WorldWideScience

Sample records for neural network architectures

  1. An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures

    Energy Technology Data Exchange (ETDEWEB)

    Schuman, Catherine D [ORNL; Plank, James [University of Tennessee (UT); Disney, Adam [University of Tennessee (UT); Reynolds, John [University of Tennessee (UT)

    2016-01-01

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

  2. Optical Neural Network Classifier Architectures

    National Research Council Canada - National Science Library

    Getbehead, Mark

    1998-01-01

    We present an adaptive opto-electronic neural network hardware architecture capable of exploiting parallel optics to realize real-time processing and classification of high-dimensional data for Air...

  3. Emulation of Neural Networks on a Nanoscale Architecture

    International Nuclear Information System (INIS)

    Eshaghian-Wilner, Mary M; Friesz, Aaron; Khitun, Alex; Navab, Shiva; Parker, Alice C; Wang, Kang L; Zhou, Chongwu

    2007-01-01

    In this paper, we propose using a nanoscale spin-wave-based architecture for implementing neural networks. We show that this architecture can efficiently realize highly interconnected neural network models such as the Hopfield model. In our proposed architecture, no point-to-point interconnection is required, so unlike standard VLSI design, no fan-in/fan-out constraint limits the interconnectivity. Using spin-waves, each neuron could broadcast to all other neurons simultaneously and similarly a neuron could concurrently receive and process multiple data. Therefore in this architecture, the total weighted sum to each neuron can be computed by the sum of the values from all the incoming waves to that neuron. In addition, using the superposition property of waves, this computation can be done in O(1) time, and neurons can update their states quite rapidly

  4. Stable architectures for deep neural networks

    Science.gov (United States)

    Haber, Eldad; Ruthotto, Lars

    2018-01-01

    Deep neural networks have become invaluable tools for supervised machine learning, e.g. classification of text or images. While often offering superior results over traditional techniques and successfully expressing complicated patterns in data, deep architectures are known to be challenging to design and train such that they generalize well to new data. Critical issues with deep architectures are numerical instabilities in derivative-based learning algorithms commonly called exploding or vanishing gradients. In this paper, we propose new forward propagation techniques inspired by systems of ordinary differential equations (ODE) that overcome this challenge and lead to well-posed learning problems for arbitrarily deep networks. The backbone of our approach is our interpretation of deep learning as a parameter estimation problem of nonlinear dynamical systems. Given this formulation, we analyze stability and well-posedness of deep learning and use this new understanding to develop new network architectures. We relate the exploding and vanishing gradient phenomenon to the stability of the discrete ODE and present several strategies for stabilizing deep learning for very deep networks. While our new architectures restrict the solution space, several numerical experiments show their competitiveness with state-of-the-art networks.

  5. Modular Neural Tile Architecture for Compact Embedded Hardware Spiking Neural Network

    NARCIS (Netherlands)

    Pande, Sandeep; Morgan, Fearghal; Cawley, Seamus; Bruintjes, Tom; Smit, Gerardus Johannes Maria; McGinley, Brian; Carrillo, Snaider; Harkin, Jim; McDaid, Liam

    2013-01-01

    Biologically-inspired packet switched network on chip (NoC) based hardware spiking neural network (SNN) architectures have been proposed as an embedded computing platform for classification, estimation and control applications. Storage of large synaptic connectivity (SNN topology) information in

  6. Optimum Neural Network Architecture for Precipitation Prediction of Myanmar

    OpenAIRE

    Khaing Win Mar; Thinn Thu Naing

    2008-01-01

    Nowadays, precipitation prediction is required for proper planning and management of water resources. Prediction with neural network models has received increasing interest in various research and application domains. However, it is difficult to determine the best neural network architecture for prediction since it is not immediately obvious how many input or hidden nodes are used in the model. In this paper, neural network model is used as a forecasting tool. The major aim is to evaluate a s...

  7. A comparison of neural network architectures for the prediction of MRR in EDM

    Science.gov (United States)

    Jena, A. R.; Das, Raja

    2017-11-01

    The aim of the research work is to predict the material removal rate of a work-piece in electrical discharge machining (EDM). Here, an effort has been made to predict the material removal rate through back-propagation neural network (BPN) and radial basis function neural network (RBFN) for a work-piece of AISI D2 steel. The input parameters for the architecture are discharge-current (Ip), pulse-duration (Ton), and duty-cycle (τ) taken for consideration to obtained the output for material removal rate of the work-piece. In the architecture, it has been observed that radial basis function neural network is comparatively faster than back-propagation neural network but logically back-propagation neural network results more real value. Therefore BPN may consider as a better process in this architecture for consistent prediction to save time and money for conducting experiments.

  8. Comparison of different artificial neural network architectures in modeling of Chlorella sp. flocculation.

    Science.gov (United States)

    Zenooz, Alireza Moosavi; Ashtiani, Farzin Zokaee; Ranjbar, Reza; Nikbakht, Fatemeh; Bolouri, Oberon

    2017-07-03

    Biodiesel production from microalgae feedstock should be performed after growth and harvesting of the cells, and the most feasible method for harvesting and dewatering of microalgae is flocculation. Flocculation modeling can be used for evaluation and prediction of its performance under different affective parameters. However, the modeling of flocculation in microalgae is not simple and has not performed yet, under all experimental conditions, mostly due to different behaviors of microalgae cells during the process under different flocculation conditions. In the current study, the modeling of microalgae flocculation is studied with different neural network architectures. Microalgae species, Chlorella sp., was flocculated with ferric chloride under different conditions and then the experimental data modeled using artificial neural network. Neural network architectures of multilayer perceptron (MLP) and radial basis function architectures, failed to predict the targets successfully, though, modeling was effective with ensemble architecture of MLP networks. Comparison between the performances of the ensemble and each individual network explains the ability of the ensemble architecture in microalgae flocculation modeling.

  9. Quantum perceptron over a field and neural network architecture selection in a quantum computer.

    Science.gov (United States)

    da Silva, Adenilton José; Ludermir, Teresa Bernarda; de Oliveira, Wilson Rosa

    2016-04-01

    In this work, we propose a quantum neural network named quantum perceptron over a field (QPF). Quantum computers are not yet a reality and the models and algorithms proposed in this work cannot be simulated in actual (or classical) computers. QPF is a direct generalization of a classical perceptron and solves some drawbacks found in previous models of quantum perceptrons. We also present a learning algorithm named Superposition based Architecture Learning algorithm (SAL) that optimizes the neural network weights and architectures. SAL searches for the best architecture in a finite set of neural network architectures with linear time over the number of patterns in the training set. SAL is the first learning algorithm to determine neural network architectures in polynomial time. This speedup is obtained by the use of quantum parallelism and a non-linear quantum operator. Copyright © 2016 Elsevier Ltd. All rights reserved.

  10. SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS

    Directory of Open Access Journals (Sweden)

    Marijana Zekić-Sušac

    2012-07-01

    Full Text Available After production and operations, finance and investments are one of the mostfrequent areas of neural network applications in business. The lack of standardizedparadigms that can determine the efficiency of certain NN architectures in a particularproblem domain is still present. The selection of NN architecture needs to take intoconsideration the type of the problem, the nature of the data in the model, as well as somestrategies based on result comparison. The paper describes previous research in that areaand suggests a forward strategy for selecting best NN algorithm and structure. Since thestrategy includes both parameter-based and variable-based testings, it can be used forselecting NN architectures as well as for extracting models. The backpropagation, radialbasis,modular, LVQ and probabilistic neural network algorithms were used on twoindependent sets: stock market and credit scoring data. The results show that neuralnetworks give better accuracy comparing to multiple regression and logistic regressionmodels. Since it is model-independant, the strategy can be used by researchers andprofessionals in other areas of application.

  11. Convolutional neural network architectures for predicting DNA–protein binding

    Science.gov (United States)

    Zeng, Haoyang; Edwards, Matthew D.; Liu, Ge; Gifford, David K.

    2016-01-01

    Motivation: Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. Results: We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. Availability and Implementation: All the models analyzed are available at http://cnn.csail.mit.edu. Contact: gifford@mit.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307608

  12. An efficient optical architecture for sparsely connected neural networks

    Science.gov (United States)

    Hine, Butler P., III; Downie, John D.; Reid, Max B.

    1990-01-01

    An architecture for general-purpose optical neural network processor is presented in which the interconnections and weights are formed by directing coherent beams holographically, thereby making use of the space-bandwidth products of the recording medium for sparsely interconnected networks more efficiently that the commonly used vector-matrix multiplier, since all of the hologram area is in use. An investigation is made of the use of computer-generated holograms recorded on such updatable media as thermoplastic materials, in order to define the interconnections and weights of a neural network processor; attention is given to limits on interconnection densities, diffraction efficiencies, and weighing accuracies possible with such an updatable thin film holographic device.

  13. Convolutional neural networks for event-related potential detection: impact of the architecture.

    Science.gov (United States)

    Cecotti, H

    2017-07-01

    The detection of brain responses at the single-trial level in the electroencephalogram (EEG) such as event-related potentials (ERPs) is a difficult problem that requires different processing steps to extract relevant discriminant features. While most of the signal and classification techniques for the detection of brain responses are based on linear algebra, different pattern recognition techniques such as convolutional neural network (CNN), as a type of deep learning technique, have shown some interests as they are able to process the signal after limited pre-processing. In this study, we propose to investigate the performance of CNNs in relation of their architecture and in relation to how they are evaluated: a single system for each subject, or a system for all the subjects. More particularly, we want to address the change of performance that can be observed between specifying a neural network to a subject, or by considering a neural network for a group of subjects, taking advantage of a larger number of trials from different subjects. The results support the conclusion that a convolutional neural network trained on different subjects can lead to an AUC above 0.9 by using an appropriate architecture using spatial filtering and shift invariant layers.

  14. Optimal artificial neural network architecture selection for performance prediction of compact heat exchanger with the EBaLM-OTR technique

    Energy Technology Data Exchange (ETDEWEB)

    Wijayasekara, Dumidu, E-mail: wija2589@vandals.uidaho.edu [Department of Computer Science, University of Idaho, 1776 Science Center Drive, Idaho Falls, ID 83402 (United States); Manic, Milos [Department of Computer Science, University of Idaho, 1776 Science Center Drive, Idaho Falls, ID 83402 (United States); Sabharwall, Piyush [Idaho National Laboratory, Idaho Falls, ID (United States); Utgikar, Vivek [Department of Chemical Engineering, University of Idaho, Idaho Falls, ID 83402 (United States)

    2011-07-15

    Highlights: > Performance prediction of PCHE using artificial neural networks. > Evaluating artificial neural network performance for PCHE modeling. > Selection of over-training resilient artificial neural networks. > Artificial neural network architecture selection for modeling problems with small data sets. - Abstract: Artificial Neural Networks (ANN) have been used in the past to predict the performance of printed circuit heat exchangers (PCHE) with satisfactory accuracy. Typically published literature has focused on optimizing ANN using a training dataset to train the network and a testing dataset to evaluate it. Although this may produce outputs that agree with experimental results, there is a risk of over-training or over-learning the network rather than generalizing it, which should be the ultimate goal. An over-trained network is able to produce good results with the training dataset but fails when new datasets with subtle changes are introduced. In this paper we present EBaLM-OTR (error back propagation and Levenberg-Marquardt algorithms for over training resilience) technique, which is based on a previously discussed method of selecting neural network architecture that uses a separate validation set to evaluate different network architectures based on mean square error (MSE), and standard deviation of MSE. The method uses k-fold cross validation. Therefore in order to select the optimal architecture for the problem, the dataset is divided into three parts which are used to train, validate and test each network architecture. Then each architecture is evaluated according to their generalization capability and capability to conform to original data. The method proved to be a comprehensive tool in identifying the weaknesses and advantages of different network architectures. The method also highlighted the fact that the architecture with the lowest training error is not always the most generalized and therefore not the optimal. Using the method the testing

  15. Optimal artificial neural network architecture selection for performance prediction of compact heat exchanger with the EBaLM-OTR technique

    International Nuclear Information System (INIS)

    Wijayasekara, Dumidu; Manic, Milos; Sabharwall, Piyush; Utgikar, Vivek

    2011-01-01

    Highlights: → Performance prediction of PCHE using artificial neural networks. → Evaluating artificial neural network performance for PCHE modeling. → Selection of over-training resilient artificial neural networks. → Artificial neural network architecture selection for modeling problems with small data sets. - Abstract: Artificial Neural Networks (ANN) have been used in the past to predict the performance of printed circuit heat exchangers (PCHE) with satisfactory accuracy. Typically published literature has focused on optimizing ANN using a training dataset to train the network and a testing dataset to evaluate it. Although this may produce outputs that agree with experimental results, there is a risk of over-training or over-learning the network rather than generalizing it, which should be the ultimate goal. An over-trained network is able to produce good results with the training dataset but fails when new datasets with subtle changes are introduced. In this paper we present EBaLM-OTR (error back propagation and Levenberg-Marquardt algorithms for over training resilience) technique, which is based on a previously discussed method of selecting neural network architecture that uses a separate validation set to evaluate different network architectures based on mean square error (MSE), and standard deviation of MSE. The method uses k-fold cross validation. Therefore in order to select the optimal architecture for the problem, the dataset is divided into three parts which are used to train, validate and test each network architecture. Then each architecture is evaluated according to their generalization capability and capability to conform to original data. The method proved to be a comprehensive tool in identifying the weaknesses and advantages of different network architectures. The method also highlighted the fact that the architecture with the lowest training error is not always the most generalized and therefore not the optimal. Using the method the

  16. A modular architecture for transparent computation in recurrent neural networks.

    Science.gov (United States)

    Carmantini, Giovanni S; Beim Graben, Peter; Desroches, Mathieu; Rodrigues, Serafim

    2017-01-01

    Computation is classically studied in terms of automata, formal languages and algorithms; yet, the relation between neural dynamics and symbolic representations and operations is still unclear in traditional eliminative connectionism. Therefore, we suggest a unique perspective on this central issue, to which we would like to refer as transparent connectionism, by proposing accounts of how symbolic computation can be implemented in neural substrates. In this study we first introduce a new model of dynamics on a symbolic space, the versatile shift, showing that it supports the real-time simulation of a range of automata. We then show that the Gödelization of versatile shifts defines nonlinear dynamical automata, dynamical systems evolving on a vectorial space. Finally, we present a mapping between nonlinear dynamical automata and recurrent artificial neural networks. The mapping defines an architecture characterized by its granular modularity, where data, symbolic operations and their control are not only distinguishable in activation space, but also spatially localizable in the network itself, while maintaining a distributed encoding of symbolic representations. The resulting networks simulate automata in real-time and are programmed directly, in the absence of network training. To discuss the unique characteristics of the architecture and their consequences, we present two examples: (i) the design of a Central Pattern Generator from a finite-state locomotive controller, and (ii) the creation of a network simulating a system of interactive automata that supports the parsing of garden-path sentences as investigated in psycholinguistics experiments. Copyright © 2016 Elsevier Ltd. All rights reserved.

  17. Framewise phoneme classification with bidirectional LSTM and other neural network architectures.

    Science.gov (United States)

    Graves, Alex; Schmidhuber, Jürgen

    2005-01-01

    In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it.

  18. Learning, memory, and the role of neural network architecture.

    Directory of Open Access Journals (Sweden)

    Ann M Hermundstad

    2011-06-01

    Full Text Available The performance of information processing systems, from artificial neural networks to natural neuronal ensembles, depends heavily on the underlying system architecture. In this study, we compare the performance of parallel and layered network architectures during sequential tasks that require both acquisition and retention of information, thereby identifying tradeoffs between learning and memory processes. During the task of supervised, sequential function approximation, networks produce and adapt representations of external information. Performance is evaluated by statistically analyzing the error in these representations while varying the initial network state, the structure of the external information, and the time given to learn the information. We link performance to complexity in network architecture by characterizing local error landscape curvature. We find that variations in error landscape structure give rise to tradeoffs in performance; these include the ability of the network to maximize accuracy versus minimize inaccuracy and produce specific versus generalizable representations of information. Parallel networks generate smooth error landscapes with deep, narrow minima, enabling them to find highly specific representations given sufficient time. While accurate, however, these representations are difficult to generalize. In contrast, layered networks generate rough error landscapes with a variety of local minima, allowing them to quickly find coarse representations. Although less accurate, these representations are easily adaptable. The presence of measurable performance tradeoffs in both layered and parallel networks has implications for understanding the behavior of a wide variety of natural and artificial learning systems.

  19. Architecture and biological applications of artificial neural networks: a tuberculosis perspective.

    Science.gov (United States)

    Darsey, Jerry A; Griffin, William O; Joginipelli, Sravanthi; Melapu, Venkata Kiran

    2015-01-01

    Advancement of science and technology has prompted researchers to develop new intelligent systems that can solve a variety of problems such as pattern recognition, prediction, and optimization. The ability of the human brain to learn in a fashion that tolerates noise and error has attracted many researchers and provided the starting point for the development of artificial neural networks: the intelligent systems. Intelligent systems can acclimatize to the environment or data and can maximize the chances of success or improve the efficiency of a search. Due to massive parallelism with large numbers of interconnected processers and their ability to learn from the data, neural networks can solve a variety of challenging computational problems. Neural networks have the ability to derive meaning from complicated and imprecise data; they are used in detecting patterns, and trends that are too complex for humans, or other computer systems. Solutions to the toughest problems will not be found through one narrow specialization; therefore we need to combine interdisciplinary approaches to discover the solutions to a variety of problems. Many researchers in different disciplines such as medicine, bioinformatics, molecular biology, and pharmacology have successfully applied artificial neural networks. This chapter helps the reader in understanding the basics of artificial neural networks, their applications, and methodology; it also outlines the network learning process and architecture. We present a brief outline of the application of neural networks to medical diagnosis, drug discovery, gene identification, and protein structure prediction. We conclude with a summary of the results from our study on tuberculosis data using neural networks, in diagnosing active tuberculosis, and predicting chronic vs. infiltrative forms of tuberculosis.

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

    Science.gov (United States)

    Bianchini, Monica; Scarselli, Franco

    2014-08-01

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

  1. Marginally Stable Triangular Recurrent Neural Network Architecture for Time Series Prediction.

    Science.gov (United States)

    Sivakumar, Seshadri; Sivakumar, Shyamala

    2017-09-25

    This paper introduces a discrete-time recurrent neural network architecture using triangular feedback weight matrices that allows a simplified approach to ensuring network and training stability. The triangular structure of the weight matrices is exploited to readily ensure that the eigenvalues of the feedback weight matrix represented by the block diagonal elements lie on the unit circle in the complex z-plane by updating these weights based on the differential of the angular error variable. Such placement of the eigenvalues together with the extended close interaction between state variables facilitated by the nondiagonal triangular elements, enhances the learning ability of the proposed architecture. Simulation results show that the proposed architecture is highly effective in time-series prediction tasks associated with nonlinear and chaotic dynamic systems with underlying oscillatory modes. This modular architecture with dual upper and lower triangular feedback weight matrices mimics fully recurrent network architectures, while maintaining learning stability with a simplified training process. While training, the block-diagonal weights (hence the eigenvalues) of the dual triangular matrices are constrained to the same values during weight updates aimed at minimizing the possibility of overfitting. The dual triangular architecture also exploits the benefit of parsing the input and selectively applying the parsed inputs to the two subnetworks to facilitate enhanced learning performance.

  2. Parallel consensual neural networks.

    Science.gov (United States)

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

    1997-01-01

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

  3. REAL-TIME VIDEO SCALING BASED ON CONVOLUTION NEURAL NETWORK ARCHITECTURE

    Directory of Open Access Journals (Sweden)

    S Safinaz

    2017-08-01

    Full Text Available In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames to high resolution frames. We compare our outcomes with multiple exiting algorithms. Our extensive results of proposed technique RemCNN (Reconstruction error minimization Convolution Neural Network shows that our model outperforms the existing technologies such as bicubic, bilinear, MCResNet and provide better reconstructed motioning images and video frames. The experimental results shows that our average PSNR result is 47.80474 considering upscale-2, 41.70209 for upscale-3 and 36.24503 for upscale-4 for Myanmar dataset which is very high in contrast to other existing techniques. This results proves our proposed model real-time video scaling based on convolution neural network architecture’s high efficiency and better performance.

  4. Neural Architectures for Control

    Science.gov (United States)

    Peterson, James K.

    1991-01-01

    The cerebellar model articulated controller (CMAC) neural architectures are shown to be viable for the purposes of real-time learning and control. Software tools for the exploration of CMAC performance are developed for three hardware platforms, the MacIntosh, the IBM PC, and the SUN workstation. All algorithm development was done using the C programming language. These software tools were then used to implement an adaptive critic neuro-control design that learns in real-time how to back up a trailer truck. The truck backer-upper experiment is a standard performance measure in the neural network literature, but previously the training of the controllers was done off-line. With the CMAC neural architectures, it was possible to train the neuro-controllers on-line in real-time on a MS-DOS PC 386. CMAC neural architectures are also used in conjunction with a hierarchical planning approach to find collision-free paths over 2-D analog valued obstacle fields. The method constructs a coarse resolution version of the original problem and then finds the corresponding coarse optimal path using multipass dynamic programming. CMAC artificial neural architectures are used to estimate the analog transition costs that dynamic programming requires. The CMAC architectures are trained in real-time for each obstacle field presented. The coarse optimal path is then used as a baseline for the construction of a fine scale optimal path through the original obstacle array. These results are a very good indication of the potential power of the neural architectures in control design. In order to reach as wide an audience as possible, we have run a seminar on neuro-control that has met once per week since 20 May 1991. This seminar has thoroughly discussed the CMAC architecture, relevant portions of classical control, back propagation through time, and adaptive critic designs.

  5. REAL-TIME VIDEO SCALING BASED ON CONVOLUTION NEURAL NETWORK ARCHITECTURE

    OpenAIRE

    S Safinaz; A V Ravi Kumar

    2017-01-01

    In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames t...

  6. Neural codes of seeing architectural styles.

    Science.gov (United States)

    Choo, Heeyoung; Nasar, Jack L; Nikrahei, Bardia; Walther, Dirk B

    2017-01-10

    Images of iconic buildings, such as the CN Tower, instantly transport us to specific places, such as Toronto. Despite the substantial impact of architectural design on people's visual experience of built environments, we know little about its neural representation in the human brain. In the present study, we have found patterns of neural activity associated with specific architectural styles in several high-level visual brain regions, but not in primary visual cortex (V1). This finding suggests that the neural correlates of the visual perception of architectural styles stem from style-specific complex visual structure beyond the simple features computed in V1. Surprisingly, the network of brain regions representing architectural styles included the fusiform face area (FFA) in addition to several scene-selective regions. Hierarchical clustering of error patterns further revealed that the FFA participated to a much larger extent in the neural encoding of architectural styles than entry-level scene categories. We conclude that the FFA is involved in fine-grained neural encoding of scenes at a subordinate-level, in our case, architectural styles of buildings. This study for the first time shows how the human visual system encodes visual aspects of architecture, one of the predominant and longest-lasting artefacts of human culture.

  7. The Laplacian spectrum of neural networks

    Science.gov (United States)

    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

  8. Tensor Basis Neural Network v. 1.0 (beta)

    Energy Technology Data Exchange (ETDEWEB)

    2017-03-28

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

  9. Genetic optimization of neural network architecture

    International Nuclear Information System (INIS)

    Harp, S.A.; Samad, T.

    1994-03-01

    Neural networks are now a popular technology for a broad variety of application domains, including the electric utility industry. Yet, as the technology continues to gain increasing acceptance, it is also increasingly apparent that the power that neural networks provide is not an unconditional blessing. Considerable care must be exercised during application development if the full benefit of the technology is to be realized. At present, no fully general theory or methodology for neural network design is available, and application development is a trial-and-error process that is time-consuming and expertise-intensive. Each application demands appropriate selections of the network input space, the network structure, and values of learning algorithm parameters-design choices that are closely coupled in ways that largely remain a mystery. This EPRI-funded exploratory research project was initiated to take the key next step in this research program: the validation of the approach on a realistic problem. We focused on the problem of modeling the thermal performance of the TVA Sequoyah nuclear power plant (units 1 and 2)

  10. Neural Network Ensembles

    DEFF Research Database (Denmark)

    Hansen, Lars Kai; Salamon, Peter

    1990-01-01

    We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar...... networks....

  11. The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding.

    Science.gov (United States)

    Testolin, Alberto; De Filippo De Grazia, Michele; Zorzi, Marco

    2017-01-01

    The recent "deep learning revolution" in artificial neural networks had strong impact and widespread deployment for engineering applications, but the use of deep learning for neurocomputational modeling has been so far limited. In this article we argue that unsupervised deep learning represents an important step forward for improving neurocomputational models of perception and cognition, because it emphasizes the role of generative learning as opposed to discriminative (supervised) learning. As a case study, we present a series of simulations investigating the emergence of neural coding of visual space for sensorimotor transformations. We compare different network architectures commonly used as building blocks for unsupervised deep learning by systematically testing the type of receptive fields and gain modulation developed by the hidden neurons. In particular, we compare Restricted Boltzmann Machines (RBMs), which are stochastic, generative networks with bidirectional connections trained using contrastive divergence, with autoencoders, which are deterministic networks trained using error backpropagation. For both learning architectures we also explore the role of sparse coding, which has been identified as a fundamental principle of neural computation. The unsupervised models are then compared with supervised, feed-forward networks that learn an explicit mapping between different spatial reference frames. Our simulations show that both architectural and learning constraints strongly influenced the emergent coding of visual space in terms of distribution of tuning functions at the level of single neurons. Unsupervised models, and particularly RBMs, were found to more closely adhere to neurophysiological data from single-cell recordings in the primate parietal cortex. These results provide new insights into how basic properties of artificial neural networks might be relevant for modeling neural information processing in biological systems.

  12. Neural networks and orbit control in accelerators

    International Nuclear Information System (INIS)

    Bozoki, E.; Friedman, A.

    1994-01-01

    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

  13. Artificial neural networks a practical course

    CERN Document Server

    da Silva, Ivan Nunes; Andrade Flauzino, Rogerio; Liboni, Luisa Helena Bartocci; dos Reis Alves, Silas Franco

    2017-01-01

    This book provides comprehensive coverage of neural networks, their evolution, their structure, the problems they can solve, and their applications. The first half of the book looks at theoretical investigations on artificial neural networks and addresses the key architectures that are capable of implementation in various application scenarios. The second half is designed specifically for the production of solutions using artificial neural networks to solve practical problems arising from different areas of knowledge. It also describes the various implementation details that were taken into account to achieve the reported results. These aspects contribute to the maturation and improvement of experimental techniques to specify the neural network architecture that is most appropriate for a particular application scope. The book is appropriate for students in graduate and upper undergraduate courses in addition to researchers and professionals.

  14. Classification of behavior using unsupervised temporal neural networks

    International Nuclear Information System (INIS)

    Adair, K.L.

    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

  15. Program Helps Simulate Neural Networks

    Science.gov (United States)

    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.

  16. Architecture and performance of neural networks for efficient A/C control in buildings

    International Nuclear Information System (INIS)

    Mahmoud, Mohamed A.; Ben-Nakhi, Abdullatif E.

    2003-01-01

    The feasibility of using neural networks (NNs) for optimizing air conditioning (AC) setback scheduling in public buildings was investigated. The main focus is on optimizing the network architecture in order to achieve best performance. To save energy, the temperature inside public buildings is allowed to rise after business hours by setting back the thermostat. The objective is to predict the time of the end of thermostat setback (EoS) such that the design temperature inside the building is restored in time for the start of business hours. State of the art building simulation software, ESP-r, was used to generate a database that covered the years 1995-1999. The software was used to calculate the EoS for two office buildings using the climate records in Kuwait. The EoS data for 1995 and 1996 were used for training and testing the NNs. The robustness of the trained NN was tested by applying them to a 'production' data set (1997-1999), which the networks have never 'seen' before. For each of the six different NN architectures evaluated, parametric studies were performed to determine the network parameters that best predict the EoS. External hourly temperature readings were used as network inputs, and the thermostat end of setback (EoS) is the output. The NN predictions were improved by developing a neural control scheme (NC). This scheme is based on using the temperature readings as they become available. For each NN architecture considered, six NNs were designed and trained for this purpose. The performance of the NN analysis was evaluated using a statistical indicator (the coefficient of multiple determination) and by statistical analysis of the error patterns, including ANOVA (analysis of variance). The results show that the NC, when used with a properly designed NN, is a powerful instrument for optimizing AC setback scheduling based only on external temperature records

  17. Seafloor classification using echo- waveforms: A method employing hybrid neural network architecture

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.; Mahale, V.; DeSouza, C.; Das, P.

    , neural network architecture, seafloor classification, self-organizing feature map (SOFM). I. INTRODUCTION S EAFLOOR classification and characterization using re- mote high-frequency acoustic system has been recognized as a useful tool (see [1...] and references therein). The seafloor’s characteristics are extremely complicated due to variations of the many parameters at different scales. The parameters include sediment grain size, relief height at the water–sediment inter- face, and variations within...

  18. Neural networks and applications tutorial

    Science.gov (United States)

    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.

  19. Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture.

    Science.gov (United States)

    Meszlényi, Regina J; Buza, Krisztian; Vidnyánszky, Zoltán

    2017-01-01

    Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network.

  20. Fuzzy neural network theory and application

    CERN Document Server

    Liu, Puyin

    2004-01-01

    This book systematically synthesizes research achievements in the field of fuzzy neural networks in recent years. It also provides a comprehensive presentation of the developments in fuzzy neural networks, with regard to theory as well as their application to system modeling and image restoration. Special emphasis is placed on the fundamental concepts and architecture analysis of fuzzy neural networks. The book is unique in treating all kinds of fuzzy neural networks and their learning algorithms and universal approximations, and employing simulation examples which are carefully designed to he

  1. Optical resonators and neural networks

    Science.gov (United States)

    Anderson, Dana Z.

    1986-08-01

    It may be possible to implement neural network models using continuous field optical architectures. These devices offer the inherent parallelism of propagating waves and an information density in principle dictated by the wavelength of light and the quality of the bulk optical elements. Few components are needed to construct a relatively large equivalent network. Various associative memories based on optical resonators have been demonstrated in the literature, a ring resonator design is discussed in detail here. Information is stored in a holographic medium and recalled through a competitive processes in the gain medium supplying energy to the ring rsonator. The resonator memory is the first realized example of a neural network function implemented with this kind of architecture.

  2. Boolean Factor Analysis by Attractor Neural Network

    Czech Academy of Sciences Publication Activity Database

    Frolov, A. A.; Húsek, Dušan; Muraviev, I. P.; Polyakov, P.Y.

    2007-01-01

    Roč. 18, č. 3 (2007), s. 698-707 ISSN 1045-9227 R&D Projects: GA AV ČR 1ET100300419; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * dimensionality reduction * features clustering * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.769, year: 2007

  3. Rotation Invariance Neural Network

    OpenAIRE

    Li, Shiyuan

    2017-01-01

    Rotation invariance and translation invariance have great values in image recognition tasks. In this paper, we bring a new architecture in convolutional neural network (CNN) named cyclic convolutional layer to achieve rotation invariance in 2-D symbol recognition. We can also get the position and orientation of the 2-D symbol by the network to achieve detection purpose for multiple non-overlap target. Last but not least, this architecture can achieve one-shot learning in some cases using thos...

  4. Memristor-based neural networks

    International Nuclear Information System (INIS)

    Thomas, Andy

    2013-01-01

    The synapse is a crucial element in biological neural networks, but a simple electronic equivalent has been absent. This complicates the development of hardware that imitates biological architectures in the nervous system. Now, the recent progress in the experimental realization of memristive devices has renewed interest in artificial neural networks. The resistance of a memristive system depends on its past states and exactly this functionality can be used to mimic the synaptic connections in a (human) brain. After a short introduction to memristors, we present and explain the relevant mechanisms in a biological neural network, such as long-term potentiation and spike time-dependent plasticity, and determine the minimal requirements for an artificial neural network. We review the implementations of these processes using basic electric circuits and more complex mechanisms that either imitate biological systems or could act as a model system for them. (topical review)

  5. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

    International Nuclear Information System (INIS)

    Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy

    2016-01-01

    There exists significant demand for improved Reynolds-averaged Navier–Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents a method of using deep neural networks to learn a model for the Reynolds stress anisotropy tensor from high-fidelity simulation data. A novel neural network architecture is proposed which uses a multiplicative layer with an invariant tensor basis to embed Galilean invariance into the predicted anisotropy tensor. It is demonstrated that this neural network architecture provides improved prediction accuracy compared with a generic neural network architecture that does not embed this invariance property. Furthermore, the Reynolds stress anisotropy predictions of this invariant neural network are propagated through to the velocity field for two test cases. For both test cases, significant improvement versus baseline RANS linear eddy viscosity and nonlinear eddy viscosity models is demonstrated.

  6. Drift chamber tracking with neural networks

    International Nuclear Information System (INIS)

    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

  7. Neural networks for triggering

    International Nuclear Information System (INIS)

    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

  8. Artificial Neural Networks as an Architectural Design Tool-Generating New Detail Forms Based On the Roman Corinthian Order Capital

    Science.gov (United States)

    Radziszewski, Kacper

    2017-10-01

    The following paper presents the results of the research in the field of the machine learning, investigating the scope of application of the artificial neural networks algorithms as a tool in architectural design. The computational experiment was held using the backward propagation of errors method of training the artificial neural network, which was trained based on the geometry of the details of the Roman Corinthian order capital. During the experiment, as an input training data set, five local geometry parameters combined has given the best results: Theta, Pi, Rho in spherical coordinate system based on the capital volume centroid, followed by Z value of the Cartesian coordinate system and a distance from vertical planes created based on the capital symmetry. Additionally during the experiment, artificial neural network hidden layers optimal count and structure was found, giving results of the error below 0.2% for the mentioned before input parameters. Once successfully trained artificial network, was able to mimic the details composition on any other geometry type given. Despite of calculating the transformed geometry locally and separately for each of the thousands of surface points, system could create visually attractive and diverse, complex patterns. Designed tool, based on the supervised learning method of machine learning, gives possibility of generating new architectural forms- free of the designer’s imagination bounds. Implementing the infinitely broad computational methods of machine learning, or Artificial Intelligence in general, not only could accelerate and simplify the design process, but give an opportunity to explore never seen before, unpredictable forms or everyday architectural practice solutions.

  9. Adaptive competitive learning neural networks

    Directory of Open Access Journals (Sweden)

    Ahmed R. Abas

    2013-11-01

    Full Text Available In this paper, the adaptive competitive learning (ACL neural network algorithm is proposed. This neural network not only groups similar input feature vectors together but also determines the appropriate number of groups of these vectors. This algorithm uses a new proposed criterion referred to as the ACL criterion. This criterion evaluates different clustering structures produced by the ACL neural network for an input data set. Then, it selects the best clustering structure and the corresponding network architecture for this data set. The selected structure is composed of the minimum number of clusters that are compact and balanced in their sizes. The selected network architecture is efficient, in terms of its complexity, as it contains the minimum number of neurons. Synaptic weight vectors of these neurons represent well-separated, compact and balanced clusters in the input data set. The performance of the ACL algorithm is evaluated and compared with the performance of a recently proposed algorithm in the literature in clustering an input data set and determining its number of clusters. Results show that the ACL algorithm is more accurate and robust in both determining the number of clusters and allocating input feature vectors into these clusters than the other algorithm especially with data sets that are sparsely distributed.

  10. A NEURAL NETWORK BASED TRAFFIC-AWARE FORWARDING STRATEGY IN NAMED DATA NETWORKING

    OpenAIRE

    Parisa Bazmi; Manijeh Keshtgary

    2016-01-01

    Named Data Networking (NDN) is a new Internet architecture which has been proposed to eliminate TCP/IP Internet architecture restrictions. This architecture is abstracting away the notion of host and working based on naming datagrams. However, one of the major challenges of NDN is supporting QoS-aware forwarding strategy so as to forward Interest packets intelligently over multiple paths based on the current network condition. In this paper, Neural Network (NN) Based Traffic-aware Forwarding ...

  11. SNAVA-A real-time multi-FPGA multi-model spiking neural network simulation architecture.

    Science.gov (United States)

    Sripad, Athul; Sanchez, Giovanny; Zapata, Mireya; Pirrone, Vito; Dorta, Taho; Cambria, Salvatore; Marti, Albert; Krishnamourthy, Karthikeyan; Madrenas, Jordi

    2018-01-01

    Spiking Neural Networks (SNN) for Versatile Applications (SNAVA) simulation platform is a scalable and programmable parallel architecture that supports real-time, large-scale, multi-model SNN computation. This parallel architecture is implemented in modern Field-Programmable Gate Arrays (FPGAs) devices to provide high performance execution and flexibility to support large-scale SNN models. Flexibility is defined in terms of programmability, which allows easy synapse and neuron implementation. This has been achieved by using a special-purpose Processing Elements (PEs) for computing SNNs, and analyzing and customizing the instruction set according to the processing needs to achieve maximum performance with minimum resources. The parallel architecture is interfaced with customized Graphical User Interfaces (GUIs) to configure the SNN's connectivity, to compile the neuron-synapse model and to monitor SNN's activity. Our contribution intends to provide a tool that allows to prototype SNNs faster than on CPU/GPU architectures but significantly cheaper than fabricating a customized neuromorphic chip. This could be potentially valuable to the computational neuroscience and neuromorphic engineering communities. Copyright © 2017 Elsevier Ltd. All rights reserved.

  12. A mixed-scale dense convolutional neural network for image analysis

    NARCIS (Netherlands)

    D.M. Pelt (Daniël); J.A. Sethian (James)

    2016-01-01

    textabstractDeep convolutional neural networks have been successfully applied to many image-processing problems in recent works. Popular network architectures often add additional operations and connections to the standard architecture to enable training deeper networks. To achieve accurate results

  13. assessment of neural networks performance in modeling rainfall ...

    African Journals Online (AJOL)

    Sholagberu

    neural network architecture for precipitation prediction of Myanmar, World Academy of. Science, Engineering and Technology, 48, pp. 130 – 134. Kumarasiri, A.D. and Sonnadara, D.U.J. (2006). Rainfall forecasting: an artificial neural network approach, Proceedings of the Technical Sessions,. 22, pp. 1-13 Institute of Physics ...

  14. A neural network approach to burst detection.

    Science.gov (United States)

    Mounce, S R; Day, A J; Wood, A S; Khan, A; Widdop, P D; Machell, J

    2002-01-01

    This paper describes how hydraulic and water quality data from a distribution network may be used to provide a more efficient leakage management capability for the water industry. The research presented concerns the application of artificial neural networks to the issue of detection and location of leakage in treated water distribution systems. An architecture for an Artificial Neural Network (ANN) based system is outlined. The neural network uses time series data produced by sensors to directly construct an empirical model for predication and classification of leaks. Results are presented using data from an experimental site in Yorkshire Water's Keighley distribution system.

