., neural networks (NNs). This protocol is based on mobile agent technologies controlled by a Hopfield neural network. In addition to this, our new routing metric is based on multicriteria optimization in order to minimize delay and blocking probability (rejected packets or their retransmission). The routing protocol observes real network parameters and real network environments. As a result of artificial logic intelligence, the proposed routing protocol should maximize usage of network resources and optimize network performance. PMID:22969360
A Neural Networks-Based Hybrid Routing Protocol for Wireless Mesh Networks
Kojić, Nenad; Reljin, Irini; Reljin, Branimir
2012-01-01
The networking infrastructure of wireless mesh networks (WMNs) is decentralized and relatively simple, but they can display reliable functioning performance while having good redundancy. WMNs provide Internet access for fixed and mobile wireless devices. Both in urban and rural areas they provide users with high-bandwidth networks over a specific coverage area. The main problems affecting these networks are changes in network topology and link quality. In order to provide regular functioning, the routing protocol has the main influence in WMN implementations. In this paper we suggest a new routing protocol for WMN, based on good results of a proactive and reactive routing protocol, and for that reason it can be classified as a hybrid routing protocol. The proposed solution should avoid flooding and creating the new routing metric. We suggest the use of artificial logic—i.e., neural networks (NNs). This protocol is based on mobile agent technologies controlled by a Hopfield neural network. In addition to this, our new routing metric is based on multicriteria optimization in order to minimize delay and blocking probability (rejected packets or their retransmission). The routing protocol observes real network parameters and real network environments. As a result of artificial logic intelligence, the proposed routing protocol should maximize usage of network resources and optimize network performance. PMID:22969360
A classifier neural network for rotordynamic systems
NASA Astrophysics Data System (ADS)
Ganesan, R.; Jionghua, Jin; Sankar, T. S.
1995-07-01
A feedforward backpropagation neural network is formed to identify the stability characteristic of a high speed rotordynamic system. The principal focus resides in accounting for the instability due to the bearing clearance effects. The abnormal operating condition of 'normal-loose' Coulomb rub, that arises in units supported by hydrodynamic bearings or rolling element bearings, is analysed in detail. The multiple-parameter stability problem is formulated and converted to a set of three-parameter algebraic inequality equations. These three parameters map the wider range of physical parameters of commonly-used rotordynamic systems into a narrow closed region, that is used in the supervised learning of the neural network. A binary-type state of the system is expressed through these inequalities that are deduced from the analytical simulation of the rotor system. Both the hidden layer as well as functional-link networks are formed and the superiority of the functional-link network is established. Considering the real time interpretation and control of the rotordynamic system, the network reliability and the learning time are used as the evaluation criteria to assess the superiority of the functional-link network. This functional-link network is further trained using the parameter values of selected rotor systems, and the classifier network is formed. The success rate of stability status identification is obtained to assess the potentials of this classifier network. The classifier network is shown that it can also be used, for control purposes, as an 'advisory' system that suggests the optimum way of parameter adjustment.
Analysis of Stochastic Response of Neural Networks with Stochastic Input
1996-10-10
Software permits the user to extend capability of his/her neural network to include probablistic characteristics of input parameter. User inputs topology and weights associated with neural network along with distributional characteristics of input parameters. Network response is provided via a cumulative density function of network response variable.
Neural dynamics in superconducting networks
NASA Astrophysics Data System (ADS)
Segall, Kenneth; Schult, Dan; Crotty, Patrick; Miller, Max
2012-02-01
We discuss the use of Josephson junction networks as analog models for simulating neuron behaviors. A single unit called a ``Josephson Junction neuron'' composed of two Josephson junctions [1] displays behavior that shows characteristics of single neurons such as action potentials, thresholds and refractory periods. Synapses can be modeled as passive filters and can be used to connect neurons together. The sign of the bias current to the Josephson neuron can be used to determine if the neuron is excitatory or inhibitory. Due to the intrinsic speed of Josephson junctions and their scaling properties as analog models, a large network of Josephson neurons measured over typical lab times contains dynamics which would essentially be impossible to calculate on a computer We discuss the operating principle of the Josephson neuron, coupling Josephson neurons together to make large networks, and the Kuramoto-like synchronization of a system of disordered junctions.[4pt] [1] ``Josephson junction simulation of neurons,'' P. Crotty, D. Schult and K. Segall, Physical Review E 82, 011914 (2010).
A Novel Higher Order Artificial Neural Networks
NASA Astrophysics Data System (ADS)
Xu, Shuxiang
2010-05-01
In this paper a new Higher Order Neural Network (HONN) model is introduced and applied in several data mining tasks. Data Mining extracts hidden patterns and valuable information from large databases. A hyperbolic tangent function is used as the neuron activation function for the new HONN model. Experiments are conducted to demonstrate the advantages and disadvantages of the new HONN model, when compared with several conventional Artificial Neural Network (ANN) models: Feedforward ANN with the sigmoid activation function; Feedforward ANN with the hyperbolic tangent activation function; and Radial Basis Function (RBF) ANN with the Gaussian activation function. The experimental results seem to suggest that the new HONN holds higher generalization capability as well as abilities in handling missing data.
Privacy-preserving backpropagation neural network learning.
Chen, Tingting; Zhong, Sheng
2009-10-01
With the development of distributed computing environment , many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms. In this paper, we focus on preserving the privacy in an important learning model, multilayer neural networks. We present a privacy-preserving two-party distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other. We provide complete correctness and security analysis of our algorithms. The effectiveness of our algorithms is verified by experiments on various real world data sets. PMID:19709975
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?
Automatic breast density classification using neural network
NASA Astrophysics Data System (ADS)
Arefan, D.; Talebpour, A.; Ahmadinejhad, N.; Kamali Asl, A.
2015-12-01
According to studies, the risk of breast cancer directly associated with breast density. Many researches are done on automatic diagnosis of breast density using mammography. In the current study, artifacts of mammograms are removed by using image processing techniques and by using the method presented in this study, including the diagnosis of points of the pectoral muscle edges and estimating them using regression techniques, pectoral muscle is detected with high accuracy in mammography and breast tissue is fully automatically extracted. In order to classify mammography images into three categories: Fatty, Glandular, Dense, a feature based on difference of gray-levels of hard tissue and soft tissue in mammograms has been used addition to the statistical features and a neural network classifier with a hidden layer. Image database used in this research is the mini-MIAS database and the maximum accuracy of system in classifying images has been reported 97.66% with 8 hidden layers in neural network.
Toward modeling a dynamic biological neural network.
Ross, M D; Dayhoff, J E; Mugler, D H
1990-01-01
Mammalian macular endorgans are linear bioaccelerometers located in the vestibular membranous labyrinth of the inner ear. In this paper, the organization of the endorgan is interpreted on physical and engineering principles. This is a necessary prerequisite to mathematical and symbolic modeling of information processing by the macular neural network. Mathematical notations that describe the functioning system were used to produce a novel, symbolic model. The model is six-tiered and is constructed to mimic the neural system. Initial simulations show that the network functions best when some of the detecting elements (type I hair cells) are excitatory and others (type II hair cells) are weakly inhibitory. The simulations also illustrate the importance of disinhibition of receptors located in the third tier in shaping nerve discharge patterns at the sixth tier in the model system. PMID:11538873
On analog implementations of discrete neural networks
Beiu, V.; Moore, K.R.
1998-12-01
The paper will show that in order to obtain minimum size neural networks (i.e., size-optimal) for implementing any Boolean function, the nonlinear activation function of the neutrons has to be the identity function. The authors shall shortly present many results dealing with the approximation capabilities of neural networks, and detail several bounds on the size of threshold gate circuits. Based on a constructive solution for Kolmogorov`s superpositions they will show that implementing Boolean functions can be done using neurons having an identity nonlinear function. It follows that size-optimal solutions can be obtained only using analog circuitry. Conclusions, and several comments on the required precision are ending the paper.
Neural network error correction for solving coupled ordinary differential equations
NASA Technical Reports Server (NTRS)
Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.
1992-01-01
A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.
Neural network with dynamically adaptable neurons
NASA Technical Reports Server (NTRS)
Tawel, Raoul (Inventor)
1994-01-01
This invention is an adaptive neuron for use in neural network processors. The adaptive neuron participates in the supervised learning phase of operation on a co-equal basis with the synapse matrix elements by adaptively changing its gain in a similar manner to the change of weights in the synapse IO elements. In this manner, training time is decreased by as much as three orders of magnitude.
Reconstructing irregularly sampled images by neural networks
NASA Technical Reports Server (NTRS)
Ahumada, Albert J., Jr.; Yellott, John I., Jr.
1989-01-01
Neural-network-like models of receptor position learning and interpolation function learning are being developed as models of how the human nervous system might handle the problems of keeping track of the receptor positions and interpolating the image between receptors. These models may also be of interest to designers of image processing systems desiring the advantages of a retina-like image sampling array.
Artificial neural network cardiopulmonary modeling and diagnosis
Kangas, Lars J.; Keller, Paul E.
1997-01-01
The present invention is a method of diagnosing a cardiopulmonary condition in an individual by comparing data from a progressive multi-stage test for the individual to a non-linear multi-variate model, preferably a recurrent artificial neural network having sensor fusion. The present invention relies on a cardiovascular model developed from physiological measurements of an individual. Any differences between the modeled parameters and the parameters of an individual at a given time are used for diagnosis.
Artificial neural network cardiopulmonary modeling and diagnosis
Kangas, L.J.; Keller, P.E.
1997-10-28
The present invention is a method of diagnosing a cardiopulmonary condition in an individual by comparing data from a progressive multi-stage test for the individual to a non-linear multi-variate model, preferably a recurrent artificial neural network having sensor fusion. The present invention relies on a cardiovascular model developed from physiological measurements of an individual. Any differences between the modeled parameters and the parameters of an individual at a given time are used for diagnosis. 12 figs.
Analog hardware for learning neural networks
NASA Technical Reports Server (NTRS)
Eberhardt, Silvio P. (Inventor)
1991-01-01
This is a recurrent or feedforward analog neural network processor having a multi-level neuron array and a synaptic matrix for storing weighted analog values of synaptic connection strengths which is characterized by temporarily changing one connection strength at a time to determine its effect on system output relative to the desired target. That connection strength is then adjusted based on the effect, whereby the processor is taught the correct response to training examples connection by connection.
Hybrid pyramid/neural network object recognition
NASA Astrophysics Data System (ADS)
Anandan, P.; Burt, Peter J.; Pearson, John C.; Spence, Clay D.
1994-02-01
This work concerns computationally efficient computer vision methods for the search for and identification of small objects in large images. The approach combines neural network pattern recognition with pyramid-based coarse-to-fine search, in a way that eliminates the drawbacks of each method when used by itself and, in addition, improves object identification through learning and exploiting the low-resolution image context associated with the objects. The presentation will describe the system architecture and the performance on illustrative problems.
Nonvolatile Array Of Synapses For Neural Network
NASA Technical Reports Server (NTRS)
Tawel, Raoul
1993-01-01
Elements of array programmed with help of ultraviolet light. A 32 x 32 very-large-scale integrated-circuit array of electronic synapses serves as building-block chip for analog neural-network computer. Synaptic weights stored in nonvolatile manner. Makes information content of array invulnerable to loss of power, and, by eliminating need for circuitry to refresh volatile synaptic memory, makes architecture simpler and more compact.
Diagnosing process faults using neural network models
Buescher, K.L.; Jones, R.D.; Messina, M.J.
1993-11-01
In order to be of use for realistic problems, a fault diagnosis method should have the following three features. First, it should apply to nonlinear processes. Second, it should not rely on extensive amounts of data regarding previous faults. Lastly, it should detect faults promptly. The authors present such a scheme for static (i.e., non-dynamic) systems. It involves using a neural network to create an associative memory whose fixed points represent the normal behavior of the system.
Learning in Neural Networks: VLSI Implementation Strategies
NASA Technical Reports Server (NTRS)
Duong, Tuan Anh
1995-01-01
Fully-parallel hardware neural network implementations may be applied to high-speed recognition, classification, and mapping tasks in areas such as vision, or can be used as low-cost self-contained units for tasks such as error detection in mechanical systems (e.g. autos). Learning is required not only to satisfy application requirements, but also to overcome hardware-imposed limitations such as reduced dynamic range of connections.
Adaptive Filtering Using Recurrent Neural Networks
NASA Technical Reports Server (NTRS)
Parlos, Alexander G.; Menon, Sunil K.; Atiya, Amir F.
2005-01-01
A method for adaptive (or, optionally, nonadaptive) filtering has been developed for estimating the states of complex process systems (e.g., chemical plants, factories, or manufacturing processes at some level of abstraction) from time series of measurements of system inputs and outputs. The method is based partly on the fundamental principles of the Kalman filter and partly on the use of recurrent neural networks. The standard Kalman filter involves an assumption of linearity of the mathematical model used to describe a process system. The extended Kalman filter accommodates a nonlinear process model but still requires linearization about the state estimate. Both the standard and extended Kalman filters involve the often unrealistic assumption that process and measurement noise are zero-mean, Gaussian, and white. In contrast, the present method does not involve any assumptions of linearity of process models or of the nature of process noise; on the contrary, few (if any) assumptions are made about process models, noise models, or the parameters of such models. In this regard, the method can be characterized as one of nonlinear, nonparametric filtering. The method exploits the unique ability of neural networks to approximate nonlinear functions. In a given case, the process model is limited mainly by limitations of the approximation ability of the neural networks chosen for that case. Moreover, despite the lack of assumptions regarding process noise, the method yields minimum- variance filters. In that they do not require statistical models of noise, the neural- network-based state filters of this method are comparable to conventional nonlinear least-squares estimators.
Applying neural networks to optimize instrumentation performance
Start, S.E.; Peters, G.G.
1995-06-01
Well calibrated instrumentation is essential in providing meaningful information about the status of a plant. Signals from plant instrumentation frequently have inherent non-linearities, may be affected by environmental conditions and can therefore cause calibration difficulties for the people who maintain them. Two neural network approaches are described in this paper for improving the accuracy of a non-linear, temperature sensitive level probe ised in Expermental Breeder Reactor II (EBR-II) that was difficult to calibrate.
Neural network architectures to analyze OPAD data
NASA Technical Reports Server (NTRS)
Whitaker, Kevin W.
1992-01-01
A prototype Optical Plume Anomaly Detection (OPAD) system is now installed on the space shuttle main engine (SSME) Technology Test Bed (TTB) at MSFC. The OPAD system requirements dictate the need for fast, efficient data processing techniques. To address this need of the OPAD system, a study was conducted into how artificial neural networks could be used to assist in the analysis of plume spectral data.
Neural Network Solves "Traveling-Salesman" Problem
NASA Technical Reports Server (NTRS)
Thakoor, Anilkumar P.; Moopenn, Alexander W.
1990-01-01
Experimental electronic neural network solves "traveling-salesman" problem. Plans round trip of minimum distance among N cities, visiting every city once and only once (without backtracking). This problem is paradigm of many problems of global optimization (e.g., routing or allocation of resources) occuring in industry, business, and government. Applied to large number of cities (or resources), circuits of this kind expected to solve problem faster and more cheaply.
Program PSNN (Plasma Spectroscopy Neural Network)
Morgan, W.L.; Larsen, J.T.
1993-08-01
This program uses the standard ``delta rule`` back-propagation supervised training algorithm for multi-layer neural networks. The inputs are line intensities in arbitrary units, which are then normalized within the program. The outputs are T{sub e}(eV), N{sub e}(cm{sup {minus}3}), and a fractional ionization, which in our testing using H- and He-like spectra, was N(He)/[N(H) + N(He)].
The next generation of neural network chips
Beiu, V.
1997-08-01
There have been many national and international neural networks research initiatives: USA (DARPA, NIBS), Canada (IRIS), Japan (HFSP) and Europe (BRAIN, GALA TEA, NERVES, ELENE NERVES 2) -- just to mention a few. Recent developments in the field of neural networks, cognitive science, bioengineering and electrical engineering have made it possible to understand more about the functioning of large ensembles of identical processing elements. There are more research papers than ever proposing solutions and hardware implementations are by no means an exception. Two fields (computing and neuroscience) are interacting in ways nobody could imagine just several years ago, and -- with the advent of new technologies -- researchers are focusing on trying to copy the Brain. Such an exciting confluence may quite shortly lead to revolutionary new computers and it is the aim of this invited session to bring to light some of the challenging research aspects dealing with the hardware realizability of future intelligent chips. Present-day (conventional) technology is (still) mostly digital and, thus, occupies wider areas and consumes much more power than the solutions envisaged. The innovative algorithmic and architectural ideals should represent important breakthroughs, paving the way towards making neural network chips available to the industry at competitive prices, in relatively small packages and consuming a fraction of the power required by equivalent digital solutions.
CALIBRATION OF ONLINE ANALYZERS USING NEURAL NETWORKS
Rajive Ganguli; Daniel E. Walsh; Shaohai Yu
2003-12-05
Neural networks were used to calibrate an online ash analyzer at the Usibelli Coal Mine, Healy, Alaska, by relating the Americium and Cesium counts to the ash content. A total of 104 samples were collected from the mine, with 47 being from screened coal, and the rest being from unscreened coal. Each sample corresponded to 20 seconds of coal on the running conveyor belt. Neural network modeling used the quick stop training procedure. Therefore, the samples were split into training, calibration and prediction subsets. Special techniques, using genetic algorithms, were developed to representatively split the sample into the three subsets. Two separate approaches were tried. In one approach, the screened and unscreened coal was modeled separately. In another, a single model was developed for the entire dataset. No advantage was seen from modeling the two subsets separately. The neural network method performed very well on average but not individually, i.e. though each prediction was unreliable, the average of a few predictions was close to the true average. Thus, the method demonstrated that the analyzers were accurate at 2-3 minutes intervals (average of 6-9 samples), but not at 20 seconds (each prediction).
Efficient implementation of neural network deinterlacing
NASA Astrophysics Data System (ADS)
Seo, Guiwon; Choi, Hyunsoo; Lee, Chulhee
2009-02-01
Interlaced scanning has been widely used in most broadcasting systems. However, there are some undesirable artifacts such as jagged patterns, flickering, and line twitters. Moreover, most recent TV monitors utilize flat panel display technologies such as LCD or PDP monitors and these monitors require progressive formats. Consequently, the conversion of interlaced video into progressive video is required in many applications and a number of deinterlacing methods have been proposed. Recently deinterlacing methods based on neural network have been proposed with good results. On the other hand, with high resolution video contents such as HDTV, the amount of video data to be processed is very large. As a result, the processing time and hardware complexity become an important issue. In this paper, we propose an efficient implementation of neural network deinterlacing using polynomial approximation of the sigmoid function. Experimental results show that these approximations provide equivalent performance with a considerable reduction of complexity. This implementation of neural network deinterlacing can be efficiently incorporated in HW implementation.
Shale Gas reservoirs characterization using neural network
NASA Astrophysics Data System (ADS)
Ouadfeul, Sid-Ali; Aliouane, Leila
2014-05-01
In this paper, a tentative of shale gas reservoirs characterization enhancement from well-logs data using neural network is established. The goal is to predict the Total Organic carbon (TOC) in boreholes where the TOC core rock or TOC well-log measurement does not exist. The Multilayer perceptron (MLP) neural network with three layers is established. The MLP input layer is constituted with five neurons corresponding to the Bulk density, Neutron porosity, sonic P wave slowness and photoelectric absorption coefficient. The hidden layer is forms with nine neurons and the output layer is formed with one neuron corresponding to the TOC log. Application to two boreholes located in Barnett shale formation where a well A is used as a pilot and a well B is used for propagation shows clearly the efficiency of the neural network method to improve the shale gas reservoirs characterization. The established formalism plays a high important role in the shale gas plays economy and long term gas energy production.