  15. Prediction based chaos control via a new neural network

    International Nuclear Information System (INIS)

    Shen Liqun; Wang Mao; Liu Wanyu; Sun Guanghui

    2008-01-01

    In this Letter, a new chaos control scheme based on chaos prediction is proposed. To perform chaos prediction, a new neural network architecture for complex nonlinear approximation is proposed. And the difficulty in building and training the neural network is also reduced. Simulation results of Logistic map and Lorenz system show the effectiveness of the proposed chaos control scheme and the proposed neural network

  16. Analysis of surface ozone using a recurrent neural network.

    Science.gov (United States)

    Biancofiore, Fabio; Verdecchia, Marco; Di Carlo, Piero; Tomassetti, Barbara; Aruffo, Eleonora; Busilacchio, Marcella; Bianco, Sebastiano; Di Tommaso, Sinibaldo; Colangeli, Carlo

    2015-05-01

    Hourly concentrations of ozone (O₃) and nitrogen dioxide (NO₂) have been measured for 16 years, from 1998 to 2013, in a seaside town in central Italy. The seasonal trends of O₃ and NO₂ recorded in this period have been studied. Furthermore, we used the data collected during one year (2005), to define the characteristics of a multiple linear regression model and a neural network model. Both models are used to model the hourly O₃ concentration, using, two scenarios: 1) in the first as inputs, only meteorological parameters and 2) in the second adding photochemical parameters at those of the first scenario. In order to evaluate the performance of the model four statistical criteria are used: correlation coefficient, fractional bias, normalized mean squared error and a factor of two. All the criteria show that the neural network gives better results, compared to the regression model, in all the model scenarios. Predictions of O₃ have been carried out by many authors using a feed forward neural architecture. In this paper we show that a recurrent architecture significantly improves the performances of neural predictors. Using only the meteorological parameters as input, the recurrent architecture shows performance better than the multiple linear regression model that uses meteorological and photochemical data as input, making the neural network model with recurrent architecture a more useful tool in areas where only weather measurements are available. Finally, we used the neural network model to forecast the O₃ hourly concentrations 1, 3, 6, 12, 24 and 48 h ahead. The performances of the model in predicting O₃ levels are discussed. Emphasis is given to the possibility of using the neural network model in operational ways in areas where only meteorological data are available, in order to predict O₃ also in sites where it has not been measured yet. Copyright © 2015 Elsevier B.V. All rights reserved.

  17. Anomaly detection in an automated safeguards system using neural networks

    International Nuclear Information System (INIS)

    Whiteson, R.; Howell, J.A.

    1992-01-01

    An automated safeguards system must be able to detect an anomalous event, identify the nature of the event, and recommend a corrective action. Neural networks represent a new way of thinking about basic computational mechanisms for intelligent information processing. In this paper, we discuss the issues involved in applying a neural network model to the first step of this process: anomaly detection in materials accounting systems. We extend our previous model to a 3-tank problem and compare different neural network architectures and algorithms. We evaluate the computational difficulties in training neural networks and explore how certain design principles affect the problems. The issues involved in building a neural network architecture include how the information flows, how the network is trained, how the neurons in a network are connected, how the neurons process information, and how the connections between neurons are modified. Our approach is based on the demonstrated ability of neural networks to model complex, nonlinear, real-time processes. By modeling the normal behavior of the processes, we can predict how a system should be behaving and, therefore, detect when an abnormality occurs

  18. Parallelization of Neural Network Training for NLP with Hogwild!

    Directory of Open Access Journals (Sweden)

    Deyringer Valentin

    2017-10-01

    Full Text Available Neural Networks are prevalent in todays NLP research. Despite their success for different tasks, training time is relatively long. We use Hogwild! to counteract this phenomenon and show that it is a suitable method to speed up training Neural Networks of different architectures and complexity. For POS tagging and translation we report considerable speedups of training, especially for the latter. We show that Hogwild! can be an important tool for training complex NLP architectures.

  19. Neural-Network Object-Recognition Program

    Science.gov (United States)

    Spirkovska, L.; Reid, M. B.

    1993-01-01

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

  20. Performance Evaluation of 14 Neural Network Architectures Used for Predicting Heat Transfer Characteristics of Engine Oils

    Science.gov (United States)

    Al-Ajmi, R. M.; Abou-Ziyan, H. Z.; Mahmoud, M. A.

    2012-01-01

    This paper reports the results of a comprehensive study that aimed at identifying best neural network architecture and parameters to predict subcooled boiling characteristics of engine oils. A total of 57 different neural networks (NNs) that were derived from 14 different NN architectures were evaluated for four different prediction cases. The NNs were trained on experimental datasets performed on five engine oils of different chemical compositions. The performance of each NN was evaluated using a rigorous statistical analysis as well as careful examination of smoothness of predicted boiling curves. One NN, out of the 57 evaluated, correctly predicted the boiling curves for all cases considered either for individual oils or for all oils taken together. It was found that the pattern selection and weight update techniques strongly affect the performance of the NNs. It was also revealed that the use of descriptive statistical analysis such as R2, mean error, standard deviation, and T and slope tests, is a necessary but not sufficient condition for evaluating NN performance. The performance criteria should also include inspection of the smoothness of the predicted curves either visually or by plotting the slopes of these curves.

  1. Information Extraction with Character-level Neural Networks and Free Noisy Supervision

    OpenAIRE

    Meerkamp, Philipp; Zhou, Zhengyi

    2016-01-01

    We present an architecture for information extraction from text that augments an existing parser with a character-level neural network. The network is trained using a measure of consistency of extracted data with existing databases as a form of noisy supervision. Our architecture combines the ability of constraint-based information extraction systems to easily incorporate domain knowledge and constraints with the ability of deep neural networks to leverage large amounts of data to learn compl...

  2. Intelligent neural network diagnostic system

    International Nuclear Information System (INIS)

    Mohamed, A.H.

    2010-01-01

    Recently, artificial neural network (ANN) has made a significant mark in the domain of diagnostic applications. Neural networks are used to implement complex non-linear mappings (functions) using simple elementary units interrelated through connections with adaptive weights. The performance of the ANN is mainly depending on their topology structure and weights. Some systems have been developed using genetic algorithm (GA) to optimize the topology of the ANN. But, they suffer from some limitations. They are : (1) The computation time requires for training the ANN several time reaching for the average weight required, (2) Slowness of GA for optimization process and (3) Fitness noise appeared in the optimization of ANN. This research suggests new issues to overcome these limitations for finding optimal neural network architectures to learn particular problems. This proposed methodology is used to develop a diagnostic neural network system. It has been applied for a 600 MW turbo-generator as a case of real complex systems. The proposed system has proved its significant performance compared to two common methods used in the diagnostic applications.

  3. A Reconfigurable and Biologically Inspired Paradigm for Computation Using Network-On-Chip and Spiking Neural Networks

    Directory of Open Access Journals (Sweden)

    Jim Harkin

    2009-01-01

    Full Text Available FPGA devices have emerged as a popular platform for the rapid prototyping of biological Spiking Neural Networks (SNNs applications, offering the key requirement of reconfigurability. However, FPGAs do not efficiently realise the biologically plausible neuron and synaptic models of SNNs, and current FPGA routing structures cannot accommodate the high levels of interneuron connectivity inherent in complex SNNs. This paper highlights and discusses the current challenges of implementing scalable SNNs on reconfigurable FPGAs. The paper proposes a novel field programmable neural network architecture (EMBRACE, incorporating low-power analogue spiking neurons, interconnected using a Network-on-Chip architecture. Results on the evaluation of the EMBRACE architecture using the XOR benchmark problem are presented, and the performance of the architecture is discussed. The paper also discusses the adaptability of the EMBRACE architecture in supporting fault tolerant computing.

  4. The plasma automata network (PAN) architecture

    International Nuclear Information System (INIS)

    Cameron-Carey, C.M.

    1991-01-01

    Conventional neural networks consist of processing elements which are interconnected according to a specified topology. Typically, the number of processing elements and the interconnection topology are fixed. A neural network's information processing capability lies mainly in the variability of interconnection strengths, which directly influence activation patterns; these patterns represent entities and their interrelationships. Contrast this architecture, with its fixed topology and variable interconnection strengths, against one having dynamic topology and fixed connection strength. This paper reports on this proposed architecture in which there are no connections between processing elements. Instead, the processing elements form a plasma, exchanging information upon collision. A plasma can be populated with several different types of processing elements, each with their won activation function and self-modification mechanism. The activation patterns that are the plasma;s response to stimulation drive natural selection among processing elements which evolve to optimize performance

  5. Artificial Neural Networks for differential diagnosis of breast lesions in MR-Mammography: A systematic approach addressing the influence of network architecture on diagnostic performance using a large clinical database

    International Nuclear Information System (INIS)

    Dietzel, Matthias; Baltzer, Pascal A.T.; Dietzel, Andreas; Zoubi, Ramy; Gröschel, Tobias; Burmeister, Hartmut P.; Bogdan, Martin; Kaiser, Werner A.

    2012-01-01

    Rationale and objectives: Differential diagnosis of lesions in MR-Mammography (MRM) remains a complex task. The aim of this MRM study was to design and to test robustness of Artificial Neural Network architectures to predict malignancy using a large clinical database. Materials and methods: For this IRB-approved investigation standardized protocols and study design were applied (T1w-FLASH; 0.1 mmol/kgBW Gd-DTPA; T2w-TSE; histological verification after MRM). All lesions were evaluated by two experienced (>500 MRM) radiologists in consensus. In every lesion, 18 previously published descriptors were assessed and documented in the database. An Artificial Neural Network (ANN) was developed to process this database (The-MathWorks/Inc., feed-forward-architecture/resilient back-propagation-algorithm). All 18 descriptors were set as input variables, whereas histological results (malignant vs. benign) was defined as classification variable. Initially, the ANN was optimized in terms of “Training Epochs” (TE), “Hidden Layers” (HL), “Learning Rate” (LR) and “Neurons” (N). Robustness of the ANN was addressed by repeated evaluation cycles (n: 9) with receiver operating characteristics (ROC) analysis of the results applying 4-fold Cross Validation. The best network architecture was identified comparing the corresponding Area under the ROC curve (AUC). Results: Histopathology revealed 436 benign and 648 malignant lesions. Enhancing the level of complexity could not increase diagnostic accuracy of the network (P: n.s.). The optimized ANN architecture (TE: 20, HL: 1, N: 5, LR: 1.2) was accurate (mean-AUC 0.888; P: <0.001) and robust (CI: 0.885–0.892; range: 0.880–0.898). Conclusion: The optimized neural network showed robust performance and high diagnostic accuracy for prediction of malignancy on unknown data.

  6. Artificial Neural Networks for differential diagnosis of breast lesions in MR-Mammography: a systematic approach addressing the influence of network architecture on diagnostic performance using a large clinical database.

    Science.gov (United States)

    Dietzel, Matthias; Baltzer, Pascal A T; Dietzel, Andreas; Zoubi, Ramy; Gröschel, Tobias; Burmeister, Hartmut P; Bogdan, Martin; Kaiser, Werner A

    2012-07-01

    Differential diagnosis of lesions in MR-Mammography (MRM) remains a complex task. The aim of this MRM study was to design and to test robustness of Artificial Neural Network architectures to predict malignancy using a large clinical database. For this IRB-approved investigation standardized protocols and study design were applied (T1w-FLASH; 0.1 mmol/kgBW Gd-DTPA; T2w-TSE; histological verification after MRM). All lesions were evaluated by two experienced (>500 MRM) radiologists in consensus. In every lesion, 18 previously published descriptors were assessed and documented in the database. An Artificial Neural Network (ANN) was developed to process this database (The-MathWorks/Inc., feed-forward-architecture/resilient back-propagation-algorithm). All 18 descriptors were set as input variables, whereas histological results (malignant vs. benign) was defined as classification variable. Initially, the ANN was optimized in terms of "Training Epochs" (TE), "Hidden Layers" (HL), "Learning Rate" (LR) and "Neurons" (N). Robustness of the ANN was addressed by repeated evaluation cycles (n: 9) with receiver operating characteristics (ROC) analysis of the results applying 4-fold Cross Validation. The best network architecture was identified comparing the corresponding Area under the ROC curve (AUC). Histopathology revealed 436 benign and 648 malignant lesions. Enhancing the level of complexity could not increase diagnostic accuracy of the network (P: n.s.). The optimized ANN architecture (TE: 20, HL: 1, N: 5, LR: 1.2) was accurate (mean-AUC 0.888; P: <0.001) and robust (CI: 0.885-0.892; range: 0.880-0.898). The optimized neural network showed robust performance and high diagnostic accuracy for prediction of malignancy on unknown data. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

  7. Artificial neural network intelligent method for prediction

    Science.gov (United States)

    Trifonov, Roumen; Yoshinov, Radoslav; Pavlova, Galya; Tsochev, Georgi

    2017-09-01

    Accounting and financial classification and prediction problems are high challenge and researchers use different methods to solve them. Methods and instruments for short time prediction of financial operations using artificial neural network are considered. The methods, used for prediction of financial data as well as the developed forecasting system with neural network are described in the paper. The architecture of a neural network used four different technical indicators, which are based on the raw data and the current day of the week is presented. The network developed is used for forecasting movement of stock prices one day ahead and consists of an input layer, one hidden layer and an output layer. The training method is algorithm with back propagation of the error. The main advantage of the developed system is self-determination of the optimal topology of neural network, due to which it becomes flexible and more precise The proposed system with neural network is universal and can be applied to various financial instruments using only basic technical indicators as input data.

  8. Neural network decoder for quantum error correcting codes

    Science.gov (United States)

    Krastanov, Stefan; Jiang, Liang

    Artificial neural networks form a family of extremely powerful - albeit still poorly understood - tools used in anything from image and sound recognition through text generation to, in our case, decoding. We present a straightforward Recurrent Neural Network architecture capable of deducing the correcting procedure for a quantum error-correcting code from a set of repeated stabilizer measurements. We discuss the fault-tolerance of our scheme and the cost of training the neural network for a system of a realistic size. Such decoders are especially interesting when applied to codes, like the quantum LDPC codes, that lack known efficient decoding schemes.

  9. ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation

    OpenAIRE

    Visin, Francesco; Ciccone, Marco; Romero, Adriana; Kastner, Kyle; Cho, Kyunghyun; Bengio, Yoshua; Matteucci, Matteo; Courville, Aaron

    2015-01-01

    We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed architecture, called ReSeg, is based on the recently introduced ReNet model for image classification. We modify and extend it to perform the more challenging task of semantic segmentation. Each ReNet layer is composed of four RNN that sweep the image horizontally ...

  10. Semantic segmentation of bioimages using convolutional neural networks

    CSIR Research Space (South Africa)

    Wiehman, S

    2016-07-01

    Full Text Available Convolutional neural networks have shown great promise in both general image segmentation problems as well as bioimage segmentation. In this paper, the application of different convolutional network architectures is explored on the C. elegans live...

  11. vDNN: Virtualized Deep Neural Networks for Scalable, Memory-Efficient Neural Network Design

    OpenAIRE

    Rhu, Minsoo; Gimelshein, Natalia; Clemons, Jason; Zulfiqar, Arslan; Keckler, Stephen W.

    2016-01-01

    The most widely used machine learning frameworks require users to carefully tune their memory usage so that the deep neural network (DNN) fits into the DRAM capacity of a GPU. This restriction hampers a researcher's flexibility to study different machine learning algorithms, forcing them to either use a less desirable network architecture or parallelize the processing across multiple GPUs. We propose a runtime memory manager that virtualizes the memory usage of DNNs such that both GPU and CPU...

  12. Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition

    Science.gov (United States)

    Mioulet, L.; Bideault, G.; Chatelain, C.; Paquet, T.; Brunessaux, S.

    2015-01-01

    The BLSTM-CTC is a novel recurrent neural network architecture that has outperformed previous state of the art algorithms in tasks such as speech recognition or handwriting recognition. It has the ability to process long term dependencies in temporal signals in order to label unsegmented data. This paper describes different ways of combining features using a BLSTM-CTC architecture. Not only do we explore the low level combination (feature space combination) but we also explore high level combination (decoding combination) and mid-level (internal system representation combination). The results are compared on the RIMES word database. Our results show that the low level combination works best, thanks to the powerful data modeling of the LSTM neurons.

  13. Recurrent Neural Network Based Boolean Factor Analysis and its Application to Word Clustering

    Czech Academy of Sciences Publication Activity Database

    Frolov, A. A.; Húsek, Dušan; Polyakov, P.Y.

    2009-01-01

    Roč. 20, č. 7 (2009), s. 1073-1086 ISSN 1045-9227 R&D Projects: GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.889, year: 2009

  14. Supervised Learning with Complex-valued Neural Networks

    CERN Document Server

    Suresh, Sundaram; Savitha, Ramasamy

    2013-01-01

    Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks.  Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to develop complex-valued neural networks and derive their learning algorithms to represent these signals at every step of the learning process. This monograph comprises a collection of new supervised learning algorithms along with novel architectures for complex-valued neural networks. The concepts of meta-cognition equipped with a self-regulated learning have been known to be the best human learning strategy. In this monograph, the principles of meta-cognition have been introduced for complex-valued neural networks in both the batch and sequential learning modes. For applications where the computati...

  15. A stochastic learning algorithm for layered neural networks

    International Nuclear Information System (INIS)

    Bartlett, E.B.; Uhrig, R.E.

    1992-01-01

    The random optimization method typically uses a Gaussian probability density function (PDF) to generate a random search vector. In this paper the random search technique is applied to the neural network training problem and is modified to dynamically seek out the optimal probability density function (OPDF) from which to select the search vector. The dynamic OPDF search process, combined with an auto-adaptive stratified sampling technique and a dynamic node architecture (DNA) learning scheme, completes the modifications of the basic method. The DNA technique determines the appropriate number of hidden nodes needed for a given training problem. By using DNA, researchers do not have to set the neural network architectures before training is initiated. The approach is applied to networks of generalized, fully interconnected, continuous perceptions. Computer simulation results are given

  16. Ideomotor feedback control in a recurrent neural network.

    Science.gov (United States)

    Galtier, Mathieu

    2015-06-01

    The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and action are simultaneously read and fed back. There are two concurrent learning rules implementing a sort of ideomotor control: (i) perception is learned along the principle that the network should predict reliably its incoming stimuli; (ii) action is learned along the principle that the prediction of the network should match a target time series. The coherent behavior of the neural network in its environment is a consequence of the interaction between the two principles. Numerical simulations show a promising performance of the approach, which can be turned into a local and better "biologically plausible" algorithm.

  17. The benefit of combining a deep neural network architecture with ideal ratio mask estimation in computational speech segregation to improve speech intelligibility

    DEFF Research Database (Denmark)

    Bentsen, Thomas; May, Tobias; Kressner, Abigail Anne

    2018-01-01

    Computational speech segregation attempts to automatically separate speech from noise. This is challenging in conditions with interfering talkers and low signal-to-noise ratios. Recent approaches have adopted deep neural networks and successfully demonstrated speech intelligibility improvements....... A selection of components may be responsible for the success with these state-of-the-art approaches: the system architecture, a time frame concatenation technique and the learning objective. The aim of this study was to explore the roles and the relative contributions of these components by measuring speech......, to a state-of-the-art deep neural network-based architecture. Another improvement of 13.9 percentage points was obtained by changing the learning objective from the ideal binary mask, in which individual time-frequency units are labeled as either speech- or noise-dominated, to the ideal ratio mask, where...

  18. Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning

    NARCIS (Netherlands)

    van der Velde, Frank; van der Velde, Frank; Besold, Tarek R.; Lamb, Luis; Serafini, Luciano; Tabor, Whitney

    2016-01-01

    Simulations are presented and discussed of learning sequential control in a Neural Blackboard Architecture (NBA) for in situ concept-based reasoning. Sequential control is learned in a reservoir network, consisting of columns with neural circuits. This allows the reservoir to control the dynamics of

  19. A TLD dose algorithm using artificial neural networks

    International Nuclear Information System (INIS)

    Moscovitch, M.; Rotunda, J.E.; Tawil, R.A.; Rathbone, B.A.

    1995-01-01

    An artificial neural network was designed and used to develop a dose algorithm for a multi-element thermoluminescence dosimeter (TLD). The neural network architecture is based on the concept of functional links network (FLN). Neural network is an information processing method inspired by the biological nervous system. A dose algorithm based on neural networks is fundamentally different as compared to conventional algorithms, as it has the capability to learn from its own experience. The neural network algorithm is shown the expected dose values (output) associated with given responses of a multi-element dosimeter (input) many times. The algorithm, being trained that way, eventually is capable to produce its own unique solution to similar (but not exactly the same) dose calculation problems. For personal dosimetry, the output consists of the desired dose components: deep dose, shallow dose and eye dose. The input consists of the TL data obtained from the readout of a multi-element dosimeter. The neural network approach was applied to the Harshaw Type 8825 TLD, and was shown to significantly improve the performance of this dosimeter, well within the U.S. accreditation requirements for personnel dosimeters

  20. Optimized Neural Network for Fault Diagnosis and Classification

    International Nuclear Information System (INIS)

    Elaraby, S.M.

    2005-01-01

    This paper presents a developed and implemented toolbox for optimizing neural network structure of fault diagnosis and classification. Evolutionary algorithm based on hierarchical genetic algorithm structure is used for optimization. The simplest feed-forward neural network architecture is selected. Developed toolbox has friendly user interface. Multiple solutions are generated. The performance and applicability of the proposed toolbox is verified with benchmark data patterns and accident diagnosis of Egyptian Second research reactor (ETRR-2)

  1. Convolutional Neural Network for Histopathological Analysis of Osteosarcoma.

    Science.gov (United States)

    Mishra, Rashika; Daescu, Ovidiu; Leavey, Patrick; Rakheja, Dinesh; Sengupta, Anita

    2018-03-01

    Pathologists often deal with high complexity and sometimes disagreement over osteosarcoma tumor classification due to cellular heterogeneity in the dataset. Segmentation and classification of histology tissue in H&E stained tumor image datasets is a challenging task because of intra-class variations, inter-class similarity, crowded context, and noisy data. In recent years, deep learning approaches have led to encouraging results in breast cancer and prostate cancer analysis. In this article, we propose convolutional neural network (CNN) as a tool to improve efficiency and accuracy of osteosarcoma tumor classification into tumor classes (viable tumor, necrosis) versus nontumor. The proposed CNN architecture contains eight learned layers: three sets of stacked two convolutional layers interspersed with max pooling layers for feature extraction and two fully connected layers with data augmentation strategies to boost performance. The use of a neural network results in higher accuracy of average 92% for the classification. We compare the proposed architecture with three existing and proven CNN architectures for image classification: AlexNet, LeNet, and VGGNet. We also provide a pipeline to calculate percentage necrosis in a given whole slide image. We conclude that the use of neural networks can assure both high accuracy and efficiency in osteosarcoma classification.

  2. Quantitative phase microscopy using deep neural networks

    Science.gov (United States)

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

    2018-02-01

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

  3. Efficient universal computing architectures for decoding neural activity.

    Directory of Open Access Journals (Sweden)

    Benjamin I Rapoport

    Full Text Available The ability to decode neural activity into meaningful control signals for prosthetic devices is critical to the development of clinically useful brain- machine interfaces (BMIs. Such systems require input from tens to hundreds of brain-implanted recording electrodes in order to deliver robust and accurate performance; in serving that primary function they should also minimize power dissipation in order to avoid damaging neural tissue; and they should transmit data wirelessly in order to minimize the risk of infection associated with chronic, transcutaneous implants. Electronic architectures for brain- machine interfaces must therefore minimize size and power consumption, while maximizing the ability to compress data to be transmitted over limited-bandwidth wireless channels. Here we present a system of extremely low computational complexity, designed for real-time decoding of neural signals, and suited for highly scalable implantable systems. Our programmable architecture is an explicit implementation of a universal computing machine emulating the dynamics of a network of integrate-and-fire neurons; it requires no arithmetic operations except for counting, and decodes neural signals using only computationally inexpensive logic operations. The simplicity of this architecture does not compromise its ability to compress raw neural data by factors greater than [Formula: see text]. We describe a set of decoding algorithms based on this computational architecture, one designed to operate within an implanted system, minimizing its power consumption and data transmission bandwidth; and a complementary set of algorithms for learning, programming the decoder, and postprocessing the decoded output, designed to operate in an external, nonimplanted unit. The implementation of the implantable portion is estimated to require fewer than 5000 operations per second. A proof-of-concept, 32-channel field-programmable gate array (FPGA implementation of this portion

  4. Advanced neural network-based computational schemes for robust fault diagnosis

    CERN Document Server

    Mrugalski, Marcin

    2014-01-01

    The present book is devoted to problems of adaptation of artificial neural networks to robust fault diagnosis schemes. It presents neural networks-based modelling and estimation techniques used for designing robust fault diagnosis schemes for non-linear dynamic systems. A part of the book focuses on fundamental issues such as architectures of dynamic neural networks, methods for designing of neural networks and fault diagnosis schemes as well as the importance of robustness. The book is of a tutorial value and can be perceived as a good starting point for the new-comers to this field. The book is also devoted to advanced schemes of description of neural model uncertainty. In particular, the methods of computation of neural networks uncertainty with robust parameter estimation are presented. Moreover, a novel approach for system identification with the state-space GMDH neural network is delivered. All the concepts described in this book are illustrated by both simple academic illustrative examples and practica...

  5. Neural networks for perception human and machine perception

    CERN Document Server

    Wechsler, Harry

    1991-01-01

    Neural Networks for Perception, Volume 1: Human and Machine Perception focuses on models for understanding human perception in terms of distributed computation and examples of PDP models for machine perception. This book addresses both theoretical and practical issues related to the feasibility of both explaining human perception and implementing machine perception in terms of neural network models. The book is organized into two parts. The first part focuses on human perception. Topics on network model ofobject recognition in human vision, the self-organization of functional architecture in t

  6. Optimization of neural network architecture for classification of radar jamming FM signals

    Science.gov (United States)

    Soto, Alberto; Mendoza, Ariadna; Flores, Benjamin C.

    2017-05-01

    The purpose of this study is to investigate several artificial Neural Network (NN) architectures in order to design a cognitive radar system capable of optimally distinguishing linear Frequency-Modulated (FM) signals from bandlimited Additive White Gaussian Noise (AWGN). The goal is to create a theoretical framework to determine an optimal NN architecture to achieve a Probability of Detection (PD) of 95% or higher and a Probability of False Alarm (PFA) of 1.5% or lower at 5 dB Signal to Noise Ratio (SNR). Literature research reveals that the frequency-domain power spectral densities characterize a signal more efficiently than its time-domain counterparts. Therefore, the input data is preprocessed by calculating the magnitude square of the Discrete Fourier Transform of the digitally sampled bandlimited AWGN and linear FM signals to populate a matrix containing N number of samples and M number of spectra. This matrix is used as input for the NN, and the spectra are divided as follows: 70% for training, 15% for validation, and 15% for testing. The study begins by experimentally deducing the optimal number of hidden neurons (1-40 neurons), then the optimal number of hidden layers (1-5 layers), and lastly, the most efficient learning algorithm. The training algorithms examined are: Resilient Backpropagation, Scaled Conjugate Gradient, Conjugate Gradient with Powell/Beale Restarts, Polak-Ribiére Conjugate Gradient, and Variable Learning Rate Backpropagation. We determine that an architecture with ten hidden neurons (or higher), one hidden layer, and a Scaled Conjugate Gradient for training algorithm encapsulates an optimal architecture for our application.

  7. Parallel protein secondary structure prediction based on neural networks.

    Science.gov (United States)

    Zhong, Wei; Altun, Gulsah; Tian, Xinmin; Harrison, Robert; Tai, Phang C; Pan, Yi

    2004-01-01

    Protein secondary structure prediction has a fundamental influence on today's bioinformatics research. In this work, binary and tertiary classifiers of protein secondary structure prediction are implemented on Denoeux belief neural network (DBNN) architecture. Hydrophobicity matrix, orthogonal matrix, BLOSUM62 and PSSM (position specific scoring matrix) are experimented separately as the encoding schemes for DBNN. The experimental results contribute to the design of new encoding schemes. New binary classifier for Helix versus not Helix ( approximately H) for DBNN produces prediction accuracy of 87% when PSSM is used for the input profile. The performance of DBNN binary classifier is comparable to other best prediction methods. The good test results for binary classifiers open a new approach for protein structure prediction with neural networks. Due to the time consuming task of training the neural networks, Pthread and OpenMP are employed to parallelize DBNN in the hyperthreading enabled Intel architecture. Speedup for 16 Pthreads is 4.9 and speedup for 16 OpenMP threads is 4 in the 4 processors shared memory architecture. Both speedup performance of OpenMP and Pthread is superior to that of other research. With the new parallel training algorithm, thousands of amino acids can be processed in reasonable amount of time. Our research also shows that hyperthreading technology for Intel architecture is efficient for parallel biological algorithms.

  8. Using a neural network approach for muon reconstruction and triggering

    CERN Document Server

    Etzion, E; Abramowicz, H; Benhammou, Ya; Horn, D; Levinson, L; Livneh, R

    2004-01-01

    The extremely high rate of events that will be produced in the future Large Hadron Collider requires the triggering mechanism to take precise decisions in a few nano-seconds. We present a study which used an artificial neural network triggering algorithm and compared it to the performance of a dedicated electronic muon triggering system. Relatively simple architecture was used to solve a complicated inverse problem. A comparison with a realistic example of the ATLAS first level trigger simulation was in favour of the neural network. A similar architecture trained after the simulation of the electronics first trigger stage showed a further background rejection.

  9. Performance of artificial neural networks and genetical evolved artificial neural networks unfolding techniques

    International Nuclear Information System (INIS)

    Ortiz R, J. M.; Martinez B, M. R.; Vega C, H. R.; Gallego D, E.; Lorente F, A.; Mendez V, R.; Los Arcos M, J. M.; Guerrero A, J. E.

    2011-01-01

    With the Bonner spheres spectrometer neutron spectrum is obtained through an unfolding procedure. Monte Carlo methods, Regularization, Parametrization, Least-squares, and Maximum Entropy are some of the techniques utilized for unfolding. In the last decade methods based on Artificial Intelligence Technology have been used. Approaches based on Genetic Algorithms and Artificial Neural Networks (Ann) have been developed in order to overcome the drawbacks of previous techniques. Nevertheless the advantages of Ann still it has some drawbacks mainly in the design process of the network, vg the optimum selection of the architectural and learning Ann parameters. In recent years the use of hybrid technologies, combining Ann and genetic algorithms, has been utilized to. In this work, several Ann topologies were trained and tested using Ann and Genetically Evolved Artificial Neural Networks in the aim to unfold neutron spectra using the count rates of a Bonner sphere spectrometer. Here, a comparative study of both procedures has been carried out. (Author)

  10. Localizing Tortoise Nests by Neural Networks.

    Directory of Open Access Journals (Sweden)

    Roberto Barbuti

    Full Text Available 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.

  11. Livermore Big Artificial Neural Network Toolkit

    Energy Technology Data Exchange (ETDEWEB)

    2016-07-01

    LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

  12. Distorted Character Recognition Via An Associative Neural Network

    Science.gov (United States)

    Messner, Richard A.; Szu, Harold H.

    1987-03-01

    The purpose of this paper is two-fold. First, it is intended to provide some preliminary results of a character recognition scheme which has foundations in on-going neural network architecture modeling, and secondly, to apply some of the neural network results in a real application area where thirty years of effort has had little effect on providing the machine an ability to recognize distorted objects within the same object class. It is the author's belief that the time is ripe to start applying in ernest the results of over twenty years of effort in neural modeling to some of the more difficult problems which seem so hard to solve by conventional means. The character recognition scheme proposed utilizes a preprocessing stage which performs a 2-dimensional Walsh transform of an input cartesian image field, then sequency filters this spectrum into three feature bands. Various features are then extracted and organized into three sets of feature vectors. These vector patterns that are stored and recalled associatively. Two possible associative neural memory models are proposed for further investigation. The first being an outer-product linear matrix associative memory with a threshold function controlling the strength of the output pattern (similar to Kohonen's crosscorrelation approach [1]). The second approach is based upon a modified version of Grossberg's neural architecture [2] which provides better self-organizing properties due to its adaptive nature. Preliminary results of the sequency filtering and feature extraction preprocessing stage and discussion about the use of the proposed neural architectures is included.

  13. Phonematic translation of Polish texts by the neural network

    International Nuclear Information System (INIS)

    Bielecki, A.; Podolak, I.T.; Wosiek, J.; Majkut, E.

    1996-01-01

    Using the back propagation algorithm, we have trained the feed forward neural network to pronounce Polish language, more precisely to translate Polish text into its phonematic counterpart. Depending on the input coding and network architecture, 88%-95% translation efficiency was achieved. (author)

  14. SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

    OpenAIRE

    Wang, Linnan; Ye, Jinmian; Zhao, Yiyang; Wu, Wei; Li, Ang; Song, Shuaiwen Leon; Xu, Zenglin; Kraska, Tim

    2018-01-01

    Going deeper and wider in neural architectures improves the accuracy, while the limited GPU DRAM places an undesired restriction on the network design domain. Deep Learning (DL) practitioners either need change to less desired network architectures, or nontrivially dissect a network across multiGPUs. These distract DL practitioners from concentrating on their original machine learning tasks. We present SuperNeurons: a dynamic GPU memory scheduling runtime to enable the network training far be...

  15. Artificial Astrocytes Improve Neural Network Performance

    Science.gov (United States)

    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

  16. Artificial astrocytes improve neural network performance.

    Directory of Open Access Journals (Sweden)

    Ana B Porto-Pazos

    Full Text Available 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.

  17. Artificial astrocytes improve neural network performance.

    Science.gov (United States)

    Porto-Pazos, Ana B; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso

    2011-04-19

    Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.

  18. Neural networks to predict exosphere temperature corrections

    Science.gov (United States)

    Choury, Anna; Bruinsma, Sean; Schaeffer, Philippe

    2013-10-01

    Precise orbit prediction requires a forecast of the atmospheric drag force with a high degree of accuracy. Artificial neural networks are universal approximators derived from artificial intelligence and are widely used for prediction. This paper presents a method of artificial neural networking for prediction of the thermosphere density by forecasting exospheric temperature, which will be used by the semiempirical thermosphere Drag Temperature Model (DTM) currently developed. Artificial neural network has shown to be an effective and robust forecasting model for temperature prediction. The proposed model can be used for any mission from which temperature can be deduced accurately, i.e., it does not require specific training. Although the primary goal of the study was to create a model for 1 day ahead forecast, the proposed architecture has been generalized to 2 and 3 days prediction as well. The impact of artificial neural network predictions has been quantified for the low-orbiting satellite Gravity Field and Steady-State Ocean Circulation Explorer in 2011, and an order of magnitude smaller orbit errors were found when compared with orbits propagated using the thermosphere model DTM2009.

  19. Optimal neural networks for protein-structure prediction

    International Nuclear Information System (INIS)

    Head-Gordon, T.; Stillinger, F.H.

    1993-01-01

    The successful application of neural-network algorithms for prediction of protein structure is stymied by three problem areas: the sparsity of the database of known protein structures, poorly devised network architectures which make the input-output mapping opaque, and a global optimization problem in the multiple-minima space of the network variables. We present a simplified polypeptide model residing in two dimensions with only two amino-acid types, A and B, which allows the determination of the global energy structure for all possible sequences of pentamer, hexamer, and heptamer lengths. This model simplicity allows us to compile a complete structural database and to devise neural networks that reproduce the tertiary structure of all sequences with absolute accuracy and with the smallest number of network variables. These optimal networks reveal that the three problem areas are convoluted, but that thoughtful network designs can actually deconvolute these detrimental traits to provide network algorithms that genuinely impact on the ability of the network to generalize or learn the desired mappings. Furthermore, the two-dimensional polypeptide model shows sufficient chemical complexity so that transfer of neural-network technology to more realistic three-dimensional proteins is evident

  20. Improving the Robustness of Deep Neural Networks via Stability Training

    OpenAIRE

    Zheng, Stephan; Song, Yang; Leung, Thomas; Goodfellow, Ian

    2016-01-01

    In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network. Such instability affects many deep architectures with state-of-the-art performance on a wide range of computer vision tasks. We present a general stability training method to stabilize deep networks against small input distortions that result from various types of common image processing, such...

  1. Brain tumor segmentation with Deep Neural Networks.

    Science.gov (United States)

    Havaei, Mohammad; Davy, Axel; Warde-Farley, David; Biard, Antoine; Courville, Aaron; Bengio, Yoshua; Pal, Chris; Jodoin, Pierre-Marc; Larochelle, Hugo

    2017-01-01

    In this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and high grade) pictured in MR images. By their very nature, these tumors can appear anywhere in the brain and have almost any kind of shape, size, and contrast. These reasons motivate our exploration of a machine learning solution that exploits a flexible, high capacity DNN while being extremely efficient. Here, we give a description of different model choices that we've found to be necessary for obtaining competitive performance. We explore in particular different architectures based on Convolutional Neural Networks (CNN), i.e. DNNs specifically adapted to image data. We present a novel CNN architecture which differs from those traditionally used in computer vision. Our CNN exploits both local features as well as more global contextual features simultaneously. Also, different from most traditional uses of CNNs, our networks use a final layer that is a convolutional implementation of a fully connected layer which allows a 40 fold speed up. We also describe a 2-phase training procedure that allows us to tackle difficulties related to the imbalance of tumor labels. Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN. Results reported on the 2013 BRATS test data-set reveal that our architecture improves over the currently published state-of-the-art while being over 30 times faster. Copyright © 2016 Elsevier B.V. All rights reserved.

  2. Patterns recognition of electric brain activity using artificial neural networks

    Science.gov (United States)

    Musatov, V. Yu.; Pchelintseva, S. V.; Runnova, A. E.; Hramov, A. E.

    2017-04-01

    An approach for the recognition of various cognitive processes in the brain activity in the perception of ambiguous images. On the basis of developed theoretical background and the experimental data, we propose a new classification of oscillating patterns in the human EEG by using an artificial neural network approach. After learning of the artificial neural network reliably identified cube recognition processes, for example, left-handed or right-oriented Necker cube with different intensity of their edges, construct an artificial neural network based on Perceptron architecture and demonstrate its effectiveness in the pattern recognition of the EEG in the experimental.

  3. Deep Neural Network-Based Chinese Semantic Role Labeling

    Institute of Scientific and Technical Information of China (English)

    ZHENG Xiaoqing; CHEN Jun; SHANG Guoqiang

    2017-01-01

    A recent trend in machine learning is to use deep architec-tures to discover multiple levels of features from data, which has achieved impressive results on various natural language processing (NLP) tasks. We propose a deep neural network-based solution to Chinese semantic role labeling (SRL) with its application on message analysis. The solution adopts a six-step strategy: text normalization, named entity recognition (NER), Chinese word segmentation and part-of-speech (POS) tagging, theme classification, SRL, and slot filling. For each step, a novel deep neural network - based model is designed and optimized, particularly for smart phone applications. Ex-periment results on all the NLP sub - tasks of the solution show that the proposed neural networks achieve state-of-the-art performance with the minimal computational cost. The speed advantage of deep neural networks makes them more competitive for large-scale applications or applications requir-ing real-time response, highlighting the potential of the pro-posed solution for practical NLP systems.

  4. Human Face Recognition Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Răzvan-Daniel Albu

    2009-10-01

    Full Text Available In this paper, I present a novel hybrid face recognition approach based on a convolutional neural architecture, designed to robustly detect highly variable face patterns. The convolutional network extracts successively larger features in a hierarchical set of layers. With the weights of the trained neural networks there are created kernel windows used for feature extraction in a 3-stage algorithm. I present experimental results illustrating the efficiency of the proposed approach. I use a database of 796 images of 159 individuals from Reims University which contains quite a high degree of variability in expression, pose, and facial details.

  5. Recurrent Neural Network for Computing the Drazin Inverse.

    Science.gov (United States)

    Stanimirović, Predrag S; Zivković, Ivan S; Wei, Yimin

    2015-11-01

    This paper presents a recurrent neural network (RNN) for computing the Drazin inverse of a real matrix in real time. This recurrent neural network (RNN) is composed of n independent parts (subnetworks), where n is the order of the input matrix. These subnetworks can operate concurrently, so parallel and distributed processing can be achieved. In this way, the computational advantages over the existing sequential algorithms can be attained in real-time applications. The RNN defined in this paper is convenient for an implementation in an electronic circuit. The number of neurons in the neural network is the same as the number of elements in the output matrix, which represents the Drazin inverse. The difference between the proposed RNN and the existing ones for the Drazin inverse computation lies in their network architecture and dynamics. The conditions that ensure the stability of the defined RNN as well as its convergence toward the Drazin inverse are considered. In addition, illustrative examples and examples of application to the practical engineering problems are discussed to show the efficacy of the proposed neural network.

  6. Fluid and flexible minds: Intelligence reflects synchrony in the brain’s intrinsic network architecture

    Directory of Open Access Journals (Sweden)

    Michael A. Ferguson

    2017-06-01

    Full Text Available Human intelligence has been conceptualized as a complex system of dissociable cognitive processes, yet studies investigating the neural basis of intelligence have typically emphasized the contributions of discrete brain regions or, more recently, of specific networks of functionally connected regions. Here we take a broader, systems perspective in order to investigate whether intelligence is an emergent property of synchrony within the brain’s intrinsic network architecture. Using a large sample of resting-state fMRI and cognitive data (n = 830, we report that the synchrony of functional interactions within and across distributed brain networks reliably predicts fluid and flexible intellectual functioning. By adopting a whole-brain, systems-level approach, we were able to reliably predict individual differences in human intelligence by characterizing features of the brain’s intrinsic network architecture. These findings hold promise for the eventual development of neural markers to predict changes in intellectual function that are associated with neurodevelopment, normal aging, and brain disease. In our study, we aimed to understand how individual differences in intellectual functioning are reflected in the intrinsic network architecture of the human brain. We applied statistical methods, known as spectral decompositions, in order to identify individual differences in the synchronous patterns of spontaneous brain activity that reliably predict core aspects of human intelligence. The synchrony of brain activity at rest across multiple discrete neural networks demonstrated positive relationships with fluid intelligence. In contrast, global synchrony within the brain’s network architecture reliably, and inversely, predicted mental flexibility, a core facet of intellectual functioning. The multinetwork systems approach described here represents a methodological and conceptual extension of earlier efforts that related differences in

  7. Implementation of neural networks on 'Connection Machine'

    International Nuclear Information System (INIS)

    Belmonte, Ghislain

    1990-12-01

    This report is a first approach to the notion of neural networks and their possible applications within the framework of artificial intelligence activities of the Department of Applied Mathematics of the Limeil-Valenton Research Center. The first part is an introduction to the field of neural networks; the main neural network models are described in this section. The applications of neural networks in the field of classification have mainly been studied because they could more particularly help to solve some of the decision support problems dealt with by the C.E.A. As the neural networks perform a large number of parallel operations, it was therefore logical to use a parallel architecture computer: the Connection Machine (which uses 16384 processors and is located at E.T.C.A. Arcueil). The second part presents some generalities on the parallelism and the Connection Machine, and two implementations of neural networks on Connection Machine. The first of these implementations concerns one of the most used algorithms to realize the learning of neural networks: the Gradient Retro-propagation algorithm. The second one, less common, concerns a network of neurons destined mainly to the recognition of forms: the Fukushima Neocognitron. The latter is studied by the C.E.A. of Bruyeres-le-Chatel in order to realize an embedded system (including hardened circuits) for the fast recognition of forms [fr

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

    Science.gov (United States)

    Sengupta, Abhronil; Shim, Yong; Roy, Kaushik

    2016-12-01

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

  9. Rule extraction from minimal neural networks for credit card screening.

    Science.gov (United States)

    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.

  10. Neural networks and their potential application in nuclear power plants

    International Nuclear Information System (INIS)

    Uhrig, R.E.

    1991-01-01

    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 modeled 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

  11. Neural architecture design based on extreme learning machine.

    Science.gov (United States)

    Bueno-Crespo, Andrés; García-Laencina, Pedro J; Sancho-Gómez, José-Luis

    2013-12-01

    Selection of the optimal neural architecture to solve a pattern classification problem entails to choose the relevant input units, the number of hidden neurons and its corresponding interconnection weights. This problem has been widely studied in many research works but their solutions usually involve excessive computational cost in most of the problems and they do not provide a unique solution. This paper proposes a new technique to efficiently design the MultiLayer Perceptron (MLP) architecture for classification using the Extreme Learning Machine (ELM) algorithm. The proposed method provides a high generalization capability and a unique solution for the architecture design. Moreover, the selected final network only retains those input connections that are relevant for the classification task. Experimental results show these advantages. Copyright © 2013 Elsevier Ltd. All rights reserved.

  12. On design and evaluation of tapped-delay neural network architectures

    DEFF Research Database (Denmark)

    Svarer, Claus; Hansen, Lars Kai; Larsen, Jan

    1993-01-01

    Pruning and evaluation of tapped-delay neural networks for the sunspot benchmark series are addressed. It is shown that the generalization ability of the networks can be improved by pruning using the optimal brain damage method of Le Cun, Denker and Solla. A stop criterion for the pruning algorithm...

  13. Seafloor classification using artificial neural network architecture from central western continental shelf of India

    Science.gov (United States)

    Mahale, Vasudev; Chakraborty, Bishwajit; Navelkar, Gajanan S.; Prabhu Desai, R. G.

    2005-04-01

    Seafloor classification studies are carried out at the central western continental shelf of India employing two frequency normal incidence single beam echo-sounder backscatter data. Echo waveform data from different seafloor sediment areas are utilized for present study. Three artificial neural network (ANN) architectures, e.g., Self-Organization Feature Maps (SOFM), Multi-Layer Perceptron (MLP), and Learning Vector Quantization (LVQ) are applied for seafloor classifications. In case of MLP, features are extracted from the received echo signal, on the basis of which, classification is carried out. In the case of the SOFM, a simple moving average echo waveform pre-processing technique is found to yield excellent classification results. Finally, LVQ, which is known as ANN of hybrid architecture is found to be the efficient seafloor classifier especially from the point of view of the real-time application. The simultaneously acquired sediment sample, multi-beam bathymetry and side scan sonar and echo waveform based seafloor classifications results are indicative of the depositional (inner shelf), non-depositional or erosion (outer shelf) environment and combination of both in the transition zone. [Work supported by DIT.

  14. Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture

    Energy Technology Data Exchange (ETDEWEB)

    Disney, Adam [University of Tennessee (UT); Reynolds, John [University of Tennessee (UT)

    2015-01-01

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

  15. Nonlinear adaptive inverse control via the unified model neural network

    Science.gov (United States)

    Jeng, Jin-Tsong; Lee, Tsu-Tian

    1999-03-01

    In this paper, we propose a new nonlinear adaptive inverse control via a unified model neural network. In order to overcome nonsystematic design and long training time in nonlinear adaptive inverse control, we propose the approximate transformable technique to obtain a Chebyshev Polynomials Based Unified Model (CPBUM) neural network for the feedforward/recurrent neural networks. It turns out that the proposed method can use less training time to get an inverse model. Finally, we apply this proposed method to control magnetic bearing system. The experimental results show that the proposed nonlinear adaptive inverse control architecture provides a greater flexibility and better performance in controlling magnetic bearing systems.

  16. Selection of an optimal neural network architecture for computer-aided detection of microcalcifications - Comparison of automated optimization techniques

    International Nuclear Information System (INIS)

    Gurcan, Metin N.; Sahiner, Berkman; Chan Heangping; Hadjiiski, Lubomir; Petrick, Nicholas

    2001-01-01

    Many computer-aided diagnosis (CAD) systems use neural networks (NNs) for either detection or classification of abnormalities. Currently, most NNs are 'optimized' by manual search in a very limited parameter space. In this work, we evaluated the use of automated optimization methods for selecting an optimal convolution neural network (CNN) architecture. Three automated methods, the steepest descent (SD), the simulated annealing (SA), and the genetic algorithm (GA), were compared. We used as an example the CNN that classifies true and false microcalcifications detected on digitized mammograms by a prescreening algorithm. Four parameters of the CNN architecture were considered for optimization, the numbers of node groups and the filter kernel sizes in the first and second hidden layers, resulting in a search space of 432 possible architectures. The area A z under the receiver operating characteristic (ROC) curve was used to design a cost function. The SA experiments were conducted with four different annealing schedules. Three different parent selection methods were compared for the GA experiments. An available data set was split into two groups with approximately equal number of samples. By using the two groups alternately for training and testing, two different cost surfaces were evaluated. For the first cost surface, the SD method was trapped in a local minimum 91% (392/432) of the time. The SA using the Boltzman schedule selected the best architecture after evaluating, on average, 167 architectures. The GA achieved its best performance with linearly scaled roulette-wheel parent selection; however, it evaluated 391 different architectures, on average, to find the best one. The second cost surface contained no local minimum. For this surface, a simple SD algorithm could quickly find the global minimum, but the SA with the very fast reannealing schedule was still the most efficient. The same SA scheme, however, was trapped in a local minimum on the first cost

  17. Solving differential equations with unknown constitutive relations as recurrent neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Hagge, Tobias J.; Stinis, Panagiotis; Yeung, Enoch H.; Tartakovsky, Alexandre M.

    2017-12-08

    We solve a system of ordinary differential equations with an unknown functional form of a sink (reaction rate) term. We assume that the measurements (time series) of state variables are partially available, and use a recurrent neural network to “learn” the reaction rate from this data. This is achieved by including discretized ordinary differential equations as part of a recurrent neural network training problem. We extend TensorFlow’s recurrent neural network architecture to create a simple but scalable and effective solver for the unknown functions, and apply it to a fedbatch bioreactor simulation problem. Use of techniques from recent deep learning literature enables training of functions with behavior manifesting over thousands of time steps. Our networks are structurally similar to recurrent neural networks, but differ in purpose, and require modified training strategies.

  18. Artificial Neural Networks to Detect Risk of Type 2 Diabetes | Baha ...

    African Journals Online (AJOL)

    A multilayer feedforward architecture with backpropagation algorithm was designed using Neural Network Toolbox of Matlab. The network was trained using batch mode backpropagation with gradient descent and momentum. Best performed network identified during the training was 2 hidden layers of 6 and 3 neurons, ...

  19. Empirical modeling of nuclear power plants using neural networks

    International Nuclear Information System (INIS)

    Parlos, A.G.; Atiya, A.; Chong, K.T.

    1991-01-01

    A summary of a procedure for nonlinear identification of process dynamics encountered in nuclear power plant components is presented in this paper using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the nonlinear structure for system identification. In the overall identification process, the feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of time-dependent system nonlinearities. The standard backpropagation learning algorithm is modified and is used to train the proposed hybrid network in a supervised manner. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The nonlinear response of a representative steam generator is predicted using a neural network and is compared to the response obtained from a sophisticated physical model during both high- and low-power operation. The transient responses compare well, though further research is warranted for training and testing of recurrent neural networks during more severe operational transients and accident scenarios

  20. Advances in Artificial Neural Networks – Methodological Development and Application

    Directory of Open Access Journals (Sweden)

    Yanbo Huang

    2009-08-01

    Full Text Available 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 networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a backpropagation training algorithm, have gained recognition in research and applications in various scientific and engineering areas. In order to accelerate the training process and overcome data over-fitting, research has been conducted to improve the backpropagation algorithm. Further, artificial neural networks have been integrated with other advanced methods such as fuzzy logic and wavelet analysis, to enhance the ability of data interpretation and modeling and to avoid subjectivity in the operation of the training algorithm. In recent years, support vector machines have emerged as a set of high-performance supervised generalized linear classifiers in parallel with artificial neural networks. A review on development history of artificial neural networks is presented and the standard architectures and algorithms of artificial neural networks are described. Furthermore, advanced artificial neural networks will be introduced with support vector machines, and limitations of ANNs will be identified. The future of artificial neural network development in tandem with support vector machines will be discussed in conjunction with further applications to food science and engineering, soil and water relationship for crop management, and decision support for precision agriculture. Along with the network structures and training algorithms, the applications of artificial neural networks will be reviewed as well, especially in the fields of agricultural and biological

  1. Stochastic Spiking Neural Networks Enabled by Magnetic Tunnel Junctions: From Nontelegraphic to Telegraphic Switching Regimes

    Science.gov (United States)

    Liyanagedera, Chamika M.; Sengupta, Abhronil; Jaiswal, Akhilesh; Roy, Kaushik

    2017-12-01

    Stochastic spiking neural networks based on nanoelectronic spin devices can be a possible pathway to achieving "brainlike" compact and energy-efficient cognitive intelligence. The computational model attempt to exploit the intrinsic device stochasticity of nanoelectronic synaptic or neural components to perform learning or inference. However, there has been limited analysis on the scaling effect of stochastic spin devices and its impact on the operation of such stochastic networks at the system level. This work attempts to explore the design space and analyze the performance of nanomagnet-based stochastic neuromorphic computing architectures for magnets with different barrier heights. We illustrate how the underlying network architecture must be modified to account for the random telegraphic switching behavior displayed by magnets with low barrier heights as they are scaled into the superparamagnetic regime. We perform a device-to-system-level analysis on a deep neural-network architecture for a digit-recognition problem on the MNIST data set.

  2. Prediction of Aerodynamic Coefficient using Genetic Algorithm Optimized Neural Network for Sparse Data

    Science.gov (United States)

    Rajkumar, T.; Bardina, Jorge; Clancy, Daniel (Technical Monitor)

    2002-01-01

    coefficients to an accuracy of 110% . In our problem, we would like to get an optimized neural network architecture and minimum data set. This has been accomplished within 500 training cycles of a neural network. After removing training pairs (outliers), the GA has produced much better results. The neural network constructed is a feed forward neural network with a back propagation learning mechanism. The main goal has been to free the network design process from constraints of human biases, and to discover better forms of neural network architectures. The automation of the network architecture search by genetic algorithms seems to have been the best way to achieve this goal.

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

    Science.gov (United States)

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

    2014-01-01

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

  4. Nonlinear identification of process dynamics using neural networks

    International Nuclear Information System (INIS)

    Parlos, A.G.; Atiya, A.F.; Chong, K.T.

    1992-01-01

    In this paper the nonlinear identification of process dynamics encountered in nuclear power plant components is addressed, in an input-output sense, using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the model structure to be identified. The feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of temporal variations in the system nonlinearities. The standard backpropagation learning algorithm is modified, and it is used for the supervised training of the proposed hybrid network. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The response of representative steam generator is predicted using a neural network, and it is compared to the response obtained from a sophisticated computer model based on first principles. The transient responses compare well, although further research is warranted to determine the predictive capabilities of these networks during more severe operational transients and accident scenarios

  5. Morphological neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Ritter, G.X.; Sussner, P. [Univ. of Florida, Gainesville, FL (United States)

    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.

  6. TRIGA control rod position and reactivity transient Monitoring by Neural Networks

    International Nuclear Information System (INIS)

    Rosa, R.; Palomba, M.; Sepielli, M.

    2008-01-01

    Plant sensors drift or malfunction and operator actions in nuclear reactor control can be supported by sensor on-line monitoring, and data validation through soft-computing process. On-line recalibration can often avoid manual calibration or drifting component replacement. DSP requires prompt response to the modified conditions. Artificial Neural Network (ANN) and Fuzzy logic ensure: prompt response, link with field measurement and physical system behaviour, data incoming interpretation, and detection of discrepancy for mis-calibration or sensor faults. ANN (Artificial Neural Network) is a system based on the operation of biological neural networks. Although computing is day by day advancing, there are certain tasks that a program made for a common microprocessor is unable to perform. A software implementation of an ANN can be made with Pros and Cons. Pros: A neural network can perform tasks that a linear program can not; When an element of the neural network fails, it can continue without any problem by their parallel nature; A neural network learns and does not need to be reprogrammed; It can be implemented in any application; It can be implemented without any problem. Cons: The architecture of a neural network is different from the architecture of microprocessors therefore needs to be emulated; it requires high processing time for large neural networks; and the neural network needs training to operate. Three possibilities of training exist: Supervised learning: the network is trained providing input and matching output patterns; Unsupervised learning: input patterns are not a priori classified and the system must develop its own representation of the input stimuli; Reinforcement Learning: intermediate form of the above two types of learning, the learning machine does some action on the environment and gets a feedback response from the environment. Two TRIGAN ANN applications are considered: control rod position and fuel temperature. The outcome obtained in this

  7. Representation of linguistic form and function in recurrent neural networks

    NARCIS (Netherlands)

    Kadar, Akos; Chrupala, Grzegorz; Alishahi, Afra

    2017-01-01

    We present novel methods for analyzing the activation patterns of recurrent neural networks from a linguistic point of view and explore the types of linguistic structure they learn. As a case study, we use a standard standalone language model, and a multi-task gated recurrent network architecture

  8. Sejarah, Penerapan, dan Analisis Resiko dari Neural Network: Sebuah Tinjauan Pustaka

    Directory of Open Access Journals (Sweden)

    Cristina Cristina

    2018-05-01

    Full Text Available A neural network is a form of artificial intelligence that has the ability to learn, grow, and adapt in a dynamic environment. Neural network began since 1890 because a great American psychologist named William James created the book "Principles of Psycology". James was the first one publish a number of facts related to the structure and function of the brain. The history of neural network development is divided into 4 epochs, the Camelot era, the Depression, the Renaissance, and the Neoconnectiosm era. Neural networks used today are not 100 percent accurate. However, neural networks are still used because of better performance than alternative computing models. The use of neural network consists of pattern recognition, signal analysis, robotics, and expert systems. For risk analysis of the neural network, it is first performed using hazards and operability studies (HAZOPS. Determining the neural network requirements in a good way will help in determining its contribution to system hazards and validating the control or mitigation of any hazards. After completion of the first stage at HAZOPS and the second stage determines the requirements, the next stage is designing. Neural network underwent repeated design-train-test development. At the design stage, the hazard analysis should consider the design aspects of the development, which include neural network architecture, size, intended use, and so on. It will be continued at the implementation stage, test phase, installation and inspection phase, operation phase, and ends at the maintenance stage.

  9. Classification of non-performing loans portfolio using Multilayer Perceptron artificial neural networks

    Directory of Open Access Journals (Sweden)

    Flávio Clésio Silva de Souza

    2014-06-01

    Full Text Available The purpose of the present research is to apply a Multilayer Perceptron (MLP neural network technique to create classification models from a portfolio of Non-Performing Loans (NPLs to classify this type of credit derivative. These credit derivatives are characterized as the amount of loans that were not paid and are already overdue more than 90 days. Since these titles are, because of legislative motives, moved by losses, Credit Rights Investment Funds (FDIC performs the purchase of these debts and the recovery of the credits. Using the Multilayer Perceptron (MLP architecture of Artificial Neural Network (ANN, classification models regarding the posterior recovery of these debts were created. To evaluate the performance of the models, evaluation metrics of classification relating to the neural networks with different architectures were presented. The results of the classifications were satisfactory, given the classification models were successful in the presented economics costs structure.

  10. Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors

    Directory of Open Access Journals (Sweden)

    Fernando Moya Rueda

    2018-05-01

    Full Text Available Human activity recognition (HAR is a classification task for recognizing human movements. Methods of HAR are of great interest as they have become tools for measuring occurrences and durations of human actions, which are the basis of smart assistive technologies and manual processes analysis. Recently, deep neural networks have been deployed for HAR in the context of activities of daily living using multichannel time-series. These time-series are acquired from body-worn devices, which are composed of different types of sensors. The deep architectures process these measurements for finding basic and complex features in human corporal movements, and for classifying them into a set of human actions. As the devices are worn at different parts of the human body, we propose a novel deep neural network for HAR. This network handles sequence measurements from different body-worn devices separately. An evaluation of the architecture is performed on three datasets, the Oportunity, Pamap2, and an industrial dataset, outperforming the state-of-the-art. In addition, different network configurations will also be evaluated. We find that applying convolutions per sensor channel and per body-worn device improves the capabilities of convolutional neural network (CNNs.

  11. Load forecasting using different architectures of neural networks with the assistance of the MATLAB toolboxes; Previsao de cargas eletricas utilizando diferentes arquiteturas de redes neurais artificiais com o auxilio das toolboxes do MATLAB

    Energy Technology Data Exchange (ETDEWEB)

    Nose Filho, Kenji; Araujo, Klayton A.M.; Maeda, Jorge L.Y.; Lotufo, Anna Diva P. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil)], Emails: kenjinose@yahoo.com.br, klayton_ama@hotmail.com, jorge-maeda@hotmail.com, annadiva@dee.feis.unesp.br

    2009-07-01

    This paper presents a development and implementation of a program to electrical load forecasting with data from a Brazilian electrical company, using four different architectures of neural networks of the MATLAB toolboxes: multilayer backpropagation gradient descendent with momentum, multilayer backpropagation Levenberg-Marquardt, adaptive network based fuzzy inference system and general regression neural network. The program presented a satisfactory performance, guaranteeing very good results. (author)

  12. Evolutionary neural network modeling for software cumulative failure time prediction

    International Nuclear Information System (INIS)

    Tian Liang; Noore, Afzel

    2005-01-01

    An evolutionary neural network modeling approach for software cumulative failure time prediction based on multiple-delayed-input single-output architecture is proposed. Genetic algorithm is used to globally optimize the number of the delayed input neurons and the number of neurons in the hidden layer of the neural network architecture. Modification of Levenberg-Marquardt algorithm with Bayesian regularization is used to improve the ability to predict software cumulative failure time. The performance of our proposed approach has been compared using real-time control and flight dynamic application data sets. Numerical results show that both the goodness-of-fit and the next-step-predictability of our proposed approach have greater accuracy in predicting software cumulative failure time compared to existing approaches

  13. The application of artificial neural networks to TLD dose algorithm

    International Nuclear Information System (INIS)

    Moscovitch, M.

    1997-01-01

    We review the application of feed forward neural networks to multi element thermoluminescence dosimetry (TLD) dose algorithm development. A Neural Network is an information processing method inspired by the biological nervous system. A dose algorithm based on a neural network is a fundamentally different approach from conventional algorithms, as it has the capability to learn from its own experience. The neural network algorithm is shown the expected dose values (output) associated with a given response of a multi-element dosimeter (input) many times.The algorithm, being trained that way, eventually is able to produce its own unique solution to similar (but not exactly the same) dose calculation problems. For personnel dosimetry, the output consists of the desired dose components: deep dose, shallow dose, and eye dose. The input consists of the TL data obtained from the readout of a multi-element dosimeter. For this application, a neural network architecture was developed based on the concept of functional links network (FLN). The FLN concept allowed an increase in the dimensionality of the input space and construction of a neural network without any hidden layers. This simplifies the problem and results in a relatively simple and reliable dose calculation algorithm. Overall, the neural network dose algorithm approach has been shown to significantly improve the precision and accuracy of dose calculations. (authors)

  14. A NEURAL NETWORK BASED TRAFFIC-AWARE FORWARDING STRATEGY IN NAMED DATA NETWORKING

    Directory of Open Access Journals (Sweden)

    Parisa Bazmi

    2016-11-01

    Full Text Available Named Data Networking (NDN is a new Internet architecture which has been proposed to eliminate TCP/IP Internet architecture restrictions. This architecture is abstracting away the notion of host and working based on naming datagrams. However, one of the major challenges of NDN is supporting QoS-aware forwarding strategy so as to forward Interest packets intelligently over multiple paths based on the current network condition. In this paper, Neural Network (NN Based Traffic-aware Forwarding strategy (NNTF is introduced in order to determine an optimal path for Interest forwarding. NN is embedded in NDN routers to select next hop dynamically based on the path overload probability achieved from the NN. This solution is characterized by load balancing and QoS-awareness via monitoring the available path and forwarding data on the traffic-aware shortest path. The performance of NNTF is evaluated using ndnSIM which shows the efficiency of this scheme in terms of network QoS improvementof17.5% and 72% reduction in network delay and packet drop respectively.

  15. Autoshaping and Automaintenance: A Neural-Network Approach

    OpenAIRE

    Burgos, José E

    2007-01-01

    This article presents an interpretation of autoshaping, and positive and negative automaintenance, based on a neural-network model. The model makes no distinction between operant and respondent learning mechanisms, and takes into account knowledge of hippocampal and dopaminergic systems. Four simulations were run, each one using an A-B-A design and four instances of feedfoward architectures. In A, networks received a positive contingency between inputs that simulated a conditioned stimulus (C...

  16. Recognition of sign language gestures using neural networks

    OpenAIRE

    Simon Vamplew

    2007-01-01

    This paper describes the structure and performance of the SLARTI sign language recognition system developed at the University of Tasmania. SLARTI uses a modular architecture consisting of multiple feature-recognition neural networks and a nearest-neighbour classifier to recognise Australian sign language (Auslan) hand gestures.

  17. A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition

    Directory of Open Access Journals (Sweden)

    Daniela Sánchez

    2017-01-01

    Full Text Available A grey wolf optimizer for modular neural network (MNN with a granular approach is proposed. The proposed method performs optimal granulation of data and design of modular neural networks architectures to perform human recognition, and to prove its effectiveness benchmark databases of ear, iris, and face biometric measures are used to perform tests and comparisons against other works. The design of a modular granular neural network (MGNN consists in finding optimal parameters of its architecture; these parameters are the number of subgranules, percentage of data for the training phase, learning algorithm, goal error, number of hidden layers, and their number of neurons. Nowadays, there is a great variety of approaches and new techniques within the evolutionary computing area, and these approaches and techniques have emerged to help find optimal solutions to problems or models and bioinspired algorithms are part of this area. In this work a grey wolf optimizer is proposed for the design of modular granular neural networks, and the results are compared against a genetic algorithm and a firefly algorithm in order to know which of these techniques provides better results when applied to human recognition.

  18. Recognition of decays of charged tracks with neural network techniques

    International Nuclear Information System (INIS)

    Stimpfl-Abele, G.

    1991-01-01

    We developed neural-network learning techniques for the recognition of decays of charged tracks using a feed-forward network with error back-propagation. Two completely different methods are described in detail and their efficiencies for several NN architectures are compared with conventional methods. Excellent results are obtained. (orig.)

  19. Automatic Classification of volcano-seismic events based on Deep Neural Networks.

    Science.gov (United States)

    Titos Luzón, M.; Bueno Rodriguez, A.; Garcia Martinez, L.; Benitez, C.; Ibáñez, J. M.

    2017-12-01

    Seismic monitoring of active volcanoes is a popular remote sensing technique to detect seismic activity, often associated to energy exchanges between the volcano and the environment. As a result, seismographs register a wide range of volcano-seismic signals that reflect the nature and underlying physics of volcanic processes. Machine learning and signal processing techniques provide an appropriate framework to analyze such data. In this research, we propose a new classification framework for seismic events based on deep neural networks. Deep neural networks are composed by multiple processing layers, and can discover intrinsic patterns from the data itself. Internal parameters can be initialized using a greedy unsupervised pre-training stage, leading to an efficient training of fully connected architectures. We aim to determine the robustness of these architectures as classifiers of seven different types of seismic events recorded at "Volcán de Fuego" (Colima, Mexico). Two deep neural networks with different pre-training strategies are studied: stacked denoising autoencoder and deep belief networks. Results are compared to existing machine learning algorithms (SVM, Random Forest, Multilayer Perceptron). We used 5 LPC coefficients over three non-overlapping segments as training features in order to characterize temporal evolution, avoid redundancy and encode the signal, regardless of its duration. Experimental results show that deep architectures can classify seismic events with higher accuracy than classical algorithms, attaining up to 92% recognition accuracy. Pre-training initialization helps these models to detect events that occur simultaneously in time (such explosions and rockfalls), increase robustness against noisy inputs, and provide better generalization. These results demonstrate deep neural networks are robust classifiers, and can be deployed in real-environments to monitor the seismicity of restless volcanoes.

  20. Modeling and control of magnetorheological fluid dampers using neural networks

    Science.gov (United States)

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

    2005-02-01

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

  1. The benefit of combining a deep neural network architecture with ideal ratio mask estimation in computational speech segregation to improve speech intelligibility.

    Science.gov (United States)

    Bentsen, Thomas; May, Tobias; Kressner, Abigail A; Dau, Torsten

    2018-01-01

    Computational speech segregation attempts to automatically separate speech from noise. This is challenging in conditions with interfering talkers and low signal-to-noise ratios. Recent approaches have adopted deep neural networks and successfully demonstrated speech intelligibility improvements. A selection of components may be responsible for the success with these state-of-the-art approaches: the system architecture, a time frame concatenation technique and the learning objective. The aim of this study was to explore the roles and the relative contributions of these components by measuring speech intelligibility in normal-hearing listeners. A substantial improvement of 25.4 percentage points in speech intelligibility scores was found going from a subband-based architecture, in which a Gaussian Mixture Model-based classifier predicts the distributions of speech and noise for each frequency channel, to a state-of-the-art deep neural network-based architecture. Another improvement of 13.9 percentage points was obtained by changing the learning objective from the ideal binary mask, in which individual time-frequency units are labeled as either speech- or noise-dominated, to the ideal ratio mask, where the units are assigned a continuous value between zero and one. Therefore, both components play significant roles and by combining them, speech intelligibility improvements were obtained in a six-talker condition at a low signal-to-noise ratio.

  2. SYNAPTIC DEPRESSION IN DEEP NEURAL NETWORKS FOR SPEECH PROCESSING.

    Science.gov (United States)

    Zhang, Wenhao; Li, Hanyu; Yang, Minda; Mesgarani, Nima

    2016-03-01

    A characteristic property of biological neurons is their ability to dynamically change the synaptic efficacy in response to variable input conditions. This mechanism, known as synaptic depression, significantly contributes to the formation of normalized representation of speech features. Synaptic depression also contributes to the robust performance of biological systems. In this paper, we describe how synaptic depression can be modeled and incorporated into deep neural network architectures to improve their generalization ability. We observed that when synaptic depression is added to the hidden layers of a neural network, it reduces the effect of changing background activity in the node activations. In addition, we show that when synaptic depression is included in a deep neural network trained for phoneme classification, the performance of the network improves under noisy conditions not included in the training phase. Our results suggest that more complete neuron models may further reduce the gap between the biological performance and artificial computing, resulting in networks that better generalize to novel signal conditions.

  3. A neural network based seafloor classification using acoustic backscatter

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.

    This paper presents a study results of the Artificial Neural Network (ANN) architectures [Self-Organizing Map (SOM) and Multi-Layer Perceptron (MLP)] using single beam echosounding data. The single beam echosounder, operable at 12 kHz, has been used...

  4. Neural Networks

    International Nuclear Information System (INIS)

    Smith, Patrick I.

    2003-01-01

    Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing

  5. A learning algorithm for oscillatory cellular neural networks.

    Science.gov (United States)

    Ho, C Y.; Kurokawa, H

    1999-07-01

    We present a cellular type oscillatory neural network for temporal segregation of stationary input patterns. The model comprises an array of locally connected neural oscillators with connections limited to a 4-connected neighborhood. The architecture is reminiscent of the well-known cellular neural network that consists of local connection for feature extraction. By means of a novel learning rule and an initialization scheme, global synchronization can be accomplished without incurring any erroneous synchrony among uncorrelated objects. Each oscillator comprises two mutually coupled neurons, and neurons share a piecewise-linear activation function characteristic. The dynamics of traditional oscillatory models is simplified by using only one plastic synapse, and the overall complexity for hardware implementation is reduced. Based on the connectedness of image segments, it is shown that global synchronization and desynchronization can be achieved by means of locally connected synapses, and this opens up a tremendous application potential for the proposed architecture. Furthermore, by using special grouping synapses it is demonstrated that temporal segregation of overlapping gray-level and color segments can also be achieved. Finally, simulation results show that the learning rule proposed circumvents the problem of component mismatches, and hence facilitates a large-scale integration.

  6. Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition.

    Science.gov (United States)

    Spoerer, Courtney J; McClure, Patrick; Kriegeskorte, Nikolaus

    2017-01-01

    Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and non-human primate brain. Here we investigate recurrent convolutional neural networks with bottom-up (B), lateral (L), and top-down (T) connections. Combining these types of connections yields four architectures (B, BT, BL, and BLT), which we systematically test and compare. We hypothesized that recurrent dynamics might improve recognition performance in the challenging scenario of partial occlusion. We introduce two novel occluded object recognition tasks to test the efficacy of the models, digit clutter (where multiple target digits occlude one another) and digit debris (where target digits are occluded by digit fragments). We find that recurrent neural networks outperform feedforward control models (approximately matched in parametric complexity) at recognizing objects, both in the absence of occlusion and in all occlusion conditions. Recurrent networks were also found to be more robust to the inclusion of additive Gaussian noise. Recurrent neural networks are better in two respects: (1) they are more neurobiologically realistic than their feedforward counterparts; (2) they are better in terms of their ability to recognize objects, especially under challenging conditions. This work shows that computer vision can benefit from using recurrent convolutional architectures and suggests that the ubiquitous recurrent connections in biological brains are essential for task performance.

  7. Neural codes of seeing architectural styles

    OpenAIRE

    Choo, Heeyoung; Nasar, Jack L.; Nikrahei, Bardia; Walther, Dirk B.

    2017-01-01

    Images of iconic buildings, such as the CN Tower, instantly transport us to specific places, such as Toronto. Despite the substantial impact of architectural design on people′s visual experience of built environments, we know little about its neural representation in the human brain. In the present study, we have found patterns of neural activity associated with specific architectural styles in several high-level visual brain regions, but not in primary visual cortex (V1). This finding sugges...

  8. A COMPARATIVE STUDY OF SYSTEM NETWORK ARCHITECTURE Vs DIGITAL NETWORK ARCHITECTURE

    OpenAIRE

    Seema; Mukesh Arya

    2011-01-01

    The efficient managing system of sources is mandatory for the successful running of any network. Here this paper describes the most popular network architectures one of developed by IBM, System Network Architecture (SNA) and other is Digital Network Architecture (DNA). As we know that the network standards and protocols are needed for the network developers as well as users. Some standards are The IEEE 802.3 standards (The Institute of Electrical and Electronics Engineers 1980) (LAN), IBM Sta...

  9. Information content of neural networks with self-control and variable activity

    International Nuclear Information System (INIS)

    Bolle, D.; Amari, S.I.; Dominguez Carreta, D.R.C.; Massolo, G.

    2001-01-01

    A self-control mechanism for the dynamics of neural networks with variable activity is discussed using a recursive scheme for the time evolution of the local field. It is based upon the introduction of a self-adapting time-dependent threshold as a function of both the neural and pattern activity in the network. This mechanism leads to an improvement of the information content of the network as well as an increase of the storage capacity and the basins of attraction. Different architectures are considered and the results are compared with numerical simulations

  10. Recognition of sign language gestures using neural networks

    Directory of Open Access Journals (Sweden)

    Simon Vamplew

    2007-04-01

    Full Text Available This paper describes the structure and performance of the SLARTI sign language recognition system developed at the University of Tasmania. SLARTI uses a modular architecture consisting of multiple feature-recognition neural networks and a nearest-neighbour classifier to recognise Australian sign language (Auslan hand gestures.

  11. Tests of track segment and vertex finding with neural networks

    International Nuclear Information System (INIS)

    Denby, B.; Lessner, E.; Lindsey, C.S.

    1990-04-01

    Feed forward neural networks have been trained, using back-propagation, to find the slopes of simulated track segments in a straw chamber and to find the vertex of tracks from both simulated and real events in a more conventional drift chamber geometry. Network architectures, training, and performance are presented. 12 refs., 7 figs

  12. Automatic target recognition using a feature-based optical neural network

    Science.gov (United States)

    Chao, Tien-Hsin

    1992-01-01

    An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.

  13. Dynamic Neural Fields as a Step Towards Cognitive Neuromorphic Architectures

    Directory of Open Access Journals (Sweden)

    Yulia eSandamirskaya

    2014-01-01

    Full Text Available Dynamic Field Theory (DFT is an established framework for modelling embodied cognition. In DFT, elementary cognitive functions such as memory formation, formation of grounded representations, attentional processes, decision making, adaptation, and learning emerge from neuronal dynamics. The basic computational element of this framework is a Dynamic Neural Field (DNF. Under constraints on the time-scale of the dynamics, the DNF is computationally equivalent to a soft winner-take-all (WTA network, which is considered one of the basic computational units in neuronal processing. Recently, it has been shown how a WTA network may be implemented in neuromorphic hardware, such as analogue Very Large Scale Integration (VLSI device. This paper leverages the relationship between DFT and soft WTA networks to systematically revise and integrate established DFT mechanisms that have previously been spread among different architectures. In addition, I also identify some novel computational and architectural mechanisms of DFT which may be implemented in neuromorphic VLSI devices using WTA networks as an intermediate computational layer. These specific mechanisms include the stabilization of working memory, the coupling of sensory systems to motor dynamics, intentionality, and autonomous learning. I further demonstrate how all these elements may be integrated into a unified architecture to generate behavior and autonomous learning.

  14. Distributed computing methodology for training neural networks in an image-guided diagnostic application.

    Science.gov (United States)

    Plagianakos, V P; Magoulas, G D; Vrahatis, M N

    2006-03-01

    Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

  15. High speed VLSI neural network for high energy physics

    NARCIS (Netherlands)

    Masa, P.; Masa, P.; Hoen, K.; Hoen, Klaas; Wallinga, Hans

    1994-01-01

    A CMOS neural network IC is discussed which was designed for very high speed applications. The parallel architecture, analog computing and digital weight storage provides unprecedented computing speed combined with ease of use. The circuit classifies up to 70 dimensional vectors within 20

  16. Function approximation of tasks by neural networks

    International Nuclear Information System (INIS)

    Gougam, L.A.; Chikhi, A.; Mekideche-Chafa, F.

    2008-01-01

    For several years now, neural network models have enjoyed wide popularity, being applied to problems of regression, classification and time series analysis. Neural networks have been recently seen as attractive tools for developing efficient solutions for many real world problems in function approximation. The latter is a very important task in environments where computation has to be based on extracting information from data samples in real world processes. In a previous contribution, we have used a well known simplified architecture to show that it provides a reasonably efficient, practical and robust, multi-frequency analysis. We have investigated the universal approximation theory of neural networks whose transfer functions are: sigmoid (because of biological relevance), Gaussian and two specified families of wavelets. The latter have been found to be more appropriate to use. The aim of the present contribution is therefore to use a m exican hat wavelet a s transfer function to approximate different tasks relevant and inherent to various applications in physics. The results complement and provide new insights into previously published results on this problem

  17. Parameter estimation in space systems using recurrent neural networks

    Science.gov (United States)

    Parlos, Alexander G.; Atiya, Amir F.; Sunkel, John W.