Analysis of complex systems using neural networks
Uhrig, R.E. . Dept. of Nuclear Engineering Oak Ridge National Lab., TN )
1992-01-01
The application of neural networks, alone or in conjunction with other advanced technologies (expert systems, fuzzy logic, and/or genetic algorithms), to some of the problems of complex engineering systems has the potential to enhance the safety, reliability, and operability of these systems. Typically, the measured variables from the systems are analog variables that must be sampled and normalized to expected peak values before they are introduced into neural networks. Often data must be processed to put it into a form more acceptable to the neural network (e.g., a fast Fourier transformation of the time-series data to produce a spectral plot of the data). Specific applications described include: (1) Diagnostics: State of the Plant (2) Hybrid System for Transient Identification, (3) Sensor Validation, (4) Plant-Wide Monitoring, (5) Monitoring of Performance and Efficiency, and (6) Analysis of Vibrations. Although specific examples described deal with nuclear power plants or their subsystems, the techniques described can be applied to a wide variety of complex engineering systems.
Analysis of complex systems using neural networks
Uhrig, R.E. |
1992-12-31
The application of neural networks, alone or in conjunction with other advanced technologies (expert systems, fuzzy logic, and/or genetic algorithms), to some of the problems of complex engineering systems has the potential to enhance the safety, reliability, and operability of these systems. Typically, the measured variables from the systems are analog variables that must be sampled and normalized to expected peak values before they are introduced into neural networks. Often data must be processed to put it into a form more acceptable to the neural network (e.g., a fast Fourier transformation of the time-series data to produce a spectral plot of the data). Specific applications described include: (1) Diagnostics: State of the Plant (2) Hybrid System for Transient Identification, (3) Sensor Validation, (4) Plant-Wide Monitoring, (5) Monitoring of Performance and Efficiency, and (6) Analysis of Vibrations. Although specific examples described deal with nuclear power plants or their subsystems, the techniques described can be applied to a wide variety of complex engineering systems.
Multiresolution training of Kohonen neural networks
NASA Astrophysics Data System (ADS)
Tamir, Dan E.
2007-09-01
This paper analyses a trade-off between convergence rate and distortion obtained through a multi-resolution training of a Kohonen Competitive Neural Network. Empirical results show that a multi-resolution approach can improve the training stage of several unsupervised pattern classification algorithms including K-means clustering, LBG vector quantization, and competitive neural networks. While, previous research concentrated on convergence rate of on-line unsupervised training. New results, reported in this paper, show that the multi-resolution approach can be used to improve training quality (measured as a derivative of the rate distortion function) on the account of convergence speed. The probability of achieving a desired point in the quality/convergence-rate space of Kohonen Competitive Neural Networks (KCNN) is evaluated using a detailed Monte Carlo set of experiments. It is shown that multi-resolution can reduce the distortion by a factor of 1.5 to 6 while maintaining the convergence rate of traditional KCNN. Alternatively, the convergence rate can be improved without loss of quality. The experiments include a controlled set of synthetic data, as well as, image data. Experimental results are reported and evaluated.
Deep learning in neural networks: an overview.
Schmidhuber, Jürgen
2015-01-01
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks. PMID:25462637
Neural network method for characterizing video cameras
NASA Astrophysics Data System (ADS)
Zhou, Shuangquan; Zhao, Dazun
1998-08-01
This paper presents a neural network method for characterizing color video camera. A multilayer feedforward network with the error back-propagation learning rule for training, is used as a nonlinear transformer to model a camera, which realizes a mapping from the CIELAB color space to RGB color space. With SONY video camera, D65 illuminant, Pritchard Spectroradiometer, 410 JIS color charts as training data and 36 charts as testing data, results show that the mean error of training data is 2.9 and that of testing data is 4.0 in a 2563 RGB space.
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Shelton, Robert O.
1991-01-01
Introduced here is a novel technique which adds the dimension of time to the well known back propagation neural network algorithm. Cited here are several reasons why the inclusion of automated spatial and temporal associations are crucial to effective systems modeling. An overview of other works which also model spatiotemporal dynamics is furnished. A detailed description is given of the processes necessary to implement the space-time network algorithm. Several demonstrations that illustrate the capabilities and performance of this new architecture are given.
The importance of artificial neural networks in biomedicine
Burke, H.B.
1995-12-31
The future explanatory power in biomedicine will be at the molecular-genetic level of analysis (rather than the epidemiologic-demographic or anatomic-cellular levels). This is the level of complex systems. Complex systems are characterized by nonlinearity and complex interactions. It is difficult for traditional statistical methods to capture complex systems because traditional methods attempt to find the model that best fits the statistician`s understanding of the phenomenon; complex systems are difficult to understand and therefore difficult to fit with a simple model. Artificial neural networks are nonparametric regression models. They can capture any phenomena, to any degree of accuracy (depending on the adequacy of the data and the power of the predictors), without prior knowledge of the phenomena. Further, artificial neural networks can be represented, not only as formulae, but also as graphical models. Graphical models can increase analytic power and flexibility. Artificial neural networks are a powerful method for capturing complex phenomena, but their use requires a paradigm shift, from exploratory analysis of the data to exploratory analysis of the model.
NASA Astrophysics Data System (ADS)
Cheng, Xinmin; Zhang, Xiaodan; Zhao, Li; Deng, Aideng; Bao, Yongqiang; Liu, Yong; Jiang, Yunliang
2014-04-01
When using acoustic emission to locate the friction fault source of rotating machinery, the effects of strong noise and waveform distortion make accurate locating difficult. Applying neural network for acoustic emission source location could be helpful. In the BP Wavelet Neural Network, BP is a local search algorithm, which falls into local minimum easily. The probability of successful search is low. We used Shuffled Frog Leaping Algorithm (SFLA) to optimize the parameters of the Wavelet Neural Network, and the optimized Wavelet Neural Network to locate the source. After having performed the experiments of friction acoustic emission's source location on the rotor friction test machine, the results show that the calculation of SFLA is simple and effective, and that locating is accurate with proper structure of the network and input parameters.
An efficient automated parameter tuning framework for spiking neural networks
Carlson, Kristofor D.; Nageswaran, Jayram Moorkanikara; Dutt, Nikil; Krichmar, Jeffrey L.
2014-01-01
As the desire for biologically realistic spiking neural networks (SNNs) increases, tuning the enormous number of open parameters in these models becomes a difficult challenge. SNNs have been used to successfully model complex neural circuits that explore various neural phenomena such as neural plasticity, vision systems, auditory systems, neural oscillations, and many other important topics of neural function. Additionally, SNNs are particularly well-adapted to run on neuromorphic hardware that will support biological brain-scale architectures. Although the inclusion of realistic plasticity equations, neural dynamics, and recurrent topologies has increased the descriptive power of SNNs, it has also made the task of tuning these biologically realistic SNNs difficult. To meet this challenge, we present an automated parameter tuning framework capable of tuning SNNs quickly and efficiently using evolutionary algorithms (EA) and inexpensive, readily accessible graphics processing units (GPUs). A sample SNN with 4104 neurons was tuned to give V1 simple cell-like tuning curve responses and produce self-organizing receptive fields (SORFs) when presented with a random sequence of counterphase sinusoidal grating stimuli. A performance analysis comparing the GPU-accelerated implementation to a single-threaded central processing unit (CPU) implementation was carried out and showed a speedup of 65× of the GPU implementation over the CPU implementation, or 0.35 h per generation for GPU vs. 23.5 h per generation for CPU. Additionally, the parameter value solutions found in the tuned SNN were studied and found to be stable and repeatable. The automated parameter tuning framework presented here will be of use to both the computational neuroscience and neuromorphic engineering communities, making the process of constructing and tuning large-scale SNNs much quicker and easier. PMID:24550771
Desynchronization in diluted neural networks
Zillmer, Ruediger; Livi, Roberto; Politi, Antonio; Torcini, Alessandro
2006-09-15
The dynamical behavior of a weakly diluted fully inhibitory network of pulse-coupled spiking neurons is investigated. Upon increasing the coupling strength, a transition from regular to stochasticlike regime is observed. In the weak-coupling phase, a periodic dynamics is rapidly approached, with all neurons firing with the same rate and mutually phase locked. The strong-coupling phase is characterized by an irregular pattern, even though the maximum Lyapunov exponent is negative. The paradox is solved by drawing an analogy with the phenomenon of 'stable chaos', i.e., by observing that the stochasticlike behavior is 'limited' to an exponentially long (with the system size) transient. Remarkably, the transient dynamics turns out to be stationary.
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.
Synthesis of neural networks for spatio-temporal spike pattern recognition and processing
Tapson, Jonathan C.; Cohen, Greg K.; Afshar, Saeed; Stiefel, Klaus M.; Buskila, Yossi; Wang, Runchun Mark; Hamilton, Tara J.; van Schaik, André
2013-01-01
The advent of large scale neural computational platforms has highlighted the lack of algorithms for synthesis of neural structures to perform predefined cognitive tasks. The Neural Engineering Framework (NEF) offers one such synthesis, but it is most effective for a spike rate representation of neural information, and it requires a large number of neurons to implement simple functions. We describe a neural network synthesis method that generates synaptic connectivity for neurons which process time-encoded neural signals, and which makes very sparse use of neurons. The method allows the user to specify—arbitrarily—neuronal characteristics such as axonal and dendritic delays, and synaptic transfer functions, and then solves for the optimal input-output relationship using computed dendritic weights. The method may be used for batch or online learning and has an extremely fast optimization process. We demonstrate its use in generating a network to recognize speech which is sparsely encoded as spike times. PMID:24009550
Probabilistic neural networks: In or out of equilibrium
Clark, J.W.
1987-01-01
The long-term behavior of neural networks following exposure to external stimuli is central to attempts at modeling brain activity and to the design of physical systems imitating biological mechanisms of memory storage and recall. A given network may exhibit many attractors, while a given attractor may correspond to a fixed point, a terminal cycle, multiperiodic motion, or chaos. If the dynamical law by which the system updates its state is probabilistic rather than deterministic, one considers an ensemble rather than a particular system. The initial preparation of the system attendant to the imposition of a temporary stimulus is reflected in the specification of an initial probability distribution (p/sub i/(0)) over microscopic system states i. Here an especially simple class of probabilistic neural network models is considered, simple in the senses that the large-t occupation probabilities are steady, implying a fixed-point attractor, and this final condition is unique, i.e. independent of initial preparation, for specified single-neuron properties and interneuronic couplings. 17 refs.
A neural network short-term forecast of significant thunderstorms
Mccann, D.W. )
1992-09-01
Neural networks, an artificial-intelligence tools that excels in pattern recognition, are reviewed, and a 3-7-h significant thunderstorm forecast developed with this technique is discussed. Two neural networks learned to forecast significant thunderstorms from fields of surface-based lifted index and surface moisture convergence. These networks are sensitive to the patterns that skilled forecasters recognize as occurring prior to strong thunderstorms. The two neural networks are combined operationally at the National Severe Storm Forecast Center into a single hourly product that enhances pattern-recognition skills. Examples of neural network products are shown, and their potential impact on significant thunderstorm forecasting is demonstrated. 22 refs.
Seismic active control by neural networks.
Tang, Y.
1998-01-01
A study on the application of artificial neural networks (ANNs) to activate structural control under seismic loads is carried out. The structure considered is a single-degree-of-freedom (SDF) system with an active bracing device. The control force is computed by a trained neural network. The feed-forward neural network architecture and an adaptive back-propagation training algorithm is used in the study. The neural net is trained to reproduce the function that represents the response-excitation relationship of the SDF system under seismic loads. The input-output training patterns are generated randomly. In the back-propagation training algorithm, the learning rate is determined by ensuring the decrease of the error function at each epoch. The computer program implemented is validated by solving the classification of the XOR problem. Then, the trained ANN is used to compute the control force according to the control strategy. If the control force exceeds the actuator's capacity limit, it is set equal to that limit. The concept of the control strategy employed herein is to apply the control force at every time step to cancel the system velocity induced at the preceding time step so that the gradual rhythmic buildup of the response is destroyed. The ground motions considered in the numerical example are the 1940 El Centro earthquake and the 1979 Imperial Valley earthquake in California. The system responses with and without the control are calculated and compared. The feasibility and potential of applying ANNs to seismic active control is asserted by the promising results obtained from the numerical examples studied.
Automated brain segmentation using neural networks
NASA Astrophysics Data System (ADS)
Powell, Stephanie; Magnotta, Vincent; Johnson, Hans; Andreasen, Nancy
2006-03-01
Automated methods to delineate brain structures of interest are required to analyze large amounts of imaging data like that being collected in several on going multi-center studies. We have previously reported on using artificial neural networks (ANN) to define subcortical brain structures such as the thalamus (0.825), caudate (0.745), and putamen (0.755). One of the inputs into the ANN is the apriori probability of a structure existing at a given location. In this previous work, the apriori probability information was generated in Talairach space using a piecewise linear registration. In this work we have increased the dimensionality of this registration using Thirion's demons registration algorithm. The input vector consisted of apriori probability, spherical coordinates, and an iris of surrounding signal intensity values. The output of the neural network determined if the voxel was defined as one of the N regions used for training. Training was performed using a standard back propagation algorithm. The ANN was trained on a set of 15 images for 750,000,000 iterations. The resulting ANN weights were then applied to 6 test images not part of the training set. Relative overlap calculated for each structure was 0.875 for the thalamus, 0.845 for the caudate, and 0.814 for the putamen. With the modifications on the neural net algorithm and the use of multi-dimensional registration, we found substantial improvement in the automated segmentation method. The resulting segmented structures are as reliable as manual raters and the output of the neural network can be used without additional rater intervention.
Detection of Wildfires with Artificial Neural Networks
NASA Astrophysics Data System (ADS)
Umphlett, B.; Leeman, J.; Morrissey, M. L.
2011-12-01
Currently fire detection for the National Oceanic and Atmospheric Administration (NOAA) using satellite data is accomplished with algorithms and error checking human analysts. Artificial neural networks (ANNs) have been shown to be more accurate than algorithms or statistical methods for applications dealing with multiple datasets of complex observed data in the natural sciences. ANNs also deal well with multiple data sources that are not all equally reliable or equally informative to the problem. An ANN was tested to evaluate its accuracy in detecting wildfires utilizing polar orbiter numerical data from the Advanced Very High Resolution Radiometer (AVHRR). Datasets containing locations of known fires were gathered from the NOAA's polar orbiting satellites via the Comprehensive Large Array-data Stewardship System (CLASS). The data was then calibrated and navigation corrected using the Environment for Visualizing Images (ENVI). Fires were located with the aid of shapefiles generated via ArcGIS. Afterwards, several smaller ten pixel by ten pixel datasets were created for each fire (using the ENVI corrected data). Several datasets were created for each fire in order to vary fire position and avoid training the ANN to look only at fires in the center of an image. Datasets containing no fires were also created. A basic pattern recognition neural network was established with the MATLAB neural network toolbox. The datasets were then randomly separated into categories used to train, validate, and test the ANN. To prevent over fitting of the data, the mean squared error (MSE) of the network was monitored and training was stopped when the MSE began to rise. Networks were tested using each channel of the AVHRR data independently, channels 3a and 3b combined, and all six channels. The number of hidden neurons for each input set was also varied between 5-350 in steps of 5 neurons. Each configuration was run 10 times, totaling about 4,200 individual network evaluations. Thirty
Tonelli, Paul; Mouret, Jean-Baptiste
2013-01-01
A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural networks are (1) the developmental process that links genes to nervous systems, which enables the evolution of large, regular neural networks, and (2) synaptic plasticity, which allows neural networks to change during their lifetime. So far, these two topics have been mainly studied separately. The present paper shows that they are actually deeply connected. Using a simple operant conditioning task and a classic evolutionary algorithm, we compare three ways to encode plastic neural networks: a direct encoding, a developmental encoding inspired by computational neuroscience models, and a developmental encoding inspired by morphogen gradients (similar to HyperNEAT). Our results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks. Complementary experiments reveal that this result is likely the consequence of the bias of developmental encodings towards regular structures: (1) in our experimental setup, encodings that tend to produce more regular networks yield networks with better general learning abilities; (2) whatever the encoding is, networks that are the more regular are statistically those that have the best learning abilities. PMID:24236099
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 Model of Memory Retrieval
Recanatesi, Stefano; Katkov, Mikhail; Romani, Sandro; Tsodyks, Misha
2015-01-01
Human memory can store large amount of information. Nevertheless, recalling is often a challenging task. In a classical free recall paradigm, where participants are asked to repeat a briefly presented list of words, people make mistakes for lists as short as 5 words. We present a model for memory retrieval based on a Hopfield neural network where transition between items are determined by similarities in their long-term memory representations. Meanfield analysis of the model reveals stable states of the network corresponding (1) to single memory representations and (2) intersection between memory representations. We show that oscillating feedback inhibition in the presence of noise induces transitions between these states triggering the retrieval of different memories. The network dynamics qualitatively predicts the distribution of time intervals required to recall new memory items observed in experiments. It shows that items having larger number of neurons in their representation are statistically easier to recall and reveals possible bottlenecks in our ability of retrieving memories. Overall, we propose a neural network model of information retrieval broadly compatible with experimental observations and is consistent with our recent graphical model (Romani et al., 2013). PMID:26732491
Sparse coding for layered neural networks
NASA Astrophysics Data System (ADS)
Katayama, Katsuki; Sakata, Yasuo; Horiguchi, Tsuyoshi
2002-07-01
We investigate storage capacity of two types of fully connected layered neural networks with sparse coding when binary patterns are embedded into the networks by a Hebbian learning rule. One of them is a layered network, in which a transfer function of even layers is different from that of odd layers. The other is a layered network with intra-layer connections, in which the transfer function of inter-layer is different from that of intra-layer, and inter-layered neurons and intra-layered neurons are updated alternately. We derive recursion relations for order parameters by means of the signal-to-noise ratio method, and then apply the self-control threshold method proposed by Dominguez and Bollé to both layered networks with monotonic transfer functions. We find that a critical value αC of storage capacity is about 0.11|a ln a| -1 ( a≪1) for both layered networks, where a is a neuronal activity. It turns out that the basin of attraction is larger for both layered networks when the self-control threshold method is applied.
NASA Technical Reports Server (NTRS)
Rai, Man Mohan (Inventor); Madavan, Nateri K. (Inventor)
2007-01-01
A method and system for data modeling that incorporates the advantages of both traditional response surface methodology (RSM) and neural networks is disclosed. The invention partitions the parameters into a first set of s simple parameters, where observable data are expressible as low order polynomials, and c complex parameters that reflect more complicated variation of the observed data. Variation of the data with the simple parameters is modeled using polynomials; and variation of the data with the complex parameters at each vertex is analyzed using a neural network. Variations with the simple parameters and with the complex parameters are expressed using a first sequence of shape functions and a second sequence of neural network functions. The first and second sequences are multiplicatively combined to form a composite response surface, dependent upon the parameter values, that can be used to identify an accurate mode
Advances in Artificial Neural Networks - Methodological Development and Application
Technology Transfer Automated Retrieval System (TEKTRAN)
Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...
Multistage neural network model for dynamic scene analysis
Ajjimarangsee, P.
1989-01-01
This research is concerned with dynamic scene analysis. The goal of scene analysis is to recognize objects and have a meaningful interpretation of the scene from which images are obtained. The task of the dynamic scene analysis process generally consists of region identification, motion analysis and object recognition. The objective of this research is to develop clustering algorithms using neural network approach and to investigate a multi-stage neural network model for region identification and motion analysis. The research is separated into three parts. First, a clustering algorithm using Kohonens' self-organizing feature map network is developed to be capable of generating continuous membership valued outputs. A newly developed version of the updating algorithm of the network is introduced to achieve a high degree of parallelism. A neural network model for the fuzzy c-means algorithm is proposed. In the second part, the parallel algorithms of a neural network model for clustering using the self-organizing feature maps approach and a neural network that models the fuzzy c-means algorithm are modified for implementation on a distributed memory parallel architecture. In the third part, supervised and unsupervised neural network models for motion analysis are investigated. For a supervised neural network, a three layer perceptron network is trained by a series of images to recognize the movement of the objects. For the unsupervised neural network, a self-organizing feature mapping network will learn to recognize the movement of the objects without an explicit training phase.