    1991-01-01

    The identification of time-varying parameters encountered in space systems is addressed, using artificial neural systems. A hybrid feedforward/feedback neural network, namely a recurrent multilayer perception, is used as the model structure in the nonlinear system identification. The feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of temporal variations in the system nonlinearities. The standard back-propagation-learning algorithm is modified and it is used for both the off-line and on-line supervised training of the proposed hybrid network. The performance of recurrent multilayer perceptron networks in identifying parameters of nonlinear dynamic systems is investigated by estimating the mass properties of a representative large spacecraft. The changes in the spacecraft inertia are predicted using a trained neural network, during two configurations corresponding to the early and late stages of the spacecraft on-orbit assembly sequence. The proposed on-line mass properties estimation capability offers encouraging results, though, further research is warranted for training and testing the predictive capabilities of these networks beyond nominal spacecraft operations.

  18. 3D multi-view convolutional neural networks for lung nodule classification

    Science.gov (United States)

    Kang, Guixia; Hou, Beibei; Zhang, Ningbo

    2017-01-01

    The 3D convolutional neural network (CNN) is able to make full use of the spatial 3D context information of lung nodules, and the multi-view strategy has been shown to be useful for improving the performance of 2D CNN in classifying lung nodules. In this paper, we explore the classification of lung nodules using the 3D multi-view convolutional neural networks (MV-CNN) with both chain architecture and directed acyclic graph architecture, including 3D Inception and 3D Inception-ResNet. All networks employ the multi-view-one-network strategy. We conduct a binary classification (benign and malignant) and a ternary classification (benign, primary malignant and metastatic malignant) on Computed Tomography (CT) images from Lung Image Database Consortium and Image Database Resource Initiative database (LIDC-IDRI). All results are obtained via 10-fold cross validation. As regards the MV-CNN with chain architecture, results show that the performance of 3D MV-CNN surpasses that of 2D MV-CNN by a significant margin. Finally, a 3D Inception network achieved an error rate of 4.59% for the binary classification and 7.70% for the ternary classification, both of which represent superior results for the corresponding task. We compare the multi-view-one-network strategy with the one-view-one-network strategy. The results reveal that the multi-view-one-network strategy can achieve a lower error rate than the one-view-one-network strategy. PMID:29145492

  19. Advanced approach to numerical forecasting using artificial neural networks

    Directory of Open Access Journals (Sweden)

    Michael Štencl

    2009-01-01

    Full Text Available Current global market is driven by many factors, such as the information age, the time and amount of information distributed by many data channels it is practically impossible analyze all kinds of incoming information flows and transform them to data with classical methods. New requirements could be met by using other methods. Once trained on patterns artificial neural networks can be used for forecasting and they are able to work with extremely big data sets in reasonable time. The patterns used for learning process are samples of past data. This paper uses Radial Basis Functions neural network in comparison with Multi Layer Perceptron network with Back-propagation learning algorithm on prediction task. The task works with simplified numerical time series and includes forty observations with prediction for next five observations. The main topic of the article is the identification of the main differences between used neural networks architectures together with numerical forecasting. Detected differences then verify on practical comparative example.

  20. A framework for plasticity implementation on the SpiNNaker neural architecture.

    Science.gov (United States)

    Galluppi, Francesco; Lagorce, Xavier; Stromatias, Evangelos; Pfeiffer, Michael; Plana, Luis A; Furber, Steve B; Benosman, Ryad B

    2014-01-01

    Many of the precise biological mechanisms of synaptic plasticity remain elusive, but simulations of neural networks have greatly enhanced our understanding of how specific global functions arise from the massively parallel computation of neurons and local Hebbian or spike-timing dependent plasticity rules. For simulating large portions of neural tissue, this has created an increasingly strong need for large scale simulations of plastic neural networks on special purpose hardware platforms, because synaptic transmissions and updates are badly matched to computing style supported by current architectures. Because of the great diversity of biological plasticity phenomena and the corresponding diversity of models, there is a great need for testing various hypotheses about plasticity before committing to one hardware implementation. Here we present a novel framework for investigating different plasticity approaches on the SpiNNaker distributed digital neural simulation platform. The key innovation of the proposed architecture is to exploit the reconfigurability of the ARM processors inside SpiNNaker, dedicating a subset of them exclusively to process synaptic plasticity updates, while the rest perform the usual neural and synaptic simulations. We demonstrate the flexibility of the proposed approach by showing the implementation of a variety of spike- and rate-based learning rules, including standard Spike-Timing dependent plasticity (STDP), voltage-dependent STDP, and the rate-based BCM rule. We analyze their performance and validate them by running classical learning experiments in real time on a 4-chip SpiNNaker board. The result is an efficient, modular, flexible and scalable framework, which provides a valuable tool for the fast and easy exploration of learning models of very different kinds on the parallel and reconfigurable SpiNNaker system.

  1. Neural networks and their potential application to nuclear power plants

    International Nuclear Information System (INIS)

    Uhrig, R.E.

    1991-01-01

    A network of artificial neurons, usually called an artificial neural network is a data processing system consisting of a number of 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 exhibit characteristics and capabilities not provided by any other technology. Neural networks may be designed so as to classify an input pattern as one of several predefined types or to create, as needed, categories or classes of system states which can be interpreted by a human operator. Neural networks have the ability to recognize patterns, even when the information comprising these patterns is noisy, sparse, or incomplete. Thus, systems of artificial neural networks show great promise for use in environments in which robust, fault-tolerant pattern recognition is necessary in a real-time mode, and in which the incoming data may be distorted or noisy. The application of neural networks, a rapidly evolving technology used extensively in defense applications, alone or in conjunction with other advanced technologies, to some of the problems of operating nuclear power plants has the potential to enhance the safety, reliability and operability of nuclear power plants. The potential applications of neural networking include, but are not limited to diagnosing specific abnormal conditions, identification of nonlinear dynamics and transients, detection of the change of mode of operation, control of temperature and pressure during start-up, signal validation, plant-wide monitoring using autoassociative neural networks, monitoring of check valves, modeling of the plant thermodynamics, emulation of core reload calculations, analysis of temporal sequences in NRC's ''licensee event reports,'' and monitoring of plant parameters

  2. Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status.

    Science.gov (United States)

    Korfiatis, Panagiotis; Kline, Timothy L; Lachance, Daniel H; Parney, Ian F; Buckner, Jan C; Erickson, Bradley J

    2017-10-01

    Predicting methylation of the O6-methylguanine methyltransferase (MGMT) gene status utilizing MRI imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare three different residual deep neural network (ResNet) architectures to evaluate their ability in predicting MGMT methylation status without the need for a distinct tumor segmentation step. We found that the ResNet50 (50 layers) architecture was the best performing model, achieving an accuracy of 94.90% (+/- 3.92%) for the test set (classification of a slice as no tumor, methylated MGMT, or non-methylated). ResNet34 (34 layers) achieved 80.72% (+/- 13.61%) while ResNet18 (18 layers) accuracy was 76.75% (+/- 20.67%). ResNet50 performance was statistically significantly better than both ResNet18 and ResNet34 architectures (p deep neural architectures can be used to predict molecular biomarkers from routine medical images.

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

    Science.gov (United States)

    Kmet', Tibor; Kmet'ová, Mária

    2009-09-01

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

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

    Science.gov (United States)

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

    2001-03-10

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

  5. Design and FPGA-implementation of multilayer neural networks with on-chip learning

    International Nuclear Information System (INIS)

    Haggag, S.S.M.Y

    2008-01-01

    Artificial Neural Networks (ANN) is used in many applications in the industry because of their parallel structure, high speed, and their ability to give easy solution to complicated problems. For example identifying the orange and apple in the sorting machine with neural network is easier than using image processing techniques to do the same thing. There are different software for designing, training, and testing the ANN, but in order to use the ANN in the industry, it should be implemented on hardware outside the computer. Neural networks are artificial systems inspired on the brain's cognitive behavior, which can learn tasks with some degree of complexity, such as signal processing, diagnosis, robotics, image processing, and pattern recognition. Many applications demand a high computing power and the traditional software implementation are not sufficient.This thesis presents design and FPGA implementation of Multilayer Neural Networks with On-chip learning in re-configurable hardware. Hardware implementation of neural network algorithm is very interesting due their high performance and they can easily be made parallel. The architecture proposed herein takes advantage of distinct data paths for the forward and backward propagation stages and a pipelined adaptation of the on- line backpropagation algorithm to significantly improve the performance of the learning phase. The architecture is easily scalable and able to cope with arbitrary network sizes with the same hardware. The implementation is targeted diagnosis of the Research Reactor accidents to avoid the risk of occurrence of a nuclear accident. The proposed designed circuits are implemented using Xilinx FPGA Chip XC40150xv and occupied 73% of Chip CLBs. It achieved 10.8 μs to take decision in the forward propagation compared with current software implemented of RPS which take 24 ms. The results show that the proposed architecture leads to significant speed up comparing to high end software solutions. On

  6. Temporal neural networks and transient analysis of complex engineering systems

    Science.gov (United States)

    Uluyol, Onder

    A theory is introduced for a multi-layered Local Output Gamma Feedback (LOGF) neural network within the paradigm of Locally-Recurrent Globally-Feedforward neural networks. It is developed for the identification, prediction, and control tasks of spatio-temporal systems and allows for the presentation of different time scales through incorporation of a gamma memory. It is initially applied to the tasks of sunspot and Mackey-Glass series prediction as benchmarks, then it is extended to the task of power level control of a nuclear reactor at different fuel cycle conditions. The developed LOGF neuron model can also be viewed as a Transformed Input and State (TIS) Gamma memory for neural network architectures for temporal processing. The novel LOGF neuron model extends the static neuron model by incorporating into it a short-term memory structure in the form of a digital gamma filter. A feedforward neural network made up of LOGF neurons can thus be used to model dynamic systems. A learning algorithm based upon the Backpropagation-Through-Time (BTT) approach is derived. It is applicable for training a general L-layer LOGF neural network. The spatial and temporal weights and parameters of the network are iteratively optimized for a given problem using the derived learning algorithm.

  7. Tomographic image reconstruction using Artificial Neural Networks

    International Nuclear Information System (INIS)

    Paschalis, P.; Giokaris, N.D.; Karabarbounis, A.; Loudos, G.K.; Maintas, D.; Papanicolas, C.N.; Spanoudaki, V.; Tsoumpas, Ch.; Stiliaris, E.

    2004-01-01

    A new image reconstruction technique based on the usage of an Artificial Neural Network (ANN) is presented. The most crucial factor in designing such a reconstruction system is the network architecture and the number of the input projections needed to reconstruct the image. Although the training phase requires a large amount of input samples and a considerable CPU time, the trained network is characterized by simplicity and quick response. The performance of this ANN is tested using several image patterns. It is intended to be used together with a phantom rotating table and the γ-camera of IASA for SPECT image reconstruction

  8. Measuring Customer Behavior with Deep Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Veaceslav Albu

    2016-03-01

    Full Text Available In this paper, we propose a neural network model for human emotion and gesture classification. We demonstrate that the proposed architecture represents an effective tool for real-time processing of customer's behavior for distributed on-land systems, such as information kiosks, automated cashiers and ATMs. The proposed approach combines most recent biometric techniques with the neural network approach for real-time emotion and behavioral analysis. In the series of experiments, emotions of human subjects were recorded, recognized, and analyzed to give statistical feedback of the overall emotions of a number of targets within a certain time frame. The result of the study allows automatic tracking of user’s behavior based on a limited set of observations.

  9. Approach to design neural cryptography: a generalized architecture and a heuristic rule.

    Science.gov (United States)

    Mu, Nankun; Liao, Xiaofeng; Huang, Tingwen

    2013-06-01

    Neural cryptography, a type of public key exchange protocol, is widely considered as an effective method for sharing a common secret key between two neural networks on public channels. How to design neural cryptography remains a great challenge. In this paper, in order to provide an approach to solve this challenge, a generalized network architecture and a significant heuristic rule are designed. The proposed generic framework is named as tree state classification machine (TSCM), which extends and unifies the existing structures, i.e., tree parity machine (TPM) and tree committee machine (TCM). Furthermore, we carefully study and find that the heuristic rule can improve the security of TSCM-based neural cryptography. Therefore, TSCM and the heuristic rule can guide us to designing a great deal of effective neural cryptography candidates, in which it is possible to achieve the more secure instances. Significantly, in the light of TSCM and the heuristic rule, we further expound that our designed neural cryptography outperforms TPM (the most secure model at present) on security. Finally, a series of numerical simulation experiments are provided to verify validity and applicability of our results.

  10. Raingauge-Based Rainfall Nowcasting with Artificial Neural Network

    Science.gov (United States)

    Liong, Shie-Yui; He, Shan

    2010-05-01

    Rainfall forecasting and nowcasting are of great importance, for instance, in real-time flood early warning systems. Long term rainfall forecasting demands global climate, land, and sea data, thus, large computing power and storage capacity are required. Rainfall nowcasting's computing requirement, on the other hand, is much less. Rainfall nowcasting may use data captured by radar and/or weather stations. This paper presents the application of Artificial Neural Network (ANN) on rainfall nowcasting using data observed at weather and/or rainfall stations. The study focuses on the North-East monsoon period (December, January and February) in Singapore. Rainfall and weather data from ten stations, between 2000 and 2006, were selected and divided into three groups for training, over-fitting test and validation of the ANN. Several neural network architectures were tried in the study. Two architectures, Backpropagation ANN and Group Method of Data Handling ANN, yielded better rainfall nowcasting, up to two hours, than the other architectures. The obtained rainfall nowcasts were then used by a catchment model to forecast catchment runoff. The results of runoff forecast are encouraging and promising.With ANN's high computational speed, the proposed approach may be deliverable for creating the real-time flood early warning system.

  11. Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

    Science.gov (United States)

    Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

    2017-04-10

    This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

  12. Comparison of four Adaboost algorithm based artificial neural networks in wind speed predictions

    International Nuclear Information System (INIS)

    Liu, Hui; Tian, Hong-qi; Li, Yan-fei; Zhang, Lei

    2015-01-01

    Highlights: • Four hybrid algorithms are proposed for the wind speed decomposition. • Adaboost algorithm is adopted to provide a hybrid training framework. • MLP neural networks are built to do the forecasting computation. • Four important network training algorithms are included in the MLP networks. • All the proposed hybrid algorithms are suitable for the wind speed predictions. - Abstract: The technology of wind speed prediction is important to guarantee the safety of wind power utilization. In this paper, four different hybrid methods are proposed for the high-precision multi-step wind speed predictions based on the Adaboost (Adaptive Boosting) algorithm and the MLP (Multilayer Perceptron) neural networks. In the hybrid Adaboost–MLP forecasting architecture, four important algorithms are adopted for the training and modeling of the MLP neural networks, including GD-ALR-BP algorithm, GDM-ALR-BP algorithm, CG-BP-FR algorithm and BFGS algorithm. The aim of the study is to investigate the promoted forecasting percentages of the MLP neural networks by the Adaboost algorithm’ optimization under various training algorithms. The hybrid models in the performance comparison include Adaboost–GD-ALR-BP–MLP, Adaboost–GDM-ALR-BP–MLP, Adaboost–CG-BP-FR–MLP, Adaboost–BFGS–MLP, GD-ALR-BP–MLP, GDM-ALR-BP–MLP, CG-BP-FR–MLP and BFGS–MLP. Two experimental results show that: (1) the proposed hybrid Adaboost–MLP forecasting architecture is effective for the wind speed predictions; (2) the Adaboost algorithm has promoted the forecasting performance of the MLP neural networks considerably; (3) among the proposed Adaboost–MLP forecasting models, the Adaboost–CG-BP-FR–MLP model has the best performance; and (4) the improved percentages of the MLP neural networks by the Adaboost algorithm decrease step by step with the following sequence of training algorithms as: GD-ALR-BP, GDM-ALR-BP, CG-BP-FR and BFGS

  13. Artificial neural network based modelling approach for municipal solid waste gasification in a fluidized bed reactor.

    Science.gov (United States)

    Pandey, Daya Shankar; Das, Saptarshi; Pan, Indranil; Leahy, James J; Kwapinski, Witold

    2016-12-01

    In this paper, multi-layer feed forward neural networks are used to predict the lower heating value of gas (LHV), lower heating value of gasification products including tars and entrained char (LHV p ) and syngas yield during gasification of municipal solid waste (MSW) during gasification in a fluidized bed reactor. These artificial neural networks (ANNs) with different architectures are trained using the Levenberg-Marquardt (LM) back-propagation algorithm and a cross validation is also performed to ensure that the results generalise to other unseen datasets. A rigorous study is carried out on optimally choosing the number of hidden layers, number of neurons in the hidden layer and activation function in a network using multiple Monte Carlo runs. Nine input and three output parameters are used to train and test various neural network architectures in both multiple output and single output prediction paradigms using the available experimental datasets. The model selection procedure is carried out to ascertain the best network architecture in terms of predictive accuracy. The simulation results show that the ANN based methodology is a viable alternative which can be used to predict the performance of a fluidized bed gasifier. Copyright © 2016 Elsevier Ltd. All rights reserved.

  14. New backpropagation algorithm with type-2 fuzzy weights for neural networks

    CERN Document Server

    Gaxiola, Fernando; Valdez, Fevrier

    2016-01-01

    In this book a neural network learning method with type-2 fuzzy weight adjustment is proposed. The mathematical analysis of the proposed learning method architecture and the adaptation of type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that handle weight adaptation and especially fuzzy weights. The internal operation of the neuron is changed to work with two internal calculations for the activation function to obtain two results as outputs of the proposed method. Simulation results and a comparative study among monolithic neural networks, neural network with type-1 fuzzy weights and neural network with type-2 fuzzy weights are presented to illustrate the advantages of the proposed method. The proposed approach is based on recent methods that handle adaptation of weights using fuzzy logic of type-1 and type-2. The proposed approach is applied to a cases of prediction for the Mackey-Glass (for ô=17) and Dow-Jones time series, and recognition of person with iris bi...

  15. Encoding Time in Feedforward Trajectories of a Recurrent Neural Network Model.

    Science.gov (United States)

    Hardy, N F; Buonomano, Dean V

    2018-02-01

    Brain activity evolves through time, creating trajectories of activity that underlie sensorimotor processing, behavior, and learning and memory. Therefore, understanding the temporal nature of neural dynamics is essential to understanding brain function and behavior. In vivo studies have demonstrated that sequential transient activation of neurons can encode time. However, it remains unclear whether these patterns emerge from feedforward network architectures or from recurrent networks and, furthermore, what role network structure plays in timing. We address these issues using a recurrent neural network (RNN) model with distinct populations of excitatory and inhibitory units. Consistent with experimental data, a single RNN could autonomously produce multiple functionally feedforward trajectories, thus potentially encoding multiple timed motor patterns lasting up to several seconds. Importantly, the model accounted for Weber's law, a hallmark of timing behavior. Analysis of network connectivity revealed that efficiency-a measure of network interconnectedness-decreased as the number of stored trajectories increased. Additionally, the balance of excitation (E) and inhibition (I) shifted toward excitation during each unit's activation time, generating the prediction that observed sequential activity relies on dynamic control of the E/I balance. Our results establish for the first time that the same RNN can generate multiple functionally feedforward patterns of activity as a result of dynamic shifts in the E/I balance imposed by the connectome of the RNN. We conclude that recurrent network architectures account for sequential neural activity, as well as for a fundamental signature of timing behavior: Weber's law.

  16. Single-Iteration Learning Algorithm for Feed-Forward Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

    Barhen, J.; Cogswell, R.; Protopopescu, V.

    1999-07-31

    A new methodology for neural learning is presented, whereby only a single iteration is required to train a feed-forward network with near-optimal results. To this aim, a virtual input layer is added to the multi-layer architecture. The virtual input layer is connected to the nominal input layer by a specird nonlinear transfer function, and to the fwst hidden layer by regular (linear) synapses. A sequence of alternating direction singular vrdue decompositions is then used to determine precisely the inter-layer synaptic weights. This algorithm exploits the known separability of the linear (inter-layer propagation) and nonlinear (neuron activation) aspects of information &ansfer within a neural network.

  17. Phylogenetic convolutional neural networks in metagenomics.

    Science.gov (United States)

    Fioravanti, Diego; Giarratano, Ylenia; Maggio, Valerio; Agostinelli, Claudio; Chierici, Marco; Jurman, Giuseppe; Furlanello, Cesare

    2018-03-08

    Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user.

  18. Predicting physical time series using dynamic ridge polynomial neural networks.

    Directory of Open Access Journals (Sweden)

    Dhiya Al-Jumeily

    Full Text Available Forecasting naturally occurring phenomena is a common problem in many domains of science, and this has been addressed and investigated by many scientists. The importance of time series prediction stems from the fact that it has wide range of applications, including control systems, engineering processes, environmental systems and economics. From the knowledge of some aspects of the previous behaviour of the system, the aim of the prediction process is to determine or predict its future behaviour. In this paper, we consider a novel application of a higher order polynomial neural network architecture called Dynamic Ridge Polynomial Neural Network that combines the properties of higher order and recurrent neural networks for the prediction of physical time series. In this study, four types of signals have been used, which are; The Lorenz attractor, mean value of the AE index, sunspot number, and heat wave temperature. The simulation results showed good improvements in terms of the signal to noise ratio in comparison to a number of higher order and feedforward neural networks in comparison to the benchmarked techniques.

  19. Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

    Directory of Open Access Journals (Sweden)

    Yoonsik Shim

    2016-10-01

    Full Text Available We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP. The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

  20. Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

    Science.gov (United States)

    Shim, Yoonsik; Philippides, Andrew; Staras, Kevin; Husbands, Phil

    2016-10-01

    We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

  1. Predicting Electrocardiogram and Arterial Blood Pressure Waveforms with Different Echo State Network Architectures

    Science.gov (United States)

    2014-11-01

    Predicting Electrocardiogram and Arterial Blood Pressure Waveforms with Different Echo State Network Architectures Allan Fong, MS1,3, Ranjeev...the medical staff in Intensive Care Units. The ability to predict electrocardiogram and arterial blood pressure waveforms can potentially help the...type of neural network for mining, understanding, and predicting electrocardiogram and arterial blood pressure waveforms. Several network

  2. Optimizing Semantic Pointer Representations for Symbol-Like Processing in Spiking Neural Networks.

    Science.gov (United States)

    Gosmann, Jan; Eliasmith, Chris

    2016-01-01

    The Semantic Pointer Architecture (SPA) is a proposal of specifying the computations and architectural elements needed to account for cognitive functions. By means of the Neural Engineering Framework (NEF) this proposal can be realized in a spiking neural network. However, in any such network each SPA transformation will accumulate noise. By increasing the accuracy of common SPA operations, the overall network performance can be increased considerably. As well, the representations in such networks present a trade-off between being able to represent all possible values and being only able to represent the most likely values, but with high accuracy. We derive a heuristic to find the near-optimal point in this trade-off. This allows us to improve the accuracy of common SPA operations by up to 25 times. Ultimately, it allows for a reduction of neuron number and a more efficient use of both traditional and neuromorphic hardware, which we demonstrate here.

  3. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices.

    Science.gov (United States)

    Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

    2017-01-01

    In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

  4. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

    Science.gov (United States)

    Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

    2017-01-01

    In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures. PMID:29066942

  5. Chaotic diagonal recurrent neural network

    International Nuclear Information System (INIS)

    Wang Xing-Yuan; Zhang Yi

    2012-01-01

    We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks. (interdisciplinary physics and related areas of science and technology)

  6. Direct Adaptive Aircraft Control Using Dynamic Cell Structure Neural Networks

    Science.gov (United States)

    Jorgensen, Charles C.

    1997-01-01

    A Dynamic Cell Structure (DCS) Neural Network was developed which learns topology representing networks (TRNS) of F-15 aircraft aerodynamic stability and control derivatives. The network is integrated into a direct adaptive tracking controller. The combination produces a robust adaptive architecture capable of handling multiple accident and off- nominal flight scenarios. This paper describes the DCS network and modifications to the parameter estimation procedure. The work represents one step towards an integrated real-time reconfiguration control architecture for rapid prototyping of new aircraft designs. Performance was evaluated using three off-line benchmarks and on-line nonlinear Virtual Reality simulation. Flight control was evaluated under scenarios including differential stabilator lock, soft sensor failure, control and stability derivative variations, and air turbulence.

  7. Characterization of Radar Signals Using Neural Networks

    Science.gov (United States)

    1990-12-01

    e***e*e*eeeeeeeeeeeesseeeeeese*eee*e*e************s /* Function Name: load.input.ptterns Number: 4.1 /* Description: This function determines wether ...XSE.last.layer Number: 8.5 */ /* Description: The function determines wether to backpropate the *f /* parameter by the sigmoidal or linear update...Sigmoidal Function," Mathematics of Control, Signals and Systems, 2:303-314 (March 1989). 6. Dayhoff, Judith E. Neural Network Architectures. New York: Van

  8. Seafloor classification using acoustic backscatter echo-waveform - Artificial neural network applications

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.; Mahale, V.; Navelkar, G.S.; Desai, R.G.P.

    In this paper seafloor classifications system based on artificial neural network (ANN) has been designed. The ANN architecture employed here is a combination of Self Organizing Feature Map (SOFM) and Linear Vector Quantization (LVQ1). Currently...

  9. Mixed Analog/Digital Matrix-Vector Multiplier for Neural Network Synapses

    DEFF Research Database (Denmark)

    Lehmann, Torsten; Bruun, Erik; Dietrich, Casper

    1996-01-01

    In this work we present a hardware efficient matrix-vector multiplier architecture for artificial neural networks with digitally stored synapse strengths. We present a novel technique for manipulating bipolar inputs based on an analog two's complements method and an accurate current rectifier...

  10. Nonlinear neural network for hemodynamic model state and input estimation using fMRI data

    KAUST Repository

    Karam, Ayman M.

    2014-11-01

    Originally inspired by biological neural networks, artificial neural networks (ANNs) are powerful mathematical tools that can solve complex nonlinear problems such as filtering, classification, prediction and more. This paper demonstrates the first successful implementation of ANN, specifically nonlinear autoregressive with exogenous input (NARX) networks, to estimate the hemodynamic states and neural activity from simulated and measured real blood oxygenation level dependent (BOLD) signals. Blocked and event-related BOLD data are used to test the algorithm on real experiments. The proposed method is accurate and robust even in the presence of signal noise and it does not depend on sampling interval. Moreover, the structure of the NARX networks is optimized to yield the best estimate with minimal network architecture. The results of the estimated neural activity are also discussed in terms of their potential use.

  11. Fundamental study on the interpretation technique for 3-D MT data using neural networks. 2; Neural network wo mochiita sanjigen MT ho data kaishaku gijutsu ni kansuru kisoteki kenkyu. 2

    Energy Technology Data Exchange (ETDEWEB)

    Fukuoka, K; Kobayashi, T [OYO Corp., Tokyo (Japan); Mogi, T [Kyushu University, Fukuoka (Japan). Faculty of Engineering; Spichak, V

    1997-10-22

    Behavior of neural networks relative to noise and the constitution of an optimum network are studied for the construction of a 3-D MT data interpretation system using neural networks. In the study, the relationship is examined between the noise level of educational data and the noise level of the neural network to be constructed. After examination it is found that the neural network is effective in interpreting data whose noise level is the same as that of educational data; it cannot correctly interpret data that it has not met in the educational stage even if such data is free of noise; that the optimum number of neurons in a hidden layer is approximately 40 in a network architecture using the current system; and that the neuron gain function enhances recognition capability when a logistic function is used in the hidden layer and a linear function is used in the output layer. 2 refs., 7 figs., 2 tabs.

  12. Bidirectional Joint Representation Learning with Symmetrical Deep Neural Networks for Multimodal and Crossmodal Applications

    OpenAIRE

    Vukotic , Vedran; Raymond , Christian; Gravier , Guillaume

    2016-01-01

    International audience; Common approaches to problems involving multiple modalities (classification, retrieval, hyperlinking, etc.) are early fusion of the initial modalities and crossmodal translation from one modality to the other. Recently, deep neural networks, especially deep autoencoders, have proven promising both for crossmodal translation and for early fusion via multimodal embedding. In this work, we propose a flexible cross-modal deep neural network architecture for multimodal and ...

  13. Improved head direction command classification using an optimised Bayesian neural network.

    Science.gov (United States)

    Nguyen, Son T; Nguyen, Hung T; Taylor, Philip B; Middleton, James

    2006-01-01

    Assistive technologies have recently emerged to improve the quality of life of severely disabled people by enhancing their independence in daily activities. Since many of those individuals have limited or non-existing control from the neck downward, alternative hands-free input modalities have become very important for these people to access assistive devices. In hands-free control, head movement has been proved to be a very effective user interface as it can provide a comfortable, reliable and natural way to access the device. Recently, neural networks have been shown to be useful not only for real-time pattern recognition but also for creating user-adaptive models. Since multi-layer perceptron neural networks trained using standard back-propagation may cause poor generalisation, the Bayesian technique has been proposed to improve the generalisation and robustness of these networks. This paper describes the use of Bayesian neural networks in developing a hands-free wheelchair control system. The experimental results show that with the optimised architecture, classification Bayesian neural networks can detect head commands of wheelchair users accurately irrespective to their levels of injuries.

  14. QCD-Aware Neural Networks for Jet Physics

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    Recent progress in applying machine learning for jet physics has been built upon an analogy between calorimeters and images. In this work, we present a novel class of recursive neural networks built instead upon an analogy between QCD and natural languages. In the analogy, four-momenta are like words and the clustering history of sequential recombination jet algorithms is like the parsing of a sentence. Our approach works directly with the four-momenta of a variable-length set of particles, and the jet-based neural network topology varies on an event-by-event basis. Our experiments highlight the flexibility of our method for building task-specific jet embeddings and show that recursive architectures are significantly more accurate and data efficient than previous image-based networks. We extend the analogy from individual jets (sentences) to full events (paragraphs), and show for the first time an event-level classifier operating...

  15. Neural networks

    International Nuclear Information System (INIS)

    Denby, Bruce; Lindsey, Clark; Lyons, Louis

    1992-01-01

    The 1980s saw a tremendous renewal of interest in 'neural' information processing systems, or 'artificial neural networks', among computer scientists and computational biologists studying cognition. Since then, the growth of interest in neural networks in high energy physics, fueled by the need for new information processing technologies for the next generation of high energy proton colliders, can only be described as explosive

  16. Random noise effects in pulse-mode digital multilayer neural networks.

    Science.gov (United States)

    Kim, Y C; Shanblatt, M A

    1995-01-01

    A pulse-mode digital multilayer neural network (DMNN) based on stochastic computing techniques is implemented with simple logic gates as basic computing elements. The pulse-mode signal representation and the use of simple logic gates for neural operations lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Algebraic neural operations are replaced by stochastic processes using pseudorandom pulse sequences. The distributions of the results from the stochastic processes are approximated using the hypergeometric distribution. Synaptic weights and neuron states are represented as probabilities and estimated as average pulse occurrence rates in corresponding pulse sequences. A statistical model of the noise (error) is developed to estimate the relative accuracy associated with stochastic computing in terms of mean and variance. Computational differences are then explained by comparison to deterministic neural computations. DMNN feedforward architectures are modeled in VHDL using character recognition problems as testbeds. Computational accuracy is analyzed, and the results of the statistical model are compared with the actual simulation results. Experiments show that the calculations performed in the DMNN are more accurate than those anticipated when Bernoulli sequences are assumed, as is common in the literature. Furthermore, the statistical model successfully predicts the accuracy of the operations performed in the DMNN.

  17. Chinese Sentence Classification Based on Convolutional Neural Network

    Science.gov (United States)

    Gu, Chengwei; Wu, Ming; Zhang, Chuang

    2017-10-01

    Sentence classification is one of the significant issues in Natural Language Processing (NLP). Feature extraction is often regarded as the key point for natural language processing. Traditional ways based on machine learning can not take high level features into consideration, such as Naive Bayesian Model. The neural network for sentence classification can make use of contextual information to achieve greater results in sentence classification tasks. In this paper, we focus on classifying Chinese sentences. And the most important is that we post a novel architecture of Convolutional Neural Network (CNN) to apply on Chinese sentence classification. In particular, most of the previous methods often use softmax classifier for prediction, we embed a linear support vector machine to substitute softmax in the deep neural network model, minimizing a margin-based loss to get a better result. And we use tanh as an activation function, instead of ReLU. The CNN model improve the result of Chinese sentence classification tasks. Experimental results on the Chinese news title database validate the effectiveness of our model.

  18. Proceedings of the workshop cum symposium on applications of neural networks in nuclear science and industry

    International Nuclear Information System (INIS)

    1993-01-01

    The Workshop cum Symposium on Application of Neural Networks in Nuclear Science and Industry was held at Bombay during November 24-26. 1993. The past decade has seen many important advances in the design and technology of artificial neural networks in research and industry. Neural networks is an interdisciplinary field covering a broad spectrum of applications in surveillance, diagnosis of nuclear power plants, nuclear spectroscopy, speech and written text recognition, robotic control, signal processing etc. The objective of the symposium was to promote awareness of advances in neural network research and applications. It was also aimed at conducting the review of the present status and giving direction for future technological developments. Contributed papers have been organized into the following groups: a) neural network architectures, learning algorithms and modelling, b) computer vision and image processing, c) signal processing, d) neural networks and fuzzy systems, e) nuclear applications and f) neural networks and allied applications. Papers relevant to INIS are indexed separately. (M.K.V.)

  19. Neural Network Machine Learning and Dimension Reduction for Data Visualization

    Science.gov (United States)

    Liles, Charles A.

    2014-01-01

    Neural network machine learning in computer science is a continuously developing field of study. Although neural network models have been developed which can accurately predict a numeric value or nominal classification, a general purpose method for constructing neural network architecture has yet to be developed. Computer scientists are often forced to rely on a trial-and-error process of developing and improving accurate neural network models. In many cases, models are constructed from a large number of input parameters. Understanding which input parameters have the greatest impact on the prediction of the model is often difficult to surmise, especially when the number of input variables is very high. This challenge is often labeled the "curse of dimensionality" in scientific fields. However, techniques exist for reducing the dimensionality of problems to just two dimensions. Once a problem's dimensions have been mapped to two dimensions, it can be easily plotted and understood by humans. The ability to visualize a multi-dimensional dataset can provide a means of identifying which input variables have the highest effect on determining a nominal or numeric output. Identifying these variables can provide a better means of training neural network models; models can be more easily and quickly trained using only input variables which appear to affect the outcome variable. The purpose of this project is to explore varying means of training neural networks and to utilize dimensional reduction for visualizing and understanding complex datasets.

  20. On the use of a pruning prior for neural networks

    DEFF Research Database (Denmark)

    Goutte, Cyril

    1996-01-01

    We address the problem of using a regularization prior that prunes unnecessary weights in a neural network architecture. This prior provides a convenient alternative to traditional weight-decay. Two examples are studied to support this method and illustrate its use. First we use the sunspots...

  1. Neutron spectrometry and dosimetry by means of evolutive neural networks

    International Nuclear Information System (INIS)

    Ortiz R, J.M.; Martinez B, M.R.; Vega C, H.R.

    2008-01-01

    The artificial neural networks and the genetic algorithms are two relatively new areas of research, which have been subject to a growing interest during the last years. Both models are inspired by the nature, however, the neural networks are interested in the learning of a single individual, which is defined as fenotypic learning, while the evolutionary algorithms are interested in the adaptation of a population to a changing environment, that which is defined as genotypic learning. Recently, the use of the technology of neural networks has been applied with success in the area of the nuclear sciences, mainly in the areas of neutron spectrometry and dosimetry. The structure (network topology), as well as the learning parameters of a neural network, are factors that contribute in a significant way with the acting of the same one, however, it has been observed that the investigators in this area, carry out the selection of the network parameters through the essay and error technique, that which produces neural networks of poor performance and low generalization capacity. From the revised sources, it has been observed that the use of the evolutionary algorithms, seen as search techniques, it has allowed him to be possible to evolve and to optimize different properties of the neural networks, just as the initialization of the synaptic weights, the network architecture or the training algorithms without the human intervention. The objective of the present work is focused in analyzing the intersection of the neural networks and the evolutionary algorithms, analyzing like it is that the same ones can be used to help in the design processes and training of a neural network, this is, in the good selection of the structural parameters and of network learning, improving its generalization capacity, in such way that the same one is able to reconstruct in an efficient way neutron spectra and to calculate equivalent doses starting from the counting rates of a Bonner sphere

  2. Classification of remotely sensed data using OCR-inspired neural network techniques. [Optical Character Recognition

    Science.gov (United States)

    Kiang, Richard K.

    1992-01-01

    Neural networks have been applied to classifications of remotely sensed data with some success. To improve the performance of this approach, an examination was made of how neural networks are applied to the optical character recognition (OCR) of handwritten digits and letters. A three-layer, feedforward network, along with techniques adopted from OCR, was used to classify Landsat-4 Thematic Mapper data. Good results were obtained. To overcome the difficulties that are characteristic of remote sensing applications and to attain significant improvements in classification accuracy, a special network architecture may be required.

  3. Selection of hadronic W-decays in DELPHI with feed forward neural networks - An update

    CERN Document Server

    Becks, K H; Müller, U; Wahlen, H

    2003-01-01

    Since 1998 feed forward neural networks have been successfully applied to select candidates of hadronic W-decays measured at different center of mass-energies by the DELPHI collaboration at the Large Electron Positron collider at CERN. To prepare the final publication, the neural network was adapted to all center of mass- energies. Detailed studies were performed concerning the level of preselection, the choice of network parameters and especially of the network architecture. The number of hidden nodes was optimized by testing different pruning methods. All studies and results will be discussed.

  4. Selection of hadronic W-decays in DELPHI with feed forward neural networks - an update

    International Nuclear Information System (INIS)

    Becks, K.-H.; Drees, J.; Mueller, U.; Wahlen, H.

    2003-01-01

    Since 1998 feed forward neural networks have been successfully applied to select candidates of hadronic W-decays measured at different center of mass-energies by the DELPHI collaboration at the Large Electron Positron collider at CERN. To prepare the final publication, the neural network was adapted to all center of mass-energies. Detailed studies were performed concerning the level of preselection, the choice of network parameters and especially of the network architecture. The number of hidden nodes was optimized by testing different pruning methods. All studies and results will be discussed

  5. Neural network modelling of planform geometry of headland-bay beaches

    Science.gov (United States)

    Iglesias, G.; López, I.; Castro, A.; Carballo, R.

    2009-02-01

    The shoreline of beaches in the lee of coastal salients or man-made structures, usually known as headland-bay beaches, has a distinctive curvature; wave fronts curve as a result of wave diffraction at the headland and in turn cause the shoreline to bend. The ensuing curved planform is of great interest both as a peculiar landform and in the context of engineering projects in which it is necessary to predict how a coastal structure will affect the sandy shoreline in its lee. A number of empirical models have been put forward, each based on a specific equation. A novel approach, based on the application of artificial neural networks, is presented in this work. Unlike the conventional method, no particular equation of the planform is embedded in the model. Instead, it is the model itself that learns about the problem from a series of examples of headland-bay beaches (the training set) and thereafter applies this self-acquired knowledge to other cases (the test set) for validation. Twenty-three headland-bay beaches from around the world were selected, of which sixteen and seven make up the training and test sets, respectively. As there is no well-developed theory for deciding upon the most convenient neural network architecture to deal with a particular data set, an experimental study was conducted in which ten different architectures with one and two hidden neuron layers and five training algorithms - 50 different options combining network architecture and training algorithm - were compared. Each of these options was implemented, trained and tested in order to find the best-performing approach for modelling the planform of headland-bay beaches. Finally, the selected neural network model was compared with a state-of-the-art planform model and was shown to outperform it.