The strategic organizational use of neural networks: An exploratory study
Wilson, R.L.
1990-01-01
Management of emerging technologies in organizations may be handled by neural networks, a brain metaphor' of information processing. In this study, technical and managerial issues surrounding the implementation of a neural network in an organizational decision setting are investigated. The study has three main emphases. (1) An exploratory experimental effort studied the effects of a number of technical implementation factors on accuracy of a trained neural network. Results indicated that composition of the training set evaluation set can significantly effect the actual and perceived decision-making accuracy. (2) A decision-support framework illustrated further important issues that must be considered in appropriately using a neural network. The importance of using a multiplicity of trained networks to assist the decision-making process was shown. (3) It was shown how a neural-network approach provides improved managerial decision support for product screening. The study illustrated that proper use of neural information processing can provide significant organizational benefits.
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks
Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli
2016-01-01
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.
Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli
2016-01-01
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423
Facial expression recognition using constructive neural networks
NASA Astrophysics Data System (ADS)
Ma, Liying; Khorasani, Khashayar
2001-08-01
The computer-based recognition of facial expressions has been an active area of research for quite a long time. The ultimate goal is to realize intelligent and transparent communications between human beings and machines. The neural network (NN) based recognition methods have been found to be particularly promising, since NN is capable of implementing mapping from the feature space of face images to the facial expression space. However, finding a proper network size has always been a frustrating and time consuming experience for NN developers. In this paper, we propose to use the constructive one-hidden-layer feed forward neural networks (OHL-FNNs) to overcome this problem. The constructive OHL-FNN will obtain in a systematic way a proper network size which is required by the complexity of the problem being considered. Furthermore, the computational cost involved in network training can be considerably reduced when compared to standard back- propagation (BP) based FNNs. In our proposed technique, the 2-dimensional discrete cosine transform (2-D DCT) is applied over the entire difference face image for extracting relevant features for recognition purpose. The lower- frequency 2-D DCT coefficients obtained are then used to train a constructive OHL-FNN. An input-side pruning technique previously proposed by the authors is also incorporated into the constructive OHL-FNN. An input-side pruning technique previously proposed by the authors is also incorporated into the constructive learning process to reduce the network size without sacrificing the performance of the resulting network. The proposed technique is applied to a database consisting of images of 60 men, each having the resulting network. The proposed technique is applied to a database consisting of images of 60 men, each having 5 facial expression images (neutral, smile, anger, sadness, and surprise). Images of 40 men are used for network training, and the remaining images are used for generalization and
Applying neural networks to ultrasonographic texture recognition
NASA Astrophysics Data System (ADS)
Gallant, Jean-Francois; Meunier, Jean; Stampfler, Robert; Cloutier, Jocelyn
1993-09-01
A neural network was trained to classify ultrasound image samples of normal, adenomatous (benign tumor) and carcinomatous (malignant tumor) thyroid gland tissue. The samples themselves, as well as their Fourier spectrum, miscellaneous cooccurrence matrices and 'generalized' cooccurrence matrices, were successively submitted to the network, to determine if it could be trained to identify discriminating features of the texture of the image, and if not, which feature extractor would give the best results. Results indicate that the network could indeed extract some distinctive features from the textures, since it could accomplish a partial classification when trained with the samples themselves. But a significant improvement both in learning speed and performance was observed when it was trained with the generalized cooccurrence matrices of the samples.
DC motor speed control using neural networks
NASA Astrophysics Data System (ADS)
Tai, Heng-Ming; Wang, Junli; Kaveh, Ashenayi
1990-08-01
This paper presents a scheme that uses a feedforward neural network for the learning and generalization of the dynamic characteristics for the starting of a dc motor. The goal is to build an intelligent motor starter which has a versatility equivalent to that possessed by a human operator. To attain a fast and safe starting from stall for a dc motor a maximum armature current should be maintained during the starting period. This can be achieved by properly adjusting the armature voltage. The network is trained to learn the inverse dynamics of the motor starting characteristics and outputs a proper armature voltage. Simulation was performed to demonstrate the feasibility and effectiveness of the model. This study also addresses the network performance as a function of the number of hidden units and the number of training samples. 1.
Biologically relevant neural network architectures for support vector machines.
Jändel, Magnus
2014-01-01
Neural network architectures that implement support vector machines (SVM) are investigated for the purpose of modeling perceptual one-shot learning in biological organisms. A family of SVM algorithms including variants of maximum margin, 1-norm, 2-norm and ν-SVM is considered. SVM training rules adapted for neural computation are derived. It is found that competitive queuing memory (CQM) is ideal for storing and retrieving support vectors. Several different CQM-based neural architectures are examined for each SVM algorithm. Although most of the sixty-four scanned architectures are unconvincing for biological modeling four feasible candidates are found. The seemingly complex learning rule of a full ν-SVM implementation finds a particularly simple and natural implementation in bisymmetric architectures. Since CQM-like neural structures are thought to encode skilled action sequences and bisymmetry is ubiquitous in motor systems it is speculated that trainable pattern recognition in low-level perception has evolved as an internalized motor programme. PMID:24126252
Learning Orthographic Structure With Sequential Generative Neural Networks.
Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco
2016-04-01
Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine (RBM), a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models (n-grams and hidden Markov models). We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. PMID:26073971
One pass learning for generalized classifier neural network.
Ozyildirim, Buse Melis; Avci, Mutlu
2016-01-01
Generalized classifier neural network introduced as a kind of radial basis function neural network, uses gradient descent based optimized smoothing parameter value to provide efficient classification. However, optimization consumes quite a long time and may cause a drawback. In this work, one pass learning for generalized classifier neural network is proposed to overcome this disadvantage. Proposed method utilizes standard deviation of each class to calculate corresponding smoothing parameter. Since different datasets may have different standard deviations and data distributions, proposed method tries to handle these differences by defining two functions for smoothing parameter calculation. Thresholding is applied to determine which function will be used. One of these functions is defined for datasets having different range of values. It provides balanced smoothing parameters for these datasets through logarithmic function and changing the operation range to lower boundary. On the other hand, the other function calculates smoothing parameter value for classes having standard deviation smaller than the threshold value. Proposed method is tested on 14 datasets and performance of one pass learning generalized classifier neural network is compared with that of probabilistic neural network, radial basis function neural network, extreme learning machines, and standard and logarithmic learning generalized classifier neural network in MATLAB environment. One pass learning generalized classifier neural network provides more than a thousand times faster classification than standard and logarithmic generalized classifier neural network. Due to its classification accuracy and speed, one pass generalized classifier neural network can be considered as an efficient alternative to probabilistic neural network. Test results show that proposed method overcomes computational drawback of generalized classifier neural network and may increase the classification performance. PMID
Training product unit neural networks with genetic algorithms
NASA Technical Reports Server (NTRS)
Janson, D. J.; Frenzel, J. F.; Thelen, D. C.
1991-01-01
The training of product neural networks using genetic algorithms is discussed. Two unusual neural network techniques are combined; product units are employed instead of the traditional summing units and genetic algorithms train the network rather than backpropagation. As an example, a neural netork is trained to calculate the optimum width of transistors in a CMOS switch. It is shown how local minima affect the performance of a genetic algorithm, and one method of overcoming this is presented.
Classification of behavior using unsupervised temporal neural networks
Adair, K.L.; Argo, P.
1998-03-01
Adding recurrent connections to unsupervised neural networks used for clustering creates a temporal neural network which clusters a sequence of inputs as they appear over time. The model presented combines the Jordan architecture with the unsupervised learning technique Adaptive Resonance Theory, Fuzzy ART. The combination yields a neural network capable of quickly clustering sequential pattern sequences as the sequences are generated. The applicability of the architecture is illustrated through a facility monitoring problem.
Proceedings of intelligent engineering systems through artificial neural networks
Dagli, C.H. . Dept. of Engineering Management); Kumara, S.R. . Dept. of Industrial Management Systems Engineering); Shin, Y.C. . School of Mechanical Engineering)
1991-01-01
This book contains the edited versions of the technical presentation of ANNIE '91, the first international meeting on Artificial Neural Networks in Engineering. The conference covered the theory of Artificial Neural Networks and its contributions in the engineering domain and attracted researchers from twelve countries. The papers in this edited book are grouped into four categories: Artificial Neural Network Architectures; Pattern Recognition; Adaptive Control, Diagnosis and Process Monitoring; and Neuro-Engineering Systems.
Face recognition using artificial neural network group-based adaptive tolerance (GAT) trees.
Zhang, M; Fulcher, J
1996-01-01
Recent artificial neural network research has focused on simple models, but such models have not been very successful in describing complex systems (such as face recognition). This paper introduces the artificial neural network group-based adaptive tolerance (GAT) tree model for translation-invariant face recognition, suitable for use in an airport security system. GAT trees use a two-stage divide-and-conquer tree-type approach. The first stage determines general properties of the input, such as whether the facial image contains glasses or a beard. The second stage identifies the individual. Face perception classification, detection of front faces with glasses and/or beards, and face recognition results using GAT trees under laboratory conditions are presented. We conclude that the neural network group-based model offers significant improvement over conventional neural network trees for this task. PMID:18263454
Physical connections between different SSVEP neural networks
Wu, Zhenghua
2016-01-01
This work investigates the mechanism of the Steady-State Visual Evoked Potential (SSVEP). One theory suggests that different SSVEP neural networks exist whose strongest response are located in different frequency bands. This theory is based on the fact that there are similar SSVEP frequency-amplitude response curves in these bands. Previous studies that employed simultaneous stimuli of different frequencies illustrated that the distribution of these networks were similar, but did not discuss the physical connection between them. By comparing the SSVEP power and distribution under a single-eye stimulus and a simultaneous, dual-eye stimulus, this work demonstrates that the distributions of different SSVEP neural networks are similar to each other and that there should be physical overlapping between them. According to the band-pass filter theory in a signal transferring channel, which we propose in this work for the first time, there are different amounts of neurons that are involved under repetitive stimuli of different frequencies and that the response intensity of each neuron is similar to each other so that the total response (i.e., the SSVEP) that is observed from the scalp is different. PMID:26952961
Neural networks for LED color control
NASA Astrophysics Data System (ADS)
Ashdown, Ian E.
2004-01-01
The design and implementation of an architectural dimming control for multicolor LED-based lighting fixtures is complicated by the need to maintain a consistent color balance under a wide variety of operating conditions. Factors to consider include nonlinear relationships between luminous flux intensity and drive current, junction temperature dependencies, LED manufacturing tolerances and binning parameters, device aging characteristics, variations in color sensor spectral responsitivities, and the approximations introduced by linear color space models. In this paper we formulate this problem as a nonlinear multidimensional function, where maintaining a consistent color balance is equivalent to determining the hyperplane representing constant chromaticity. To be useful for an architectural dimming control design, this determination must be made in real time as the lighting fixture intensity is adjusted. Further, the LED drive current must be continuously adjusted in response to color sensor inputs to maintain constant chromaticity for a given intensity setting. Neural networks are known to be universal approximators capable of representing any continuously differentiable bounded function. We therefore use a radial basis function neural network to represent the multidimensional function and provide the feedback signals needed to maintain constant chromaticity. The network can be trained on the factory floor using individual device measurements such as spectral radiant intensity and color sensor characteristics. This provides a flexible solution that is mostly independent of LED manufacturing tolerances and binning parameters.
Neural network and its application to CT imaging
Nikravesh, M.; Kovscek, A.R.; Patzek, T.W.
1997-02-01
We present an integrated approach to imaging the progress of air displacement by spontaneous imbibition of oil into sandstone. We combine Computerized Tomography (CT) scanning and neural network image processing. The main aspects of our approach are (I) visualization of the distribution of oil and air saturation by CT, (II) interpretation of CT scans using neural networks, and (III) reconstruction of 3-D images of oil saturation from the CT scans with a neural network model. Excellent agreement between the actual images and the neural network predictions is found.
Using Neural Networks to Describe Complex Phase Transformation Behavior
Vitek, J.M.; David, S.A.
1999-05-24
Final microstructures can often be the end result of a complex sequence of phase transformations. Fundamental analyses may be used to model various stages of the overall behavior but they are often impractical or cumbersome when considering multicomponent systems covering a wide range of compositions. Neural network analysis may be a useful alternative method of identifying and describing phase transformation beavior. A neural network model for ferrite prediction in stainless steel welds is described. It is shown that the neural network analysis provides valuable information that accounts for alloying element interactions. It is suggested that neural network analysis may be extremely useful for analysis when more fundamental approaches are unavailable or overly burdensome.
Optical-Correlator Neural Network Based On Neocognitron
NASA Technical Reports Server (NTRS)
Chao, Tien-Hsin; Stoner, William W.
1994-01-01
Multichannel optical correlator implements shift-invariant, high-discrimination pattern-recognizing neural network based on paradigm of neocognitron. Selected as basic building block of this neural network because invariance under shifts is inherent advantage of Fourier optics included in optical correlators in general. Neocognitron is conceptual electronic neural-network model for recognition of visual patterns. Multilayer processing achieved by iteratively feeding back output of feature correlator to input spatial light modulator and updating Fourier filters. Neural network trained by use of characteristic features extracted from target images. Multichannel implementation enables parallel processing of large number of selected features.
Neural networks and their application to nuclear power plant diagnosis
Reifman, J.
1997-10-01
The authors present a survey of artificial neural network-based computer systems that have been proposed over the last decade for the detection and identification of component faults in thermal-hydraulic systems of nuclear power plants. The capabilities and advantages of applying neural networks as decision support systems for nuclear power plant operators and their inherent characteristics are discussed along with their limitations and drawbacks. The types of neural network structures used and their applications are described and the issues of process diagnosis and neural network-based diagnostic systems are identified. A total of thirty-four publications are reviewed.
Neural network models: Insights and prescriptions from practical applications
Samad, T.
1995-12-31
Neural networks are no longer just a research topic; numerous applications are now testament to their practical utility. In the course of developing these applications, researchers and practitioners have been faced with a variety of issues. This paper briefly discusses several of these, noting in particular the rich connections between neural networks and other, more conventional technologies. A more comprehensive version of this paper is under preparation that will include illustrations on real examples. Neural networks are being applied in several different ways. Our focus here is on neural networks as modeling technology. However, much of the discussion is also relevant to other types of applications such as classification, control, and optimization.
Application of artificial neural networks to composite ply micromechanics
NASA Technical Reports Server (NTRS)
Brown, D. A.; Murthy, P. L. N.; Berke, L.
1991-01-01
Artificial neural networks can provide improved computational efficiency relative to existing methods when an algorithmic description of functional relationships is either totally unavailable or is complex in nature. For complex calculations, significant reductions in elapsed computation time are possible. The primary goal is to demonstrate the applicability of artificial neural networks to composite material characterization. As a test case, a neural network was trained to accurately predict composite hygral, thermal, and mechanical properties when provided with basic information concerning the environment, constituent materials, and component ratios used in the creation of the composite. A brief introduction on neural networks is provided along with a description of the project itself.
Predicate calculus for an architecture of multiple neural networks
NASA Astrophysics Data System (ADS)
Consoli, Robert H.
1990-08-01
Future projects with neural networks will require multiple individual network components. Current efforts along these lines are ad hoc. This paper relates the neural network to a classical device and derives a multi-part architecture from that model. Further it provides a Predicate Calculus variant for describing the location and nature of the trainings and suggests Resolution Refutation as a method for determining the performance of the system as well as the location of needed trainings for specific proofs. 2. THE NEURAL NETWORK AND A CLASSICAL DEVICE Recently investigators have been making reports about architectures of multiple neural networksL234. These efforts are appearing at an early stage in neural network investigations they are characterized by architectures suggested directly by the problem space. Touretzky and Hinton suggest an architecture for processing logical statements1 the design of this architecture arises from the syntax of a restricted class of logical expressions and exhibits syntactic limitations. In similar fashion a multiple neural netword arises out of a control problem2 from the sequence learning problem3 and from the domain of machine learning. 4 But a general theory of multiple neural devices is missing. More general attempts to relate single or multiple neural networks to classical computing devices are not common although an attempt is made to relate single neural devices to a Turing machines and Sun et a!. develop a multiple neural architecture that performs pattern classification.
Artificial neural networks and Abelian harmonic analysis
NASA Astrophysics Data System (ADS)
Rodriguez, Domingo; Pertuz-Campo, Jairo
1991-12-01
This work deals with the use of artificial neural networks (ANN) for the digital processing of finite discrete time signals. The effort concentrates on the efficient replacement of fast Fourier transform (FFT) algorithms with ANN algorithms in certain engineering and scientific applications. The FFT algorithms are efficient methods of computing the discrete Fourier transform (DFT). The ubiquitous DFT is utilized in almost every digital signal processing application where harmonic analysis information is needed. Applications abound in areas such as audio acoustics, geophysics, biomedicine, telecommunications, astrophysics, etc. To identify more efficient methods to obtain a desired spectral information will result in a reduction in the computational effort required to implement these applications.
Convolution neural networks for ship type recognition
NASA Astrophysics Data System (ADS)
Rainey, Katie; Reeder, John D.; Corelli, Alexander G.
2016-05-01
Algorithms to automatically recognize ship type from satellite imagery are desired for numerous maritime applications. This task is difficult, and example imagery accurately labeled with ship type is hard to obtain. Convolutional neural networks (CNNs) have shown promise in image recognition settings, but many of these applications rely on the availability of thousands of example images for training. This work attempts to under- stand for which types of ship recognition tasks CNNs might be well suited. We report the results of baseline experiments applying a CNN to several ship type classification tasks, and discuss many of the considerations that must be made in approaching this problem.
Artificial Neural Network applied to lightning flashes
NASA Astrophysics Data System (ADS)
Gin, R. B.; Guedes, D.; Bianchi, R.
2013-05-01
The development of video cameras enabled cientists to study lightning discharges comportment with more precision. The main goal of this project is to create a system able to detect images of lightning discharges stored in videos and classify them using an Artificial Neural Network (ANN)using C Language and OpenCV libraries. The developed system, can be split in two different modules: detection module and classification module. The detection module uses OpenCV`s computer vision libraries and image processing techniques to detect if there are significant differences between frames in a sequence, indicating that something, still not classified, occurred. Whenever there is a significant difference between two consecutive frames, two main algorithms are used to analyze the frame image: brightness and shape algorithms. These algorithms detect both shape and brightness of the event, removing irrelevant events like birds, as well as detecting the relevant events exact position, allowing the system to track it over time. The classification module uses a neural network to classify the relevant events as horizontal or vertical lightning, save the event`s images and calculates his number of discharges. The Neural Network was implemented using the backpropagation algorithm, and was trained with 42 training images , containing 57 lightning events (one image can have more than one lightning). TheANN was tested with one to five hidden layers, with up to 50 neurons each. The best configuration achieved a success rate of 95%, with one layer containing 20 neurons (33 test images with 42 events were used in this phase). This configuration was implemented in the developed system to analyze 20 video files, containing 63 lightning discharges previously manually detected. Results showed that all the lightning discharges were detected, many irrelevant events were unconsidered, and the event's number of discharges was correctly computed. The neural network used in this project achieved a
Solving inversion problems with neural networks
NASA Technical Reports Server (NTRS)
Kamgar-Parsi, Behzad; Gualtieri, J. A.
1990-01-01
A class of inverse problems in remote sensing can be characterized by Q = F(x), where F is a nonlinear and noninvertible (or hard to invert) operator, and the objective is to infer the unknowns, x, from the observed quantities, Q. Since the number of observations is usually greater than the number of unknowns, these problems are formulated as optimization problems, which can be solved by a variety of techniques. The feasibility of neural networks for solving such problems is presently investigated. As an example, the problem of finding the atmospheric ozone profile from measured ultraviolet radiances is studied.
Digital Image Compression Using Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Serra-Ricart, M.; Garrido, L.; Gaitan, V.; Aloy, A.
1993-01-01
The problem of storing, transmitting, and manipulating digital images is considered. Because of the file sizes involved, large amounts of digitized image information are becoming common in modern projects. Our goal is to described an image compression transform coder based on artificial neural networks techniques (NNCTC). A comparison of the compression results obtained from digital astronomical images by the NNCTC and the method used in the compression of the digitized sky survey from the Space Telescope Science Institute based on the H-transform is performed in order to assess the reliability of the NNCTC.
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. PMID:26264170
An efficient neural network approach to dynamic robot motion planning.
Yang, S X; Meng, M
2000-03-01
In this paper, a biologically inspired neural network approach to real-time collision-free motion planning of mobile robots or robot manipulators in a nonstationary environment is proposed. Each neuron in the topologically organized neural network has only local connections, whose neural dynamics is characterized by a shunting equation. Thus the computational complexity linearly depends on the neural network size. The real-time robot motion is planned through the dynamic activity landscape of the neural network without any prior knowledge of the dynamic environment, without explicitly searching over the free workspace or the collision paths, and without any learning procedures. Therefore it is computationally efficient. The global stability of the neural network is guaranteed by qualitative analysis and the Lyapunov stability theory. The effectiveness and efficiency of the proposed approach are demonstrated through simulation studies. PMID:10935758
Resource constrained design of artificial neural networks using comparator neural network
NASA Technical Reports Server (NTRS)
Wah, Benjamin W.; Karnik, Tanay S.
1992-01-01
We present a systematic design method executed under resource constraints for automating the design of artificial neural networks using the back error propagation algorithm. Our system aims at finding the best possible configuration for solving the given application with proper tradeoff between the training time and the network complexity. The design of such a system is hampered by three related problems. First, there are infinitely many possible network configurations, each may take an exceedingly long time to train; hence, it is impossible to enumerate and train all of them to completion within fixed time, space, and resource constraints. Second, expert knowledge on predicting good network configurations is heuristic in nature and is application dependent, rendering it difficult to characterize fully in the design process. A learning procedure that refines this knowledge based on examples on training neural networks for various applications is, therefore, essential. Third, the objective of the network to be designed is ill-defined, as it is based on a subjective tradeoff between the training time and the network cost. A design process that proposes alternate configurations under different cost-performance tradeoff is important. We have developed a Design System which schedules the available time, divided into quanta, for testing alternative network configurations. Its goal is to select/generate and test alternative network configurations in each quantum, and find the best network when time is expended. Since time is limited, a dynamic schedule that determines the network configuration to be tested in each quantum is developed. The schedule is based on relative comparison of predicted training times of alternative network configurations using comparator network paradigm. The comparator network has been trained to compare training times for a large variety of traces of TSSE-versus-time collected during back-propagation learning of various applications.
Molnets: An Artificial Chemistry Based on Neural Networks
NASA Technical Reports Server (NTRS)
Colombano, Silvano; Luk, Johnny; Segovia-Juarez, Jose L.; Lohn, Jason; Clancy, Daniel (Technical Monitor)
2002-01-01
The fundamental problem in the evolution of matter is to understand how structure-function relationships are formed and increase in complexity from the molecular level all the way to a genetic system. We have created a system where structure-function relationships arise naturally and without the need of ad hoc function assignments to given structures. The idea was inspired by neural networks, where the structure of the net embodies specific computational properties. In this system networks interact with other networks to create connections between the inputs of one net and the outputs of another. The newly created net then recomputes its own synaptic weights, based on anti-hebbian rules. As a result some connections may be cut, and multiple nets can emerge as products of a 'reaction'. The idea is to study emergent reaction behaviors, based on simple rules that constitute a pseudophysics of the system. These simple rules are parameterized to produce behaviors that emulate chemical reactions. We find that these simple rules show a gradual increase in the size and complexity of molecules. We have been building a virtual artificial chemistry laboratory for discovering interesting reactions and for testing further ideas on the evolution of primitive molecules. Some of these ideas include the potential effect of membranes and selective diffusion according to molecular size.
Neural network identifications of spectral signatures
Gisler, G.; Borel, C.
1996-02-01
We have investigated the application of neural nets to the determination of fundamental leaf canopy parameters from synthetic spectra. We describe some preliminary runs in which we separately determine leaf chemistry, leaf structure, leaf area index, and soil characteristics, and then we perform a simultaneous determination of all these parameters in a single neural network run with synthetic six-band Landsat data. We find that neural nets offer considerable promise in the determination of fundamental parameters of agricultural and environmental interest from broad-band multispectral data. The determination of the quantities of interest is frequently performed with accuracies of 5% or better, though as expected, the accuracy of determination in any one parameter depends to some extent on the value of other parameters, most importantly the leaf area index. Soil characterization, for example, is best done at low lai, while leaf chemistry is most reliably done at high lai. We believe that these techniques, particularly when implemented in fast parallel hardware and mounted directly on remote sensing platforms, will be useful for various agricultural and environmental applications.
Distributed neural computations for embedded sensor networks
NASA Astrophysics Data System (ADS)
Peckens, Courtney A.; Lynch, Jerome P.; Pei, Jin-Song
2011-04-01
Wireless sensing technologies have recently emerged as an inexpensive and robust method of data collection in a variety of structural monitoring applications. In comparison with cabled monitoring systems, wireless systems offer low-cost and low-power communication between a network of sensing devices. Wireless sensing networks possess embedded data processing capabilities which allow for data processing directly at the sensor, thereby eliminating the need for the transmission of raw data. In this study, the Volterra/Weiner neural network (VWNN), a powerful modeling tool for nonlinear hysteretic behavior, is decentralized for embedment in a network of wireless sensors so as to take advantage of each sensor's processing capabilities. The VWNN was chosen for modeling nonlinear dynamic systems because its architecture is computationally efficient and allows computational tasks to be decomposed for parallel execution. In the algorithm, each sensor collects it own data and performs a series of calculations. It then shares its resulting calculations with every other sensor in the network, while the other sensors are simultaneously exchanging their information. Because resource conservation is important in embedded sensor design, the data is pruned wherever possible to eliminate excessive communication between sensors. Once a sensor has its required data, it continues its calculations and computes a prediction of the system acceleration. The VWNN is embedded in the computational core of the Narada wireless sensor node for on-line execution. Data generated by a steel framed structure excited by seismic ground motions is used for validation of the embedded VWNN model.
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
Multisensory integration substantiates distributed and overlapping neural networks.
Pasqualotto, Achille
2016-01-01
The hypothesis that highly overlapping networks underlie brain functions (neural reuse) is decisively supported by three decades of multisensory research. Multisensory areas process information from more than one sensory modality and therefore represent the best examples of neural reuse. Recent evidence of multisensory processing in primary visual cortices further indicates that neural reuse is a basic feature of the brain. PMID:27562234
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
Energy coding in neural network with inhibitory neurons.
Wang, Ziyin; Wang, Rubin; Fang, Ruiyan
2015-04-01
This paper aimed at assessing and comparing the effects of the inhibitory neurons in the neural network on the neural energy distribution, and the network activities in the absence of the inhibitory neurons to understand the nature of neural energy distribution and neural energy coding. Stimulus, synchronous oscillation has significant difference between neural networks with and without inhibitory neurons, and this difference can be quantitatively evaluated by the characteristic energy distribution. In addition, the synchronous oscillation difference of the neural activity can be quantitatively described by change of the energy distribution if the network parameters are gradually adjusted. Compared with traditional method of correlation coefficient analysis, the quantitative indicators based on nervous energy distribution characteristics are more effective in reflecting the dynamic features of the neural network activities. Meanwhile, this neural coding method from a global perspective of neural activity effectively avoids the current defects of neural encoding and decoding theory and enormous difficulties encountered. Our studies have shown that neural energy coding is a new coding theory with high efficiency and great potential. PMID:25806094
A convolutional neural network neutrino event classifier
Aurisano, A.; Radovic, A.; Rocco, D.; Himmel, A.; Messier, M. D.; Niner, E.; Pawloski, G.; Psihas, F.; Sousa, A.; Vahle, P.
2016-09-01
Here, convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less
Neural networks for fault location in substations
Alves da Silva, A.P.; Silveira, P.M. da; Lambert-Torres, G.; Insfran, A.H.F.
1996-01-01
Faults producing load disconnections or emergency situations have to be located as soon as possible to start the electric network reconfiguration, restoring normal energy supply. This paper proposes the use of artificial neural networks (ANNs), of the associative memory type, to solve the fault location problem. The main idea is to store measurement sets representing the normal behavior of the protection system, considering the basic substation topology only, into associated memories. Afterwards, these memories are employed on-line for fault location using the protection system equipment status. The associative memories work correctly even in case of malfunction of the protection system and different pre-fault configurations. Although the ANNs are trained with single contingencies only, their generalization capability allows a good performance for multiple contingencies. The resultant fault location system is in operation at the 500 kV gas-insulated substation of the Itaipu system.
Programmable synaptic chip for electronic neural networks
NASA Technical Reports Server (NTRS)
Moopenn, A.; Langenbacher, H.; Thakoor, A. P.; Khanna, S. K.
1988-01-01
A binary synaptic matrix chip has been developed for electronic neural networks. The matrix chip contains a programmable 32X32 array of 'long channel' NMOSFET binary connection elements implemented in a 3-micron bulk CMOS process. Since the neurons are kept off-chip, the synaptic chip serves as a 'cascadable' building block for a multi-chip synaptic network as large as 512X512 in size. As an alternative to the programmable NMOSFET (long channel) connection elements, tailored thin film resistors are deposited, in series with FET switches, on some CMOS test chips, to obtain the weak synaptic connections. Although deposition and patterning of the resistors require additional processing steps, they promise substantial savings in silicon area. The performance of synaptic chip in a 32-neuron breadboard system in an associative memory test application is discussed.
Orthogonal patterns in binary neural networks
NASA Technical Reports Server (NTRS)
Baram, Yoram
1988-01-01
A binary neural network that stores only mutually orthogonal patterns is shown to converge, when probed by any pattern, to a pattern in the memory space, i.e., the space spanned by the stored patterns. The latter are shown to be the only members of the memory space under a certain coding condition, which allows maximum storage of M=(2N) sup 0.5 patterns, where N is the number of neurons. The stored patterns are shown to have basins of attraction of radius N/(2M), within which errors are corrected with probability 1 in a single update cycle. When the probe falls outside these regions, the error correction capability can still be increased to 1 by repeatedly running the network with the same probe.
Parameterized neural networks for high-energy physics
NASA Astrophysics Data System (ADS)
Baldi, Pierre; Cranmer, Kyle; Faucett, Taylor; Sadowski, Peter; Whiteson, Daniel
2016-05-01
We investigate a new structure for machine learning classifiers built with neural networks and applied to problems in high-energy physics by expanding the inputs to include not only measured features but also physics parameters. The physics parameters represent a smoothly varying learning task, and the resulting parameterized classifier can smoothly interpolate between them and replace sets of classifiers trained at individual values. This simplifies the training process and gives improved performance at intermediate values, even for complex problems requiring deep learning. Applications include tools parameterized in terms of theoretical model parameters, such as the mass of a particle, which allow for a single network to provide improved discrimination across a range of masses. This concept is simple to implement and allows for optimized interpolatable results.
Evolving networks and the development of neural systems
NASA Astrophysics Data System (ADS)
Johnson, Samuel; Marro, J.; Torres, Joaquín J.
2010-03-01
It is now generally assumed that the heterogeneity of most networks in nature probably arises via preferential attachment of some sort. However, the origin of various other topological features, such as degree-degree correlations and related characteristics, is often not clear, and they may arise from specific functional conditions. We show how it is possible to analyse a very general scenario in which nodes can gain or lose edges according to any (e.g., nonlinear) function of local and/or global degree information. Applying our method to two rather different examples of brain development—synaptic pruning in humans and the neural network of the worm C. Elegans—we find that simple biologically motivated assumptions lead to very good agreement with experimental data. In particular, many nontrivial topological features of the worm's brain arise naturally at a critical point.
Pattern classification and associative recall by neural networks
Chiueh, Tzi-Dar.
1989-01-01
The first part of this dissertation discusses a new classifier based on a multilayer feed-forward network architecture. The main idea is to map irregularly-distributed prototypes in a classification problem to codewords that are organized in some way. Then the pattern classification problem is transformed into a threshold decoding problem, which is easily solved using simple hard-limiter neurons. At first the author proposes the new model and introduce two families of good internal representation codes. Then some analyses and software simulation concerning the storage capacity of this new model are done. The results show that the new classifier is much better than the classifier based on the Hopfield model in terms of both the storage capacity and the ability to classify correlated prototypes. A general model for neural network associative memories with a feedback structure is proposed. Many existing neural network associative memories can be expressed as special cases of this general model. Among these models, there is a class of associative memories, called correlation associative memories, that are capable of storing a large number of memory patterns. If the function used in the evolution equation is monotonically nondecreasing, then a correlation associative memory can be proved to be asymptotically stable in both the synchronous and asynchronous updating modes. Of these correlation associative memories, one stands out because of its VLSI implementation feasibility and large storage capacity. This memory uses the exponentiation function in its evolution equation; hence it is called exponential correlation associative memory (ECAM).
Adaptive neural network motion control of manipulators with experimental evaluations.
Puga-Guzmán, S; Moreno-Valenzuela, J; Santibáñez, V
2014-01-01
A nonlinear proportional-derivative controller plus adaptive neuronal network compensation is proposed. With the aim of estimating the desired torque, a two-layer neural network is used. Then, adaptation laws for the neural network weights are derived. Asymptotic convergence of the position and velocity tracking errors is proven, while the neural network weights are shown to be uniformly bounded. The proposed scheme has been experimentally validated in real time. These experimental evaluations were carried in two different mechanical systems: a horizontal two degrees-of-freedom robot and a vertical one degree-of-freedom arm which is affected by the gravitational force. In each one of the two experimental set-ups, the proposed scheme was implemented without and with adaptive neural network compensation. Experimental results confirmed the tracking accuracy of the proposed adaptive neural network-based controller. PMID:24574910
USING A NEURAL NETWORK TO PREDICT ELECTRICITY GENERATION
The paper discusses using a neural network to predict electricity generation. uch predictions are important in developing forecasts of air pollutant release and in evaluating the effectiveness of alternative policies which may reduce pollution. eural network model (NUMOD) that pr...
Microarray data classified by artificial neural networks.
Linder, Roland; Richards, Tereza; Wagner, Mathias
2007-01-01
Systems biology has enjoyed explosive growth in both the number of people participating in this area of research and the number of publications on the topic. The field of systems biology encompasses the in silico analysis of high-throughput data as provided by DNA or protein microarrays. Along with the increasing availability of microarray data, attention is focused on methods of analyzing the expression rates. One important type of analysis is the classification task, for example, distinguishing different types of cell functions or tumors. Recently, interest has been awakened toward artificial neural networks (ANN), which have many appealing characteristics such as an exceptional degree of accuracy. Nonlinear relationships or independence from certain assumptions regarding the data distribution are also considered. The current work reviews advantages as well as disadvantages of neural networks in the context of microarray analysis. Comparisons are drawn to alternative methods. Selected solutions are discussed, and finally algorithms for the effective combination of multiple ANNs are presented. The development of approaches to use ANN-processed microarray data applicable to run cell and tissue simulations may be slated for future investigation. PMID:18220242
Sentence alignment using feed forward neural network.
Fattah, Mohamed Abdel; Ren, Fuji; Kuroiwa, Shingo
2006-12-01
Parallel corpora have become an essential resource for work in multi lingual natural language processing. However, sentence aligned parallel corpora are more efficient than non-aligned parallel corpora for cross language information retrieval and machine translation applications. In this paper, we present a new approach to align sentences in bilingual parallel corpora based on feed forward neural network classifier. A feature parameter vector is extracted from the text pair under consideration. This vector contains text features such as length, punctuate score, and cognate score values. A set of manually prepared training data has been assigned to train the feed forward neural network. Another set of data was used for testing. Using this new approach, we could achieve an error reduction of 60% over length based approach when applied on English-Arabic parallel documents. Moreover this new approach is valid for any language pair and it is quite flexible approach since the feature parameter vector may contain more/less or different features than that we used in our system such as lexical match feature. PMID:17285688
Multiresolution neural networks for mammographic mass detection
NASA Astrophysics Data System (ADS)
Spence, Clay D.; Sajda, Paul
1999-01-01
We have previously presented a hierarchical pyramid/neural network (HPNN) architecture which combines multi-scale image processing techniques with neural networks. This coarse-to- fine HPNN was designed to learn large-scale context information for detecting small objects. We have developed a similar architecture to detect mammographic masses (malignant tumors). Since masses are large, extended objects, the coarse-to-fine HPNN architecture is not suitable for the problem. Instead we constructed a fine-to- coarse HPNN architecture which is designed to learn small- scale detail structure associated with the extended objects. Our initial result applying the fine-to-coarse HPNN to mass detection are encouraging, with detection performance improvements of about 30%. We conclude that the ability of the HPNN architecture to integrate information across scales, from fine to coarse in the case of masses, makes it well suited for detecting objects which may have detail structure occurring at scales other than the natural scale of the object.
Boundary Depth Information Using Hopfield Neural Network
NASA Astrophysics Data System (ADS)
Xu, Sheng; Wang, Ruisheng
2016-06-01
Depth information is widely used for representation, reconstruction and modeling of 3D scene. Generally two kinds of methods can obtain the depth information. One is to use the distance cues from the depth camera, but the results heavily depend on the device, and the accuracy is degraded greatly when the distance from the object is increased. The other one uses the binocular cues from the matching to obtain the depth information. It is more and more mature and convenient to collect the depth information of different scenes by stereo matching methods. In the objective function, the data term is to ensure that the difference between the matched pixels is small, and the smoothness term is to smooth the neighbors with different disparities. Nonetheless, the smoothness term blurs the boundary depth information of the object which becomes the bottleneck of the stereo matching. This paper proposes a novel energy function for the boundary to keep the discontinuities and uses the Hopfield neural network to solve the optimization. We first extract the region of interest areas which are the boundary pixels in original images. Then, we develop the boundary energy function to calculate the matching cost. At last, we solve the optimization globally by the Hopfield neural network. The Middlebury stereo benchmark is used to test the proposed method, and results show that our boundary depth information is more accurate than other state-of-the-art methods and can be used to optimize the results of other stereo matching methods.
Prospecting droughts with stochastic artificial neural networks
NASA Astrophysics Data System (ADS)
Ochoa-Rivera, Juan Camilo
2008-04-01
SummaryA non-linear multivariate model based on an artificial neural network multilayer perceptron is presented, that includes a random component. The developed model is applied to generate monthly streamflows, which are used to obtain synthetic annual droughts. The calibration of the model was undertaken using monthly streamflow records of several geographical sites of a basin. The model calibration consisted of training the neural network with the error back-propagation learning algorithm, and adding a normally distributed random noise. The model was validated by comparing relevant statistics of synthetic streamflow series to those of historical records. Annual droughts were calculated from the generated streamflow series, and then the expected values of length, intensity and magnitude of the droughts were assessed. An exercise on identical basis was made applying a second order auto-regressive multivariate model, AR(2), to compare its results with those of the developed model. The proposed model outperforms the AR(2) model in reproducing the future drought scenarios.
Temporal-kernel recurrent neural networks.
Sutskever, Ilya; Hinton, Geoffrey
2010-03-01
A Recurrent Neural Network (RNN) is a powerful connectionist model that can be applied to many challenging sequential problems, including problems that naturally arise in language and speech. However, RNNs are extremely hard to train on problems that have long-term dependencies, where it is necessary to remember events for many timesteps before using them to make a prediction. In this paper we consider the problem of training RNNs to predict sequences that exhibit significant long-term dependencies, focusing on a serial recall task where the RNN needs to remember a sequence of characters for a large number of steps before reconstructing it. We introduce the Temporal-Kernel Recurrent Neural Network (TKRNN), which is a variant of the RNN that can cope with long-term dependencies much more easily than a standard RNN, and show that the TKRNN develops short-term memory that successfully solves the serial recall task by representing the input string with a stable state of its hidden units. PMID:19932002
Ordinal neural networks without iterative tuning.