  6. Large-scale simulations of plastic neural networks on neuromorphic hardware

    Directory of Open Access Journals (Sweden)

    James Courtney Knight

    2016-04-01

    Full Text Available SpiNNaker is a digital, neuromorphic architecture designed for simulating large-scale spiking neural networks at speeds close to biological real-time. Rather than using bespoke analog or digital hardware, the basic computational unit of a SpiNNaker system is a general-purpose ARM processor, allowing it to be programmed to simulate a wide variety of neuron and synapse models. This flexibility is particularly valuable in the study of biological plasticity phenomena. A recently proposed learning rule based on the Bayesian Confidence Propagation Neural Network (BCPNN paradigm offers a generic framework for modeling the interaction of different plasticity mechanisms using spiking neurons. However, it can be computationally expensive to simulate large networks with BCPNN learning since it requires multiple state variables for each synapse, each of which needs to be updated every simulation time-step. We discuss the trade-offs in efficiency and accuracy involved in developing an event-based BCPNN implementation for SpiNNaker based on an analytical solution to the BCPNN equations, and detail the steps taken to fit this within the limited computational and memory resources of the SpiNNaker architecture. We demonstrate this learning rule by learning temporal sequences of neural activity within a recurrent attractor network which we simulate at scales of up to 20000 neurons and 51200000 plastic synapses: the largest plastic neural network ever to be simulated on neuromorphic hardware. We also run a comparable simulation on a Cray XC-30 supercomputer system and find that, if it is to match the run-time of our SpiNNaker simulation, the super computer system uses approximately more power. This suggests that cheaper, more power efficient neuromorphic systems are becoming useful discovery tools in the study of plasticity in large-scale brain models.

  7. Neural networks for aircraft control

    Science.gov (United States)

    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.

  8. Modelling and Forecasting Cruise Tourism Demand to İzmir by Different Artificial Neural Network Architectures

    Directory of Open Access Journals (Sweden)

    Murat Cuhadar

    2014-03-01

    Full Text Available Abstract Cruise ports emerged as an important sector for the economy of Turkey bordered on three sides by water. Forecasting cruise tourism demand ensures better planning, efficient preparation at the destination and it is the basis for elaboration of future plans. In the recent years, new techniques such as; artificial neural networks were employed for developing of the predictive models to estimate tourism demand. In this study, it is aimed to determine the forecasting method that provides the best performance when compared the forecast accuracy of Multi-layer Perceptron (MLP, Radial Basis Function (RBF and Generalized Regression neural network (GRNN to estimate the monthly inbound cruise tourism demand to İzmir via the method giving best results. We used the total number of foreign cruise tourist arrivals as a measure of inbound cruise tourism demand and monthly cruise tourist arrivals to İzmir Cruise Port in the period of January 2005 ‐December 2013 were utilized to appropriate model. Experimental results showed that radial basis function (RBF neural network outperforms multi-layer perceptron (MLP and the generalised regression neural networks (GRNN in terms of forecasting accuracy. By the means of the obtained RBF neural network model, it has been forecasted the monthly inbound cruise tourism demand to İzmir for the year 2014.

  9. Semantic Segmentation of Convolutional Neural Network for Supervised Classification of Multispectral Remote Sensing

    Science.gov (United States)

    Xue, L.; Liu, C.; Wu, Y.; Li, H.

    2018-04-01

    Semantic segmentation is a fundamental research in remote sensing image processing. Because of the complex maritime environment, the classification of roads, vegetation, buildings and water from remote Sensing Imagery is a challenging task. Although the neural network has achieved excellent performance in semantic segmentation in the last years, there are a few of works using CNN for ground object segmentation and the results could be further improved. This paper used convolution neural network named U-Net, its structure has a contracting path and an expansive path to get high resolution output. In the network , We added BN layers, which is more conducive to the reverse pass. Moreover, after upsampling convolution , we add dropout layers to prevent overfitting. They are promoted to get more precise segmentation results. To verify this network architecture, we used a Kaggle dataset. Experimental results show that U-Net achieved good performance compared with other architectures, especially in high-resolution remote sensing imagery.

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

    Science.gov (United States)

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

    2017-07-18

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

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

    Science.gov (United States)

    Wilson, Edward

    1995-01-01

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

  12. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

    Directory of Open Access Journals (Sweden)

    Tayfun Gokmen

    2017-10-01

    Full Text Available In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU devices to convolutional neural networks (CNNs. We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

  13. The Analysis of User Behaviour of a Network Management Training Tool using a Neural Network

    Directory of Open Access Journals (Sweden)

    Helen Donelan

    2005-10-01

    Full Text Available A novel method for the analysis and interpretation of data that describes the interaction between trainee network managers and a network management training tool is presented. A simulation based approach is currently being used to train network managers, through the use of a simulated network. The motivation is to provide a tool for exposing trainees to a life like situation without disrupting a live network. The data logged by this system describes the detailed interaction between trainee network manager and simulated network. The work presented here provides an analysis of this interaction data that enables an assessment of the capabilities of the trainee network manager as well as an understanding of how the network management tasks are being approached. A neural network architecture is implemented in order to perform an exploratory data analysis of the interaction data. The neural network employs a novel form of continuous self-organisation to discover key features in the data and thus provide new insights into the learning and teaching strategies employed.

  14. Artificial neural network models for biomass gasification in fluidized bed gasifiers

    DEFF Research Database (Denmark)

    Puig Arnavat, Maria; Hernández, J. Alfredo; Bruno, Joan Carles

    2013-01-01

    Artificial neural networks (ANNs) have been applied for modeling biomass gasification process in fluidized bed reactors. Two architectures of ANNs models are presented; one for circulating fluidized bed gasifiers (CFB) and the other for bubbling fluidized bed gasifiers (BFB). Both models determine...

  15. Maximum entropy methods for extracting the learned features of deep neural networks.

    Science.gov (United States)

    Finnegan, Alex; Song, Jun S

    2017-10-01

    New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

  16. Detecting and diagnosing SSME faults using an autoassociative neural network topology

    Science.gov (United States)

    Ali, M.; Dietz, W. E.; Kiech, E. L.

    1989-01-01

    An effort is underway at the University of Tennessee Space Institute to develop diagnostic expert system methodologies based on the analysis of patterns of behavior of physical mechanisms. In this approach, fault diagnosis is conceptualized as the mapping or association of patterns of sensor data to patterns representing fault conditions. Neural networks are being investigated as a means of storing and retrieving fault scenarios. Neural networks offer several powerful features in fault diagnosis, including (1) general pattern matching capabilities, (2) resistance to noisy input data, (3) the ability to be trained by example, and (4) the potential for implementation on parallel computer architectures. This paper presents (1) an autoassociative neural network topology, i.e. the network input and output is identical when properly trained, and hence learning is unsupervised; (2) the training regimen used; and (3) the response of the system to inputs representing both previously observed and unkown fault scenarios. The effects of noise on the integrity of the diagnosis are also evaluated.

  17. Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks

    Science.gov (United States)

    Ray, Loye Lynn

    2014-01-01

    The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…

  18. Neural-Network Quantum States, String-Bond States, and Chiral Topological States

    Science.gov (United States)

    Glasser, Ivan; Pancotti, Nicola; August, Moritz; Rodriguez, Ivan D.; Cirac, J. Ignacio

    2018-01-01

    Neural-network quantum states have recently been introduced as an Ansatz for describing the wave function of quantum many-body systems. We show that there are strong connections between neural-network quantum states in the form of restricted Boltzmann machines and some classes of tensor-network states in arbitrary dimensions. In particular, we demonstrate that short-range restricted Boltzmann machines are entangled plaquette states, while fully connected restricted Boltzmann machines are string-bond states with a nonlocal geometry and low bond dimension. These results shed light on the underlying architecture of restricted Boltzmann machines and their efficiency at representing many-body quantum states. String-bond states also provide a generic way of enhancing the power of neural-network quantum states and a natural generalization to systems with larger local Hilbert space. We compare the advantages and drawbacks of these different classes of states and present a method to combine them together. This allows us to benefit from both the entanglement structure of tensor networks and the efficiency of neural-network quantum states into a single Ansatz capable of targeting the wave function of strongly correlated systems. While it remains a challenge to describe states with chiral topological order using traditional tensor networks, we show that, because of their nonlocal geometry, neural-network quantum states and their string-bond-state extension can describe a lattice fractional quantum Hall state exactly. In addition, we provide numerical evidence that neural-network quantum states can approximate a chiral spin liquid with better accuracy than entangled plaquette states and local string-bond states. Our results demonstrate the efficiency of neural networks to describe complex quantum wave functions and pave the way towards the use of string-bond states as a tool in more traditional machine-learning applications.

  19. Predicting recurrent aphthous ulceration using genetic algorithms-optimized neural networks

    Directory of Open Access Journals (Sweden)

    Najla S Dar-Odeh

    2010-05-01

    Full Text Available Najla S Dar-Odeh1, Othman M Alsmadi2, Faris Bakri3, Zaer Abu-Hammour2, Asem A Shehabi3, Mahmoud K Al-Omiri1, Shatha M K Abu-Hammad4, Hamzeh Al-Mashni4, Mohammad B Saeed4, Wael Muqbil4, Osama A Abu-Hammad1 1Faculty of Dentistry, 2Faculty of Engineering and Technology, 3Faculty of Medicine, University of Jordan, Amman, Jordan; 4Dental Department, University of Jordan Hospital, Amman, JordanObjective: To construct and optimize a neural network that is capable of predicting the occurrence of recurrent aphthous ulceration (RAU based on a set of appropriate input data.Participants and methods: Artificial neural networks (ANN software employing genetic algorithms to optimize the architecture neural networks was used. Input and output data of 86 participants (predisposing factors and status of the participants with regards to recurrent aphthous ulceration were used to construct and train the neural networks. The optimized neural networks were then tested using untrained data of a further 10 participants.Results: The optimized neural network, which produced the most accurate predictions for the presence or absence of recurrent aphthous ulceration was found to employ: gender, hematological (with or without ferritin and mycological data of the participants, frequency of tooth brushing, and consumption of vegetables and fruits.Conclusions: Factors appearing to be related to recurrent aphthous ulceration and appropriate for use as input data to construct ANNs that predict recurrent aphthous ulceration were found to include the following: gender, hemoglobin, serum vitamin B12, serum ferritin, red cell folate, salivary candidal colony count, frequency of tooth brushing, and the number of fruits or vegetables consumed daily.Keywords: artifical neural networks, recurrent, aphthous ulceration, ulcer

  20. Hidden neural networks

    DEFF Research Database (Denmark)

    Krogh, Anders Stærmose; Riis, Søren Kamaric

    1999-01-01

    A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability...... parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum...... likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear...

  1. Modeling of methane emissions using artificial neural network approach

    Directory of Open Access Journals (Sweden)

    Stamenković Lidija J.

    2015-01-01

    Full Text Available The aim of this study was to develop a model for forecasting CH4 emissions at the national level, using Artificial Neural Networks (ANN with broadly available sustainability, economical and industrial indicators as their inputs. ANN modeling was performed using two different types of architecture; a Backpropagation Neural Network (BPNN and a General Regression Neural Network (GRNN. A conventional multiple linear regression (MLR model was also developed in order to compare model performance and assess which model provides the best results. ANN and MLR models were developed and tested using the same annual data for 20 European countries. The ANN model demonstrated very good performance, significantly better than the MLR model. It was shown that a forecast of CH4 emissions at the national level using the ANN model can be made successfully and accurately for a future period of up to two years, thereby opening the possibility to apply such a modeling technique which can be used to support the implementation of sustainable development strategies and environmental management policies. [Projekat Ministarstva nauke Republike Srbije, br. 172007

  2. Gap Filling of Daily Sea Levels by Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Lyubka Pashova

    2013-06-01

    Full Text Available In the recent years, intelligent methods as artificial neural networks are successfully applied for data analysis from different fields of the geosciences. One of the encountered practical problems is the availability of gaps in the time series that prevent their comprehensive usage for the scientific and practical purposes. The article briefly describes two types of the artificial neural network (ANN architectures - Feed-Forward Backpropagation (FFBP and recurrent Echo state network (ESN. In some cases, the ANN can be used as an alternative on the traditional methods, to fill in missing values in the time series. We have been conducted several experiments to fill the missing values of daily sea levels spanning a 5-years period using both ANN architectures. A multiple linear regression for the same purpose has been also applied. The sea level data are derived from the records of the tide gauge Burgas, which is located on the western Black Sea coast. The achieved results have shown that the performance of ANN models is better than that of the classical one and they are very promising for the real-time interpolation of missing data in the time series.

  3. An Artificial Neural Network for Data Forecasting Purposes

    Directory of Open Access Journals (Sweden)

    Catalina Lucia COCIANU

    2015-01-01

    Full Text Available Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data.

  4. Invariant moments based convolutional neural networks for image analysis

    Directory of Open Access Journals (Sweden)

    Vijayalakshmi G.V. Mahesh

    2017-01-01

    Full Text Available The paper proposes a method using convolutional neural network to effectively evaluate the discrimination between face and non face patterns, gender classification using facial images and facial expression recognition. The novelty of the method lies in the utilization of the initial trainable convolution kernels coefficients derived from the zernike moments by varying the moment order. The performance of the proposed method was compared with the convolutional neural network architecture that used random kernels as initial training parameters. The multilevel configuration of zernike moments was significant in extracting the shape information suitable for hierarchical feature learning to carry out image analysis and classification. Furthermore the results showed an outstanding performance of zernike moment based kernels in terms of the computation time and classification accuracy.

  5. Towards a networkArchitecture

    DEFF Research Database (Denmark)

    Rüdiger, Bjarne; Tournay, Bruno

    2001-01-01

    Planche, bidrag til DAL-konkurrencen. Hvor industrien har været inspirationen for udviklingen af den moderne arkitektur, er IT det tekniske og æstetiske grundlag for den spirende NetworkArchitecture. Computeren og netværker af computerne er således mere end en metafor for NetworkArchitecture....... NetworkArchitecture består af intelligente byggekomponenter forbundet med hinanden i et netværk og i interaktion med omgivelser....

  6. Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks

    OpenAIRE

    Khalifa, Nour Eldeen M.; Taha, Mohamed Hamed N.; Hassanien, Aboul Ella; Selim, I. M.

    2017-01-01

    In this paper, a deep convolutional neural network architecture for galaxies classification is presented. The galaxy can be classified based on its features into main three categories Elliptical, Spiral, and Irregular. The proposed deep galaxies architecture consists of 8 layers, one main convolutional layer for features extraction with 96 filters, followed by two principles fully connected layers for classification. It is trained over 1356 images and achieved 97.272% in testing accuracy. A c...

  7. Recurrent Neural Network Applications for Astronomical Time Series

    Science.gov (United States)

    Protopapas, Pavlos

    2017-06-01

    The benefits of good predictive models in astronomy lie in early event prediction systems and effective resource allocation. Current time series methods applicable to regular time series have not evolved to generalize for irregular time series. In this talk, I will describe two Recurrent Neural Network methods, Long Short-Term Memory (LSTM) and Echo State Networks (ESNs) for predicting irregular time series. Feature engineering along with a non-linear modeling proved to be an effective predictor. For noisy time series, the prediction is improved by training the network on error realizations using the error estimates from astronomical light curves. In addition to this, we propose a new neural network architecture to remove correlation from the residuals in order to improve prediction and compensate for the noisy data. Finally, I show how to set hyperparameters for a stable and performant solution correctly. In this work, we circumvent this obstacle by optimizing ESN hyperparameters using Bayesian optimization with Gaussian Process priors. This automates the tuning procedure, enabling users to employ the power of RNN without needing an in-depth understanding of the tuning procedure.

  8. Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

    Directory of Open Access Journals (Sweden)

    Chernoded Andrey

    2017-01-01

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

  9. Joint multiple fully connected convolutional neural network with extreme learning machine for hepatocellular carcinoma nuclei grading.

    Science.gov (United States)

    Li, Siqi; Jiang, Huiyan; Pang, Wenbo

    2017-05-01

    Accurate cell grading of cancerous tissue pathological image is of great importance in medical diagnosis and treatment. This paper proposes a joint multiple fully connected convolutional neural network with extreme learning machine (MFC-CNN-ELM) architecture for hepatocellular carcinoma (HCC) nuclei grading. First, in preprocessing stage, each grayscale image patch with the fixed size is obtained using center-proliferation segmentation (CPS) method and the corresponding labels are marked under the guidance of three pathologists. Next, a multiple fully connected convolutional neural network (MFC-CNN) is designed to extract the multi-form feature vectors of each input image automatically, which considers multi-scale contextual information of deep layer maps sufficiently. After that, a convolutional neural network extreme learning machine (CNN-ELM) model is proposed to grade HCC nuclei. Finally, a back propagation (BP) algorithm, which contains a new up-sample method, is utilized to train MFC-CNN-ELM architecture. The experiment comparison results demonstrate that our proposed MFC-CNN-ELM has superior performance compared with related works for HCC nuclei grading. Meanwhile, external validation using ICPR 2014 HEp-2 cell dataset shows the good generalization of our MFC-CNN-ELM architecture. Copyright © 2017 Elsevier Ltd. All rights reserved.

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

    Science.gov (United States)

    Chao, Tien-Hsin; Stoner, William W.

    1993-01-01

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

  11. Autoshaped choice in artificial neural networks: implications for behavioral economics and neuroeconomics.

    Science.gov (United States)

    Burgos, José E; García-Leal, Óscar

    2015-05-01

    An existing neural network model of conditioning was used to simulate autoshaped choice. In this phenomenon, pigeons first receive an autoshaping procedure with two keylight stimuli X and Y separately paired with food in a forward-delay manner, intermittently for X and continuously for Y. Then pigeons receive unreinforced choice test trials of X and Y concurrently present. Most pigeons choose Y. This preference for a more valuable response alternative is a form of economic behavior that makes the phenomenon relevant to behavioral economics. The phenomenon also suggests a role for Pavlovian contingencies in economic behavior. The model used, in contrast to others, predicts autoshaping and automaintenance, so it is uniquely positioned to predict autoshaped choice. The model also contemplates neural substrates of economic behavior in neuroeconomics, such as dopaminergic and hippocampal systems. A feedforward neural network architecture was designed to simulate a neuroanatomical differentiation between two environment-behavior relations X-R1 and Y-R2, [corrected] where R1 and R2 denote two different emitted responses (not unconditionally elicited by the reward). Networks with this architecture received a training protocol that simulated an autoshaped-choice procedure. Most networks simulated the phenomenon. Implications for behavioral economics and neuroeconomics, limitations, and the issue of model appraisal are discussed. Copyright © 2015 Elsevier B.V. All rights reserved.

  12. Modelling and prediction for chaotic fir laser attractor using rational function neural network.

    Science.gov (United States)

    Cho, S

    2001-02-01

    Many real-world systems such as irregular ECG signal, volatility of currency exchange rate and heated fluid reaction exhibit highly complex nonlinear characteristic known as chaos. These chaotic systems cannot be retreated satisfactorily using linear system theory due to its high dimensionality and irregularity. This research focuses on prediction and modelling of chaotic FIR (Far InfraRed) laser system for which the underlying equations are not given. This paper proposed a method for prediction and modelling a chaotic FIR laser time series using rational function neural network. Three network architectures, TDNN (Time Delayed Neural Network), RBF (radial basis function) network and the RF (rational function) network, are also presented. Comparisons between these networks performance show the improvements introduced by the RF network in terms of a decrement in network complexity and better ability of predictability.

  13. Biological neural networks as model systems for designing future parallel processing computers

    Science.gov (United States)

    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.

  14. Hybrid Neural Network Approach Based Tool for the Modelling of Photovoltaic Panels

    Directory of Open Access Journals (Sweden)

    Antonino Laudani

    2015-01-01

    Full Text Available A hybrid neural network approach based tool for identifying the photovoltaic one-diode model is presented. The generalization capabilities of neural networks are used together with the robustness of the reduced form of one-diode model. Indeed, from the studies performed by the authors and the works present in the literature, it was found that a direct computation of the five parameters via multiple inputs and multiple outputs neural network is a very difficult task. The reduced form consists in a series of explicit formulae for the support to the neural network that, in our case, is aimed at predicting just two parameters among the five ones identifying the model: the other three parameters are computed by reduced form. The present hybrid approach is efficient from the computational cost point of view and accurate in the estimation of the five parameters. It constitutes a complete and extremely easy tool suitable to be implemented in a microcontroller based architecture. Validations are made on about 10000 PV panels belonging to the California Energy Commission database.

  15. Recurrent Artificial Neural Networks and Finite State Natural Language Processing.

    Science.gov (United States)

    Moisl, Hermann

    It is argued that pessimistic assessments of the adequacy of artificial neural networks (ANNs) for natural language processing (NLP) on the grounds that they have a finite state architecture are unjustified, and that their adequacy in this regard is an empirical issue. First, arguments that counter standard objections to finite state NLP on the…

  16. Exploiting Hidden Layer Responses of Deep Neural Networks for Language Recognition

    Science.gov (United States)

    2016-09-08

    Target Languages Arabic (ara) Egyptian , Iraqi, Levantine, Maghrebi,Modern Standard Chinese (chi) Cantonese, Mandarin, Min, Wu English (eng) British...Frame-by-frame DNN classification x1 x2 x3 xT-­1xT Figure 1: Frame-by-frame DNN Language Identification Figure 1 shows the architecture of the DNN...compare direct DNN system with proposed DNN I-vector system, we trained a single neural network to classify all 20 languages. The architecture of this

  17. PRED-CLASS: cascading neural networks for generalized protein classification and genome-wide applications

    OpenAIRE

    Pasquier, Claude; Promponas, Vasilis; Hamodrakas, Stavros

    2009-01-01

    International audience; A cascading system of hierarchical, artificial neural networks (named PRED-CLASS) is presented for the generalized classification of proteins into four distinct classes-transmembrane, fibrous, globular, and mixed-from information solely encoded in their amino acid sequences. The architecture of the individual component networks is kept very simple, reducing the number of free parameters (network synaptic weights) for faster training, improved generalization, and the av...

  18. Brain states recognition during visual perception by means of artificial neural network in the different EEG frequency ranges

    Science.gov (United States)

    Musatov, V. Yu.; Runnova, A. E.; Andreev, A. V.; Zhuravlev, M. O.

    2018-04-01

    In the present paper, the possibility of classification by artificial neural networks of a certain architecture of ambiguous images is investigated using the example of the Necker cube from the experimentally obtained EEG recording data of several operators. The possibilities of artificial neural network classification of ambiguous images are investigated in the different frequency ranges of EEG recording signals.

  19. Modified-hybrid optical neural network filter for multiple object recognition within cluttered scenes

    Science.gov (United States)

    Kypraios, Ioannis; Young, Rupert C. D.; Chatwin, Chris R.

    2009-08-01

    Motivated by the non-linear interpolation and generalization abilities of the hybrid optical neural network filter between the reference and non-reference images of the true-class object we designed the modifiedhybrid optical neural network filter. We applied an optical mask to the hybrid optical neural network's filter input. The mask was built with the constant weight connections of a randomly chosen image included in the training set. The resulted design of the modified-hybrid optical neural network filter is optimized for performing best in cluttered scenes of the true-class object. Due to the shift invariance properties inherited by its correlator unit the filter can accommodate multiple objects of the same class to be detected within an input cluttered image. Additionally, the architecture of the neural network unit of the general hybrid optical neural network filter allows the recognition of multiple objects of different classes within the input cluttered image by modifying the output layer of the unit. We test the modified-hybrid optical neural network filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. The filter is shown to exhibit with a single pass over the input data simultaneously out-of-plane rotation, shift invariance and good clutter tolerance. It is able to successfully detect and classify correctly the true-class objects within background clutter for which there has been no previous training.

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

    Science.gov (United States)

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

    2016-01-01

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

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

    Directory of Open Access Journals (Sweden)

    Yongcheng Li

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

  2. An Artificial Neural Networks Approach to Estimate Occupational Accident: A National Perspective for Turkey

    Directory of Open Access Journals (Sweden)

    Hüseyin Ceylan

    2014-01-01

    Full Text Available Occupational accident estimation models were developed by using artificial neural networks (ANNs for Turkey. Using these models the number of occupational accidents and death and permanent incapacity numbers resulting from occupational accidents were estimated for Turkey until the year of 2025 by the three different scenarios. In the development of the models, insured workers, workplace, occupational accident, death, and permanent incapacity values were used as model parameters with data between 1970 and 2012. 2-5-1 neural network architecture was selected as the best network architecture. Sigmoid was used in hidden layers and linear function was used at output layer. The feed forward back propagation algorithm was used to train the network. In order to obtain a useful model, the network was trained between 1970 and 1999 to estimate the values of 2000 to 2012. The result was compared with the real values and it was seen that it is applicable for this aim. The performances of all developed models were evaluated using mean absolute percent errors (MAPE, mean absolute errors (MAE, and root mean square errors (RMSE.

  3. Application of Artificial Neural Network to Predict the use of Runway at Juanda International Airport

    Science.gov (United States)

    Putra, J. C. P.; Safrilah

    2017-06-01

    Artificial neural network approaches are useful to solve many complicated problems. It solves a number of problems in various areas such as engineering, medicine, business, manufacturing, etc. This paper presents an application of artificial neural network to predict a runway capacity at Juanda International Airport. An artificial neural network model of backpropagation and multi-layer perceptron is adopted to this research to learning process of runway capacity at Juanda International Airport. The results indicate that the training data is successfully recognizing the certain pattern of runway use at Juanda International Airport. Whereas, testing data indicate vice versa. Finally, it can be concluded that the approach of uniformity data and network architecture is the critical part to determine the accuracy of prediction results.

  4. Incidents Prediction in Road Junctions Using Artificial Neural Networks

    Science.gov (United States)

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

    2018-05-01

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

  5. A Neutral-Network-Fusion Architecture for Automatic Extraction of Oceanographic Features from Satellite Remote Sensing Imagery

    National Research Council Canada - National Science Library

    Askari, Farid

    1999-01-01

    This report describes an approach for automatic feature detection from fusion of remote sensing imagery using a combination of neural network architecture and the Dempster-Shafer (DS) theory of evidence...

  6. Application of artificial neural networks to evaluate weld defects of nuclear components

    International Nuclear Information System (INIS)

    Amin, E.S.

    2007-01-01

    Artificial neural networks (ANNs) are computational representations based on the biological neural architecture of the brain. ANNs have been successfully applied to a wide range of engineering and scientific applications, such as signal, image processing and data analysis. Although Radiographic testing is widely used for welding defects, it is unsuccessful in identifying some welding defects because of the nature of image formation and quality. Neoteric algorithms have been used for the purpose of weld defects identifications in radiographic images to replace the expert knowledge. The application of artificial neural networks in noise detection of radiographic films is used. Radial Basis (RB) and learning vector quantization (LVQ) were applied. The method shows good performance in weld defects recognition and classification problems.

  7. Radiometric calibration of digital cameras using neural networks

    Science.gov (United States)

    Grunwald, Michael; Laube, Pascal; Schall, Martin; Umlauf, Georg; Franz, Matthias O.

    2017-08-01

    Digital cameras are used in a large variety of scientific and industrial applications. For most applications, the acquired data should represent the real light intensity per pixel as accurately as possible. However, digital cameras are subject to physical, electronic and optical effects that lead to errors and noise in the raw image. Temperature- dependent dark current, read noise, optical vignetting or different sensitivities of individual pixels are examples of such effects. The purpose of radiometric calibration is to improve the quality of the resulting images by reducing the influence of the various types of errors on the measured data and thus improving the quality of the overall application. In this context, we present a specialized neural network architecture for radiometric calibration of digital cameras. Neural networks are used to learn a temperature- and exposure-dependent mapping from observed gray-scale values to true light intensities for each pixel. In contrast to classical at-fielding, neural networks have the potential to model nonlinear mappings which allows for accurately capturing the temperature dependence of the dark current and for modeling cameras with nonlinear sensitivities. Both scenarios are highly relevant in industrial applications. The experimental comparison of our network approach to classical at-fielding shows a consistently higher reconstruction quality, also for linear cameras. In addition, the calibration is faster than previous machine learning approaches based on Gaussian processes.

  8. Filtering and spectral processing of 1-D signals using cellular neural networks

    NARCIS (Netherlands)

    Moreira-Tamayo, O.; Pineda de Gyvez, J.

    1996-01-01

    This paper presents cellular neural networks (CNN) for one-dimensional discrete signal processing. Although CNN has been extensively used in image processing applications, little has been done for 1-dimensional signal processing. We propose a novel CNN architecture to carry out these tasks. This

  9. GPU implementation of Bayesian neural network construction for data-intensive applications

    International Nuclear Information System (INIS)

    Perry, Michelle; Meyer-Baese, Anke; Prosper, Harrison B

    2014-01-01

    We describe a graphical processing unit (GPU) implementation of the Hybrid Markov Chain Monte Carlo (HMC) method for training Bayesian Neural Networks (BNN). Our implementation uses NVIDIA's parallel computing architecture, CUDA. We briefly review BNNs and the HMC method and we describe our implementations and give preliminary results.

  10. Convolutional neural networks for segmentation and object detection of human semen

    DEFF Research Database (Denmark)

    Nissen, Malte Stær; Krause, Oswin; Almstrup, Kristian

    2017-01-01

    We compare a set of convolutional neural network (CNN) architectures for the task of segmenting and detecting human sperm cells in an image taken from a semen sample. In contrast to previous work, samples are not stained or washed to allow for full sperm quality analysis, making analysis harder due...

  11. Characterizing root response phenotypes by neural network analysis

    OpenAIRE

    Hatzig, Sarah V.; Schiessl, Sarah; Stahl, Andreas; Snowdon, Rod J.

    2015-01-01

    Roots play an immediate role as the interface for water acquisition. To improve sustainability in low-water environments, breeders of major crops must therefore pay closer attention to advantageous root phenotypes; however, the complexity of root architecture in response to stress can be difficult to quantify. Here, the Sholl method, an established technique from neurobiology used for the characterization of neural network anatomy, was adapted to more adequately describe root responses to osm...

  12. High-Performance Neural Networks for Visual Object Classification

    OpenAIRE

    Cireşan, Dan C.; Meier, Ueli; Masci, Jonathan; Gambardella, Luca M.; Schmidhuber, Jürgen

    2011-01-01

    We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates of 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better ...

  13. One-day-ahead streamflow forecasting via super-ensembles of several neural network architectures based on the Multi-Level Diversity Model

    Science.gov (United States)

    Brochero, Darwin; Hajji, Islem; Pina, Jasson; Plana, Queralt; Sylvain, Jean-Daniel; Vergeynst, Jenna; Anctil, Francois

    2015-04-01

    Theories about generalization error with ensembles are mainly based on the diversity concept, which promotes resorting to many members of different properties to support mutually agreeable decisions. Kuncheva (2004) proposed the Multi Level Diversity Model (MLDM) to promote diversity in model ensembles, combining different data subsets, input subsets, models, parameters, and including a combiner level in order to optimize the final ensemble. This work tests the hypothesis about the minimisation of the generalization error with ensembles of Neural Network (NN) structures. We used the MLDM to evaluate two different scenarios: (i) ensembles from a same NN architecture, and (ii) a super-ensemble built by a combination of sub-ensembles of many NN architectures. The time series used correspond to the 12 basins of the MOdel Parameter Estimation eXperiment (MOPEX) project that were used by Duan et al. (2006) and Vos (2013) as benchmark. Six architectures are evaluated: FeedForward NN (FFNN) trained with the Levenberg Marquardt algorithm (Hagan et al., 1996), FFNN trained with SCE (Duan et al., 1993), Recurrent NN trained with a complex method (Weins et al., 2008), Dynamic NARX NN (Leontaritis and Billings, 1985), Echo State Network (ESN), and leak integrator neuron (L-ESN) (Lukosevicius and Jaeger, 2009). Each architecture performs separately an Input Variable Selection (IVS) according to a forward stepwise selection (Anctil et al., 2009) using mean square error as objective function. Post-processing by Predictor Stepwise Selection (PSS) of the super-ensemble has been done following the method proposed by Brochero et al. (2011). IVS results showed that the lagged stream flow, lagged precipitation, and Standardized Precipitation Index (SPI) (McKee et al., 1993) were the most relevant variables. They were respectively selected as one of the firsts three selected variables in 66, 45, and 28 of the 72 scenarios. A relationship between aridity index (Arora, 2002) and NN

  14. Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition.

    Science.gov (United States)

    Lin, Tsung-Yu; RoyChowdhury, Aruni; Maji, Subhransu

    2017-07-04

    We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs are related to orderless texture representations built on deep features but can be trained in an end-to-end manner. Our most accurate model obtains 84.1%, 79.4%, 84.5% and 91.3% per-image accuracy on the Caltech-UCSD birds [66], NABirds [63], FGVC aircraft [42], and Stanford cars [33] dataset respectively and runs at 30 frames-per-second on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn.

  15. Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS

    Directory of Open Access Journals (Sweden)

    Christopher Bergmeir

    2012-01-01

    Full Text Available Neural networks are important standard machine learning procedures for classification and regression. We describe the R package RSNNS that provides a convenient interface to the popular Stuttgart Neural Network Simulator SNNS. The main features are (a encapsulation of the relevant SNNS parts in a C++ class, for sequential and parallel usage of different networks, (b accessibility of all of the SNNSalgorithmic functionality from R using a low-level interface, and (c a high-level interface for convenient, R-style usage of many standard neural network procedures. The package also includes functions for visualization and analysis of the models and the training procedures, as well as functions for data input/output from/to the original SNNSfile formats.

  16. Neural Networks: Implementations and Applications

    OpenAIRE

    Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.

    1996-01-01

    Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas

  17. Heterogeneous network architectures

    DEFF Research Database (Denmark)

    Christiansen, Henrik Lehrmann

    2006-01-01

    is flexibility. This thesis investigates such heterogeneous network architectures and how to make them flexible. A survey of algorithms for network design is presented, and it is described how using heuristics can increase the speed. A hierarchical, MPLS based network architecture is described......Future networks will be heterogeneous! Due to the sheer size of networks (e.g., the Internet) upgrades cannot be instantaneous and thus heterogeneity appears. This means that instead of trying to find the olution, networks hould be designed as being heterogeneous. One of the key equirements here...... and it is discussed that it is advantageous to heterogeneous networks and illustrated by a number of examples. Modeling and simulation is a well-known way of doing performance evaluation. An approach to event-driven simulation of communication networks is presented and mixed complexity modeling, which can simplify...

  18. Forecasting short-term data center network traffic load with convolutional neural networks

    Science.gov (United States)

    Ordozgoiti, Bruno; Gómez-Canaval, Sandra

    2018-01-01

    Efficient resource management in data centers is of central importance to content service providers as 90 percent of the network traffic is expected to go through them in the coming years. In this context we propose the use of convolutional neural networks (CNNs) to forecast short-term changes in the amount of traffic crossing a data center network. This value is an indicator of virtual machine activity and can be utilized to shape the data center infrastructure accordingly. The behaviour of network traffic at the seconds scale is highly chaotic and therefore traditional time-series-analysis approaches such as ARIMA fail to obtain accurate forecasts. We show that our convolutional neural network approach can exploit the non-linear regularities of network traffic, providing significant improvements with respect to the mean absolute and standard deviation of the data, and outperforming ARIMA by an increasingly significant margin as the forecasting granularity is above the 16-second resolution. In order to increase the accuracy of the forecasting model, we exploit the architecture of the CNNs using multiresolution input distributed among separate channels of the first convolutional layer. We validate our approach with an extensive set of experiments using a data set collected at the core network of an Internet Service Provider over a period of 5 months, totalling 70 days of traffic at the one-second resolution. PMID:29408936

  19. Forecasting short-term data center network traffic load with convolutional neural networks.

    Science.gov (United States)

    Mozo, Alberto; Ordozgoiti, Bruno; Gómez-Canaval, Sandra

    2018-01-01

    Efficient resource management in data centers is of central importance to content service providers as 90 percent of the network traffic is expected to go through them in the coming years. In this context we propose the use of convolutional neural networks (CNNs) to forecast short-term changes in the amount of traffic crossing a data center network. This value is an indicator of virtual machine activity and can be utilized to shape the data center infrastructure accordingly. The behaviour of network traffic at the seconds scale is highly chaotic and therefore traditional time-series-analysis approaches such as ARIMA fail to obtain accurate forecasts. We show that our convolutional neural network approach can exploit the non-linear regularities of network traffic, providing significant improvements with respect to the mean absolute and standard deviation of the data, and outperforming ARIMA by an increasingly significant margin as the forecasting granularity is above the 16-second resolution. In order to increase the accuracy of the forecasting model, we exploit the architecture of the CNNs using multiresolution input distributed among separate channels of the first convolutional layer. We validate our approach with an extensive set of experiments using a data set collected at the core network of an Internet Service Provider over a period of 5 months, totalling 70 days of traffic at the one-second resolution.

  20. Neural electrical activity and neural network growth.

    Science.gov (United States)

    Gafarov, F M

    2018-05-01

    The development of central and peripheral neural system depends in part on the emergence of the correct functional connectivity in its input and output pathways. Now it is generally accepted that molecular factors guide neurons to establish a primary scaffold that undergoes activity-dependent refinement for building a fully functional circuit. However, a number of experimental results obtained recently shows that the neuronal electrical activity plays an important role in the establishing of initial interneuronal connections. Nevertheless, these processes are rather difficult to study experimentally, due to the absence of theoretical description and quantitative parameters for estimation of the neuronal activity influence on growth in neural networks. In this work we propose a general framework for a theoretical description of the activity-dependent neural network growth. The theoretical description incorporates a closed-loop growth model in which the neural activity can affect neurite outgrowth, which in turn can affect neural activity. We carried out the detailed quantitative analysis of spatiotemporal activity patterns and studied the relationship between individual cells and the network as a whole to explore the relationship between developing connectivity and activity patterns. The model, developed in this work will allow us to develop new experimental techniques for studying and quantifying the influence of the neuronal activity on growth processes in neural networks and may lead to a novel techniques for constructing large-scale neural networks by self-organization. Copyright © 2018 Elsevier Ltd. All rights reserved.

  1. Standard representation and unified stability analysis for dynamic artificial neural network models.

    Science.gov (United States)

    Kim, Kwang-Ki K; Patrón, Ernesto Ríos; Braatz, Richard D

    2018-02-01

    An overview is provided of dynamic artificial neural network models (DANNs) for nonlinear dynamical system identification and control problems, and convex stability conditions are proposed that are less conservative than past results. The three most popular classes of dynamic artificial neural network models are described, with their mathematical representations and architectures followed by transformations based on their block diagrams that are convenient for stability and performance analyses. Classes of nonlinear dynamical systems that are universally approximated by such models are characterized, which include rigorous upper bounds on the approximation errors. A unified framework and linear matrix inequality-based stability conditions are described for different classes of dynamic artificial neural network models that take additional information into account such as local slope restrictions and whether the nonlinearities within the DANNs are odd. A theoretical example shows reduced conservatism obtained by the conditions. Copyright © 2017. Published by Elsevier Ltd.