Fernández-Navarro, Francisco; Riccardi, Annalisa; Carloni, Sante
2014-11-01
Ordinal regression (OR) is an important branch of supervised learning in between the multiclass classification and regression. In this paper, the traditional classification scheme of neural network is adapted to learn ordinal ranks. The model proposed imposes monotonicity constraints on the weights connecting the hidden layer with the output layer. To do so, the weights are transcribed using padding variables. This reformulation leads to the so-called inequality constrained least squares (ICLS) problem. Its numerical solution can be obtained by several iterative methods, for example, trust region or line search algorithms. In this proposal, the optimum is determined analytically according to the closed-form solution of the ICLS problem estimated from the Karush-Kuhn-Tucker conditions. Furthermore, following the guidelines of the extreme learning machine framework, the weights connecting the input and the hidden layers are randomly generated, so the final model estimates all its parameters without iterative tuning. The model proposed achieves competitive performance compared with the state-of-the-art neural networks methods for OR. PMID:25330430
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.
Speaker Verification Using Subword Neural Tree Networks.
NASA Astrophysics Data System (ADS)
Liou, Han-Sheng
1995-01-01
In this dissertation, a new neural-network-based algorithm for text-dependent speaker verification is presented. The algorithm uses a set of concatenated Neural Tree Networks (NTN's) trained on subword units to model a password. In contrast to the conventional stochastic approaches which model the subword units by Hidden Markov Models (HMM's), the new approach utilizes the discriminative training scheme to train a NTN for each subword unit. Two types of subword unit are investigated, phone-like units (PLU's) and HMM state-based units (HSU's). The training of the models includes the following steps. The training utterances of a password is first segmented into subword units using a HMM-based segmentation method. A NTN is then trained for each subword unit. In order to retrieve the temporal information which is relatively important in text-dependent speaker verification, the proposed paradigm integrates the discriminatory ability of the NTN with the temporal models of the HMM. A new scoring method using phonetic weighting to improve the speaker verification performance is also introduced. The proposed algorithms are evaluated by experiments on a TI isolated-word database, YOHO database, and several hundred utterances collected over telephone channel. Performance improvements are obtained over conventional techniques.
Neural network analysis for hazardous waste characterization
Misra, M.; Pratt, L.Y.; Farris, C.
1995-12-31
This paper is a summary of our work in developing a system for interpreting electromagnetic (EM) and magnetic sensor information from the dig face characterization experimental cell at INEL to determine the depth and nature of buried objects. This project contained three primary components: (1) development and evaluation of several geophysical interpolation schemes for correcting missing or noisy data, (2) development and evaluation of several wavelet compression schemes for removing redundancies from the data, and (3) construction of two neural networks that used the results of steps (1) and (2) to determine the depth and nature of buried objects. This work is a proof-of-concept study that demonstrates the feasibility of this approach. The resulting system was able to determine the nature of buried objects correctly 87% of the time and was able to locate a buried object to within an average error of 0.8 feet. These statistics were gathered based on a large test set and so can be considered reliable. Considering the limited nature of this study, these results strongly indicate the feasibility of this approach, and the importance of appropriate preprocessing of neural network input data.
Altered Synchronizations among Neural Networks in Geriatric Depression
Wang, Lihong; Chou, Ying-Hui; Potter, Guy G.; Steffens, David C.
2015-01-01
Although major depression has been considered as a manifestation of discoordinated activity between affective and cognitive neural networks, only a few studies have examined the relationships among neural networks directly. Because of the known disconnection theory, geriatric depression could be a useful model in studying the interactions among different networks. In the present study, using independent component analysis to identify intrinsically connected neural networks, we investigated the alterations in synchronizations among neural networks in geriatric depression to better understand the underlying neural mechanisms. Resting-state fMRI data was collected from thirty-two patients with geriatric depression and thirty-two age-matched never-depressed controls. We compared the resting-state activities between the two groups in the default-mode, central executive, attention, salience, and affective networks as well as correlations among these networks. The depression group showed stronger activity than the controls in an affective network, specifically within the orbitofrontal region. However, unlike the never-depressed controls, geriatric depression group lacked synchronized/antisynchronized activity between the affective network and the other networks. Those depressed patients with lower executive function has greater synchronization between the salience network with the executive and affective networks. Our results demonstrate the effectiveness of the between-network analyses in examining neural models for geriatric depression. PMID:26180795
Neural network classifier of attacks in IP telephony
NASA Astrophysics Data System (ADS)
Safarik, Jakub; Voznak, Miroslav; Mehic, Miralem; Partila, Pavol; Mikulec, Martin
2014-05-01
Various types of monitoring mechanism allow us to detect and monitor behavior of attackers in VoIP networks. Analysis of detected malicious traffic is crucial for further investigation and hardening the network. This analysis is typically based on statistical methods and the article brings a solution based on neural network. The proposed algorithm is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. Information about attacks on these honeypots is collected on a centralized server and then classified. This classification is based on different mechanisms. One of them is based on the multilayer perceptron neural network. The article describes inner structure of used neural network and also information about implementation of this network. The learning set for this neural network is based on real attack data collected from IP telephony honeypot called Dionaea. We prepare the learning set from real attack data after collecting, cleaning and aggregation of this information. After proper learning is the neural network capable to classify 6 types of most commonly used VoIP attacks. Using neural network classifier brings more accurate attack classification in a distributed system of honeypots. With this approach is possible to detect malicious behavior in a different part of networks, which are logically or geographically divided and use the information from one network to harden security in other networks. Centralized server for distributed set of nodes serves not only as a collector and classifier of attack data, but also as a mechanism for generating a precaution steps against attacks.
Altered Synchronizations among Neural Networks in Geriatric Depression.
Wang, Lihong; Chou, Ying-Hui; Potter, Guy G; Steffens, David C
2015-01-01
Although major depression has been considered as a manifestation of discoordinated activity between affective and cognitive neural networks, only a few studies have examined the relationships among neural networks directly. Because of the known disconnection theory, geriatric depression could be a useful model in studying the interactions among different networks. In the present study, using independent component analysis to identify intrinsically connected neural networks, we investigated the alterations in synchronizations among neural networks in geriatric depression to better understand the underlying neural mechanisms. Resting-state fMRI data was collected from thirty-two patients with geriatric depression and thirty-two age-matched never-depressed controls. We compared the resting-state activities between the two groups in the default-mode, central executive, attention, salience, and affective networks as well as correlations among these networks. The depression group showed stronger activity than the controls in an affective network, specifically within the orbitofrontal region. However, unlike the never-depressed controls, geriatric depression group lacked synchronized/antisynchronized activity between the affective network and the other networks. Those depressed patients with lower executive function has greater synchronization between the salience network with the executive and affective networks. Our results demonstrate the effectiveness of the between-network analyses in examining neural models for geriatric depression. PMID:26180795
NASA Astrophysics Data System (ADS)
Saito, Hiroshi; Katahira, Kentaro; Okanoya, Kazuo; Okada, Masato
2011-05-01
Neural networks can learn flexible input-output associations by changing their synaptic weights. The representational performance and learning dynamics of neural networks are intensively studied in several fields. Neural networks face the “credit assignment problem” in situations in which only incomplete performance evaluations are available. The credit assignment problem is that a network should assign credit or blame for its behaviors according to the contribution to the network performance. In reinforcement learning, a scalar evaluation signal is delivered to a network. The two main types of credit assignment problems in reinforcement learning are structural and temporal, that is, which parameters of the network (structural) and which past network activities (temporal) are related to an evaluation signal given from an environment. In this study, we apply statistical mechanical analysis to the learning processes in a simple neural network model to clarify the effects of two kinds of credit assignments and their interactions. Our model is based on node perturbation learning with eligibility trace. Node perturbation is a stochastic gradient learning method that can solve structural credit assignment problems by introducing a perturbation into the system output. The eligibility trace preserves the past network activities with a temporal credit to deal with the delay of an instruction signal. We show that both credit assignment effects mutually interact and the optimal time constant of the eligibility trace varies not only for the evaluation delay but also the network size.
Random neural network recognition of shaped objects in strong clutter
NASA Astrophysics Data System (ADS)
Bakircioglu, Hakan; Gelenbe, Erol
1998-04-01
Detecting objects in images containing strong clutter is an important issue in a variety of applications such as medical imaging and automatic target recognition. Artificial neural networks are used as non-parametric pattern recognizers to cope with different problems due to their inherent ability to learn from training data. In this paper we propose a neural approach based on the Random Neural Network model (Gelenbe 1989, 1990, 1991, 1993), to detect shaped targets with the help of multiple neural networks whose outputs are combined for making decisions.
Syntactic neural network for character recognition
NASA Astrophysics Data System (ADS)
Jaravine, Viktor A.
1992-08-01
This article presents a synergism of syntactic 2-D parsing of images and multilayered, feed- forward network techniques. This approach makes it possible to build a written text reading system with absolute recognition rate for unambiguous text strings. The Syntactic Neural Network (SNN) is created during image parsing process by capturing the higher order statistical structure in the ensemble of input image examples. Acquired knowledge is stored in the form of hierarchical image elements dictionary and syntactic network. The number of hidden layers and neuron units is not fixed and is determined by the structural complexity of the teaching set. A proposed syntactic neuron differs from conventional numerical neuron by its symbolic input/output and usage of the dictionary for determining the output. This approach guarantees exact recognition of an image that is a combinatorial variation of the images from the training set. The system is taught to generalize and to make stochastic parsing of distorted and shifted patterns. The generalizations enables the system to perform continuous incremental optimization of its work. New image data learned by SNN doesn''t interfere with previously stored knowledge, thus leading to unlimited storage capacity of the network.
Improved Adjoint-Operator Learning For A Neural Network
NASA Technical Reports Server (NTRS)
Toomarian, Nikzad; Barhen, Jacob
1995-01-01
Improved method of adjoint-operator learning reduces amount of computation and associated computational memory needed to make electronic neural network learn temporally varying pattern (e.g., to recognize moving object in image) in real time. Method extension of method described in "Adjoint-Operator Learning for a Neural Network" (NPO-18352).
A Neural Network Approach to the Classification of Autism.
ERIC Educational Resources Information Center
Cohen, Ira L.; And Others
1993-01-01
Neural network technology was compared with simultaneous and stepwise linear discriminant analysis in terms of their ability to classify and predict persons (n=138) as having autism or mental retardation. The neural network methodology was superior in both classifying groups and in generalizing to new cases that were not part of the training…
Multiple image sensor data fusion through artificial neural networks
Technology Transfer Automated Retrieval System (TEKTRAN)
With multisensor data fusion technology, the data from multiple sensors are fused in order to make a more accurate estimation of the environment through measurement, processing and analysis. Artificial neural networks are the computational models that mimic biological neural networks. With high per...
Using Neural Networks to Predict MBA Student Success
ERIC Educational Resources Information Center
Naik, Bijayananda; Ragothaman, Srinivasan
2004-01-01
Predicting MBA student performance for admission decisions is crucial for educational institutions. This paper evaluates the ability of three different models--neural networks, logit, and probit to predict MBA student performance in graduate programs. The neural network technique was used to classify applicants into successful and marginal student…
Application of four-layer neural network on information extraction.
Han, Min; Cheng, Lei; Meng, Hua
2003-01-01
This paper applies neural network to extract marsh information. An adaptive back-propagation algorithm based on a robust error function is introduced to build a four-layer neural network, and it is used to classify Thematic Mapper (TM) image of Zhalong Wetland in China and then extract marsh information. Comparing marsh information extraction results of the four-layer neural network with three-layer neural network and the maximum likelihood classifier, conclusion can be drawn as follows: the structure of the four-layer neural network and the adaptive back-propagation algorithm based on the robust error function is effective to extract marsh information. The four-layer neural network adopted in this paper succeeded in building the complex model of TM image, and it avoided the problem of great storage of remotely sensed data, and the adaptive back-propagation algorithm speeded up the descending of error. Above all, the four-layer neural network is superior to the three-layer neural network and the maximum likelihood classifier in the accuracy of the total classification and marsh information extraction. PMID:12850006
The use of neural networks for approximation of nuclear data
Korovin, Yu. A.; Maksimushkina, A. V.
2015-12-15
The article discusses the possibility of using neural networks for approximation or reconstruction of data such as the reaction cross sections. The quality of the approximation using fitting criteria is also evaluated. The activity of materials under irradiation is calculated from data obtained using neural networks.
Adjoint-Operator Learning For A Neural Network
NASA Technical Reports Server (NTRS)
Barhen, Jacob; Toomarian, Nikzad
1993-01-01
Electronic neural networks made to synthesize initially unknown mathematical models of time-dependent phenomena or to learn temporally evolving patterns by use of algorithms based on adjoint operators. Algorithms less complicated, involve less computation and solve learning equations forward in time possibly simultaneously with equations of evolution of neural network, thereby both increasing computational efficiency and making real-time applications possible.
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.
Information processing in neural networks with the complex dynamic thresholds
NASA Astrophysics Data System (ADS)
Kirillov, S. Yu.; Nekorkin, V. I.
2016-06-01
A control mechanism of the information processing in neural networks is investigated, based on the complex dynamic threshold of the neural excitation. The threshold properties are controlled by the slowly varying synaptic current. The dynamic threshold shows high sensitivity to the rate of the synaptic current variation. It allows both to realize flexible selective tuning of the network elements and to provide nontrivial regimes of neural coding.
ERIC Educational Resources Information Center
Treurniet, William
A study applied artificial neural networks, trained with the back-propagation learning algorithm, to modelling phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base. A number of proposed network architectures were applied to the phoneme classification task, ranging from the simple feedforward multilayer network to more…
A More Accurate Characterization of UH-60A Pitch Link Loads Using Neural Networks
NASA Technical Reports Server (NTRS)
Kottapalli, Sesi; Aiken, Ed (Technical Monitor)
1998-01-01
A more accurate, neural-network-based characterization of the full-scale UH-60A maximum, vibratory pitch link loads (MXVPLL) was obtained. The MXVPLL data were taken from the NASA/Army UH-60A Airloads Program flight test database. This database includes data from level flights, and both simple and "complex" maneuvers. In the present context, a complex maneuver was defined as one which involved simultaneous, non-zero aircraft angle-of-bank (associated with turns) and aircraft pitch-rate (associated with a pull-up or a push-over). The present approach combines physical insight followed by the neural networks application. Since existing load factors do not represent the above-defined complex maneuver, a new, combined load factor ('p resent-load-factor') was introduced. A back-propagation type of neural network with five inputs and one output was used to characterize the UH-60A MXVPLL. The neural network inputs were as follows: rotor advance ratio, aircraft gross weight, rotor RPM, air density ratio, and the present-load-factor. The neural network output was the maximum, vibratory pitch link load (MXVPLL). It was shown that a more accurate characterization of the full-scale flight test pitch link loads can be obtained by combining physical insight with a neural-network-based approach.
Application of neural networks to health monitoring of bridge structures
NASA Astrophysics Data System (ADS)
Loh, Chin-Hsiung; Yeh, ShyChing
2000-06-01
A procedure based on the use of artificial neural networks for the identification of dynamic system is developed and applied to the bridge structure under earthquake excitation. This neural network-based approach is also applied for the detection of changes in the characteristics of structure- unknown system. Based on the vibration measurement from a linear/healthy system to train the neural network for identification purposes, then the trained network is fed comparable vibration measurements from the same structure under different episodes of response in order to monitor the nonlinearity of the system. The learning ability of the network is examined for the use of multiple inputs. The effects of the network parameters on learning and accuracy of predictions are discussed. Based on this study it is found that the configuration of neural network model is the same as NARMA model and has the potential for structural damage detection.
Thermoelastic steam turbine rotor control based on neural network
NASA Astrophysics Data System (ADS)
Rzadkowski, Romuald; Dominiczak, Krzysztof; Radulski, Wojciech; Szczepanik, R.
2015-12-01
Considered here are Nonlinear Auto-Regressive neural networks with eXogenous inputs (NARX) as a mathematical model of a steam turbine rotor for controlling steam turbine stress on-line. In order to obtain neural networks that locate critical stress and temperature points in the steam turbine during transient states, an FE rotor model was built. This model was used to train the neural networks on the basis of steam turbine transient operating data. The training included nonlinearity related to steam turbine expansion, heat exchange and rotor material properties during transients. Simultaneous neural networks are algorithms which can be implemented on PLC controllers. This allows for the application neural networks to control steam turbine stress in industrial power plants.
Neural network computation with DNA strand displacement cascades.
Qian, Lulu; Winfree, Erik; Bruck, Jehoshua
2011-07-21
The impressive capabilities of the mammalian brain--ranging from perception, pattern recognition and memory formation to decision making and motor activity control--have inspired their re-creation in a wide range of artificial intelligence systems for applications such as face recognition, anomaly detection, medical diagnosis and robotic vehicle control. Yet before neuron-based brains evolved, complex biomolecular circuits provided individual cells with the 'intelligent' behaviour required for survival. However, the study of how molecules can 'think' has not produced an equal variety of computational models and applications of artificial chemical systems. Although biomolecular systems have been hypothesized to carry out neural-network-like computations in vivo and the synthesis of artificial chemical analogues has been proposed theoretically, experimental work has so far fallen short of fully implementing even a single neuron. Here, building on the richness of DNA computing and strand displacement circuitry, we show how molecular systems can exhibit autonomous brain-like behaviours. Using a simple DNA gate architecture that allows experimental scale-up of multilayer digital circuits, we systematically transform arbitrary linear threshold circuits (an artificial neural network model) into DNA strand displacement cascades that function as small neural networks. Our approach even allows us to implement a Hopfield associative memory with four fully connected artificial neurons that, after training in silico, remembers four single-stranded DNA patterns and recalls the most similar one when presented with an incomplete pattern. Our results suggest that DNA strand displacement cascades could be used to endow autonomous chemical systems with the capability of recognizing patterns of molecular events, making decisions and responding to the environment. PMID:21776082
Quantum neural networks: Current status and prospects for development
NASA Astrophysics Data System (ADS)
Altaisky, M. V.; Kaputkina, N. E.; Krylov, V. A.
2014-11-01
The idea of quantum artificial neural networks, first formulated in [34], unites the artificial neural network concept with the quantum computation paradigm. Quantum artificial neural networks were first systematically considered in the PhD thesis by T. Menneer (1998). Based on the works of Menneer and Narayanan [42, 43], Kouda, Matsui, and Nishimura [35, 36], Altaisky [2, 68], Zhou [67], and others, quantum-inspired learning algorithms for neural networks were developed, and are now used in various training programs and computer games [29, 30]. The first practically realizable scaled hardware-implemented model of the quantum artificial neural network is obtained by D-Wave Systems, Inc. [33]. It is a quantum Hopfield network implemented on the basis of superconducting quantum interference devices (SQUIDs). In this work we analyze possibilities and underlying principles of an alternative way to implement quantum neural networks on the basis of quantum dots. A possibility of using quantum neural network algorithms in automated control systems, associative memory devices, and in modeling biological and social networks is examined.
Estimation of bullet striation similarity using neural networks.
Banno, Atsuhiko
2004-05-01
A new method that searches for similar striation patterns using neural networks is described. Neural networks have been developed based on the human brain, which is good at pattern recognition. Therefore, neural networks would be expected to be effective in identifying striated toolmarks on bullets. The neural networks used in this study deal with binary signals derived from striation images. This signal plays a significant role in identification, because this signal is the key to the individually of the striations. The neural network searches a database for similar striations by means of these binary signals. The neural network used here is a multilayer network consisting of 96 neurons in the input layer, 15 neurons in the middle, and one neuron in the output layer. Two signals are inputted into the network and a score is estimated based on the similarity of these signals. For this purpose, the network is assigned to a previous learning. To initially test the validity of the procedure, the network identifies artificial patterns that are randomly produced on a personal computer. The results were acceptable and showed robustness for the deformation of patterns. Moreover, with ten unidentified bullets and ten database bullets, the network consistently was able to select the correct pair. PMID:15171166
Sea level forecasts using neural networks
NASA Astrophysics Data System (ADS)
Röske, Frank
1997-03-01
In this paper, a new method for predicting the sea level employing a neural network approach is introduced. It was designed to improve the prediction of the sea level along the German North Sea Coast under standard conditions. The sea level at any given time depends upon the tides as well as meteorological and oceanographic factors, such as the winds and external surges induced by air pressure. Since tidal predictions are already sufficiently accurate, they have been subtracted from the observed sea levels. The differences will be predicted up to 18 hours in advance. In this paper, the differences are called anomalies. The prediction of the sea level each hour is distinguished from its predictions at the times of high and low tide. For this study, Cuxhaven was selected as a reference site. The predictions made using neural networks were compared for accuracy with the prognoses prepared using six models: two hydrodynamic models, a statistical model, a nearest neighbor model, which is based on analogies, the persistence model, and the verbal forecasts that are broadcast and kept on record by the Sea Level Forecast Service of the Federal Maritime and Hydrography Agency (BSH) in Hamburg. Predictions were calculated for the year 1993 and compared with the actual levels measured. Artificial neural networks are capable of learning. By applying them to the prediction of sea levels, learning from past events has been attempted. It was also attempted to make the experiences of expert forecasters objective. Instead of using the wide-spread back-propagation networks, the self-organizing feature map of Kohonen, or “Kohonen network”, was applied. The fundamental principle of this network is the transformation of the signal similarity into the neighborhood of the neurons while preserving the topology of the signal space. The self-organization procedure of Kohonen networks can be visualized. To make predictions, these networks have been subdivided into a part describing the
Application of artificial neural networks in nonlinear analysis of trusses
NASA Technical Reports Server (NTRS)
Alam, J.; Berke, L.
1991-01-01
A method is developed to incorporate neural network model based upon the Backpropagation algorithm for material response into nonlinear elastic truss analysis using the initial stiffness method. Different network configurations are developed to assess the accuracy of neural network modeling of nonlinear material response. In addition to this, a scheme based upon linear interpolation for material data, is also implemented for comparison purposes. It is found that neural network approach can yield very accurate results if used with care. For the type of problems under consideration, it offers a viable alternative to other material modeling methods.
Massively parallel neural network intelligent browse
NASA Astrophysics Data System (ADS)
Maxwell, Thomas P.; Zion, Philip M.
1992-04-01
A massively parallel neural network architecture is currently being developed as a potential component of a distributed information system in support of NASA's Earth Observing System. This architecture can be trained, via an iterative learning process, to recognize objects in images based on texture features, allowing scientists to search for all patterns which are similar to a target pattern in a database of images. It may facilitate scientific inquiry by allowing scientists to automatically search for physical features of interest in a database through computer pattern recognition, alleviating the need for exhaustive visual searches through possibly thousands of images. The architecture is implemented on a Connection Machine such that each physical processor contains a simulated 'neuron' which views a feature vector derived from a subregion of the input image. Each of these neurons is trained, via the perceptron rule, to identify the same pattern. The network output gives a probability distribution over the input image of finding the target pattern in a given region. In initial tests the architecture was trained to separate regions containing clouds from clear regions in 512 by 512 pixel AVHRR images. We found that in about 10 minutes we can train a network to perform with high accuracy in recognizing clouds which were texturally similar to a target cloud group. These promising results suggest that this type of architecture may play a significant role in coping with the forthcoming flood of data from the Earth-monitoring missions of the major space-faring nations.
Neural network classification of sweet potato embryos
NASA Astrophysics Data System (ADS)
Molto, Enrique; Harrell, Roy C.
1993-05-01
Somatic embryogenesis is a process that allows for the in vitro propagation of thousands of plants in sub-liter size vessels and has been successfully applied to many significant species. The heterogeneity of maturity and quality of embryos produced with this technique requires sorting to obtain a uniform product. An automated harvester is being developed at the University of Florida to sort embryos in vitro at different stages of maturation in a suspension culture. The system utilizes machine vision to characterize embryo morphology and a fluidic based separation device to isolate embryos associated with a pre-defined, targeted morphology. Two different backpropagation neural networks (BNN) were used to classify embryos based on information extracted from the vision system. One network utilized geometric features such as embryo area, length, and symmetry as inputs. The alternative network utilized polar coordinates of an embryo's perimeter with respect to its centroid as inputs. The performances of both techniques were compared with each other and with an embryo classification method based on linear discriminant analysis (LDA). Similar results were obtained with all three techniques. Classification efficiency was improved by reducing the dimension of the feature vector trough a forward stepwise analysis by LDA. In order to enhance the purity of the sample selected as harvestable, a reject to classify option was introduced in the model and analyzed. The best classifier performances (76% overall correct classifications, 75% harvestable objects properly classified, homogeneity improvement ratio 1.5) were obtained using 8 features in a BNN.
Antagonistic neural networks underlying differentiated leadership roles
Boyatzis, Richard E.; Rochford, Kylie; Jack, Anthony I.
2014-01-01
The emergence of two distinct leadership roles, the task leader and the socio-emotional leader, has been documented in the leadership literature since the 1950s. Recent research in neuroscience suggests that the division between task-oriented and socio-emotional-oriented roles derives from a fundamental feature of our neurobiology: an antagonistic relationship between two large-scale cortical networks – the task-positive network (TPN) and the default mode network (DMN). Neural activity in TPN tends to inhibit activity in the DMN, and vice versa. The TPN is important for problem solving, focusing of attention, making decisions, and control of action. The DMN plays a central role in emotional self-awareness, social cognition, and ethical decision making. It is also strongly linked to creativity and openness to new ideas. Because activation of the TPN tends to suppress activity in the DMN, an over-emphasis on task-oriented leadership may prove deleterious to social and emotional aspects of leadership. Similarly, an overemphasis on the DMN would result in difficulty focusing attention, making decisions, and solving known problems. In this paper, we will review major streams of theory and research on leadership roles in the context of recent findings from neuroscience and psychology. We conclude by suggesting that emerging research challenges the assumption that role differentiation is both natural and necessary, in particular when openness to new ideas, people, emotions, and ethical concerns are important to success. PMID:24624074
Antagonistic neural networks underlying differentiated leadership roles.
Boyatzis, Richard E; Rochford, Kylie; Jack, Anthony I
2014-01-01
The emergence of two distinct leadership roles, the task leader and the socio-emotional leader, has been documented in the leadership literature since the 1950s. Recent research in neuroscience suggests that the division between task-oriented and socio-emotional-oriented roles derives from a fundamental feature of our neurobiology: an antagonistic relationship between two large-scale cortical networks - the task-positive network (TPN) and the default mode network (DMN). Neural activity in TPN tends to inhibit activity in the DMN, and vice versa. The TPN is important for problem solving, focusing of attention, making decisions, and control of action. The DMN plays a central role in emotional self-awareness, social cognition, and ethical decision making. It is also strongly linked to creativity and openness to new ideas. Because activation of the TPN tends to suppress activity in the DMN, an over-emphasis on task-oriented leadership may prove deleterious to social and emotional aspects of leadership. Similarly, an overemphasis on the DMN would result in difficulty focusing attention, making decisions, and solving known problems. In this paper, we will review major streams of theory and research on leadership roles in the context of recent findings from neuroscience and psychology. We conclude by suggesting that emerging research challenges the assumption that role differentiation is both natural and necessary, in particular when openness to new ideas, people, emotions, and ethical concerns are important to success. PMID:24624074
Fault classification by neural networks and fuzzy logic
Chwan-Hwa ``John`` Wu; Chihwen Li; Shih, H.; Alexion, C.C.; Ovick, N.L.; Murphy, J.H.
1995-01-25
A neural fuzzy-based and a backpropagation neural network-based fault classifier for a three-phase motor will be described in this paper. In order to acquire knowledge, the neural fuzzy classifier incorporates a learning technique to automatically generate membership functions for fuzzy rules, and the backpropagation algorithm is used to train the neural network model. Therefore, in this paper, the preprocessing of signals, fuzzy and neural models, training methods, implementations for real-time response and testing results will be discussed in detail. Furthermore, the generalization capabilities of the neural fuzzy- and backpropagation-based classifiers for waveforms with varying magnitudes, frequencies, noises and positions of spikes and chops in a cycle of a sine wave will be investigated, and the computation requirements needed to achieve real-time response for both fuzzy and neural methods will be compared. {copyright} 1995 {ital American} {ital Institute} {ital of} {ital Physics}
Neural network analysis of W UMa eclipsing binaries
NASA Astrophysics Data System (ADS)
Zeraatgari, F. Z.; Abedi, A.; Farshad, M.; Ebadian, M.; Riazi, N.
2015-04-01
We try five different artificial neural models, four models based on PNN (Perceptron Neural Network), and one using GRNN (Generalized Regression Neural Network) as tools for the automated light curve analysis of W UMa-type eclipsing binary systems. These algorithms, which are inspired by the Rucinski method, are designed and trained using MATLAB 7.6. A total of 17,820 generated contact binary light curves are first analyzed using a truncated cosine series with 11 coefficients and the most significant coefficients are applied as inputs of the neural models. The required sample light curves are systematically generated, using the WD2007 program (Wilson and Devinney 2007). The trained neural models are then applied to estimate the geometrical parameters of seven W UMa-type systems. The efficiency of different neural network models are then evaluated and compared to find the most efficient one.
Neural networks supporting switching, hypothesis testing, and rule application.
Liu, Zhiya; Braunlich, Kurt; Wehe, Hillary S; Seger, Carol A
2015-10-01
We identified dynamic changes in recruitment of neural connectivity networks across three phases of a flexible rule learning and set-shifting task similar to the Wisconsin Card Sort Task: switching, rule learning via hypothesis testing, and rule application. During fMRI scanning, subjects viewed pairs of stimuli that differed across four dimensions (letter, color, size, screen location), chose one stimulus, and received feedback. Subjects were informed that the correct choice was determined by a simple unidimensional rule, for example "choose the blue letter". Once each rule had been learned and correctly applied for 4-7 trials, subjects were cued via either negative feedback or visual cues to switch to learning a new rule. Task performance was divided into three phases: Switching (first trial after receiving the switch cue), hypothesis testing (subsequent trials through the last error trial), and rule application (correct responding after the rule was learned). We used both univariate analysis to characterize activity occurring within specific regions of the brain, and a multivariate method, constrained principal component analysis for fMRI (fMRI-CPCA), to investigate how distributed regions coordinate to subserve different processes. As hypothesized, switching was subserved by a limbic network including the ventral striatum, thalamus, and parahippocampal gyrus, in conjunction with cortical salience network regions including the anterior cingulate and frontoinsular cortex. Activity in the ventral striatum was associated with switching regardless of how switching was cued; visually cued shifts were associated with additional visual cortical activity. After switching, as subjects moved into the hypothesis testing phase, a broad fronto-parietal-striatal network (associated with the cognitive control, dorsal attention, and salience networks) increased in activity. This network was sensitive to rule learning speed, with greater extended activity for the slowest
Deep Neural Networks with Multistate Activation Functions
Cai, Chenghao; Xu, Yanyan; Ke, Dengfeng; Su, Kaile
2015-01-01
We propose multistate activation functions (MSAFs) for deep neural networks (DNNs). These MSAFs are new kinds of activation functions which are capable of representing more than two states, including the N-order MSAFs and the symmetrical MSAF. DNNs with these MSAFs can be trained via conventional Stochastic Gradient Descent (SGD) as well as mean-normalised SGD. We also discuss how these MSAFs perform when used to resolve classification problems. Experimental results on the TIMIT corpus reveal that, on speech recognition tasks, DNNs with MSAFs perform better than the conventional DNNs, getting a relative improvement of 5.60% on phoneme error rates. Further experiments also reveal that mean-normalised SGD facilitates the training processes of DNNs with MSAFs, especially when being with large training sets. The models can also be directly trained without pretraining when the training set is sufficiently large, which results in a considerable relative improvement of 5.82% on word error rates. PMID:26448739
Continuous neural network with windowed Hebbian learning.
Fotouhi, M; Heidari, M; Sharifitabar, M
2015-06-01
We introduce an extension of the classical neural field equation where the dynamics of the synaptic kernel satisfies the standard Hebbian type of learning (synaptic plasticity). Here, a continuous network in which changes in the weight kernel occurs in a specified time window is considered. A novelty of this model is that it admits synaptic weight decrease as well as the usual weight increase resulting from correlated activity. The resulting equation leads to a delay-type rate model for which the existence and stability of solutions such as the rest state, bumps, and traveling fronts are investigated. Some relations between the length of the time window and the bump width is derived. In addition, the effect of the delay parameter on the stability of solutions is shown. Also numerical simulations for solutions and their stability are presented. PMID:25677526
Stationary and integrated autoregressive neural network processes.
Trapletti, A; Leisch, F; Hornik, K
2000-10-01
We consider autoregressive neural network (AR-NN) processes driven by additive noise and demonstrate that the characteristic roots of the shortcuts-the standard conditions from linear time-series analysis-determine the stochastic behavior of the overall AR-NN process. If all the characteristic roots are outside the unit circle, then the process is ergodic and stationary. If at least one characteristic root lies inside the unit circle, then the process is transient. AR-NN processes with characteristic roots lying on the unit circle exhibit either ergodic, random walk, or transient behavior. We also analyze the class of integrated AR-NN (ARI-NN) processes and show that a standardized ARI-NN process "converges" to a Wiener process. Finally, least-squares estimation (training) of the stationary models and testing for nonstationarity is discussed. The estimators are shown to be consistent, and expressions on the limiting distributions are given. PMID:11032041
Microturbine control based on fuzzy neural network
NASA Astrophysics Data System (ADS)
Yan, Shijie; Bian, Chunyuan; Wang, Zhiqiang
2006-11-01
As microturbine generator (MTG) is a clean, efficient, low cost and reliable energy supply system. From outside characteristics of MTG, it is multi-variable, time-varying and coupling system, so it is difficult to be identified on-line and conventional control law adopted before cannot achieve desirable result. A novel fuzzy-neural networks (FNN) control algorithm was proposed in combining with the conventional PID control. In the paper, IF-THEN rules for tuning were applied by a first-order Sugeno fuzzy model with seven fuzzy rules and the membership function was given as the continuous GAUSSIAN function. Some sample data were utilized to train FNN. Through adjusting shape of membership function and weight continually, objective of auto-tuning fuzzy-rules can be achieved. The FNN algorithm had been applied to "100kW Microturbine control and power converter system". The results of simulation and experiment are shown that the algorithm can work very well.
Delayed switching applied to memristor neural networks
NASA Astrophysics Data System (ADS)
Wang, Frank Z.; Helian, Na; Wu, Sining; Yang, Xiao; Guo, Yike; Lim, Guan; Rashid, Md Mamunur
2012-04-01
Magnetic flux and electric charge are linked in a memristor. We reported recently that a memristor has a peculiar effect in which the switching takes place with a time delay because a memristor possesses a certain inertia. This effect was named the "delayed switching effect." In this work, we elaborate on the importance of delayed switching in a brain-like computer using memristor neural networks. The effect is used to control the switching of a memristor synapse between two neurons that fire together (the Hebbian rule). A theoretical formula is found, and the design is verified by a simulation. We have also built an experimental setup consisting of electronic memristive synapses and electronic neurons.
Associated neural network independent component analysis structure
NASA Astrophysics Data System (ADS)
Kim, Keehoon; Kostrzweski, Andrew
2006-05-01
Detection, classification, and localization of potential security breaches in extremely high-noise environments are important for perimeter protection and threat detection both for homeland security and for military force protection. Physical Optics Corporation has developed a threat detection system to separate acoustic signatures from unknown, mixed sources embedded in extremely high-noise environments where signal-to-noise ratios (SNRs) are very low. Associated neural network structures based on independent component analysis are designed to detect/separate new acoustic sources and to provide reliability information. The structures are tested through computer simulations for each critical component, including a spontaneous detection algorithm for potential threat detection without a predefined knowledge base, a fast target separation algorithm, and nonparametric methodology for quantified confidence measure. The results show that the method discussed can separate hidden acoustic sources of SNR in 5 dB noisy environments with an accuracy of 80%.
The Neural Network In Coordinate Transformation
NASA Astrophysics Data System (ADS)
Urusan, Ahmet Yucel
2011-12-01
In international literature, Coordinate operations is divided into two categories. They are coordinate conversion and coordinate transformation. Coordinates converted from coordinate system A to coordinate system B in the same datum (mean origine, scale and axis directions are same) by coordinate conversion. There are two different datum in coordinate transformation. The basis of each datum to a different coordinate reference system. In Coordinate transformation, coordinates are transformed from coordinate reference system A to coordinate referance system B. Geodetic studies based on physical measurements. Coordinate transformation needs identical points which were measured in each coordinate reference system (A and B). However it is difficult (and need a big reserved budget) to measure in some places like as top of mountain, boundry of countries and seaside. In this study, this sample problem solution was researched. The method of learning which is one of the neural network methods, was used for solution of this problem.
Neural network-based sensor signal accelerator.
Vogt, M. C.
2000-10-16
A strategy has been developed to computationally accelerate the response time of a generic electronic sensor. The strategy can be deployed as an algorithm in a control system or as a physical interface (on an embedded microcontroller) between a slower responding external sensor and a higher-speed control system. Optional code implementations are available to adjust algorithm performance when computational capability is limited. In one option, the actual sensor signal can be sampled at the slower rate with adaptive linear neural networks predicting the sensor's future output and interpolating intermediate synthetic output values. In another option, a synchronized collection of predictors sequentially controls the corresponding synthetic output voltage. Error is adaptively corrected in both options. The core strategy has been demonstrated with automotive oxygen sensor data. A prototype interface device is under construction. The response speed increase afforded by this strategy could greatly offset the cost of developing a replacement sensor with a faster physical response time.
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. PMID:26718948
Ge Detector Data Classification with Neural Networks
NASA Astrophysics Data System (ADS)
Wilson, Carly; Martin, Ryan; Majorana Collaboration
2014-09-01
The Majorana Demonstrator experiment is searching for neutrinoless double beta-decay using p-type point contact PPC germanium detectors at the Sanford Underground Research Facility, in South Dakota. Pulse shape discrimination can be used in PPC detectors to distinguish signal-like events from backgrounds. This research program explored the possibility of building a self-organizing map that takes data collected from germanium detectors and classifies the events as either signal or background. Self organizing maps are a type of neural network that are self-learning and less susceptible to being biased from imperfect training data. We acknowledge support from the Office of Nuclear Physics in the DOE Office of Science, the Particle and Nuclear Astrophysics Program of the National Science Foundation and the Russian Foundation for Basic Research.
Demonstrations of Neural Network Computations Involving Students
May, Christopher J.
2010-01-01
David Marr famously proposed three levels of analysis (implementational, algorithmic, and computational) for understanding information processing systems such as the brain. While two of these levels are commonly taught in neuroscience courses (the implementational level through neurophysiology and the computational level through systems/cognitive neuroscience), the algorithmic level is typically neglected. This leaves an explanatory gap in students’ understanding of how, for example, the flow of sodium ions enables cognition. Neural networks bridge these two levels by demonstrating how collections of interacting neuron-like units can give rise to more overtly cognitive phenomena. The demonstrations in this paper are intended to facilitate instructors’ introduction and exploration of how neurons “process information.” PMID:23493501
Neural network training as a dissipative process.
Gori, Marco; Maggini, Marco; Rossi, Alessandro
2016-09-01
This paper analyzes the practical issues and reports some results on a theory in which learning is modeled as a continuous temporal process driven by laws describing the interactions of intelligent agents with their own environment. The classic regularization framework is paired with the idea of temporal manifolds by introducing the principle of least cognitive action, which is inspired by the related principle of mechanics. The introduction of the counterparts of the kinetic and potential energy leads to an interpretation of learning as a dissipative process. As an example, we apply the theory to supervised learning in neural networks and show that the corresponding Euler-Lagrange differential equations can be connected to the classic gradient descent algorithm on the supervised pairs. We give preliminary experiments to confirm the soundness of the theory. PMID:27389569
Mesh deformation based on artificial neural networks
NASA Astrophysics Data System (ADS)
Stadler, Domen; Kosel, Franc; Čelič, Damjan; Lipej, Andrej
2011-09-01
In the article a new mesh deformation algorithm based on artificial neural networks is introduced. This method is a point-to-point method, meaning that it does not use connectivity information for calculation of the mesh deformation. Two already known point-to-point methods, based on interpolation techniques, are also presented. In contrast to the two known interpolation methods, the new method does not require a summation over all boundary nodes for one displacement calculation. The consequence of this fact is a shorter computational time of mesh deformation, which is proven by different deformation tests. The quality of the deformed meshes with all three deformation methods was also compared. Finally, the generated and the deformed three-dimensional meshes were used in the computational fluid dynamics numerical analysis of a Francis water turbine. A comparison of the analysis results was made to prove the applicability of the new method in every day computation.