  2. An artificial neural network approach to laser-induced breakdown spectroscopy quantitative analysis

    International Nuclear Information System (INIS)

    D’Andrea, Eleonora; Pagnotta, Stefano; Grifoni, Emanuela; Lorenzetti, Giulia; Legnaioli, Stefano; Palleschi, Vincenzo; Lazzerini, Beatrice

    2014-01-01

    The usual approach to laser-induced breakdown spectroscopy (LIBS) quantitative analysis is based on the use of calibration curves, suitably built using appropriate reference standards. More recently, statistical methods relying on the principles of artificial neural networks (ANN) are increasingly used. However, ANN analysis is often used as a ‘black box’ system and the peculiarities of the LIBS spectra are not exploited fully. An a priori exploration of the raw data contained in the LIBS spectra, carried out by a neural network to learn what are the significant areas of the spectrum to be used for a subsequent neural network delegated to the calibration, is able to throw light upon important information initially unknown, although already contained within the spectrum. This communication will demonstrate that an approach based on neural networks specially taylored for dealing with LIBS spectra would provide a viable, fast and robust method for LIBS quantitative analysis. This would allow the use of a relatively limited number of reference samples for the training of the network, with respect to the current approaches, and provide a fully automatizable approach for the analysis of a large number of samples. - Highlights: • A methodological approach to neural network analysis of LIBS spectra is proposed. • The architecture of the network and the number of inputs are optimized. • The method is tested on bronze samples already analyzed using a calibration-free LIBS approach. • The results are validated, compared and discussed

  3. Iterative free-energy optimization for recurrent neural networks (INFERNO)

    Science.gov (United States)

    2017-01-01

    The intra-parietal lobe coupled with the Basal Ganglia forms a working memory that demonstrates strong planning capabilities for generating robust yet flexible neuronal sequences. Neurocomputational models however, often fails to control long range neural synchrony in recurrent spiking networks due to spontaneous activity. As a novel framework based on the free-energy principle, we propose to see the problem of spikes’ synchrony as an optimization problem of the neurons sub-threshold activity for the generation of long neuronal chains. Using a stochastic gradient descent, a reinforcement signal (presumably dopaminergic) evaluates the quality of one input vector to move the recurrent neural network to a desired activity; depending on the error made, this input vector is strengthened to hill-climb the gradient or elicited to search for another solution. This vector can be learned then by one associative memory as a model of the basal-ganglia to control the recurrent neural network. Experiments on habit learning and on sequence retrieving demonstrate the capabilities of the dual system to generate very long and precise spatio-temporal sequences, above two hundred iterations. Its features are applied then to the sequential planning of arm movements. In line with neurobiological theories, we discuss its relevance for modeling the cortico-basal working memory to initiate flexible goal-directed neuronal chains of causation and its relation to novel architectures such as Deep Networks, Neural Turing Machines and the Free-Energy Principle. PMID:28282439

  4. Deep learning with convolutional neural networks: a resource for the control of robotic prosthetic hands via electromyography

    Directory of Open Access Journals (Sweden)

    Manfredo Atzori

    2016-09-01

    Full Text Available Motivation: Natural control methods based on surface electromyography and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications and commercial prostheses are in the best case capable to offer natural control for only a few movements. Objective: In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its capabilities for the natural control of robotic hands via surface electromyography by providing a baseline on a large number of intact and amputated subjects. Methods: We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 hand amputated subjects. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets.Results: The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods but lower than the results obtained with the best reference methods in our tests. Significance: The results show that convolutional neural networks with a very simple architecture can produce accuracy comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters can be fundamental for the analysis of surface electromyography data. Finally, the results suggest that deeper and more complex networks may increase dexterous control robustness, thus contributing to bridge the gap between the market and scientific research

  5. Hybrid digital signal processing and neural networks for automated diagnostics using NDE methods

    International Nuclear Information System (INIS)

    Upadhyaya, B.R.; Yan, W.

    1993-11-01

    The primary purpose of the current research was to develop an integrated approach by combining information compression methods and artificial neural networks for the monitoring of plant components using nondestructive examination data. Specifically, data from eddy current inspection of heat exchanger tubing were utilized to evaluate this technology. The focus of the research was to develop and test various data compression methods (for eddy current data) and the performance of different neural network paradigms for defect classification and defect parameter estimation. Feedforward, fully-connected neural networks, that use the back-propagation algorithm for network training, were implemented for defect classification and defect parameter estimation using a modular network architecture. A large eddy current tube inspection database was acquired from the Metals and Ceramics Division of ORNL. These data were used to study the performance of artificial neural networks for defect type classification and for estimating defect parameters. A PC-based data preprocessing and display program was also developed as part of an expert system for data management and decision making. The results of the analysis showed that for effective (low-error) defect classification and estimation of parameters, it is necessary to identify proper feature vectors using different data representation methods. The integration of data compression and artificial neural networks for information processing was established as an effective technique for automation of diagnostics using nondestructive examination methods

  6. Natural language acquisition in large scale neural semantic networks

    Science.gov (United States)

    Ealey, Douglas

    This thesis puts forward the view that a purely signal- based approach to natural language processing is both plausible and desirable. By questioning the veracity of symbolic representations of meaning, it argues for a unified, non-symbolic model of knowledge representation that is both biologically plausible and, potentially, highly efficient. Processes to generate a grounded, neural form of this model-dubbed the semantic filter-are discussed. The combined effects of local neural organisation, coincident with perceptual maturation, are used to hypothesise its nature. This theoretical model is then validated in light of a number of fundamental neurological constraints and milestones. The mechanisms of semantic and episodic development that the model predicts are then used to explain linguistic properties, such as propositions and verbs, syntax and scripting. To mimic the growth of locally densely connected structures upon an unbounded neural substrate, a system is developed that can grow arbitrarily large, data- dependant structures composed of individual self- organising neural networks. The maturational nature of the data used results in a structure in which the perception of concepts is refined by the networks, but demarcated by subsequent structure. As a consequence, the overall structure shows significant memory and computational benefits, as predicted by the cognitive and neural models. Furthermore, the localised nature of the neural architecture also avoids the increasing error sensitivity and redundancy of traditional systems as the training domain grows. The semantic and episodic filters have been demonstrated to perform as well, or better, than more specialist networks, whilst using significantly larger vocabularies, more complex sentence forms and more natural corpora.

  7. Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks.

    Science.gov (United States)

    Pu, Yi-Fei; Yi, Zhang; Zhou, Ji-Liu

    2017-10-01

    This paper mainly discusses a novel conceptual framework: fractional Hopfield neural networks (FHNN). As is commonly known, fractional calculus has been incorporated into artificial neural networks, mainly because of its long-term memory and nonlocality. Some researchers have made interesting attempts at fractional neural networks and gained competitive advantages over integer-order neural networks. Therefore, it is naturally makes one ponder how to generalize the first-order Hopfield neural networks to the fractional-order ones, and how to implement FHNN by means of fractional calculus. We propose to introduce a novel mathematical method: fractional calculus to implement FHNN. First, we implement fractor in the form of an analog circuit. Second, we implement FHNN by utilizing fractor and the fractional steepest descent approach, construct its Lyapunov function, and further analyze its attractors. Third, we perform experiments to analyze the stability and convergence of FHNN, and further discuss its applications to the defense against chip cloning attacks for anticounterfeiting. The main contribution of our work is to propose FHNN in the form of an analog circuit by utilizing a fractor and the fractional steepest descent approach, construct its Lyapunov function, prove its Lyapunov stability, analyze its attractors, and apply FHNN to the defense against chip cloning attacks for anticounterfeiting. A significant advantage of FHNN is that its attractors essentially relate to the neuron's fractional order. FHNN possesses the fractional-order-stability and fractional-order-sensitivity characteristics.

  8. A convolutional neural network neutrino event classifier

    International Nuclear Information System (INIS)

    Aurisano, A.; Sousa, A.; Radovic, A.; Vahle, P.; Rocco, D.; Pawloski, G.; Himmel, A.; Niner, E.; Messier, M.D.; Psihas, F.

    2016-01-01

    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 without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

  9. A Design Methodology for Efficient Implementation of Deconvolutional Neural Networks on an FPGA

    OpenAIRE

    Zhang, Xinyu; Das, Srinjoy; Neopane, Ojash; Kreutz-Delgado, Ken

    2017-01-01

    In recent years deep learning algorithms have shown extremely high performance on machine learning tasks such as image classification and speech recognition. In support of such applications, various FPGA accelerator architectures have been proposed for convolutional neural networks (CNNs) that enable high performance for classification tasks at lower power than CPU and GPU processors. However, to date, there has been little research on the use of FPGA implementations of deconvolutional neural...

  10. Artificial neural networks in NDT

    International Nuclear Information System (INIS)

    Abdul Aziz Mohamed

    2001-01-01

    Artificial neural networks, simply known as neural networks, have attracted considerable interest in recent years largely because of a growing recognition of the potential of these computational paradigms as powerful alternative models to conventional pattern recognition or function approximation techniques. The neural networks approach is having a profound effect on almost all fields, and has been utilised in fields Where experimental inter-disciplinary work is being carried out. Being a multidisciplinary subject with a broad knowledge base, Nondestructive Testing (NDT) or Nondestructive Evaluation (NDE) is no exception. This paper explains typical applications of neural networks in NDT/NDE. Three promising types of neural networks are highlighted, namely, back-propagation, binary Hopfield and Kohonen's self-organising maps. (Author)

  11. The super-Turing computational power of plastic recurrent neural networks.

    Science.gov (United States)

    Cabessa, Jérémie; Siegelmann, Hava T

    2014-12-01

    We study the computational capabilities of a biologically inspired neural model where the synaptic weights, the connectivity pattern, and the number of neurons can evolve over time rather than stay static. Our study focuses on the mere concept of plasticity of the model so that the nature of the updates is assumed to be not constrained. In this context, we show that the so-called plastic recurrent neural networks (RNNs) are capable of the precise super-Turing computational power--as the static analog neural networks--irrespective of whether their synaptic weights are modeled by rational or real numbers, and moreover, irrespective of whether their patterns of plasticity are restricted to bi-valued updates or expressed by any other more general form of updating. Consequently, the incorporation of only bi-valued plastic capabilities in a basic model of RNNs suffices to break the Turing barrier and achieve the super-Turing level of computation. The consideration of more general mechanisms of architectural plasticity or of real synaptic weights does not further increase the capabilities of the networks. These results support the claim that the general mechanism of plasticity is crucially involved in the computational and dynamical capabilities of biological neural networks. They further show that the super-Turing level of computation reflects in a suitable way the capabilities of brain-like models of computation.

  12. Neural networks for tracking of unknown SISO discrete-time nonlinear dynamic systems.

    Science.gov (United States)

    Aftab, Muhammad Saleheen; Shafiq, Muhammad

    2015-11-01

    This article presents a Lyapunov function based neural network tracking (LNT) strategy for single-input, single-output (SISO) discrete-time nonlinear dynamic systems. The proposed LNT architecture is composed of two feedforward neural networks operating as controller and estimator. A Lyapunov function based back propagation learning algorithm is used for online adjustment of the controller and estimator parameters. The controller and estimator error convergence and closed-loop system stability analysis is performed by Lyapunov stability theory. Moreover, two simulation examples and one real-time experiment are investigated as case studies. The achieved results successfully validate the controller performance. Copyright © 2015 ISA. Published by Elsevier Ltd. All rights reserved.

  13. Virtualized cognitive network architecture for 5G cellular networks

    KAUST Repository

    Elsawy, Hesham

    2015-07-17

    Cellular networks have preserved an application agnostic and base station (BS) centric architecture1 for decades. Network functionalities (e.g. user association) are decided and performed regardless of the underlying application (e.g. automation, tactile Internet, online gaming, multimedia). Such an ossified architecture imposes several hurdles against achieving the ambitious metrics of next generation cellular systems. This article first highlights the features and drawbacks of such architectural ossification. Then the article proposes a virtualized and cognitive network architecture, wherein network functionalities are implemented via software instances in the cloud, and the underlying architecture can adapt to the application of interest as well as to changes in channels and traffic conditions. The adaptation is done in terms of the network topology by manipulating connectivities and steering traffic via different paths, so as to attain the applications\\' requirements and network design objectives. The article presents cognitive strategies to implement some of the classical network functionalities, along with their related implementation challenges. The article further presents a case study illustrating the performance improvement of the proposed architecture as compared to conventional cellular networks, both in terms of outage probability and handover rate.

  14. Development of the brain's functional network architecture.

    Science.gov (United States)

    Vogel, Alecia C; Power, Jonathan D; Petersen, Steven E; Schlaggar, Bradley L

    2010-12-01

    A full understanding of the development of the brain's functional network architecture requires not only an understanding of developmental changes in neural processing in individual brain regions but also an understanding of changes in inter-regional interactions. Resting state functional connectivity MRI (rs-fcMRI) is increasingly being used to study functional interactions between brain regions in both adults and children. We briefly review methods used to study functional interactions and networks with rs-fcMRI and how these methods have been used to define developmental changes in network functional connectivity. The developmental rs-fcMRI studies to date have found two general properties. First, regional interactions change from being predominately anatomically local in children to interactions spanning longer cortical distances in young adults. Second, this developmental change in functional connectivity occurs, in general, via mechanisms of segregation of local regions and integration of distant regions into disparate subnetworks.

  15. Lifelong learning of human actions with deep neural network self-organization.

    Science.gov (United States)

    Parisi, German I; Tani, Jun; Weber, Cornelius; Wermter, Stefan

    2017-12-01

    Lifelong learning is fundamental in autonomous robotics for the acquisition and fine-tuning of knowledge through experience. However, conventional deep neural models for action recognition from videos do not account for lifelong learning but rather learn a batch of training data with a predefined number of action classes and samples. Thus, there is the need to develop learning systems with the ability to incrementally process available perceptual cues and to adapt their responses over time. We propose a self-organizing neural architecture for incrementally learning to classify human actions from video sequences. The architecture comprises growing self-organizing networks equipped with recurrent neurons for processing time-varying patterns. We use a set of hierarchically arranged recurrent networks for the unsupervised learning of action representations with increasingly large spatiotemporal receptive fields. Lifelong learning is achieved in terms of prediction-driven neural dynamics in which the growth and the adaptation of the recurrent networks are driven by their capability to reconstruct temporally ordered input sequences. Experimental results on a classification task using two action benchmark datasets show that our model is competitive with state-of-the-art methods for batch learning also when a significant number of sample labels are missing or corrupted during training sessions. Additional experiments show the ability of our model to adapt to non-stationary input avoiding catastrophic interference. Copyright © 2017 The Author(s). Published by Elsevier Ltd.. All rights reserved.

  16. Reconstruction of coupling architecture of neural field networks from vector time series

    Science.gov (United States)

    Sysoev, Ilya V.; Ponomarenko, Vladimir I.; Pikovsky, Arkady

    2018-04-01

    We propose a method of reconstruction of the network coupling matrix for a basic voltage-model of the neural field dynamics. Assuming that the multivariate time series of observations from all nodes are available, we describe a technique to find coupling constants which is unbiased in the limit of long observations. Furthermore, the method is generalized for reconstruction of networks with time-delayed coupling, including the reconstruction of unknown time delays. The approach is compared with other recently proposed techniques.

  17. Implementation of a feed-forward artificial neural network in VHDL on FPGA

    NARCIS (Netherlands)

    Dondon, P.; Carvalho, J.; Gardere, R.; Lahalle, P.; Tsenov, G.; Mladenov, V.M.; Reljin, B.; Stankovic, S.

    2014-01-01

    Describing an Artificial Neural Network (ANN) using VHDL allows a further implementation of such a system on FPGA. Indeed, the principal point of using FPGA for ANNs is flexibility that gives it an advantage toward other systems like ASICS which are entirely dedicated to one unique architecture and

  18. A swarm intelligence framework for reconstructing gene networks: searching for biologically plausible architectures.

    Science.gov (United States)

    Kentzoglanakis, Kyriakos; Poole, Matthew

    2012-01-01

    In this paper, we investigate the problem of reverse engineering the topology of gene regulatory networks from temporal gene expression data. We adopt a computational intelligence approach comprising swarm intelligence techniques, namely particle swarm optimization (PSO) and ant colony optimization (ACO). In addition, the recurrent neural network (RNN) formalism is employed for modeling the dynamical behavior of gene regulatory systems. More specifically, ACO is used for searching the discrete space of network architectures and PSO for searching the corresponding continuous space of RNN model parameters. We propose a novel solution construction process in the context of ACO for generating biologically plausible candidate architectures. The objective is to concentrate the search effort into areas of the structure space that contain architectures which are feasible in terms of their topological resemblance to real-world networks. The proposed framework is initially applied to the reconstruction of a small artificial network that has previously been studied in the context of gene network reverse engineering. Subsequently, we consider an artificial data set with added noise for reconstructing a subnetwork of the genetic interaction network of S. cerevisiae (yeast). Finally, the framework is applied to a real-world data set for reverse engineering the SOS response system of the bacterium Escherichia coli. Results demonstrate the relative advantage of utilizing problem-specific knowledge regarding biologically plausible structural properties of gene networks over conducting a problem-agnostic search in the vast space of network architectures.

  19. Neural Network in Fixed Time for Collision Detection between Two Convex Polyhedra

    OpenAIRE

    M. Khouil; N. Saber; M. Mestari

    2014-01-01

    In this paper, a different architecture of a collision detection neural network (DCNN) is developed. This network, which has been particularly reviewed, has enabled us to solve with a new approach the problem of collision detection between two convex polyhedra in a fixed time (O (1) time). We used two types of neurons, linear and threshold logic, which simplified the actual implementation of all the networks proposed. The study of the collision detection is divided into two sections, the coll...

  20. NNETS - NEURAL NETWORK ENVIRONMENT ON A TRANSPUTER SYSTEM

    Science.gov (United States)

    Villarreal, J.

    1994-01-01

    The primary purpose of NNETS (Neural Network Environment on a Transputer System) is to provide users a high degree of flexibility in creating and manipulating a wide variety of neural network topologies at processing speeds not found in conventional computing environments. To accomplish this purpose, NNETS supports back propagation and back propagation related algorithms. The back propagation algorithm used is an implementation of Rumelhart's Generalized Delta Rule. NNETS was developed on the INMOS Transputer. NNETS predefines a Back Propagation Network, a Jordan Network, and a Reinforcement Network to assist users in learning and defining their own networks. The program also allows users to configure other neural network paradigms from the NNETS basic architecture. The Jordan network is basically a feed forward network that has the outputs connected to a pseudo input layer. The state of the network is dependent on the inputs from the environment plus the state of the network. The Reinforcement network learns via a scalar feedback signal called reinforcement. The network propagates forward randomly. The environment looks at the outputs of the network to produce a reinforcement signal that is fed back to the network. NNETS was written for the INMOS C compiler D711B version 1.3 or later (MS-DOS version). A small portion of the software was written in the OCCAM language to perform the communications routing between processors. NNETS is configured to operate on a 4 X 10 array of Transputers in sequence with a Transputer based graphics processor controlled by a master IBM PC 286 (or better) Transputer. A RGB monitor is required which must be capable of 512 X 512 resolution. It must be able to receive red, green, and blue signals via BNC connectors. NNETS is meant for experienced Transputer users only. The program is distributed on 5.25 inch 1.2Mb MS-DOS format diskettes. NNETS was developed in 1991. Transputer and OCCAM are registered trademarks of Inmos Corporation. MS

  1. Introduction to neural networks

    International Nuclear Information System (INIS)

    Pavlopoulos, P.

    1996-01-01

    This lecture is a presentation of today's research in neural computation. Neural computation is inspired by knowledge from neuro-science. It draws its methods in large degree from statistical physics and its potential applications lie mainly in computer science and engineering. Neural networks models are algorithms for cognitive tasks, such as learning and optimization, which are based on concepts derived from research into the nature of the brain. The lecture first gives an historical presentation of neural networks development and interest in performing complex tasks. Then, an exhaustive overview of data management and networks computation methods is given: the supervised learning and the associative memory problem, the capacity of networks, the Perceptron networks, the functional link networks, the Madaline (Multiple Adalines) networks, the back-propagation networks, the reduced coulomb energy (RCE) networks, the unsupervised learning and the competitive learning and vector quantization. An example of application in high energy physics is given with the trigger systems and track recognition system (track parametrization, event selection and particle identification) developed for the CPLEAR experiment detectors from the LEAR at CERN. (J.S.). 56 refs., 20 figs., 1 tab., 1 appendix

  2. Automatic disease diagnosis using optimised weightless neural networks for low-power wearable devices.

    Science.gov (United States)

    Cheruku, Ramalingaswamy; Edla, Damodar Reddy; Kuppili, Venkatanareshbabu; Dharavath, Ramesh; Beechu, Nareshkumar Reddy

    2017-08-01

    Low-power wearable devices for disease diagnosis are used at anytime and anywhere. These are non-invasive and pain-free for the better quality of life. However, these devices are resource constrained in terms of memory and processing capability. Memory constraint allows these devices to store a limited number of patterns and processing constraint provides delayed response. It is a challenging task to design a robust classification system under above constraints with high accuracy. In this Letter, to resolve this problem, a novel architecture for weightless neural networks (WNNs) has been proposed. It uses variable sized random access memories to optimise the memory usage and a modified binary TRIE data structure for reducing the test time. In addition, a bio-inspired-based genetic algorithm has been employed to improve the accuracy. The proposed architecture is experimented on various disease datasets using its software and hardware realisations. The experimental results prove that the proposed architecture achieves better performance in terms of accuracy, memory saving and test time as compared to standard WNNs. It also outperforms in terms of accuracy as compared to conventional neural network-based classifiers. The proposed architecture is a powerful part of most of the low-power wearable devices for the solution of memory, accuracy and time issues.

  3. The architectural design of networks of protein domain architectures.

    Science.gov (United States)

    Hsu, Chia-Hsin; Chen, Chien-Kuo; Hwang, Ming-Jing

    2013-08-23

    Protein domain architectures (PDAs), in which single domains are linked to form multiple-domain proteins, are a major molecular form used by evolution for the diversification of protein functions. However, the design principles of PDAs remain largely uninvestigated. In this study, we constructed networks to connect domain architectures that had grown out from the same single domain for every single domain in the Pfam-A database and found that there are three main distinctive types of these networks, which suggests that evolution can exploit PDAs in three different ways. Further analysis showed that these three different types of PDA networks are each adopted by different types of protein domains, although many networks exhibit the characteristics of more than one of the three types. Our results shed light on nature's blueprint for protein architecture and provide a framework for understanding architectural design from a network perspective.

  4. An efficient approach for electric load forecasting using distributed ART (adaptive resonance theory) and HS-ARTMAP (Hyper-spherical ARTMAP network) neural network

    International Nuclear Information System (INIS)

    Cai, Yuan; Wang, Jian-zhou; Tang, Yun; Yang, Yu-chen

    2011-01-01

    This paper presents a neural network based on adaptive resonance theory, named distributed ART (adaptive resonance theory) and HS-ARTMAP (Hyper-spherical ARTMAP network), applied to the electric load forecasting problem. The distributed ART combines the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multi-layer perceptions. The HS-ARTMAP, a hybrid of an RBF (Radial Basis Function)-network-like module which uses hyper-sphere basis function substitute the Gaussian basis function and an ART-like module, performs incremental learning capabilities in function approximation problem. The HS-ARTMAP only receives the compressed distributed coding processed by distributed ART to deal with the proliferation problem which ARTMAP (adaptive resonance theory map) architecture often encounters and still performs well in electric load forecasting. To demonstrate the performance of the methodology, data from New South Wales and Victoria in Australia are illustrated. Results show that the developed method is much better than the traditional BP and single HS-ARTMAP neural network. -- Research highlights: → The processing of the presented network is based on compressed distributed data. It's an innovation among the adaptive resonance theory architecture. → The presented network decreases the proliferation the Fuzzy ARTMAP architectures usually encounter. → The network on-line forecasts electrical load accurately, stably. → Both one-period and multi-period load forecasting are executed using data of different cities.

  5. An artificial neural network architecture for non-parametric visual odometry in wireless capsule endoscopy

    Science.gov (United States)

    Dimas, George; Iakovidis, Dimitris K.; Karargyris, Alexandros; Ciuti, Gastone; Koulaouzidis, Anastasios

    2017-09-01

    Wireless capsule endoscopy is a non-invasive screening procedure of the gastrointestinal (GI) tract performed with an ingestible capsule endoscope (CE) of the size of a large vitamin pill. Such endoscopes are equipped with a usually low-frame-rate color camera which enables the visualization of the GI lumen and the detection of pathologies. The localization of the commercially available CEs is performed in the 3D abdominal space using radio-frequency (RF) triangulation from external sensor arrays, in combination with transit time estimation. State-of-the-art approaches, such as magnetic localization, which have been experimentally proved more accurate than the RF approach, are still at an early stage. Recently, we have demonstrated that CE localization is feasible using solely visual cues and geometric models. However, such approaches depend on camera parameters, many of which are unknown. In this paper the authors propose a novel non-parametric visual odometry (VO) approach to CE localization based on a feed-forward neural network architecture. The effectiveness of this approach in comparison to state-of-the-art geometric VO approaches is validated using a robotic-assisted in vitro experimental setup.

  6. An artificial neural network architecture for non-parametric visual odometry in wireless capsule endoscopy

    International Nuclear Information System (INIS)

    Dimas, George; Iakovidis, Dimitris K; Karargyris, Alexandros; Ciuti, Gastone; Koulaouzidis, Anastasios

    2017-01-01

    Wireless capsule endoscopy is a non-invasive screening procedure of the gastrointestinal (GI) tract performed with an ingestible capsule endoscope (CE) of the size of a large vitamin pill. Such endoscopes are equipped with a usually low-frame-rate color camera which enables the visualization of the GI lumen and the detection of pathologies. The localization of the commercially available CEs is performed in the 3D abdominal space using radio-frequency (RF) triangulation from external sensor arrays, in combination with transit time estimation. State-of-the-art approaches, such as magnetic localization, which have been experimentally proved more accurate than the RF approach, are still at an early stage. Recently, we have demonstrated that CE localization is feasible using solely visual cues and geometric models. However, such approaches depend on camera parameters, many of which are unknown. In this paper the authors propose a novel non-parametric visual odometry (VO) approach to CE localization based on a feed-forward neural network architecture. The effectiveness of this approach in comparison to state-of-the-art geometric VO approaches is validated using a robotic-assisted in vitro experimental setup. (paper)

  7. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands.

    Science.gov (United States)

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

  8. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

    Science.gov (United States)

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too. PMID:27656140

  9. Shakeout: A New Approach to Regularized Deep Neural Network Training.

    Science.gov (United States)

    Kang, Guoliang; Li, Jun; Tao, Dacheng

    2018-05-01

    Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training. In this paper, we present a new regularized training approach: Shakeout. Instead of randomly discarding units as Dropout does at the training stage, Shakeout randomly chooses to enhance or reverse each unit's contribution to the next layer. This minor modification of Dropout has the statistical trait: the regularizer induced by Shakeout adaptively combines , and regularization terms. Our classification experiments with representative deep architectures on image datasets MNIST, CIFAR-10 and ImageNet show that Shakeout deals with over-fitting effectively and outperforms Dropout. We empirically demonstrate that Shakeout leads to sparser weights under both unsupervised and supervised settings. Shakeout also leads to the grouping effect of the input units in a layer. Considering the weights in reflecting the importance of connections, Shakeout is superior to Dropout, which is valuable for the deep model compression. Moreover, we demonstrate that Shakeout can effectively reduce the instability of the training process of the deep architecture.

  10. Hand Posture Prediction Using Neural Networks within a Biomechanical Model

    Directory of Open Access Journals (Sweden)

    Marta C. Mora

    2012-10-01

    Full Text Available This paper proposes the use of artificial neural networks (ANNs in the framework of a biomechanical hand model for grasping. ANNs enhance the model capabilities as they substitute estimated data for the experimental inputs required by the grasping algorithm used. These inputs are the tentative grasping posture and the most open posture during grasping. As a consequence, more realistic grasping postures are predicted by the grasping algorithm, along with the contact information required by the dynamic biomechanical model (contact points and normals. Several neural network architectures are tested and compared in terms of prediction errors, leading to encouraging results. The performance of the overall proposal is also shown through simulation, where a grasping experiment is replicated and compared to the real grasping data collected by a data glove device.

  11. Neural network for adapting nuclear power plant control for wide-range operation

    International Nuclear Information System (INIS)

    Ku, C.C.; Lee, K.Y.; Edwards, R.M.

    1991-01-01

    A new concept of using neural networks has been evaluated for optimal control of a nuclear reactor. The neural network uses the architecture of a standard backpropagation network; however, a new dynamic learning algorithm has been developed to capture the underlying system dynamics. The learning algorithm is based on parameter estimation for dynamic systems. The approach is demonstrated on an optimal reactor temperature controller by adjusting the feedback gains for wide-range operation. Application of optimal control to a reactor has been considered for improving temperature response using a robust fifth-order reactor power controller. Conventional gain scheduling can be employed to extend the range of good performance to accommodate large changes in power where nonlinear characteristics significantly modify the dynamics of the power plant. Gain scheduling is developed based on expected parameter variations, and it may be advantageous to further adapt feedback gains on-line to better match actual plant performance. A neural network approach is used here to adapt the gains to better accommodate plant uncertainties and thereby achieve improved robustness characteristics

  12. Character Recognition Using Genetically Trained Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

    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

  13. Neural Networks and Their Applications for the Oil Industry Les réseaux neuronaux et leurs applications pour l'industrie pétrolière

    Directory of Open Access Journals (Sweden)

    Fogelman-Soulie F.

    2006-11-01

    Full Text Available Neural Networks can be used in many different areas of problems related to Petroleum Exploration and Production. There already exist well defined classes of applications, together with appropriate Neural Networks architectures. Detailed theoretical results allow to monitor and evaluate the results obtained by Neural Networks. Sophisticated applications will certainly require the use of multi-modular architectures. Les réseaux neuronaux peuvent être utilisés pour de nombreux problèmes dans les domaines de l'exploration et la production de pétrole. Il existe d'ores et déjà des classes d'applications bien définies, pour lesquelles on connaît les architectures neuronales les plus adaptées. Des résultats théoriques précis permettent de contrôler et d'évaluer les performances obtenues avec les réseaux neuronaux. Les applications complexes demanderont certainement la mise en oeuvre d'architectures multi-modulaires.

  14. A Parallel Supercomputer Implementation of a Biological Inspired Neural Network and its use for Pattern Recognition

    International Nuclear Information System (INIS)

    De Ladurantaye, Vincent; Lavoie, Jean; Bergeron, Jocelyn; Parenteau, Maxime; Lu Huizhong; Pichevar, Ramin; Rouat, Jean

    2012-01-01

    A parallel implementation of a large spiking neural network is proposed and evaluated. The neural network implements the binding by synchrony process using the Oscillatory Dynamic Link Matcher (ODLM). Scalability, speed and performance are compared for 2 implementations: Message Passing Interface (MPI) and Compute Unified Device Architecture (CUDA) running on clusters of multicore supercomputers and NVIDIA graphical processing units respectively. A global spiking list that represents at each instant the state of the neural network is described. This list indexes each neuron that fires during the current simulation time so that the influence of their spikes are simultaneously processed on all computing units. Our implementation shows a good scalability for very large networks. A complex and large spiking neural network has been implemented in parallel with success, thus paving the road towards real-life applications based on networks of spiking neurons. MPI offers a better scalability than CUDA, while the CUDA implementation on a GeForce GTX 285 gives the best cost to performance ratio. When running the neural network on the GTX 285, the processing speed is comparable to the MPI implementation on RQCHP's Mammouth parallel with 64 notes (128 cores).

  15. Information network architectures

    Science.gov (United States)

    Murray, N. D.

    1985-01-01

    Graphs, charts, diagrams and outlines of information relative to information network architectures for advanced aerospace missions, such as the Space Station, are presented. Local area information networks are considered a likely technology solution. The principle needs for the network are listed.

  16. A single network adaptive critic (SNAC) architecture for optimal control synthesis for a class of nonlinear systems.

    Science.gov (United States)

    Padhi, Radhakant; Unnikrishnan, Nishant; Wang, Xiaohua; Balakrishnan, S N

    2006-12-01

    Even though dynamic programming offers an optimal control solution in a state feedback form, the method is overwhelmed by computational and storage requirements. Approximate dynamic programming implemented with an Adaptive Critic (AC) neural network structure has evolved as a powerful alternative technique that obviates the need for excessive computations and storage requirements in solving optimal control problems. In this paper, an improvement to the AC architecture, called the "Single Network Adaptive Critic (SNAC)" is presented. This approach is applicable to a wide class of nonlinear systems where the optimal control (stationary) equation can be explicitly expressed in terms of the state and costate variables. The selection of this terminology is guided by the fact that it eliminates the use of one neural network (namely the action network) that is part of a typical dual network AC setup. As a consequence, the SNAC architecture offers three potential advantages: a simpler architecture, lesser computational load and elimination of the approximation error associated with the eliminated network. In order to demonstrate these benefits and the control synthesis technique using SNAC, two problems have been solved with the AC and SNAC approaches and their computational performances are compared. One of these problems is a real-life Micro-Electro-Mechanical-system (MEMS) problem, which demonstrates that the SNAC technique is applicable to complex engineering systems.

  17. A comparison of back propagation and generalized regression neural networks performance in neutron spectrometry

    International Nuclear Information System (INIS)

    Ortiz R, J. M.; Martinez B, M. R.; Solis S, L. O.; Castaneda M, R.; Vega C, H. R.

    2015-10-01

    The process of unfolding the neutron energy spectrum has been the subject of research for many years. Monte Carlo, iterative methods, the bayesian theory, the principle of maximum entropy are some of the methods used. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Back Propagation Neural Networks (BPNN), have been applied with success in the neutron spectrometry and dosimetry domains, however, the structure and the learning parameters are factors that contribute in a significant way in the networks performance. In artificial neural network domain, Generalized Regression Neural Network (GRNN) is one of the simplest neural networks in term of network architecture and learning algorithm. The learning is instantaneous, which mean require no time for training. Opposite to BPNN, a GRNN would be formed instantly with just a 1-pass training with the development data. In the network development phase, the only hurdle is to tune the hyper parameter, which is known as sigma, governing the smoothness of the network. The aim of this work was to compare the performance of BPNN and GRNN in the solution of the neutron spectrometry problem. From results obtained can be observed that despite the very similar results, GRNN performs better than BPNN. (Author)

  18. A comparison of back propagation and generalized regression neural networks performance in neutron spectrometry

    Energy Technology Data Exchange (ETDEWEB)

    Ortiz R, J. M.; Martinez B, M. R.; Solis S, L. O.; Castaneda M, R. [Universidad Autonoma de Zacatecas, Unidad Academica de Ingenieria Electrica, Av. Ramon Lopez Velarde 801, Col. Centro, 98000 Zacatecas, Zac. (Mexico); Vega C, H. R., E-mail: morvymm@yahoo.com.mx [Universidad Autonoma de Zacatecas, Unidad Academica de Estudios Nucleares, Cipres No. 10, Fracc. La Penuela, 98068 Zacatecas, Zac. (Mexico)

    2015-10-15

    The process of unfolding the neutron energy spectrum has been the subject of research for many years. Monte Carlo, iterative methods, the bayesian theory, the principle of maximum entropy are some of the methods used. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Back Propagation Neural Networks (BPNN), have been applied with success in the neutron spectrometry and dosimetry domains, however, the structure and the learning parameters are factors that contribute in a significant way in the networks performance. In artificial neural network domain, Generalized Regression Neural Network (GRNN) is one of the simplest neural networks in term of network architecture and learning algorithm. The learning is instantaneous, which mean require no time for training. Opposite to BPNN, a GRNN would be formed instantly with just a 1-pass training with the development data. In the network development phase, the only hurdle is to tune the hyper parameter, which is known as sigma, governing the smoothness of the network. The aim of this work was to compare the performance of BPNN and GRNN in the solution of the neutron spectrometry problem. From results obtained can be observed that despite the very similar results, GRNN performs better than BPNN. (Author)

  19. Brain architecture: a design for natural computation.

    Science.gov (United States)

    Kaiser, Marcus

    2007-12-15

    Fifty years ago, John von Neumann compared the architecture of the brain with that of the computers he invented and which are still in use today. In those days, the organization of computers was based on concepts of brain organization. Here, we give an update on current results on the global organization of neural systems. For neural systems, we outline how the spatial and topological architecture of neuronal and cortical networks facilitates robustness against failures, fast processing and balanced network activation. Finally, we discuss mechanisms of self-organization for such architectures. After all, the organization of the brain might again inspire computer architecture.

  20. Deep architecture neural network-based real-time image processing for image-guided radiotherapy.

    Science.gov (United States)

    Mori, Shinichiro

    2017-08-01

    To develop real-time image processing for image-guided radiotherapy, we evaluated several neural network models for use with different imaging modalities, including X-ray fluoroscopic image denoising. Setup images of prostate cancer patients were acquired with two oblique X-ray fluoroscopic units. Two types of residual network were designed: a convolutional autoencoder (rCAE) and a convolutional neural network (rCNN). We changed the convolutional kernel size and number of convolutional layers for both networks, and the number of pooling and upsampling layers for rCAE. The ground-truth image was applied to the contrast-limited adaptive histogram equalization (CLAHE) method of image processing. Network models were trained to keep the quality of the output image close to that of the ground-truth image from the input image without image processing. For image denoising evaluation, noisy input images were used for the training. More than 6 convolutional layers with convolutional kernels >5×5 improved image quality. However, this did not allow real-time imaging. After applying a pair of pooling and upsampling layers to both networks, rCAEs with >3 convolutions each and rCNNs with >12 convolutions with a pair of pooling and upsampling layers achieved real-time processing at 30 frames per second (fps) with acceptable image quality. Use of our suggested network achieved real-time image processing for contrast enhancement and image denoising by the use of a conventional modern personal computer. Copyright © 2017 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.