Delayed switching applied to memristor neural networks
Wang, Frank Z.; Yang Xiao; Lim Guan; Helian Na; Wu Sining; Guo Yike; Rashid, Md Mamunur
2012-04-01
Magnetic flux and electric charge are linked in a memristor. We reported recently that a memristor has a peculiar effect in which the switching takes place with a time delay because a memristor possesses a certain inertia. This effect was named the ''delayed switching effect.'' In this work, we elaborate on the importance of delayed switching in a brain-like computer using memristor neural networks. The effect is used to control the switching of a memristor synapse between two neurons that fire together (the Hebbian rule). A theoretical formula is found, and the design is verified by a simulation. We have also built an experimental setup consisting of electronic memristive synapses and electronic neurons.
Neural networks in support of manned space
NASA Technical Reports Server (NTRS)
Werbos, Paul J.
1989-01-01
Many lobbyists in Washington have argued that artificial intelligence (AI) is an alternative to manned space activity. In actuality, this is the opposite of the truth, especially as regards artificial neural networks (ANNs), that form of AI which has the greatest hope of mimicking human abilities in learning, ability to interface with sensors and actuators, flexibility and balanced judgement. ANNs and their relation to expert systems (the more traditional form of AI), and the limitations of both technologies are briefly reviewed. A Few highlights of recent work on ANNs, including an NSF-sponsored workshop on ANNs for control applications are given. Current thinking on ANNs for use in certain key areas (the National Aerospace Plane, teleoperation, the control of large structures, fault diagnostics, and docking) which may be crucial to the long term future of man in space is discussed.
Bacterial colony counting by Convolutional Neural Networks.
Ferrari, Alessandro; Lombardi, Stefano; Signoroni, Alberto
2015-08-01
Counting bacterial colonies on microbiological culture plates is a time-consuming, error-prone, nevertheless fundamental task in microbiology. Computer vision based approaches can increase the efficiency and the reliability of the process, but accurate counting is challenging, due to the high degree of variability of agglomerated colonies. In this paper, we propose a solution which adopts Convolutional Neural Networks (CNN) for counting the number of colonies contained in confluent agglomerates, that scored an overall accuracy of the 92.8% on a large challenging dataset. The proposed CNN-based technique for estimating the cardinality of colony aggregates outperforms traditional image processing approaches, becoming a promising approach to many related applications. PMID:26738016
Financial Time Series Prediction Using Spiking Neural Networks
Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam
2014-01-01
In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two “traditional”, rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments. PMID:25170618
Financial time series prediction using spiking neural networks.
Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam
2014-01-01
In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two "traditional", rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments. PMID:25170618
Neural networks and psychiatry: candidate applications in clinical decision making.
Florio, T; Einfeld, S; Levy, F
1994-12-01
Neural networks comprise a fundamentally new type of computer system inspired by the functioning of neurons in the brain. Such networks are good at solving problems that involve pattern recognition and categorisation. An important difference between a neural network and a traditional computer system is that in developing an application, a neural network is not programmed; instead, it is trained to solve a particular type of problem. This ability to learn to solve a problem makes neural networks adaptable to solving a wide variety of problems, some of which have proved intractable using a traditional computing approach. Neural networks are particularly suited to tasks involving the categorisation of patterns of information, such as is required in diagnosis and clinical decision making. In the last three years reports of applications involving neural networks have begun to appear in the medical literature, and these are described in this paper. However, a comprehensive search of the literature has shown that there have not as yet been reports of any applications in psychiatry. This paper discusses the nature of clinical decision making, outlines the sorts of problems in psychiatry which neural networks applications might be developed to address, and gives examples of candidate applications in clinical decision making. PMID:7794209
Modeling Aircraft Wing Loads from Flight Data Using Neural Networks
NASA Technical Reports Server (NTRS)
Allen, Michael J.; Dibley, Ryan P.
2003-01-01
Neural networks were used to model wing bending-moment loads, torsion loads, and control surface hinge-moments of the Active Aeroelastic Wing (AAW) aircraft. Accurate loads models are required for the development of control laws designed to increase roll performance through wing twist while not exceeding load limits. Inputs to the model include aircraft rates, accelerations, and control surface positions. Neural networks were chosen to model aircraft loads because they can account for uncharacterized nonlinear effects while retaining the capability to generalize. The accuracy of the neural network models was improved by first developing linear loads models to use as starting points for network training. Neural networks were then trained with flight data for rolls, loaded reversals, wind-up-turns, and individual control surface doublets for load excitation. Generalization was improved by using gain weighting and early stopping. Results are presented for neural network loads models of four wing loads and four control surface hinge moments at Mach 0.90 and an altitude of 15,000 ft. An average model prediction error reduction of 18.6 percent was calculated for the neural network models when compared to the linear models. This paper documents the input data conditioning, input parameter selection, structure, training, and validation of the neural network models.
Hidden Markov models and neural networks for fault detection in dynamic systems
NASA Technical Reports Server (NTRS)
Smyth, Padhraic
1994-01-01
Neural networks plus hidden Markov models (HMM) can provide excellent detection and false alarm rate performance in fault detection applications, as shown in this viewgraph presentation. Modified models allow for novelty detection. Key contributions of neural network models are: (1) excellent nonparametric discrimination capability; (2) a good estimator of posterior state probabilities, even in high dimensions, and thus can be embedded within overall probabilistic model (HMM); and (3) simple to implement compared to other nonparametric models. Neural network/HMM monitoring model is currently being integrated with the new Deep Space Network (DSN) antenna controller software and will be on-line monitoring a new DSN 34-m antenna (DSS-24) by July, 1994.
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.
Forecasting Zakat collection using artificial neural network
NASA Astrophysics Data System (ADS)
Sy Ahmad Ubaidillah, Sh. Hafizah; Sallehuddin, Roselina
2013-04-01
'Zakat', "that which purifies" or "alms", is the giving of a fixed portion of one's wealth to charity, generally to the poor and needy. It is one of the five pillars of Islam, and must be paid by all practicing Muslims who have the financial means (nisab). 'Nisab' is the minimum level to determine whether there is a 'zakat' to be paid on the assets. Today, in most Muslim countries, 'zakat' is collected through a decentralized and voluntary system. Under this voluntary system, 'zakat' committees are established, which are tasked with the collection and distribution of 'zakat' funds. 'Zakat' promotes a more equitable redistribution of wealth, and fosters a sense of solidarity amongst members of the 'Ummah'. The Malaysian government has established a 'zakat' center at every state to facilitate the management of 'zakat'. The center has to have a good 'zakat' management system to effectively execute its functions especially in the collection and distribution of 'zakat'. Therefore, a good forecasting model is needed. The purpose of this study is to develop a forecasting model for Pusat Zakat Pahang (PZP) to predict the total amount of collection from 'zakat' of assets more precisely. In this study, two different Artificial Neural Network (ANN) models using two different learning algorithms are developed; Back Propagation (BP) and Levenberg-Marquardt (LM). Both models are developed and compared in terms of their accuracy performance. The best model is determined based on the lowest mean square error and the highest correlations values. Based on the results obtained from the study, BP neural network is recommended as the forecasting model to forecast the collection from 'zakat' of assets for PZP.
Analysis of torsional oscillations using an artificial neural network
Hsu, Y.Y.; Jeng, L,H. )
1992-12-01
In this paper, a novel approach using an artificial neural network (ANN) is proposed for the analysis of torsional oscillations in a power system. In the developed artificial neural network, those system variables such as generator loadings and capacitor compensation ratio which have major impacts on the damping characteristics of torsional oscillatio modes are employed as the inputs. The outputs of the neural net provide the desired eigenvalues for torsional modes. Once the connection weights of the neural network have been learned using a set of training data derived off-line, the neural network can be applied to torsional analysis in real-time situations. To demonstrate the effectiveness of the proposed neural net, torsional analysis is performed on the IEEE First Benchmark Model. It is concluded from the test results that accurate assessment of the torsional mode eigenvalues can be achieved by the neural network in a very efficient manner. Thereofore, the proposed neural network approach can serve as a valuable tool to system operators in conducting SSR analysis in operational planning.
Neural network based speech synthesizer: A preliminary report
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Mcintire, Gary
1987-01-01
A neural net based speech synthesis project is discussed. The novelty is that the reproduced speech was extracted from actual voice recordings. In essence, the neural network learns the timing, pitch fluctuations, connectivity between individual sounds, and speaking habits unique to that individual person. The parallel distributed processing network used for this project is the generalized backward propagation network which has been modified to also learn sequences of actions or states given in a particular plan.
The Neural Basis for Learning of Simple Motor Skills.
ERIC Educational Resources Information Center
Lisberger, Stephen G.
1988-01-01
Discusses the vestibulo-ocular reflex (VOR) which is used to investigate the neural basis for motor learning in monkeys. Suggests organizing principles that may apply in forms of motor learning as a result of similarities among VOR and other motor systems. (Author/RT)
Design of neural networks for classification of remotely sensed imagery
NASA Technical Reports Server (NTRS)
Chettri, Samir R.; Cromp, Robert F.; Birmingham, Mark
1992-01-01
Classification accuracies of a backpropagation neural network are discussed and compared with a maximum likelihood classifier (MLC) with multivariate normal class models. We have found that, because of its nonparametric nature, the neural network outperforms the MLC in this area. In addition, we discuss techniques for constructing optimal neural nets on parallel hardware like the MasPar MP-1 currently at GSFC. Other important discussions are centered around training and classification times of the two methods, and sensitivity to the training data. Finally, we discuss future work in the area of classification and neural nets.
NASA Astrophysics Data System (ADS)
Timofeew, Sergey; Eliseev, Vladimir; Tcherkassov, Oleg; Birukow, Valentin; Orbachevskyi, Leonid; Shamsutdinov, Uriy
1998-04-01
Some problems of creation of medical expert systems and the ways of their overcoming using artificial neural networks are discussed. The instrumental system for projecting neural network algorithms `Neural Architector', developed by the authors, is described. It allows to perform effective modeling of artificial neural networks and to analyze their work. The example of the application of the `Neural Architector' system in composing an expert system for diagnostics of pulmonological diseases is shown.
Semantic segmentation based on neural network and Bayesian network
NASA Astrophysics Data System (ADS)
Ge, Wenying; Liu, Guoying
2013-10-01
It is rather difficult for low-level visual features to describe the need for specific applications of image understanding, which results in the inconsistency between vision information and application need. In this paper, a new model is proposed to reduce this gap by combining low-level visual features with semantic features. It uses the output of neural network as the semantic feature, which is accompanied with the priori label features to describe the image after making normalization. And then, the proposed method employs Potts to model the distribution of label priori, and utilizes the Bayesian network to classify images. Several experiments on both synthetic and real images have verified that this method can get more accurate segmentation.
The Neural Correlates of Emotional Prosody Comprehension: Disentangling Simple from Complex Emotion
Alba-Ferrara, Lucy; Hausmann, Markus; Mitchell, Rachel L.; Weis, Susanne
2011-01-01
Background Emotional prosody comprehension (EPC), the ability to interpret another person's feelings by listening to their tone of voice, is crucial for effective social communication. Previous studies assessing the neural correlates of EPC have found inconsistent results, particularly regarding the involvement of the medial prefrontal cortex (mPFC). It remained unclear whether the involvement of the mPFC is linked to an increased demand in socio-cognitive components of EPC such as mental state attribution and if basic perceptual processing of EPC can be performed without the contribution of this region. Methods fMRI was used to delineate neural activity during the perception of prosodic stimuli conveying simple and complex emotion. Emotional trials in general, as compared to neutral ones, activated a network comprising temporal and lateral frontal brain regions, while complex emotion trials specifically showed an additional involvement of the mPFC, premotor cortex, frontal operculum and left insula. Conclusion These results indicate that the mPFC and premotor areas might be associated, but are not crucial to EPC. However, the mPFC supports socio-cognitive skills necessary to interpret complex emotion such as inferring mental states. Additionally, the premotor cortex involvement may reflect the participation of the mirror neuron system for prosody processing particularly of complex emotion. PMID:22174872
Learning evasive maneuvers using evolutionary algorithms and neural networks
NASA Astrophysics Data System (ADS)
Kang, Moung Hung
In this research, evolutionary algorithms and recurrent neural networks are combined to evolve control knowledge to help pilots avoid being struck by a missile, based on a two-dimensional air combat simulation model. The recurrent neural network is used for representing the pilot's control knowledge and evolutionary algorithms (i.e., Genetic Algorithms, Evolution Strategies, and Evolutionary Programming) are used for optimizing the weights and/or topology of the recurrent neural network. The simulation model of the two-dimensional evasive maneuver problem evolved is used for evaluating the performance of the recurrent neural network. Five typical air combat conditions were selected to evaluate the performance of the recurrent neural networks evolved by the evolutionary algorithms. Analysis of Variance (ANOVA) tests and response graphs were used to analyze the results. Overall, there was little difference in the performance of the three evolutionary algorithms used to evolve the control knowledge. However, the number of generations of each algorithm required to obtain the best performance was significantly different. ES converges the fastest, followed by EP and then by GA. The recurrent neural networks evolved by the evolutionary algorithms provided better performance than the traditional recommendations for evasive maneuvers, maximum gravitational turn, for each air combat condition. Furthermore, the recommended actions of the recurrent neural networks are reasonable and can be used for pilot training.
An artificial neural network for wavelet steganalysis
NASA Astrophysics Data System (ADS)
Davidson, Jennifer; Bergman, Clifford; Bartlett, Eric
2005-08-01
Hiding messages in image data, called steganography, is used for both legal and illicit purposes. The detection of hidden messages in image data stored on websites and computers, called steganalysis, is of prime importance to cyber forensics personnel. Automating the detection of hidden messages is a requirement, since the shear amount of image data stored on computers or websites makes it impossible for a person to investigate each image separately. This paper describes research on a prototype software system that automatically classifies an image as having hidden information or not, using a sophisticated artificial neural network (ANN) system. An ANN software package, the ISU ACL NetWorks Toolkit, is trained on a selection of image features that distinguish between stego and nonstego images. The novelty of this ANN is that it is a blind classifier that gives more accurate results than previous systems. It can detect messages hidden using a variety of different types of embedding algorithms. A Graphical User Interface (GUI) combines the ANN, feature selection, and embedding algorithms into a prototype software package that is not currently available to the cyber forensics community.
DEM interpolation based on artificial neural networks
NASA Astrophysics Data System (ADS)
Jiao, Limin; Liu, Yaolin
2005-10-01
This paper proposed a systemic resolution scheme of Digital Elevation model (DEM) interpolation based on Artificial Neural Networks (ANNs). In this paper, we employ BP network to fit terrain surface, and then detect and eliminate the samples with gross errors. This paper uses Self-organizing Feature Map (SOFM) to cluster elevation samples. The study area is divided into many more homogenous tiles after clustering. BP model is employed to interpolate DEM in each cluster. Because error samples are eliminated and clusters are built, interpolation result is better. The case study indicates that ANN interpolation scheme is feasible. It also shows that ANN can get a more accurate result by comparing ANN with polynomial and spline interpolation. ANN interpolation doesn't need to determine the interpolation function beforehand, so manmade influence is lessened. The ANN interpolation is more automatic and intelligent. At the end of the paper, we propose the idea of constructing ANN surface model. This model can be used in multi-scale DEM visualization, and DEM generalization, etc.
Design of an adaptive neural network based power system stabilizer.
Liu, Wenxin; Venayagamoorthy, Ganesh K; Wunsch, Donald C
2003-01-01
Power system stabilizers (PSS) are used to generate supplementary control signals for the excitation system in order to damp the low frequency power system oscillations. To overcome the drawbacks of conventional PSS (CPSS), numerous techniques have been proposed in the literature. Based on the analysis of existing techniques, this paper presents an indirect adaptive neural network based power system stabilizer (IDNC) design. The proposed IDNC consists of a neuro-controller, which is used to generate a supplementary control signal to the excitation system, and a neuro-identifier, which is used to model the dynamics of the power system and to adapt the neuro-controller parameters. The proposed method has the features of a simple structure, adaptivity and fast response. The proposed IDNC is evaluated on a single machine infinite bus power system under different operating conditions and disturbances to demonstrate its effectiveness and robustness. PMID:12850048
a Simple Neuron Network Based on Hebb's Rule
NASA Astrophysics Data System (ADS)
Zhang, Gui-Qing; Yu, Zi; Yang, Qiu-Ying; Chen, Tian-Lun
A weighted mechanism in neural networks is studied. This paper focuses on the neuron's behaviors in an area of brain. Our model could regenerate the power-law behaviors and finite size effects of neural avalanche. The probability density functions (PDFs) for the neural avalanche size differing at different times (lattice size) have fat tails with a q-Gaussian shape and the same parameter value of q in the thermodynamical limit. Above two kinds of behaviors show that our neural model can well present self-organized critical behavior. The robustness of PDFs shows the stability of self-organized criticality. Meanwhile, the avalanche scaling relation of the waiting time has been found.
Higher-order neural network software for distortion invariant object recognition
NASA Technical Reports Server (NTRS)
Reid, Max B.; Spirkovska, Lilly
1991-01-01
The state-of-the-art in pattern recognition for such applications as automatic target recognition and industrial robotic vision relies on digital image processing. We present a higher-order neural network model and software which performs the complete feature extraction-pattern classification paradigm required for automatic pattern recognition. Using a third-order neural network, we demonstrate complete, 100 percent accurate invariance to distortions of scale, position, and in-plate rotation. In a higher-order neural network, feature extraction is built into the network, and does not have to be learned. Only the relatively simple classification step must be learned. This is key to achieving very rapid training. The training set is much smaller than with standard neural network software because the higher-order network only has to be shown one view of each object to be learned, not every possible view. The software and graphical user interface run on any Sun workstation. Results of the use of the neural software in autonomous robotic vision systems are presented. Such a system could have extensive application in robotic manufacturing.
On-line lower-order modeling via neural networks.
Ho, H F; Rad, A B; Wong, Y K; Lo, W L
2003-10-01
This paper presents a novel method to determine the parameters of a first-order plus dead-time model using neural networks. The outputs of the neural networks are the gain, dominant time constant, and apparent time delay. By combining this algorithm with a conventional PI or PID controller, we also present an adaptive controller which requires very little a priori knowledge about the plant under control. The simplicity of the scheme for real-time control provides a new approach for implementing neural network applications for a variety of on-line industrial control problems. Simulation and experimental results demonstrate the feasibility and adaptive property of the proposed scheme. PMID:14582882
Pseudogradient Training For A Class Of Neural Networks
NASA Technical Reports Server (NTRS)
Zeng, Zheng; Goodman, Rodney M.; Smyth, Padhraic J.
1995-01-01
Developmental second-order recurrent neural networks of special type modified to enhance stability in face of inputs beyond range of inputs on which trained. Second-order recurrent neural networks contain product feedback units and can be trained, by use of example inputs and outputs, to act as finite-state automatons. Particular second-order recurrent neural networks in question learn grammars in sense they are trained to generate binary responses to input training sequences of ones and zeros, each sequence being marked "legal" or "illegal" according to grammar to be learned.
Autonomous Navigation Apparatus With Neural Network for a Mobile Vehicle
NASA Technical Reports Server (NTRS)
Quraishi, Naveed (Inventor)
1996-01-01
An autonomous navigation system for a mobile vehicle arranged to move within an environment includes a plurality of sensors arranged on the vehicle and at least one neural network including an input layer coupled to the sensors, a hidden layer coupled to the input layer, and an output layer coupled to the hidden layer. The neural network produces output signals representing respective positions of the vehicle, such as the X coordinate, the Y coordinate, and the angular orientation of the vehicle. A plurality of patch locations within the environment are used to train the neural networks to produce the correct outputs in response to the distances sensed.
Predicting cloud-to-ground lightning with neural networks
NASA Technical Reports Server (NTRS)
Barnes, Arnold A., Jr.; Frankel, Donald; Draper, James Stark
1991-01-01
A neural network is being trained to predict lightning at Cape Canaveral for periods up to two hours in advance. Inputs consist of ground based field mill data, meteorological tower data, lightning location data, and radiosonde data. High values of the field mill data and rapid changes in the field mill data, offset in time, provide the forecasts or desired output values used to train the neural network through backpropagation. Examples of input data are shown and an example of data compression using a hidden layer in the neural network is discussed.
Beneficial role of noise in artificial neural networks
Monterola, Christopher; Saloma, Caesar; Zapotocky, Martin
2008-06-18
We demonstrate enhancement of neural networks efficacy to recognize frequency encoded signals and/or to categorize spatial patterns of neural activity as a result of noise addition. For temporal information recovery, noise directly added to the receiving neurons allow instantaneous improvement of signal-to-noise ratio [Monterola and Saloma, Phys. Rev. Lett. 2002]. For spatial patterns however, recurrence is necessary to extend and homogenize the operating range of a feed-forward neural network [Monterola and Zapotocky, Phys. Rev. E 2005]. Finally, using the size of the basin of attraction of the networks learned patterns (dynamical fixed points), a procedure for estimating the optimal noise is demonstrated.
Implementations of learning control systems using neural networks
NASA Technical Reports Server (NTRS)
Sartori, Michael A.; Antsaklis, Panos J.
1992-01-01
The systematic storage in neural networks of prior information to be used in the design of various control subsystems is investigated. Assuming that the prior information is available in a certain form (namely, input/output data points and specifications between the data points), a particular neural network and a corresponding parameter design method are introduced. The proposed neural network addresses the issue of effectively using prior information in the areas of dynamical system (plant and controller) modeling, fault detection and identification, information extraction, and control law scheduling.
Robust neural network with applications to credit portfolio data analysis
Feng, Yijia; Li, Runze; Sudjianto, Agus; Zhang, Yiyun
2011-01-01
In this article, we study nonparametric conditional quantile estimation via neural network structure. We proposed an estimation method that combines quantile regression and neural network (robust neural network, RNN). It provides good smoothing performance in the presence of outliers and can be used to construct prediction bands. A Majorization-Minimization (MM) algorithm was developed for optimization. Monte Carlo simulation study is conducted to assess the performance of RNN. Comparison with other nonparametric regression methods (e.g., local linear regression and regression splines) in real data application demonstrate the advantage of the newly proposed procedure. PMID:21687821
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.
Genetic Algorithm Based Neural Networks for Nonlinear Optimization
1994-09-28
This software develops a novel approach to nonlinear optimization using genetic algorithm based neural networks. To our best knowledge, this approach represents the first attempt at applying both neural network and genetic algorithm techniques to solve a nonlinear optimization problem. The approach constructs a neural network structure and an appropriately shaped energy surface whose minima correspond to optimal solutions of the problem. A genetic algorithm is employed to perform a parallel and powerful search ofmore » the energy surface.« less
Failure behavior identification for a space antenna via neural networks
NASA Technical Reports Server (NTRS)
Sartori, Michael A.; Antsaklis, Panos J.
1992-01-01
By using neural networks, a method for the failure behavior identification of a space antenna model is investigated. The proposed method uses three stages. If a fault is suspected by the first stage of fault detection, a diagnostic test is performed on the antenna. The diagnostic test results are used by the second and third stages to identify which fault occurred and to diagnose the extent of the fault, respectively. The first stage uses a multilayer perceptron, the second stage uses a multilayer perceptron and neural networks trained with the quadratic optimization algorithm, a novel training procedure, and the third stage uses backpropagation trained neural networks.
Neural network based expert system for compressor stall monitoring
NASA Technical Reports Server (NTRS)
Lo, Ching F.; Shi, G. Z.
1991-01-01
This research is designed to apply a new information processing technology, artificial neural networks, to monitoring compressor stall. The outputs of neural networks support the dynamic knowledge data base of an expert system. This is the open-loop mode to avoid compressor stall. The integration of a control system with neural networks is the closed-loop mode in stall avoidance. The feasibility of the concept has been demonstrated for the compressor of 16-foot transonic/supersonic propulsion wind tunnels. The construction of a prototpye expert system has been initiated.
Styles Of Programming In Neural Networks And Expert Systems
NASA Astrophysics Data System (ADS)
Duda, Richard O.
1989-03-01
Neural networks and expert systems provide different ways to reduce the programming effort required to build complex systems. Adaptive neural networks are programmed merely by training them with examples. Rule-based expert system are developed incrementally merely by adding rules. Although neural networks seem best suited for low-level sensory processing and expert systems seem best suited for high-level symbolic processing, strikingly similar issues arise when these approaches are used in large-scale applications. Illustrative examples of such applications are presented and discussed.
Biological neural networks as model systems for designing future parallel processing computers
NASA Technical Reports Server (NTRS)
Ross, Muriel D.
1991-01-01
One of the more interesting debates of the present day centers on whether human intelligence can be simulated by computer. The author works under the premise that neurons individually are not smart at all. Rather, they are physical units which are impinged upon continuously by other matter that influences the direction of voltage shifts across the units membranes. It is only the action of a great many neurons, billions in the case of the human nervous system, that intelligent behavior emerges. What is required to understand even the simplest neural system is painstaking analysis, bit by bit, of the architecture and the physiological functioning of its various parts. The biological neural network studied, the vestibular utricular and saccular maculas of the inner ear, are among the most simple of the mammalian neural networks to understand and model. While there is still a long way to go to understand even this most simple neural network in sufficient detail for extrapolation to computers and robots, a start was made. Moreover, the insights obtained and the technologies developed help advance the understanding of the more complex neural networks that underlie human intelligence.
Rule extraction from minimal neural networks for credit card screening.
Setiono, Rudy; Baesens, Bart; Mues, Christophe
2011-08-01
While feedforward neural networks have been widely accepted as effective tools for solving classification problems, the issue of finding the best network architecture remains unresolved, particularly so in real-world problem settings. We address this issue in the context of credit card screening, where it is important to not only find a neural network with good predictive performance but also one that facilitates a clear explanation of how it produces its predictions. We show that minimal neural networks with as few as one hidden unit provide good predictive accuracy, while having the added advantage of making it easier to generate concise and comprehensible classification rules for the user. To further reduce model size, a novel approach is suggested in which network connections from the input units to this hidden unit are removed by a very straightaway pruning procedure. In terms of predictive accuracy, both the minimized neural networks and the rule sets generated from them are shown to compare favorably with other neural network based classifiers. The rules generated from the minimized neural networks are concise and thus easier to validate in a real-life setting. PMID:21809474
Devices and circuits for nanoelectronic implementation of artificial neural networks
NASA Astrophysics Data System (ADS)
Turel, Ozgur
Biological neural networks perform complicated information processing tasks at speeds better than conventional computers based on conventional algorithms. This has inspired researchers to look into the way these networks function, and propose artificial networks that mimic their behavior. Unfortunately, most artificial neural networks, either software or hardware, do not provide either the speed or the complexity of a human brain. Nanoelectronics, with high density and low power dissipation that it provides, may be used in developing more efficient artificial neural networks. This work consists of two major contributions in this direction. First is the proposal of the CMOL concept, hybrid CMOS-molecular hardware [1-8]. CMOL may circumvent most of the problems in posed by molecular devices, such as low yield, vet provide high active device density, ˜1012/cm 2. The second contribution is CrossNets, artificial neural networks that are based on CMOL. We showed that CrossNets, with their fault tolerance, exceptional speed (˜ 4 to 6 orders of magnitude faster than biological neural networks) can perform any task any artificial neural network can perform. Moreover, there is a hope that if their integration scale is increased to that of human cerebral cortex (˜ 1010 neurons and ˜ 1014 synapses), they may be capable of performing more advanced tasks.
Neural network models for a resource allocation problem.
Walczak, S
1998-01-01
University admissions and business personnel offices use a limited number of resources to process an ever-increasing quantity of student and employment applications. Application systems are further constrained to identify and acquire, in a limited time period, those candidates who are most likely to accept an offer of enrolment or employment. Neural networks are a new methodology to this particular domain. Various neural network architectures and learning algorithms are analyzed comparatively to determine the applicability of supervised learning neural networks to the domain problem of personnel resource allocation and to identify optimal learning strategies in this domain. This paper focuses on multilayer perceptron backpropagation, radial basis function, counterpropagation, general regression, fuzzy ARTMAP, and linear vector quantization neural networks. Each neural network predicts the probability of enrolment and nonenrolment for individual student applicants. Backpropagation networks produced the best overall performance. Network performance results are measured by the reduction in counsellors student case load and corresponding increases in student enrolment. The backpropagation neural networks achieve a 56% reduction in counsellor case load. PMID:18255946
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.
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.
Noise-enhanced convolutional neural networks.
Audhkhasi, Kartik; Osoba, Osonde; Kosko, Bart
2016-06-01
Injecting carefully chosen noise can speed convergence in the backpropagation training of a convolutional neural network (CNN). The Noisy CNN algorithm speeds training on average because the backpropagation algorithm is a special case of the generalized expectation-maximization (EM) algorithm and because such carefully chosen noise always speeds up the EM algorithm on average. The CNN framework gives a practical way to learn and recognize images because backpropagation scales with training data. It has only linear time complexity in the number of training samples. The Noisy CNN algorithm finds a special separating hyperplane in the network's noise space. The hyperplane arises from the likelihood-based positivity condition that noise-boosts the EM algorithm. The hyperplane cuts through a uniform-noise hypercube or Gaussian ball in the noise space depending on the type of noise used. Noise chosen from above the hyperplane speeds training on average. Noise chosen from below slows it on average. The algorithm can inject noise anywhere in the multilayered network. Adding noise to the output neurons reduced the average per-iteration training-set cross entropy by 39% on a standard MNIST image test set of handwritten digits. It also reduced the average per-iteration training-set classification error by 47%. Adding noise to the hidden layers can also reduce these performance measures. The noise benefit is most pronounced for smaller data sets because the largest EM hill-climbing gains tend to occur in the first few iterations. This noise effect can assist random sampling from large data sets because it allows a smaller random sample to give the same or better performance than a noiseless sample gives. PMID:26700535
NASA Astrophysics Data System (ADS)
Shoaib, Muhammad; Shamseldin, Asaad Y.; Melville, Bruce W.; Khan, Mudasser Muneer
2016-04-01
In order to predict runoff accurately from a rainfall event, the multilayer perceptron type of neural network models are commonly used in hydrology. Furthermore, the wavelet coupled multilayer perceptron neural network (MLPNN) models has also been found superior relative to the simple neural network models which are not coupled with wavelet. However, the MLPNN models are considered as static and memory less networks and lack the ability to examine the temporal dimension of data. Recurrent neural network models, on the other hand, have the ability to learn from the preceding conditions of the system and hence considered as dynamic models. This study for the first time explores the potential of wavelet coupled time lagged recurrent neural network (TLRNN) models for runoff prediction using rainfall data. The Discrete Wavelet Transformation (DWT) is employed in this study to decompose the input rainfall data using six of the most commonly used wavelet functions. The performance of the simple and the wavelet coupled static MLPNN models is compared with their counterpart dynamic TLRNN models. The study found that the dynamic wavelet coupled TLRNN models can be considered as alternative to the static wavelet MLPNN models. The study also investigated the effect of memory depth on the performance of static and dynamic neural network models. The memory depth refers to how much past information (lagged data) is required as it is not known a priori. The db8 wavelet function is found to yield the best results with the static MLPNN models and with the TLRNN models having small memory depths. The performance of the wavelet coupled TLRNN models with large memory depths is found insensitive to the selection of the wavelet function as all wavelet functions have similar performance.
An adaptive holographic implementation of a neural network
NASA Technical Reports Server (NTRS)
Downie, John D.; Hine, Butler P., III; Reid, Max B.
1990-01-01
A holographic implementation for neural networks is proposed and demonstrated as an alternative to the optical matrix-vector multiplier architecture. In comparison, the holographic architecture makes more efficient use of the system space-bandwidth product for certain types of neural networks. The principal network component is a thermoplastic hologram, used to provide both interconnection weights and beam direction. Given the updatable nature of this type of hologram, adaptivity or network learning is possible in the optical system. Two networks with fixed weights are experimentally implemented and verified, and for one of these examples the advantage of the holographic implementation with respect to the matrix-vector processor is demonstrated.
Combining neural network models for automated diagnostic systems.
Ubeyli, Elif Derya
2006-12-01
This paper illustrates the use of combined neural network (CNN) models to guide model selection for diagnosis of internal carotid arterial (ICA) disorders. The ICA Doppler signals were decomposed into time-frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The first level networks were implemented for the diagnosis of ICA disorders using the statistical features as inputs. To improve diagnostic accuracy, the second level network was trained using the outputs of the first level networks as input data. The CNN models achieved accuracy rates which were higher than that of the stand-alone neural network models. PMID:17233161
Time series prediction using a rational fraction neural networks
Lee, K.; Lee, Y.C.; Barnes, C.; Aldrich, C.H.; Kindel, J.
1988-01-01
An efficient neural network based on a rational fraction representation has been trained to perform time series prediction. The network is a generalization of the Volterra-Wiener network while still retaining the computational efficiency of the latter. Because of the second order convergent nature of the learning algorithm, the rational net is computationally far more efficient than multilayer networks. The rational fractional representation is, however, more restrictive than the multilayer networks.
Neural Network Based Intelligent Sootblowing System
Mark Rhode
2005-04-01
, particulate matter is also a by-product of coal combustion. Modern day utility boilers are usually fitted with electrostatic precipitators to aid in the collection of particulate matter. Although extremely efficient, these devices are sensitive to rapid changes in inlet mass concentration as well as total mass loading. Traditionally, utility boilers are equipped with devices known as sootblowers, which use, steam, water or air to dislodge and clean the surfaces within the boiler and are operated based upon established rule or operator's judgment. Poor sootblowing regimes can influence particulate mass loading to the electrostatic precipitators. The project applied a neural network intelligent sootblowing system in conjunction with state-of-the-art controls and instruments to optimize the operation of a utility boiler and systematically control boiler slagging/fouling. This optimization process targeted reduction of NOx of 30%, improved efficiency of 2% and a reduction in opacity of 5%. The neural network system proved to be a non-invasive system which can readily be adapted to virtually any utility boiler. Specific conclusions from this neural network application are listed below. These conclusions should be used in conjunction with the specific details provided in the technical discussions of this report to develop a thorough understanding of the process.
Mandal, Sudip; Khan, Abhinandan; Saha, Goutam; Pal, Rajat K.
2016-01-01
The accurate prediction of genetic networks using computational tools is one of the greatest challenges in the postgenomic era. Recurrent Neural Network is one of the most popular but simple approaches to model the network dynamics from time-series microarray data. To date, it has been successfully applied to computationally derive small-scale artificial and real-world genetic networks with high accuracy. However, they underperformed for large-scale genetic networks. Here, a new methodology has been proposed where a hybrid Cuckoo Search-Flower Pollination Algorithm has been implemented with Recurrent Neural Network. Cuckoo Search is used to search the best combination of regulators. Moreover, Flower Pollination Algorithm is applied to optimize the model parameters of the Recurrent Neural Network formalism. Initially, the proposed method is tested on a benchmark large-scale artificial network for both noiseless and noisy data. The results obtained show that the proposed methodology is capable of increasing the inference of correct regulations and decreasing false regulations to a high degree. Secondly, the proposed methodology has been validated against the real-world dataset of the DNA SOS repair network of Escherichia coli. However, the proposed method sacrifices computational time complexity in both cases due to the hybrid optimization process. PMID:26989410
Mandal, Sudip; Khan, Abhinandan; Saha, Goutam; Pal, Rajat K
2016-01-01
The accurate prediction of genetic networks using computational tools is one of the greatest challenges in the postgenomic era. Recurrent Neural Network is one of the most popular but simple approaches to model the network dynamics from time-series microarray data. To date, it has been successfully applied to computationally derive small-scale artificial and real-world genetic networks with high accuracy. However, they underperformed for large-scale genetic networks. Here, a new methodology has been proposed where a hybrid Cuckoo Search-Flower Pollination Algorithm has been implemented with Recurrent Neural Network. Cuckoo Search is used to search the best combination of regulators. Moreover, Flower Pollination Algorithm is applied to optimize the model parameters of the Recurrent Neural Network formalism. Initially, the proposed method is tested on a benchmark large-scale artificial network for both noiseless and noisy data. The results obtained show that the proposed methodology is capable of increasing the inference of correct regulations and decreasing false regulations to a high degree. Secondly, the proposed methodology has been validated against the real-world dataset of the DNA SOS repair network of Escherichia coli. However, the proposed method sacrifices computational time complexity in both cases due to the hybrid optimization process. PMID:26989410
RM-SORN: a reward-modulated self-organizing recurrent neural network.
Aswolinskiy, Witali; Pipa, Gordon
2015-01-01
Neural plasticity plays an important role in learning and memory. Reward-modulation of plasticity offers an explanation for the ability of the brain to adapt its neural activity to achieve a rewarded goal. Here, we define a neural network model that learns through the interaction of Intrinsic Plasticity (IP) and reward-modulated Spike-Timing-Dependent Plasticity (STDP). IP enables the network to explore possible output sequences and STDP, modulated by reward, reinforces the creation of the rewarded output sequences. The model is tested on tasks for prediction, recall, non-linear computation, pattern recognition, and sequence generation. It achieves performance comparable to networks trained with supervised learning, while using simple, biologically motivated plasticity rules, and rewarding strategies. The results confirm the importance of investigating the interaction of several plasticity rules in the context of reward-modulated learning and whether reward-modulated self-organization can explain the amazing capabilities of the brain. PMID:25852533
RM-SORN: a reward-modulated self-organizing recurrent neural network
Aswolinskiy, Witali; Pipa, Gordon
2015-01-01
Neural plasticity plays an important role in learning and memory. Reward-modulation of plasticity offers an explanation for the ability of the brain to adapt its neural activity to achieve a rewarded goal. Here, we define a neural network model that learns through the interaction of Intrinsic Plasticity (IP) and reward-modulated Spike-Timing-Dependent Plasticity (STDP). IP enables the network to explore possible output sequences and STDP, modulated by reward, reinforces the creation of the rewarded output sequences. The model is tested on tasks for prediction, recall, non-linear computation, pattern recognition, and sequence generation. It achieves performance comparable to networks trained with supervised learning, while using simple, biologically motivated plasticity rules, and rewarding strategies. The results confirm the importance of investigating the interaction of several plasticity rules in the context of reward-modulated learning and whether reward-modulated self-organization can explain the amazing capabilities of the brain. PMID:25852533
Neural Networks Used to Compare Designed and Measured Time-Average Patterns
NASA Technical Reports Server (NTRS)
Decker, Arthur J.; Fite, E. Brian; Mehmed, Oral; Thorp, Scott A.
1999-01-01
Electronic time-average holograms are convenient for comparing the measured vibration modes of fan blades with those calculated by finite-element models. At the NASA Lewis Research Center, neural networks recently were trained to perform what had been a simple visual comparison of the predictions of the design models with the measurements. Finite-element models were used to train neural networks to recognize damage and strain information encoded in subtle changes in the time-average patterns of cantilevers. But the design-grade finite element models were unable to train the neural networks to detect damage in complex blade shapes. The design-model-generated patterns simply did not agree well enough with the measured patterns. Instead, hybrid-training records, with measured time-average patterns as the input and model-generated strain information as the output, were used to effect successful training.