  1. Hierarchical modular structure enhances the robustness of self-organized criticality in neural networks

    International Nuclear Information System (INIS)

    Wang Shengjun; Zhou Changsong

    2012-01-01

    One of the most prominent architecture properties of neural networks in the brain is the hierarchical modular structure. How does the structure property constrain or improve brain function? It is thought that operating near criticality can be beneficial for brain function. Here, we find that networks with modular structure can extend the parameter region of coupling strength over which critical states are reached compared to non-modular networks. Moreover, we find that one aspect of network function—dynamical range—is highest for the same parameter region. Thus, hierarchical modularity enhances robustness of criticality as well as function. However, too much modularity constrains function by preventing the neural networks from reaching critical states, because the modular structure limits the spreading of avalanches. Our results suggest that the brain may take advantage of the hierarchical modular structure to attain criticality and enhanced function. (paper)

  2. A microsensor array for quantification of lubricant contaminants using a back propagation artificial neural network

    International Nuclear Information System (INIS)

    Zhu, Xiaoliang; Du, Li; Zhe, Jiang; Liu, Bendong

    2016-01-01

    We present a method based on an electrochemical sensor array and a back propagation artificial neural network for detection and quantification of four properties of lubrication oil, namely water (0, 500 ppm, 1000 ppm), total acid number (TAN) (13.1, 13.7, 14.4, 15.6 mg KOH g −1 ), soot (0, 1%, 2%, 3%) and sulfur content (1.3%, 1.37%, 1.44%, 1.51%). The sensor array, consisting of four micromachined electrochemical sensors, detects the four properties with overlapping sensitivities. A total set of 36 oil samples containing mixtures of water, soot, and sulfuric acid with different concentrations were prepared for testing. The sensor array’s responses were then divided to three sets: training sets (80% data), validation sets (10%) and testing sets (10%). Several back propagation artificial neural network architectures were trained with the training and validation sets; one architecture with four input neurons, 50 and 5 neurons in the first and second hidden layer, and four neurons in the output layer was selected. The selected neural network was then tested using the four sets of testing data (10%). Test results demonstrated that the developed artificial neural network is able to quantitatively determine the four lubrication properties (water, TAN, soot, and sulfur content) with a maximum prediction error of 18.8%, 6.0%, 6.7%, and 5.4%, respectively, indicting a good match between the target and predicted values. With the developed network, the sensor array could be potentially used for online lubricant oil condition monitoring. (paper)

  3. Artificial neural network modeling and optimization of ultrahigh pressure extraction of green tea polyphenols.

    Science.gov (United States)

    Xi, Jun; Xue, Yujing; Xu, Yinxiang; Shen, Yuhong

    2013-11-01

    In this study, the ultrahigh pressure extraction of green tea polyphenols was modeled and optimized by a three-layer artificial neural network. A feed-forward neural network trained with an error back-propagation algorithm was used to evaluate the effects of pressure, liquid/solid ratio and ethanol concentration on the total phenolic content of green tea extracts. The neural network coupled with genetic algorithms was also used to optimize the conditions needed to obtain the highest yield of tea polyphenols. The obtained optimal architecture of artificial neural network model involved a feed-forward neural network with three input neurons, one hidden layer with eight neurons and one output layer including single neuron. The trained network gave the minimum value in the MSE of 0.03 and the maximum value in the R(2) of 0.9571, which implied a good agreement between the predicted value and the actual value, and confirmed a good generalization of the network. Based on the combination of neural network and genetic algorithms, the optimum extraction conditions for the highest yield of green tea polyphenols were determined as follows: 498.8 MPa for pressure, 20.8 mL/g for liquid/solid ratio and 53.6% for ethanol concentration. The total phenolic content of the actual measurement under the optimum predicated extraction conditions was 582.4 ± 0.63 mg/g DW, which was well matched with the predicted value (597.2mg/g DW). This suggests that the artificial neural network model described in this work is an efficient quantitative tool to predict the extraction efficiency of green tea polyphenols. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.

  4. SYNTHESIS AND REDUCED LOGIC GATE REALIZATION OF MULTI-VALUED LOGIC FUNCTIONS USING NEURAL NETWORK DEPLOYMENT ALGORITHM

    Directory of Open Access Journals (Sweden)

    A. K. CHOWDHURY

    2016-02-01

    Full Text Available In this paper an evolutionary technique for synthesizing Multi-Valued Logic (MVL functions using Neural Network Deployment Algorithm (NNDA is presented. The algorithm is combined with back-propagation learning capability and neural MVL operators. This research article is done to observe the anomalistic characteristics of MVL neural operators and their role in synthesis. The advantages of NNDA-MVL algorithm is demonstrated with realization of synthesized many valued functions with lesser MVL operators. The characteristic feature set consists of MVL gate count, network link count, network propagation delay and accuracy achieved in training. In brief, this paper depicts an effort of reduced network size for synthesized MVL functions. Trained MVL operators improve the basic architecture by reducing MIN gate and interlink connection by 52.94% and 23.38% respectively.

  5. FTS2000 network architecture

    Science.gov (United States)

    Klenart, John

    1991-01-01

    The network architecture of FTS2000 is graphically depicted. A map of network A topology is provided, with interservice nodes. Next, the four basic element of the architecture is laid out. Then, the FTS2000 time line is reproduced. A list of equipment supporting FTS2000 dedicated transmissions is given. Finally, access alternatives are shown.

  6. EMG-Based Estimation of Limb Movement Using Deep Learning With Recurrent Convolutional Neural Networks.

    Science.gov (United States)

    Xia, Peng; Hu, Jie; Peng, Yinghong

    2017-10-25

    A novel model based on deep learning is proposed to estimate kinematic information for myoelectric control from multi-channel electromyogram (EMG) signals. The neural information of limb movement is embedded in EMG signals that are influenced by all kinds of factors. In order to overcome the negative effects of variability in signals, the proposed model employs the deep architecture combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The EMG signals are transformed to time-frequency frames as the input to the model. The limb movement is estimated by the model that is trained with the gradient descent and backpropagation procedure. We tested the model for simultaneous and proportional estimation of limb movement in eight healthy subjects and compared it with support vector regression (SVR) and CNNs on the same data set. The experimental studies show that the proposed model has higher estimation accuracy and better robustness with respect to time. The combination of CNNs and RNNs can improve the model performance compared with using CNNs alone. The model of deep architecture is promising in EMG decoding and optimization of network structures can increase the accuracy and robustness. © 2017 International Center for Artificial Organs and Transplantation and Wiley Periodicals, Inc.

  7. Safety control of nuclear power operations using self-programming neural networks

    International Nuclear Information System (INIS)

    Jouse, W.C.; Williams, J.G.

    1993-01-01

    In the design and operation of nuclear reactors, safety-related goals must be embedded in complex multivariate control strategies. It is often the case that the goals exist only as mental models in the mind of the designer or the operator. In order to effect control that is risk averse, the goals must be translated into an effective control strategy that can be both verified and validated. The relation that these safety goals have to a particular architecture of artificial neural network, the Barto-Sutton architecture, is examined and the capability of the network to embed safety goals in nontrivial control tasks is demonstrated. To realize these goals, the network was extended to encompass a multiple-input/multiple-output control structure. The network synthesizes a control schedule through the construction of artificial precursors to failure; these serve as an additional, virtual layer in the defenses against fission product release. The synthesized schedule can be visually inspected for anomalies and inconsistencies and is validated during training

  8. Comments on "The multisynapse neural network and its application to fuzzy clustering".

    Science.gov (United States)

    Yu, Jian; Hao, Pengwei

    2005-05-01

    In the above-mentioned paper, Wei and Fahn proposed a neural architecture, the multisynapse neural network, to solve constrained optimization problems including high-order, logarithmic, and sinusoidal forms, etc. As one of its main applications, a fuzzy bidirectional associative clustering network (FBACN) was proposed for fuzzy-partition clustering according to the objective-functional method. The connection between the objective-functional-based fuzzy c-partition algorithms and FBACN is the Lagrange multiplier approach. Unfortunately, the Lagrange multiplier approach was incorrectly applied so that FBACN does not equivalently minimize its corresponding constrained objective-function. Additionally, Wei and Fahn adopted traditional definition of fuzzy c-partition, which is not satisfied by FBACN. Therefore, FBACN can not solve constrained optimization problems, either.

  9. Rock property estimates using multiple seismic attributes and neural networks; Pegasus Field, West Texas

    Energy Technology Data Exchange (ETDEWEB)

    Schuelke, J.S.; Quirein, J.A.; Sarg, J.F.

    1998-12-31

    This case study shows the benefit of using multiple seismic trace attributes and the pattern recognition capabilities of neural networks to predict reservoir architecture and porosity distribution in the Pegasus Field, West Texas. The study used the power of neural networks to integrate geologic, borehole and seismic data. Illustrated are the improvements between the new neural network approach and the more traditional method of seismic trace inversion for porosity estimation. Comprehensive statistical methods and interpretational/subjective measures are used in the prediction of porosity from seismic attributes. A 3-D volume of seismic derived porosity estimates for the Devonian reservoir provide a very detailed estimate of porosity, both spatially and vertically, for the field. The additional reservoir porosity detail provided, between the well control, allows for optimal placement of horizontal wells and improved field development. 6 refs., 2 figs.

  10. Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

    Science.gov (United States)

    Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

    2017-11-01

    Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

  11. UMA/GAN network architecture analysis

    Science.gov (United States)

    Yang, Liang; Li, Wensheng; Deng, Chunjian; Lv, Yi

    2009-07-01

    This paper is to critically analyze the architecture of UMA which is one of Fix Mobile Convergence (FMC) solutions, and also included by the third generation partnership project(3GPP). In UMA/GAN network architecture, UMA Network Controller (UNC) is the key equipment which connects with cellular core network and mobile station (MS). UMA network could be easily integrated into the existing cellular networks without influencing mobile core network, and could provides high-quality mobile services with preferentially priced indoor voice and data usage. This helps to improve subscriber's experience. On the other hand, UMA/GAN architecture helps to integrate other radio technique into cellular network which includes WiFi, Bluetooth, and WiMax and so on. This offers the traditional mobile operators an opportunity to integrate WiMax technique into cellular network. In the end of this article, we also give an analysis of potential influence on the cellular core networks ,which is pulled by UMA network.

  12. Recurrent Neural Networks to Correct Satellite Image Classification Maps

    Science.gov (United States)

    Maggiori, Emmanuel; Charpiat, Guillaume; Tarabalka, Yuliya; Alliez, Pierre

    2017-09-01

    While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them good at recognizing but poor at localizing objects precisely. This problem is magnified in the context of aerial and satellite image labeling, where a spatially fine object outlining is of paramount importance. Different iterative enhancement algorithms have been presented in the literature to progressively improve the coarse CNN outputs, seeking to sharpen object boundaries around real image edges. However, one must carefully design, choose and tune such algorithms. Instead, our goal is to directly learn the iterative process itself. For this, we formulate a generic iterative enhancement process inspired from partial differential equations, and observe that it can be expressed as a recurrent neural network (RNN). Consequently, we train such a network from manually labeled data for our enhancement task. In a series of experiments we show that our RNN effectively learns an iterative process that significantly improves the quality of satellite image classification maps.

  13. Optical neural network system for pose determination of spinning satellites

    Science.gov (United States)

    Lee, Andrew; Casasent, David

    1990-01-01

    An optical neural network architecture and algorithm based on a Hopfield optimization network are presented for multitarget tracking. This tracker utilizes a neuron for every possible target track, and a quadratic energy function of neural activities which is minimized using gradient descent neural evolution. The neural net tracker is demonstrated as part of a system for determining position and orientation (pose) of spinning satellites with respect to a robotic spacecraft. The input to the system is time sequence video from a single camera. Novelty detection and filtering are utilized to locate and segment novel regions from the input images. The neural net multitarget tracker determines the correspondences (or tracks) of the novel regions as a function of time, and hence the paths of object (satellite) parts. The path traced out by a given part or region is approximately elliptical in image space, and the position, shape and orientation of the ellipse are functions of the satellite geometry and its pose. Having a geometric model of the satellite, and the elliptical path of a part in image space, the three-dimensional pose of the satellite is determined. Digital simulation results using this algorithm are presented for various satellite poses and lighting conditions.

  14. Neural network to diagnose lining condition

    Science.gov (United States)

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

    2018-03-01

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

  15. Drive reinforcement neural networks for reactor control. Final report

    International Nuclear Information System (INIS)

    Williams, J.G.; Jouse, W.C.

    1995-01-01

    In view of the loss of the third year funding, the scope of the project goals has been revised. The revision in project scope no longer allows for the detailed modeling of the EBR-11 start-up task that was originally envisaged. The authors are continuing, however, to model the control of the rapid power ascent of the University of Arizona TRIGA reactor using a model-based controller and using a drive reinforcement neural network. These will be combined during the concluding period of the project into a hierarchical control architecture. In addition, the modeling of a PWR feedwater heater has continued, and an autonomous fault-tolerant software architecture for its control has been proposed

  16. Deep Neural Architectures for Mapping Scalp to Intracranial EEG.

    Science.gov (United States)

    Antoniades, Andreas; Spyrou, Loukianos; Martin-Lopez, David; Valentin, Antonio; Alarcon, Gonzalo; Sanei, Saeid; Took, Clive Cheong

    2018-03-19

    Data is often plagued by noise which encumbers machine learning of clinically useful biomarkers and electroencephalogram (EEG) data is no exemption. Intracranial EEG (iEEG) data enhances the training of deep learning models of the human brain, yet is often prohibitive due to the invasive recording process. A more convenient alternative is to record brain activity using scalp electrodes. However, the inherent noise associated with scalp EEG data often impedes the learning process of neural models, achieving substandard performance. Here, an ensemble deep learning architecture for nonlinearly mapping scalp to iEEG data is proposed. The proposed architecture exploits the information from a limited number of joint scalp-intracranial recording to establish a novel methodology for detecting the epileptic discharges from the sEEG of a general population of subjects. Statistical tests and qualitative analysis have revealed that the generated pseudo-intracranial data are highly correlated with the true intracranial data. This facilitated the detection of IEDs from the scalp recordings where such waveforms are not often visible. As a real-world clinical application, these pseudo-iEEGs are then used by a convolutional neural network for the automated classification of intracranial epileptic discharges (IEDs) and non-IED of trials in the context of epilepsy analysis. Although the aim of this work was to circumvent the unavailability of iEEG and the limitations of sEEG, we have achieved a classification accuracy of 68% an increase of 6% over the previously proposed linear regression mapping.

  17. On-Line Tracking Controller for Brushless DC Motor Drives Using Artificial Neural Networks

    Science.gov (United States)

    Rubaai, Ahmed

    1996-01-01

    A real-time control architecture is developed for time-varying nonlinear brushless dc motors operating in a high performance drives environment. The developed control architecture possesses the capabilities of simultaneous on-line identification and control. The dynamics of the motor are modeled on-line and controlled using an artificial neural network, as the system runs. The control architecture combines the experience and dependability of adaptive tracking systems with potential and promise of the neural computing technology. The sensitivity of real-time controller to parametric changes that occur during training is investigated. Such changes are usually manifested by rapid changes in the load of the brushless motor drives. This sudden change in the external load is simulated for the sigmoidal and sinusoidal reference tracks. The ability of the neuro-controller to maintain reasonable tracking accuracy in the presence of external noise is also verified for a number of desired reference trajectories.

  18. Neural network technique for orbit correction in accelerators/storage rings

    International Nuclear Information System (INIS)

    Bozoki, E.; Friedman, A.

    1995-01-01

    The authors are exploring the use of Neural Networks, using the SNNS simulator, for orbit control in accelerators (primarily circular accelerators) and storage rings. The orbit of the beam in those machines are measured by orbit monitors (input nodes) and controlled by orbit corrector magnets (output nodes). The physical behavior of an accelerator is changing slowly in time. Thus, an adoptive algorithm is necessary. The goal is to have a trained net which will predict the exact corrector strengths which will minimize a measured orbit. The relationship between open-quotes kickclose quotes from the correctors and open-quotes responseclose quotes from the monitors is in general non-linear and may slowly change during long-term operation of the machine. In the study, several network architectures are examined as well as various training methods for each architecture

  19. Neural Networks in Control Applications

    DEFF Research Database (Denmark)

    Sørensen, O.

    The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...... in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...

  20. The parallel implementation of a backpropagation neural network and its applicability to SPECT image reconstruction

    Energy Technology Data Exchange (ETDEWEB)

    Kerr, John Patrick [Iowa State Univ., Ames, IA (United States)

    1992-01-01

    The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.

  1. Evaluation of oil thickness by neural network analysis of IR imagery

    International Nuclear Information System (INIS)

    Wood, P.; Strachan, I.; Davies, L.; Lunel, T.

    1997-01-01

    The feasibility of using neural network analysis of conventional thermal infra-red data gathered from surveillance aircraft to determine the thickness of oil at sea, was examined. Sea trial data was examined using Multi-Layer Perceptron neural network architecture, based on indications that it was the most appropriate configuration for determining oil thickness. Core input variables included oil brightness, time of day, sea brightness, wind speed, oil type, and sea temperature. Other variables, such as altitude, wave height, air temperature, camera gain, and others, did not appear to produce any significant difference in the prediction performance. By using only a restricted sea trial data set in training the network, it was found that it was possible to correctly classify about 80 per cent of the data into one of four thickness classes. Since there was no additional data available to validate the network, these results were considered encouraging, but not definitive. Additional data will be collected in planned future sea trials to further evaluate the accuracy of the trained network. 4 refs., 6 tabs., 4 figs

  2. Prediction of Aerodynamic Coefficients for Wind Tunnel Data using a Genetic Algorithm Optimized Neural Network

    Science.gov (United States)

    Rajkumar, T.; Aragon, Cecilia; Bardina, Jorge; Britten, Roy

    2002-01-01

    A fast, reliable way of predicting aerodynamic coefficients is produced using a neural network optimized by a genetic algorithm. Basic aerodynamic coefficients (e.g. lift, drag, pitching moment) are modelled as functions of angle of attack and Mach number. The neural network is first trained on a relatively rich set of data from wind tunnel tests of numerical simulations to learn an overall model. Most of the aerodynamic parameters can be well-fitted using polynomial functions. A new set of data, which can be relatively sparse, is then supplied to the network to produce a new model consistent with the previous model and the new data. Because the new model interpolates realistically between the sparse test data points, it is suitable for use in piloted simulations. The genetic algorithm is used to choose a neural network architecture to give best results, avoiding over-and under-fitting of the test data.

  3. Practical neural network recipies in C++

    CERN Document Server

    Masters

    2014-01-01

    This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assum

  4. Optimization of recurrent neural networks for time series modeling

    DEFF Research Database (Denmark)

    Pedersen, Morten With

    1997-01-01

    The present thesis is about optimization of recurrent neural networks applied to time series modeling. In particular is considered fully recurrent networks working from only a single external input, one layer of nonlinear hidden units and a li near output unit applied to prediction of discrete time...... series. The overall objective s are to improve training by application of second-order methods and to improve generalization ability by architecture optimization accomplished by pruning. The major topics covered in the thesis are: 1. The problem of training recurrent networks is analyzed from a numerical...... of solution obtained as well as computation time required. 3. A theoretical definition of the generalization error for recurrent networks is provided. This definition justifies a commonly adopted approach for estimating generalization ability. 4. The viability of pruning recurrent networks by the Optimal...

  5. A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks.

    Science.gov (United States)

    Alauthaman, Mohammad; Aslam, Nauman; Zhang, Li; Alasem, Rafe; Hossain, M A

    2018-01-01

    In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

  6. Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction

    OpenAIRE

    Cui, Zhiyong; Ke, Ruimin; Wang, Yinhai

    2018-01-01

    Short-term traffic forecasting based on deep learning methods, especially long short-term memory (LSTM) neural networks, has received much attention in recent years. However, the potential of deep learning methods in traffic forecasting has not yet fully been exploited in terms of the depth of the model architecture, the spatial scale of the prediction area, and the predictive power of spatial-temporal data. In this paper, a deep stacked bidirectional and unidirectional LSTM (SBU- LSTM) neura...

  7. Photosensitive-polyimide based method for fabricating various neural electrode architectures

    Directory of Open Access Journals (Sweden)

    Yasuhiro X Kato

    2012-06-01

    Full Text Available An extensive photosensitive polyimide (PSPI-based method for designing and fabricating various neural electrode architectures was developed. The method aims to broaden the design flexibility and expand the fabrication capability for neural electrodes to improve the quality of recorded signals and integrate other functions. After characterizing PSPI’s properties for micromachining processes, we successfully designed and fabricated various neural electrodes even on a non-flat substrate using only one PSPI as an insulation material and without the time-consuming dry etching processes. The fabricated neural electrodes were an electrocorticogram electrode, a mesh intracortical electrode with a unique lattice-like mesh structure to fixate neural tissue, and a guide cannula electrode with recording microelectrodes placed on the curved surface of a guide cannula as a microdialysis probe. In vivo neural recordings using anesthetized rats demonstrated that these electrodes can be used to record neural activities repeatedly without any breakage and mechanical failures, which potentially promises stable recordings for long periods of time. These successes make us believe that this PSPI-based fabrication is a powerful method, permitting flexible design and easy optimization of electrode architectures for a variety of electrophysiological experimental research with improved neural recording performance.

  8. A neural network approach to breast cancer diagnosis as a constraint satisfaction problem

    International Nuclear Information System (INIS)

    Tourassi, Georgia D.; Markey, Mia K.; Lo, Joseph Y.; Floyd, Carey E. Jr.

    2001-01-01

    A constraint satisfaction neural network (CSNN) approach is proposed for breast cancer diagnosis using mammographic and patient history findings. Initially, the diagnostic decision to biopsy was formulated as a constraint satisfaction problem. Then, an associative memory type neural network was applied to solve the problem. The proposed network has a flexible, nonhierarchical architecture that allows it to operate not only as a predictive tool but also as an analysis tool for knowledge discovery of association rules. The CSNN was developed and evaluated using a database of 500 nonpalpable breast lesions with definitive histopathological diagnosis. The CSNN diagnostic performance was evaluated using receiver operating characteristic analysis (ROC). The results of the study showed that the CSNN ROC area index was 0.84±0.02. The CSNN predictive performance is competitive with that achieved by experienced radiologists and backpropagation artificial neural networks (BP-ANNs) presented before. Furthermore, the study illustrates how CSNN can be used as a knowledge discovery tool overcoming some of the well-known limitations of BP-ANNs

  9. Comparison of Classifier Architectures for Online Neural Spike Sorting.

    Science.gov (United States)

    Saeed, Maryam; Khan, Amir Ali; Kamboh, Awais Mehmood

    2017-04-01

    High-density, intracranial recordings from micro-electrode arrays need to undergo Spike Sorting in order to associate the recorded neuronal spikes to particular neurons. This involves spike detection, feature extraction, and classification. To reduce the data transmission and power requirements, on-chip real-time processing is becoming very popular. However, high computational resources are required for classifiers in on-chip spike-sorters, making scalability a great challenge. In this review paper, we analyze several popular classifiers to propose five new hardware architectures using the off-chip training with on-chip classification approach. These include support vector classification, fuzzy C-means classification, self-organizing maps classification, moving-centroid K-means classification, and Cosine distance classification. The performance of these architectures is analyzed in terms of accuracy and resource requirement. We establish that the neural networks based Self-Organizing Maps classifier offers the most viable solution. A spike sorter based on the Self-Organizing Maps classifier, requires only 7.83% of computational resources of the best-reported spike sorter, hierarchical adaptive means, while offering a 3% better accuracy at 7 dB SNR.

  10. Signal Processing and Neural Network Simulator

    Science.gov (United States)

    Tebbe, Dennis L.; Billhartz, Thomas J.; Doner, John R.; Kraft, Timothy T.

    1995-04-01

    The signal processing and neural network simulator (SPANNS) is a digital signal processing simulator with the capability to invoke neural networks into signal processing chains. This is a generic tool which will greatly facilitate the design and simulation of systems with embedded neural networks. The SPANNS is based on the Signal Processing WorkSystemTM (SPWTM), a commercial-off-the-shelf signal processing simulator. SPW provides a block diagram approach to constructing signal processing simulations. Neural network paradigms implemented in the SPANNS include Backpropagation, Kohonen Feature Map, Outstar, Fully Recurrent, Adaptive Resonance Theory 1, 2, & 3, and Brain State in a Box. The SPANNS was developed by integrating SAIC's Industrial Strength Neural Networks (ISNN) Software into SPW.

  11. A review and analysis of neural networks for classification of remotely sensed multispectral imagery

    Science.gov (United States)

    Paola, Justin D.; Schowengerdt, Robert A.

    1993-01-01

    A literature survey and analysis of the use of neural networks for the classification of remotely sensed multispectral imagery is presented. As part of a brief mathematical review, the backpropagation algorithm, which is the most common method of training multi-layer networks, is discussed with an emphasis on its application to pattern recognition. The analysis is divided into five aspects of neural network classification: (1) input data preprocessing, structure, and encoding; (2) output encoding and extraction of classes; (3) network architecture, (4) training algorithms; and (5) comparisons to conventional classifiers. The advantages of the neural network method over traditional classifiers are its non-parametric nature, arbitrary decision boundary capabilities, easy adaptation to different types of data and input structures, fuzzy output values that can enhance classification, and good generalization for use with multiple images. The disadvantages of the method are slow training time, inconsistent results due to random initial weights, and the requirement of obscure initialization values (e.g., learning rate and hidden layer size). Possible techniques for ameliorating these problems are discussed. It is concluded that, although the neural network method has several unique capabilities, it will become a useful tool in remote sensing only if it is made faster, more predictable, and easier to use.

  12. Molecular evolution of a peptide GPCR ligand driven by artificial neural networks.

    Directory of Open Access Journals (Sweden)

    Sebastian Bandholtz

    Full Text Available Peptide ligands of G protein-coupled receptors constitute valuable natural lead structures for the development of highly selective drugs and high-affinity tools to probe ligand-receptor interaction. Currently, pharmacological and metabolic modification of natural peptides involves either an iterative trial-and-error process based on structure-activity relationships or screening of peptide libraries that contain many structural variants of the native molecule. Here, we present a novel neural network architecture for the improvement of metabolic stability without loss of bioactivity. In this approach the peptide sequence determines the topology of the neural network and each cell corresponds one-to-one to a single amino acid of the peptide chain. Using a training set, the learning algorithm calculated weights for each cell. The resulting network calculated the fitness function in a genetic algorithm to explore the virtual space of all possible peptides. The network training was based on gradient descent techniques which rely on the efficient calculation of the gradient by back-propagation. After three consecutive cycles of sequence design by the neural network, peptide synthesis and bioassay this new approach yielded a ligand with 70fold higher metabolic stability compared to the wild type peptide without loss of the subnanomolar activity in the biological assay. Combining specialized neural networks with an exploration of the combinatorial amino acid sequence space by genetic algorithms represents a novel rational strategy for peptide design and optimization.

  13. USC orthogonal multiprocessor for image processing with neural networks

    Science.gov (United States)

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

    1990-07-01

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

  14. Trimaran Resistance Artificial Neural Network

    Science.gov (United States)

    2011-01-01

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

  15. A comparison of back propagation and Generalized Regression Neural Networks performance in neutron spectrometry

    International Nuclear Information System (INIS)

    Martínez-Blanco, Ma. del Rosario

    2016-01-01

    The process of unfolding the neutron energy spectrum has been subject of research for many years. Monte Carlo, iterative methods, the bayesian theory, the principle of maximum entropy are some of the methods used. The drawbacks associated with traditional unfolding procedures have motivated the research of complementary approaches. Back Propagation Neural Networks (BPNN), have been applied with success in neutron spectrometry and dosimetry domains, however, the structure and learning parameters are factors that highly impact in the networks performance. In ANN domain, Generalized Regression Neural Network (GRNN) is one of the simplest neural networks in term of network architecture and learning algorithm. The learning is instantaneous, requiring no time for training. Opposite to BPNN, a GRNN would be formed instantly with just a 1-pass training on the development data. In the network development phase, the only hurdle is to optimize the hyper-parameter, which is known as sigma, governing the smoothness of the network. The aim of this work was to compare the performance of BPNN and GRNN in the solution of the neutron spectrometry problem. From results obtained it can be observed that despite the very similar results, GRNN performs better than BPNN.

  16. Neural network regulation driven by autonomous neural firings

    Science.gov (United States)

    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.

  17. Analysing 21cm signal with artificial neural network

    Science.gov (United States)

    Shimabukuro, Hayato; a Semelin, Benoit

    2018-05-01

    The 21cm signal at epoch of reionization (EoR) should be observed within next decade. We expect that cosmic 21cm signal at the EoR provides us both cosmological and astrophysical information. In order to extract fruitful information from observation data, we need to develop inversion method. For such a method, we introduce artificial neural network (ANN) which is one of the machine learning techniques. We apply the ANN to inversion problem to constrain astrophysical parameters from 21cm power spectrum. We train the architecture of the neural network with 70 training datasets and apply it to 54 test datasets with different value of parameters. We find that the quality of the parameter reconstruction depends on the sensitivity of the power spectrum to the different parameter sets at a given redshift and also find that the accuracy of reconstruction is improved by increasing the number of given redshifts. We conclude that the ANN is viable inversion method whose main strength is that they require a sparse extrapolation of the parameter space and thus should be usable with full simulation.

  18. Optimization of workflow scheduling in Utility Management System with hierarchical neural network

    Directory of Open Access Journals (Sweden)

    Srdjan Vukmirovic

    2011-08-01

    Full Text Available Grid computing could be the future computing paradigm for enterprise applications, one of its benefits being that it can be used for executing large scale applications. Utility Management Systems execute very large numbers of workflows with very high resource requirements. This paper proposes architecture for a new scheduling mechanism that dynamically executes a scheduling algorithm using feedback about the current status Grid nodes. Two Artificial Neural Networks were created in order to solve the scheduling problem. A case study is created for the Meter Data Management system with measurements from the Smart Metering system for the city of Novi Sad, Serbia. Performance tests show that significant improvement of overall execution time can be achieved by Hierarchical Artificial Neural Networks.

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

    Science.gov (United States)

    Kuljaca, Ognjen

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

  20. Variable synaptic strengths controls the firing rate distribution in feedforward neural networks.

    Science.gov (United States)

    Ly, Cheng; Marsat, Gary

    2018-02-01

    Heterogeneity of firing rate statistics is known to have severe consequences on neural coding. Recent experimental recordings in weakly electric fish indicate that the distribution-width of superficial pyramidal cell firing rates (trial- and time-averaged) in the electrosensory lateral line lobe (ELL) depends on the stimulus, and also that network inputs can mediate changes in the firing rate distribution across the population. We previously developed theoretical methods to understand how two attributes (synaptic and intrinsic heterogeneity) interact and alter the firing rate distribution in a population of integrate-and-fire neurons with random recurrent coupling. Inspired by our experimental data, we extend these theoretical results to a delayed feedforward spiking network that qualitatively capture the changes of firing rate heterogeneity observed in in-vivo recordings. We demonstrate how heterogeneous neural attributes alter firing rate heterogeneity, accounting for the effect with various sensory stimuli. The model predicts how the strength of the effective network connectivity is related to intrinsic heterogeneity in such delayed feedforward networks: the strength of the feedforward input is positively correlated with excitability (threshold value for spiking) when firing rate heterogeneity is low and is negatively correlated with excitability with high firing rate heterogeneity. We also show how our theory can be used to predict effective neural architecture. We demonstrate that neural attributes do not interact in a simple manner but rather in a complex stimulus-dependent fashion to control neural heterogeneity and discuss how it can ultimately shape population codes.

  1. Neural networks with discontinuous/impact activations

    CERN Document Server

    Akhmet, Marat

    2014-01-01

    This book presents as its main subject new models in mathematical neuroscience. A wide range of neural networks models with discontinuities are discussed, including impulsive differential equations, differential equations with piecewise constant arguments, and models of mixed type. These models involve discontinuities, which are natural because huge velocities and short distances are usually observed in devices modeling the networks. A discussion of the models, appropriate for the proposed applications, is also provided. This book also: Explores questions related to the biological underpinning for models of neural networks\\ Considers neural networks modeling using differential equations with impulsive and piecewise constant argument discontinuities Provides all necessary mathematical basics for application to the theory of neural networks Neural Networks with Discontinuous/Impact Activations is an ideal book for researchers and professionals in the field of engineering mathematics that have an interest in app...

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

    Science.gov (United States)

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

    2018-05-01

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

  3. Estimating tree bole volume using artificial neural network models for four species in Turkey.

    Science.gov (United States)

    Ozçelik, Ramazan; Diamantopoulou, Maria J; Brooks, John R; Wiant, Harry V

    2010-01-01

    Tree bole volumes of 89 Scots pine (Pinus sylvestris L.), 96 Brutian pine (Pinus brutia Ten.), 107 Cilicica fir (Abies cilicica Carr.) and 67 Cedar of Lebanon (Cedrus libani A. Rich.) trees were estimated using Artificial Neural Network (ANN) models. Neural networks offer a number of advantages including the ability to implicitly detect complex nonlinear relationships between input and output variables, which is very helpful in tree volume modeling. Two different neural network architectures were used and produced the Back propagation (BPANN) and the Cascade Correlation (CCANN) Artificial Neural Network models. In addition, tree bole volume estimates were compared to other established tree bole volume estimation techniques including the centroid method, taper equations, and existing standard volume tables. An overview of the features of ANNs and traditional methods is presented and the advantages and limitations of each one of them are discussed. For validation purposes, actual volumes were determined by aggregating the volumes of measured short sections (average 1 meter) of the tree bole using Smalian's formula. The results reported in this research suggest that the selected cascade correlation artificial neural network (CCANN) models are reliable for estimating the tree bole volume of the four examined tree species since they gave unbiased results and were superior to almost all methods in terms of error (%) expressed as the mean of the percentage errors. 2009 Elsevier Ltd. All rights reserved.

  4. Simplified LQG Control with Neural Networks

    DEFF Research Database (Denmark)

    Sørensen, O.

    1997-01-01

    A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce...

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

    Science.gov (United States)

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

    1994-03-01

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

  6. Sustained Activity in Hierarchical Modular Neural Networks: Self-Organized Criticality and Oscillations

    Science.gov (United States)

    Wang, Sheng-Jun; Hilgetag, Claus C.; Zhou, Changsong

    2010-01-01

    Cerebral cortical brain networks possess a number of conspicuous features of structure and dynamics. First, these networks have an intricate, non-random organization. In particular, they are structured in a hierarchical modular fashion, from large-scale regions of the whole brain, via cortical areas and area subcompartments organized as structural and functional maps to cortical columns, and finally circuits made up of individual neurons. Second, the networks display self-organized sustained activity, which is persistent in the absence of external stimuli. At the systems level, such activity is characterized by complex rhythmical oscillations over a broadband background, while at the cellular level, neuronal discharges have been observed to display avalanches, indicating that cortical networks are at the state of self-organized criticality (SOC). We explored the relationship between hierarchical neural network organization and sustained dynamics using large-scale network modeling. Previously, it was shown that sparse random networks with balanced excitation and inhibition can sustain neural activity without external stimulation. We found that a hierarchical modular architecture can generate sustained activity better than random networks. Moreover, the system can simultaneously support rhythmical oscillations and SOC, which are not present in the respective random networks. The mechanism underlying the sustained activity is that each dense module cannot sustain activity on its own, but displays SOC in the presence of weak perturbations. Therefore, the hierarchical modular networks provide the coupling among subsystems with SOC. These results imply that the hierarchical modular architecture of cortical networks plays an important role in shaping the ongoing spontaneous activity of the brain, potentially allowing the system to take advantage of both the sensitivity of critical states and the predictability and timing of oscillations for efficient information

  7. Sustained activity in hierarchical modular neural networks: self-organized criticality and oscillations

    Directory of Open Access Journals (Sweden)

    Sheng-Jun Wang

    2011-06-01

    Full Text Available Cerebral cortical brain networks possess a number of conspicuous features of structure and dynamics. First, these networks have an intricate, non-random organization. They are structured in a hierarchical modular fashion, from large-scale regions of the whole brain, via cortical areas and area subcompartments organized as structural and functional maps to cortical columns, and finally circuits made up of individual neurons. Second, the networks display self-organized sustained activity, which is persistent in the absence of external stimuli. At the systems level, such activity is characterized by complex rhythmical oscillations over a broadband background, while at the cellular level, neuronal discharges have been observed to display avalanches, indicating that cortical networks are at the state of self-organized criticality. We explored the relationship between hierarchical neural network organization and sustained dynamics using large-scale network modeling. It was shown that sparse random networks with balanced excitation and inhibition can sustain neural activity without external stimulation. We find that a hierarchical modular architecture can generate sustained activity better than random networks. Moreover, the system can simultaneously support rhythmical oscillations and self-organized criticality, which are not present in the respective random networks. The underlying mechanism is that each dense module cannot sustain activity on its own, but displays self-organized criticality in the presence of weak perturbations. The hierarchical modular networks provide the coupling among subsystems with self-organized criticality. These results imply that the hierarchical modular architecture of cortical networks plays an important role in shaping the ongoing spontaneous activity of the brain, potentially allowing the system to take advantage of both the sensitivityof critical state and predictability and timing of oscillations for efficient

  8. Modular representation of layered neural networks.

    Science.gov (United States)

    Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

    2018-01-01

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

  9. Introduction to Artificial Neural Networks

    DEFF Research Database (Denmark)

    Larsen, Jan

    1999-01-01

    The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....

  10. Quantum Entanglement in Neural Network States

    Directory of Open Access Journals (Sweden)

    Dong-Ling Deng

    2017-05-01

    Full Text Available Machine learning, one of today’s most rapidly growing interdisciplinary fields, promises an unprecedented perspective for solving intricate quantum many-body problems. Understanding the physical aspects of the representative artificial neural-network states has recently become highly desirable in the applications of machine-learning techniques to quantum many-body physics. In this paper, we explore the data structures that encode the physical features in the network states by studying the quantum entanglement properties, with a focus on the restricted-Boltzmann-machine (RBM architecture. We prove that the entanglement entropy of all short-range RBM states satisfies an area law for arbitrary dimensions and bipartition geometry. For long-range RBM states, we show by using an exact construction that such states could exhibit volume-law entanglement, implying a notable capability of RBM in representing quantum states with massive entanglement. Strikingly, the neural-network representation for these states is remarkably efficient, in the sense that the number of nonzero parameters scales only linearly with the system size. We further examine the entanglement properties of generic RBM states by randomly sampling the weight parameters of the RBM. We find that their averaged entanglement entropy obeys volume-law scaling, and the meantime strongly deviates from the Page entropy of the completely random pure states. We show that their entanglement spectrum has no universal part associated with random matrix theory and bears a Poisson-type level statistics. Using reinforcement learning, we demonstrate that RBM is capable of finding the ground state (with power-law entanglement of a model Hamiltonian with a long-range interaction. In addition, we show, through a concrete example of the one-dimensional symmetry-protected topological cluster states, that the RBM representation may also be used as a tool to analytically compute the entanglement spectrum. Our

  11. Neural network feedforward control of a closed-circuit wind tunnel

    Science.gov (United States)

    Sutcliffe, Peter

    Accurate control of wind-tunnel test conditions can be dramatically enhanced using feedforward control architectures which allow operating conditions to be maintained at a desired setpoint through the use of mathematical models as the primary source of prediction. However, as the desired accuracy of the feedforward prediction increases, the model complexity also increases, so that an ever increasing computational load is incurred. This drawback can be avoided by employing a neural network that is trained offline using the output of a high fidelity wind-tunnel mathematical model, so that the neural network can rapidly reproduce the predictions of the model with a greatly reduced computational overhead. A novel neural network database generation method, developed through the use of fractional factorial arrays, was employed such that a neural network can accurately predict wind-tunnel parameters across a wide range of operating conditions whilst trained upon a highly efficient database. The subsequent network was incorporated into a Neural Network Model Predictive Control (NNMPC) framework to allow an optimised output schedule capable of providing accurate control of the wind-tunnel operating parameters. Facilitation of an optimised path through the solution space is achieved through the use of a chaos optimisation algorithm such that a more globally optimum solution is likely to be found with less computational expense than the gradient descent method. The parameters associated with the NNMPC such as the control horizon are determined through the use of a Taguchi methodology enabling the minimum number of experiments to be carried out to determine the optimal combination. The resultant NNMPC scheme was employed upon the Hessert Low Speed Wind Tunnel at the University of Notre Dame to control the test-section temperature such that it follows a pre-determined reference trajectory during changes in the test-section velocity. Experimental testing revealed that the

  12. A neutron spectrum unfolding computer code based on artificial neural networks

    International Nuclear Information System (INIS)

    Ortiz-Rodríguez, J.M.; Reyes Alfaro, A.; Reyes Haro, A.; Cervantes Viramontes, J.M.; Vega-Carrillo, H.R.

    2014-01-01

    The Bonner Spheres Spectrometer consists of a thermal neutron sensor placed at the center of a number of moderating polyethylene spheres of different diameters. From the measured readings, information can be derived about the spectrum of the neutron field where measurements were made. Disadvantages of the Bonner system are the weight associated with each sphere and the need to sequentially irradiate the spheres, requiring long exposure periods. Provided a well-established response matrix and adequate irradiation conditions, the most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Intelligence, mainly Artificial Neural Networks, have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This code is called Neutron Spectrometry and Dosimetry with Artificial Neural networks unfolding code that was designed in a graphical interface. The core of the code is an embedded neural network architecture previously optimized using the robust design of artificial neural networks methodology. The main features of the code are: easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6 LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, for unfolding the neutron spectrum, only seven rate counts measured with seven Bonner spheres are required; simultaneously the code calculates 15 dosimetric quantities as well as the total flux for radiation protection purposes. This code generates a full report with all information of the unfolding

  13. Artificial Neural Network Analysis System

    Science.gov (United States)

    2001-02-27

    Contract No. DASG60-00-M-0201 Purchase request no.: Foot in the Door-01 Title Name: Artificial Neural Network Analysis System Company: Atlantic... Artificial Neural Network Analysis System 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) Powell, Bruce C 5d. PROJECT NUMBER 5e. TASK NUMBER...34) 27-02-2001 Report Type N/A Dates Covered (from... to) ("DD MON YYYY") 28-10-2000 27-02-2001 Title and Subtitle Artificial Neural Network Analysis

  14. HONTIOR - HIGHER-ORDER NEURAL NETWORK FOR TRANSFORMATION INVARIANT OBJECT RECOGNITION

    Science.gov (United States)

    Spirkovska, L.

    1994-01-01

    Neural networks have been applied in numerous fields, including transformation invariant object recognition, wherein an object is recognized despite changes in the object's position in the input field, size, or rotation. One of the more successful neural network methods used in invariant object recognition is the higher-order neural network (HONN) method. With a HONN, known relationships are exploited and the desired invariances are built directly into the architecture of the network, eliminating the need for the network to learn invariance to transformations. This results in a significant reduction in the training time required, since the network needs to be trained on only one view of each object, not on numerous transformed views. Moreover, one hundred percent accuracy is guaranteed for images characterized by the built-in distortions, providing noise is not introduced through pixelation. The program HONTIOR implements a third-order neural network having invariance to translation, scale, and in-plane rotation built directly into the architecture, Thus, for 2-D transformation invariance, the network needs only to be trained on just one view of each object. HONTIOR can also be used for 3-D transformation invariant object recognition by training the network only on a set of out-of-plane rotated views. Historically, the major drawback of HONNs has been that the size of the input field was limited to the memory required for the large number of interconnections in a fully connected network. HONTIOR solves this problem by coarse coding the input images (coding an image as a set of overlapping but offset coarser images). Using this scheme, large input fields (4096 x 4096 pixels) can easily be represented using very little virtual memory (30Mb). The HONTIOR distribution consists of three main programs. The first program contains the training and testing routines for a third-order neural network. The second program contains the same training and testing procedures as the

  15. DEVELOPMENT OF A COMPUTER SYSTEM FOR IDENTITY AUTHENTICATION USING ARTIFICIAL NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    Timur Kartbayev

    2017-03-01

    Full Text Available The aim of the study is to increase the effectiveness of automated face recognition to authenticate identity, considering features of change of the face parameters over time. The improvement of the recognition accuracy, as well as consideration of the features of temporal changes in a human face can be based on the methodology of artificial neural networks. Hybrid neural networks, combining the advantages of classical neural networks and fuzzy logic systems, allow using the network learnability along with the explanation of the findings. The structural scheme of intelligent system for identification based on artificial neural networks is proposed in this work. It realizes the principles of digital information processing and identity recognition taking into account the forecast of key characteristics’ changes over time (e.g., due to aging. The structural scheme has a three-tier architecture and implements preliminary processing, recognition and identification of images obtained as a result of monitoring. On the basis of expert knowledge, the fuzzy base of products is designed. It allows assessing possible changes in key characteristics, used to authenticate identity based on the image. To take this possibility into consideration, a neuro-fuzzy network of ANFIS type was used, which implements the algorithm of Tagaki-Sugeno. The conducted experiments showed high efficiency of the developed neural network and a low value of learning errors, which allows recommending this approach for practical implementation. Application of the developed system of fuzzy production rules that allow predicting changes in individuals over time, will improve the recognition accuracy, reduce the number of authentication failures and improve the efficiency of information processing and decision-making in applications, such as authentication of bank customers, users of mobile applications, or in video monitoring systems of sensitive sites.

  16. Neural network fusion capabilities for efficient implementation of tracking algorithms

    Science.gov (United States)

    Sundareshan, Malur K.; Amoozegar, Farid

    1997-03-01

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

  17. Deep Recurrent Neural Networks for Human Activity Recognition

    Directory of Open Access Journals (Sweden)

    Abdulmajid Murad

    2017-11-01

    Full Text Available Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM and k-nearest neighbors (KNN. Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs and CNNs.

  18. Deep Recurrent Neural Networks for Human Activity Recognition.

    Science.gov (United States)

    Murad, Abdulmajid; Pyun, Jae-Young

    2017-11-06

    Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs.

  19. Complex-Valued Neural Networks

    CERN Document Server

    Hirose, Akira

    2012-01-01

    This book is the second enlarged and revised edition of the first successful monograph on complex-valued neural networks (CVNNs) published in 2006, which lends itself to graduate and undergraduate courses in electrical engineering, informatics, control engineering, mechanics, robotics, bioengineering, and other relevant fields. In the second edition the recent trends in CVNNs research are included, resulting in e.g. almost a doubled number of references. The parametron invented in 1954 is also referred to with discussion on analogy and disparity. Also various additional arguments on the advantages of the complex-valued neural networks enhancing the difference to real-valued neural networks are given in various sections. The book is useful for those beginning their studies, for instance, in adaptive signal processing for highly functional sensing and imaging, control in unknown and changing environment, robotics inspired by human neural systems, and brain-like information processing, as well as interdisciplina...

  20. Modular architectures for quantum networks

    Science.gov (United States)

    Pirker, A.; Wallnöfer, J.; Dür, W.

    2018-05-01

    We consider the problem of generating multipartite entangled states in a quantum network upon request. We follow a top-down approach, where the required entanglement is initially present in the network in form of network states shared between network devices, and then manipulated in such a way that the desired target state is generated. This minimizes generation times, and allows for network structures that are in principle independent of physical links. We present a modular and flexible architecture, where a multi-layer network consists of devices of varying complexity, including quantum network routers, switches and clients, that share certain resource states. We concentrate on the generation of graph states among clients, which are resources for numerous distributed quantum tasks. We assume minimal functionality for clients, i.e. they do not participate in the complex and distributed generation process of the target state. We present architectures based on shared multipartite entangled Greenberger–Horne–Zeilinger states of different size, and fully connected decorated graph states, respectively. We compare the features of these architectures to an approach that is based on bipartite entanglement, and identify advantages of the multipartite approach in terms of memory requirements and complexity of state manipulation. The architectures can handle parallel requests, and are designed in such a way that the network state can be dynamically extended if new clients or devices join the network. For generation or dynamical extension of the network states, we propose a quantum network configuration protocol, where entanglement purification is used to establish high fidelity states. The latter also allows one to show that the entanglement generated among clients is private, i.e. the network is secure.

  1. Cellular Neural Network-Based Methods for Distributed Network Intrusion Detection

    Directory of Open Access Journals (Sweden)

    Kang Xie

    2015-01-01

    Full Text Available According to the problems of current distributed architecture intrusion detection systems (DIDS, a new online distributed intrusion detection model based on cellular neural network (CNN was proposed, in which discrete-time CNN (DTCNN was used as weak classifier in each local node and state-controlled CNN (SCCNN was used as global detection method, respectively. We further proposed a new method for design template parameters of SCCNN via solving Linear Matrix Inequality. Experimental results based on KDD CUP 99 dataset show its feasibility and effectiveness. Emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI implementation which allows the distributed intrusion detection to be performed better.

  2. Brain tumor segmentation in multi-spectral MRI using convolutional neural networks (CNN).

    Science.gov (United States)

    Iqbal, Sajid; Ghani, M Usman; Saba, Tanzila; Rehman, Amjad

    2018-04-01

    A tumor could be found in any area of the brain and could be of any size, shape, and contrast. There may exist multiple tumors of different types in a human brain at the same time. Accurate tumor area segmentation is considered primary step for treatment of brain tumors. Deep Learning is a set of promising techniques that could provide better results as compared to nondeep learning techniques for segmenting timorous part inside a brain. This article presents a deep convolutional neural network (CNN) to segment brain tumors in MRIs. The proposed network uses BRATS segmentation challenge dataset which is composed of images obtained through four different modalities. Accordingly, we present an extended version of existing network to solve segmentation problem. The network architecture consists of multiple neural network layers connected in sequential order with the feeding of Convolutional feature maps at the peer level. Experimental results on BRATS 2015 benchmark data thus show the usability of the proposed approach and its superiority over the other approaches in this area of research. © 2018 Wiley Periodicals, Inc.

  3. Prototype-Incorporated Emotional Neural Network.

    Science.gov (United States)

    Oyedotun, Oyebade K; Khashman, Adnan

    2017-08-15

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

  4. NEURAL NETWORK SYSTEM FOR DIAGNOSTICS OF AVIATION DESIGNATION PRODUCTS

    Directory of Open Access Journals (Sweden)

    В. Єременко

    2011-02-01

    Full Text Available In the article for solving the classification problem of the technical state of the  object, proposed to use a hybrid neural network with a Kohonen layer and multilayer perceptron. The information-measuring system can be used for standardless diagnostics, cluster analysis and to classify the products which made from composite materials. The advantage of this architecture is flexibility, high performance, ability to use different methods for collecting diagnostic information about unit under test, high reliability of information processing

  5. Antenna analysis using neural networks

    Science.gov (United States)

    Smith, William T.

    1992-01-01

    Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern

  6. Forecasting influenza-like illness dynamics for military populations using neural networks and social media.

    Directory of Open Access Journals (Sweden)

    Svitlana Volkova

    Full Text Available This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs units capable of nowcasting (predicting in "real-time" and forecasting (predicting the future ILI dynamics in the 2011 - 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus

  7. Forecasting influenza-like illness dynamics for military populations using neural networks and social media.

    Science.gov (United States)

    Volkova, Svitlana; Ayton, Ellyn; Porterfield, Katherine; Corley, Courtney D

    2017-01-01

    This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs) units capable of nowcasting (predicting in "real-time") and forecasting (predicting the future) ILI dynamics in the 2011 - 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a) Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from

  8. Deconvolution using a neural network

    Energy Technology Data Exchange (ETDEWEB)

    Lehman, S.K.

    1990-11-15

    Viewing one dimensional deconvolution as a matrix inversion problem, we compare a neural network backpropagation matrix inverse with LMS, and pseudo-inverse. This is a largely an exercise in understanding how our neural network code works. 1 ref.

  9. Optimal source coding, removable noise elimination, and natural coordinate system construction for general vector sources using replicator neural networks

    Science.gov (United States)

    Hecht-Nielsen, Robert

    1997-04-01

    A new universal one-chart smooth manifold model for vector information sources is introduced. Natural coordinates (a particular type of chart) for such data manifolds are then defined. Uniformly quantized natural coordinates form an optimal vector quantization code for a general vector source. Replicator neural networks (a specialized type of multilayer perceptron with three hidden layers) are the introduced. As properly configured examples of replicator networks approach minimum mean squared error (e.g., via training and architecture adjustment using randomly chosen vectors from the source), these networks automatically develop a mapping which, in the limit, produces natural coordinates for arbitrary source vectors. The new concept of removable noise (a noise model applicable to a wide variety of real-world noise processes) is then discussed. Replicator neural networks, when configured to approach minimum mean squared reconstruction error (e.g., via training and architecture adjustment on randomly chosen examples from a vector source, each with randomly chosen additive removable noise contamination), in the limit eliminate removable noise and produce natural coordinates for the data vector portions of the noise-corrupted source vectors. Consideration regarding selection of the dimension of a data manifold source model and the training/configuration of replicator neural networks are discussed.

  10. Computational Models and Emergent Properties of Respiratory Neural Networks

    Science.gov (United States)

    Lindsey, Bruce G.; Rybak, Ilya A.; Smith, Jeffrey C.

    2012-01-01

    Computational models of the neural control system for breathing in mammals provide a theoretical and computational framework bringing together experimental data obtained from different animal preparations under various experimental conditions. Many of these models were developed in parallel and iteratively with experimental studies and provided predictions guiding new experiments. This data-driven modeling approach has advanced our understanding of respiratory network architecture and neural mechanisms underlying generation of the respiratory rhythm and pattern, including their functional reorganization under different physiological conditions. Models reviewed here vary in neurobiological details and computational complexity and span multiple spatiotemporal scales of respiratory control mechanisms. Recent models describe interacting populations of respiratory neurons spatially distributed within the Bötzinger and pre-Bötzinger complexes and rostral ventrolateral medulla that contain core circuits of the respiratory central pattern generator (CPG). Network interactions within these circuits along with intrinsic rhythmogenic properties of neurons form a hierarchy of multiple rhythm generation mechanisms. The functional expression of these mechanisms is controlled by input drives from other brainstem components, including the retrotrapezoid nucleus and pons, which regulate the dynamic behavior of the core circuitry. The emerging view is that the brainstem respiratory network has rhythmogenic capabilities at multiple levels of circuit organization. This allows flexible, state-dependent expression of different neural pattern-generation mechanisms under various physiological conditions, enabling a wide repertoire of respiratory behaviors. Some models consider control of the respiratory CPG by pulmonary feedback and network reconfiguration during defensive behaviors such as cough. Future directions in modeling of the respiratory CPG are considered. PMID:23687564

  11. NeuroFlow: A General Purpose Spiking Neural Network Simulation Platform using Customizable Processors.

    Science.gov (United States)

    Cheung, Kit; Schultz, Simon R; Luk, Wayne

    2015-01-01

    NeuroFlow is a scalable spiking neural network simulation platform for off-the-shelf high performance computing systems using customizable hardware processors such as Field-Programmable Gate Arrays (FPGAs). Unlike multi-core processors and application-specific integrated circuits, the processor architecture of NeuroFlow can be redesigned and reconfigured to suit a particular simulation to deliver optimized performance, such as the degree of parallelism to employ. The compilation process supports using PyNN, a simulator-independent neural network description language, to configure the processor. NeuroFlow supports a number of commonly used current or conductance based neuronal models such as integrate-and-fire and Izhikevich models, and the spike-timing-dependent plasticity (STDP) rule for learning. A 6-FPGA system can simulate a network of up to ~600,000 neurons and can achieve a real-time performance of 400,000 neurons. Using one FPGA, NeuroFlow delivers a speedup of up to 33.6 times the speed of an 8-core processor, or 2.83 times the speed of GPU-based platforms. With high flexibility and throughput, NeuroFlow provides a viable environment for large-scale neural network simulation.

  12. Accelerating learning of neural networks with conjugate gradients for nuclear power plant applications

    International Nuclear Information System (INIS)

    Reifman, J.; Vitela, J.E.

    1994-01-01

    The method of conjugate gradients is used to expedite the learning process of feedforward multilayer artificial neural networks and to systematically update both the learning parameter and the momentum parameter at each training cycle. The mechanism for the occurrence of premature saturation of the network nodes observed with the back propagation algorithm is described, suggestions are made to eliminate this undesirable phenomenon, and the reason by which this phenomenon is precluded in the method of conjugate gradients is presented. The proposed method is compared with the standard back propagation algorithm in the training of neural networks to classify transient events in neural power plants simulated by the Midland Nuclear Power Plant Unit 2 simulator. The comparison results indicate that the rate of convergence of the proposed method is much greater than the standard back propagation, that it reduces both the number of training cycles and the CPU time, and that it is less sensitive to the choice of initial weights. The advantages of the method are more noticeable and important for problems where the network architecture consists of a large number of nodes, the training database is large, and a tight convergence criterion is desired

  13. Neurally and mathematically motivated architecture for language and thought.

    Science.gov (United States)

    Perlovsky, L I; Ilin, R

    2010-01-01

    Neural structures of interaction between thinking and language are unknown. This paper suggests a possible architecture motivated by neural and mathematical considerations. A mathematical requirement of computability imposes significant constraints on possible architectures consistent with brain neural structure and with a wealth of psychological knowledge. How language interacts with cognition. Do we think with words, or is thinking independent from language with words being just labels for decisions? Why is language learned by the age of 5 or 7, but acquisition of knowledge represented by learning to use this language knowledge takes a lifetime? This paper discusses hierarchical aspects of language and thought and argues that high level abstract thinking is impossible without language. We discuss a mathematical technique that can model the joint language-thought architecture, while overcoming previously encountered difficulties of computability. This architecture explains a contradiction between human ability for rational thoughtful decisions and irrationality of human thinking revealed by Tversky and Kahneman; a crucial role in this contradiction might be played by language. The proposed model resolves long-standing issues: how the brain learns correct words-object associations; why animals do not talk and think like people. We propose the role played by language emotionality in its interaction with thought. We relate the mathematical model to Humboldt's "firmness" of languages; and discuss possible influence of language grammar on its emotionality. Psychological and brain imaging experiments related to the proposed model are discussed. Future theoretical and experimental research is outlined.

  14. Success of Anomia Treatment in Aphasia Is Associated With Preserved Architecture of Global and Left Temporal Lobe Structural Networks.

    Science.gov (United States)

    Bonilha, Leonardo; Gleichgerrcht, Ezequiel; Nesland, Travis; Rorden, Chris; Fridriksson, Julius

    2016-03-01

    Targeted speech therapy can lead to substantial naming improvement in some subjects with anomia following dominant-hemisphere stroke. We investigated whether treatment-induced improvement in naming is associated with poststroke preservation of structural neural network architecture. Twenty-four patients with poststroke chronic aphasia underwent 30 hours of speech therapy over a 2-week period and were assessed at baseline and after therapy. Whole brain maps of neural architecture were constructed from pretreatment diffusion tensor magnetic resonance imaging to derive measures of global brain network architecture (network small-worldness) and regional network influence (nodal betweenness centrality). Their relationship with naming recovery was evaluated with multiple linear regressions. Treatment-induced improvement in correct naming was associated with poststroke preservation of global network small worldness and of betweenness centrality in temporal lobe cortical regions. Together with baseline aphasia severity, these measures explained 78% of the variability in treatment response. Preservation of global and left temporal structural connectivity broadly explains the variability in treatment-related naming improvement in aphasia. These findings corroborate and expand on previous classical lesion-symptom mapping studies by elucidating some of the mechanisms by which brain damage may relate to treated aphasia recovery. Favorable naming outcomes may result from the intact connections between spared cortical areas that are functionally responsive to treatment. © The Author(s) 2015.

  15. A comparison of back propagation and Generalized Regression Neural Networks performance in neutron spectrometry.

    Science.gov (United States)

    Martínez-Blanco, Ma Del Rosario; Ornelas-Vargas, Gerardo; Solís-Sánchez, Luis Octavio; Castañeda-Miranada, Rodrigo; Vega-Carrillo, Héctor René; Celaya-Padilla, José M; Garza-Veloz, Idalia; Martínez-Fierro, Margarita; Ortiz-Rodríguez, José Manuel

    2016-11-01

    The process of unfolding the neutron energy spectrum has been subject of research for many years. Monte Carlo, iterative methods, the bayesian theory, the principle of maximum entropy are some of the methods used. The drawbacks associated with traditional unfolding procedures have motivated the research of complementary approaches. Back Propagation Neural Networks (BPNN), have been applied with success in neutron spectrometry and dosimetry domains, however, the structure and learning parameters are factors that highly impact in the networks performance. In ANN domain, Generalized Regression Neural Network (GRNN) is one of the simplest neural networks in term of network architecture and learning algorithm. The learning is instantaneous, requiring no time for training. Opposite to BPNN, a GRNN would be formed instantly with just a 1-pass training on the development data. In the network development phase, the only hurdle is to optimize the hyper-parameter, which is known as sigma, governing the smoothness of the network. The aim of this work was to compare the performance of BPNN and GRNN in the solution of the neutron spectrometry problem. From results obtained it can be observed that despite the very similar results, GRNN performs better than BPNN. Copyright © 2016 Elsevier Ltd. All rights reserved.

  16. Modeling of an industrial drying process by artificial neural networks

    Directory of Open Access Journals (Sweden)

    E. Assidjo

    2008-09-01

    Full Text Available A suitable method is needed to solve the nonquality problem in the grated coconut industry due to the poor control of product humidity during the process. In this study the possibility of using an artificial neural network (ANN, precisely a Multilayer Perceptron, for modeling the drying step of the production of grated coconut process is highlighted. Drying must confer to the product a final moisture of 3%. Unfortunately, under industrial conditions, this moisture varies from 1.9 to 4.8 %. In order to control this parameter and consequently reduce the proportion of the product that does not meet the humidity specification, a 9-4-1 neural network architecture was established using data gathered from an industrial plant. This Multilayer Perceptron can satisfactorily model the process with less bias, ranging from -0.35 to 0.34%, and can reduce the rate of rejected products from 92% to 3% during the first cycle of drying.

  17. Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers

    Directory of Open Access Journals (Sweden)

    Ryan Henderson

    2017-09-01

    Full Text Available Picasso is a free open-source (Eclipse Public License web application written in Python for rendering standard visualizations useful for analyzing convolutional neural networks. Picasso ships with occlusion maps and saliency maps, two visualizations which help reveal issues that evaluation metrics like loss and accuracy might hide: for example, learning a proxy classification task. Picasso works with the Tensorflow deep learning framework, and Keras (when the model can be loaded into the Tensorflow backend. Picasso can be used with minimal configuration by deep learning researchers and engineers alike across various neural network architectures. Adding new visualizations is simple: the user can specify their visualization code and HTML template separately from the application code.

  18. Neural networks and statistical learning

    CERN Document Server

    Du, Ke-Lin

    2014-01-01

    Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...

  19. Neural network recognition of mammographic lesions

    International Nuclear Information System (INIS)

    Oldham, W.J.B.; Downes, P.T.; Hunter, V.

    1987-01-01

    A method for recognition of mammographic lesions through the use of neural networks is presented. Neural networks have exhibited the ability to learn the shape andinternal structure of patterns. Digitized mammograms containing circumscribed and stelate lesions were used to train a feedfoward synchronous neural network that self-organizes to stable attractor states. Encoding of data for submission to the network was accomplished by performing a fractal analysis of the digitized image. This results in scale invariant representation of the lesions. Results are discussed

  20. Accurate prediction of the dew points of acidic combustion gases by using an artificial neural network model

    International Nuclear Information System (INIS)

    ZareNezhad, Bahman; Aminian, Ali

    2011-01-01

    This paper presents a new approach based on using an artificial neural network (ANN) model for predicting the acid dew points of the combustion gases in process and power plants. The most important acidic combustion gases namely, SO 3 , SO 2 , NO 2 , HCl and HBr are considered in this investigation. Proposed Network is trained using the Levenberg-Marquardt back propagation algorithm and the hyperbolic tangent sigmoid activation function is applied to calculate the output values of the neurons of the hidden layer. According to the network's training, validation and testing results, a three layer neural network with nine neurons in the hidden layer is selected as the best architecture for accurate prediction of the acidic combustion gases dew points over wide ranges of acid and moisture concentrations. The proposed neural network model can have significant application in predicting the condensation temperatures of different acid gases to mitigate the corrosion problems in stacks, pollution control devices and energy recovery systems.

  1. Neural Networks and Micromechanics

    Science.gov (United States)

    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.

  2. Neural networks for feedback feedforward nonlinear control systems.

    Science.gov (United States)

    Parisini, T; Zoppoli, R

    1994-01-01

    This paper deals with the problem of designing feedback feedforward control strategies to drive the state of a dynamic system (in general, nonlinear) so as to track any desired trajectory joining the points of given compact sets, while minimizing a certain cost function (in general, nonquadratic). Due to the generality of the problem, conventional methods are difficult to apply. Thus, an approximate solution is sought by constraining control strategies to take on the structure of multilayer feedforward neural networks. After discussing the approximation properties of neural control strategies, a particular neural architecture is presented, which is based on what has been called the "linear-structure preserving principle". The original functional problem is then reduced to a nonlinear programming one, and backpropagation is applied to derive the optimal values of the synaptic weights. Recursive equations to compute the gradient components are presented, which generalize the classical adjoint system equations of N-stage optimal control theory. Simulation results related to nonlinear nonquadratic problems show the effectiveness of the proposed method.

  3. Parameterization Of Solar Radiation Using Neural Network

    International Nuclear Information System (INIS)

    Jiya, J. D.; Alfa, B.

    2002-01-01

    This paper presents a neural network technique for parameterization of global solar radiation. The available data from twenty-one stations is used for training the neural network and the data from other ten stations is used to validate the neural model. The neural network utilizes latitude, longitude, altitude, sunshine duration and period number to parameterize solar radiation values. The testing data was not used in the training to demonstrate the performance of the neural network in unknown stations to parameterize solar radiation. The results indicate a good agreement between the parameterized solar radiation values and actual measured values

  4. Analysis of neural networks through base functions

    NARCIS (Netherlands)

    van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, L.

    Problem statement. Despite their success-story, neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more

  5. Character-level neural network for biomedical named entity recognition.

    Science.gov (United States)

    Gridach, Mourad

    2017-06-01

    Biomedical named entity recognition (BNER), which extracts important named entities such as genes and proteins, is a challenging task in automated systems that mine knowledge in biomedical texts. The previous state-of-the-art systems required large amounts of task-specific knowledge in the form of feature engineering, lexicons and data pre-processing to achieve high performance. In this paper, we introduce a novel neural network architecture that benefits from both word- and character-level representations automatically, by using a combination of bidirectional long short-term memory (LSTM) and conditional random field (CRF) eliminating the need for most feature engineering tasks. We evaluate our system on two datasets: JNLPBA corpus and the BioCreAtIvE II Gene Mention (GM) corpus. We obtained state-of-the-art performance by outperforming the previous systems. To the best of our knowledge, we are the first to investigate the combination of deep neural networks, CRF, word embeddings and character-level representation in recognizing biomedical named entities. Copyright © 2017 Elsevier Inc. All rights reserved.

  6. Neural Networks for Optimal Control

    DEFF Research Database (Denmark)

    Sørensen, O.

    1995-01-01

    Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....

  7. Medical Concept Normalization in Social Media Posts with Recurrent Neural Networks.

    Science.gov (United States)

    Tutubalina, Elena; Miftahutdinov, Zulfat; Nikolenko, Sergey; Malykh, Valentin

    2018-06-12

    Text mining of scientific libraries and social media has already proven itself as a reliable tool for drug repurposing and hypothesis generation. The task of mapping a disease mention to a concept in a controlled vocabulary, typically to the standard thesaurus in the Unified Medical Language System (UMLS), is known as medical concept normalization. This task is challenging due to the differences in the use of medical terminology between health care professionals and social media texts coming from the lay public. To bridge this gap, we use sequence learning with recurrent neural networks and semantic representation of one- or multi-word expressions: we develop end-to-end architectures directly tailored to the task, including bidirectional Long Short-Term Memory, Gated Recurrent Units with an attention mechanism, and additional semantic similarity features based on UMLS. Our evaluation against a standard benchmark shows that recurrent neural networks improve results over an effective baseline for classification based on convolutional neural networks. A qualitative examination of mentions discovered in a dataset of user reviews collected from popular online health information platforms as well as a quantitative evaluation both show improvements in the semantic representation of health-related expressions in social media. Copyright © 2018. Published by Elsevier Inc.

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

    Science.gov (United States)

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

    2015-05-01

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

  9. From biological neural networks to thinking machines: Transitioning biological organizational principles to computer technology

    Science.gov (United States)

    Ross, Muriel D.

    1991-01-01

    The three-dimensional organization of the vestibular macula is under study by computer assisted reconstruction and simulation methods as a model for more complex neural systems. One goal of this research is to transition knowledge of biological neural network architecture and functioning to computer technology, to contribute to the development of thinking computers. Maculas are organized as weighted neural networks for parallel distributed processing of information. The network is characterized by non-linearity of its terminal/receptive fields. Wiring appears to develop through constrained randomness. A further property is the presence of two main circuits, highly channeled and distributed modifying, that are connected through feedforward-feedback collaterals and biasing subcircuit. Computer simulations demonstrate that differences in geometry of the feedback (afferent) collaterals affects the timing and the magnitude of voltage changes delivered to the spike initiation zone. Feedforward (efferent) collaterals act as voltage followers and likely inhibit neurons of the distributed modifying circuit. These results illustrate the importance of feedforward-feedback loops, of timing, and of inhibition in refining neural network output. They also suggest that it is the distributed modifying network that is most involved in adaptation, memory, and learning. Tests of macular adaptation, through hyper- and microgravitational studies, support this hypothesis since synapses in the distributed modifying circuit, but not the channeled circuit, are altered. Transitioning knowledge of biological systems to computer technology, however, remains problematical.

  10. An Architectural Modelfor Intelligent Network Management

    Institute of Scientific and Technical Information of China (English)

    罗军舟; 顾冠群; 费翔

    2000-01-01

    Traditional network management approach involves the management of each vendor's equipment and network segment in isolation through its own proprietary element management system. It is necessary to set up a new network management architecture that calls for operation consolidation across vendor and technology boundaries. In this paper, an architectural model for Intelligent Network Management (INM) is presented. The INM system includes a manager system, which controls all subsystems and coordinates different management tasks; an expert system, which is responsible for handling particularly difficult problems, and intelligent agents, which bring the management closer to applications and user requirements by spreading intelligent agents through network segments or domain. In the expert system model proposed, especially an intelligent fault management system is given.The architectural model is to build the INM system to meet the need of managing modern network systems.

  11. Neural networks at the Tevatron

    International Nuclear Information System (INIS)

    Badgett, W.; Burkett, K.; Campbell, M.K.; Wu, D.Y.; Bianchin, S.; DeNardi, M.; Pauletta, G.; Santi, L.; Caner, A.; Denby, B.; Haggerty, H.; Lindsey, C.S.; Wainer, N.; Dall'Agata, M.; Johns, K.; Dickson, M.; Stanco, L.; Wyss, J.L.

    1992-10-01

    This paper summarizes neural network applications at the Fermilab Tevatron, including the first online hardware application in high energy physics (muon tracking): the CDF and DO neural network triggers; offline quark/gluon discrimination at CDF; ND a new tool for top to multijets recognition at CDF

  12. Logarithmic r-θ mapping for hybrid optical neural network filter for multiple objects recognition within cluttered scenes

    Science.gov (United States)

    Kypraios, Ioannis; Young, Rupert C. D.; Chatwin, Chris R.; Birch, Phil M.

    2009-04-01

    θThe window unit in the design of the complex logarithmic r-θ mapping for hybrid optical neural network filter can allow multiple objects of the same class to be detected within the input image. Additionally, the architecture of the neural network unit of the complex logarithmic r-θ mapping for hybrid optical neural network filter becomes attractive for accommodating the recognition of multiple objects of different classes within the input image by modifying the output layer of the unit. We test the overall filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. Logarithmic r-θ mapping for hybrid optical neural network filter is shown to exhibit with a single pass over the input data simultaneously in-plane rotation, out-of-plane rotation, scale, log r-θ map translation and shift invariance, and good clutter tolerance by recognizing correctly the different objects within the cluttered scenes. We record in our results additional extracted information from the cluttered scenes about the objects' relative position, scale and in-plane rotation.

  13. Genetic Algorithm Optimized Neural Networks Ensemble as ...

    African Journals Online (AJOL)

    NJD

    Improvements in neural network calibration models by a novel approach using neural network ensemble (NNE) for the simultaneous ... process by training a number of neural networks. .... Matlab® version 6.1 was employed for building principal component ... provide a fair simulation of calibration data set with some degree.

  14. Home networking architecture for IPv6

    OpenAIRE

    Arkko, Jari; Weil, Jason; Troan, Ole; Brandt, Anders

    2012-01-01

    This text describes evolving networking technology within increasingly large residential home networks. The goal of this document is to define an architecture for IPv6-based home networking while describing the associated principles, considerations and requirements. The text briefly highlights the specific implications of the introduction of IPv6 for home networking, discusses the elements of the architecture, and suggests how standard IPv6 mechanisms and addressing can be employed in home ne...

  15. Application of neural network to CT

    International Nuclear Information System (INIS)

    Ma, Xiao-Feng; Takeda, Tatsuoki

    1999-01-01

    This paper presents a new method for two-dimensional image reconstruction by using a multilayer neural network. Multilayer neural networks are extensively investigated and practically applied to solution of various problems such as inverse problems or time series prediction problems. From learning an input-output mapping from a set of examples, neural networks can be regarded as synthesizing an approximation of multidimensional function (that is, solving the problem of hypersurface reconstruction, including smoothing and interpolation). From this viewpoint, neural networks are well suited to the solution of CT image reconstruction. Though a conventionally used object function of a neural network is composed of a sum of squared errors of the output data, we can define an object function composed of a sum of residue of an integral equation. By employing an appropriate line integral for this integral equation, we can construct a neural network that can be used for CT. We applied this method to some model problems and obtained satisfactory results. As it is not necessary to discretized the integral equation using this reconstruction method, therefore it is application to the problem of complicated geometrical shapes is also feasible. Moreover, in neural networks, interpolation is performed quite smoothly, as a result, inverse mapping can be achieved smoothly even in case of including experimental and numerical errors, However, use of conventional back propagation technique for optimization leads to an expensive computation cost. To overcome this drawback, 2nd order optimization methods or parallel computing will be applied in future. (J.P.N.)

  16. Mobile networks architecture

    CERN Document Server

    Perez, Andre

    2013-01-01

    This book explains the evolutions of architecture for mobiles and summarizes the different technologies:- 2G: the GSM (Global System for Mobile) network, the GPRS (General Packet Radio Service) network and the EDGE (Enhanced Data for Global Evolution) evolution;- 3G: the UMTS (Universal Mobile Telecommunications System) network and the HSPA (High Speed Packet Access) evolutions:- HSDPA (High Speed Downlink Packet Access),- HSUPA (High Speed Uplink Packet Access),- HSPA+;- 4G: the EPS (Evolved Packet System) network.The telephone service and data transmission are the

  17. Fuzzy logic and neural networks basic concepts & application

    CERN Document Server

    Alavala, Chennakesava R

    2008-01-01

    About the Book: The primary purpose of this book is to provide the student with a comprehensive knowledge of basic concepts of fuzzy logic and neural networks. The hybridization of fuzzy logic and neural networks is also included. No previous knowledge of fuzzy logic and neural networks is required. Fuzzy logic and neural networks have been discussed in detail through illustrative examples, methods and generic applications. Extensive and carefully selected references is an invaluable resource for further study of fuzzy logic and neural networks. Each chapter is followed by a question bank

  18. Wavelet-enhanced convolutional neural network: a new idea in a deep learning paradigm.

    Science.gov (United States)

    Savareh, Behrouz Alizadeh; Emami, Hassan; Hajiabadi, Mohamadreza; Azimi, Seyed Majid; Ghafoori, Mahyar

    2018-05-29

    Manual brain tumor segmentation is a challenging task that requires the use of machine learning techniques. One of the machine learning techniques that has been given much attention is the convolutional neural network (CNN). The performance of the CNN can be enhanced by combining other data analysis tools such as wavelet transform. In this study, one of the famous implementations of CNN, a fully convolutional network (FCN), was used in brain tumor segmentation and its architecture was enhanced by wavelet transform. In this combination, a wavelet transform was used as a complementary and enhancing tool for CNN in brain tumor segmentation. Comparing the performance of basic FCN architecture against the wavelet-enhanced form revealed a remarkable superiority of enhanced architecture in brain tumor segmentation tasks. Using mathematical functions and enhancing tools such as wavelet transform and other mathematical functions can improve the performance of CNN in any image processing task such as segmentation and classification.

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

    Science.gov (United States)

    Kriegeskorte, Nikolaus

    2015-11-24

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

  20. An Efficient Neural-Network-Based Microseismic Monitoring Platform for Hydraulic Fracture on an Edge Computing Architecture

    Directory of Open Access Journals (Sweden)

    Xiaopu Zhang

    2018-06-01

    Full Text Available Microseismic monitoring is one of the most critical technologies for hydraulic fracturing in oil and gas production. To detect events in an accurate and efficient way, there are two major challenges. One challenge is how to achieve high accuracy due to a poor signal-to-noise ratio (SNR. The other one is concerned with real-time data transmission. Taking these challenges into consideration, an edge-computing-based platform, namely Edge-to-Center LearnReduce, is presented in this work. The platform consists of a data center with many edge components. At the data center, a neural network model combined with convolutional neural network (CNN and long short-term memory (LSTM is designed and this model is trained by using previously obtained data. Once the model is fully trained, it is sent to edge components for events detection and data reduction. At each edge component, a probabilistic inference is added to the neural network model to improve its accuracy. Finally, the reduced data is delivered to the data center. Based on experiment results, a high detection accuracy (over 96% with less transmitted data (about 90% was achieved by using the proposed approach on a microseismic monitoring system. These results show that the platform can simultaneously improve the accuracy and efficiency of microseismic monitoring.

  1. An Efficient Neural-Network-Based Microseismic Monitoring Platform for Hydraulic Fracture on an Edge Computing Architecture.

    Science.gov (United States)

    Zhang, Xiaopu; Lin, Jun; Chen, Zubin; Sun, Feng; Zhu, Xi; Fang, Gengfa

    2018-06-05

    Microseismic monitoring is one of the most critical technologies for hydraulic fracturing in oil and gas production. To detect events in an accurate and efficient way, there are two major challenges. One challenge is how to achieve high accuracy due to a poor signal-to-noise ratio (SNR). The other one is concerned with real-time data transmission. Taking these challenges into consideration, an edge-computing-based platform, namely Edge-to-Center LearnReduce, is presented in this work. The platform consists of a data center with many edge components. At the data center, a neural network model combined with convolutional neural network (CNN) and long short-term memory (LSTM) is designed and this model is trained by using previously obtained data. Once the model is fully trained, it is sent to edge components for events detection and data reduction. At each edge component, a probabilistic inference is added to the neural network model to improve its accuracy. Finally, the reduced data is delivered to the data center. Based on experiment results, a high detection accuracy (over 96%) with less transmitted data (about 90%) was achieved by using the proposed approach on a microseismic monitoring system. These results show that the platform can simultaneously improve the accuracy and efficiency of microseismic monitoring.

  2. Neural network stochastic simulation applied for quantifying uncertainties

    Directory of Open Access Journals (Sweden)

    N Foudil-Bey

    2016-09-01

    Full Text Available Generally the geostatistical simulation methods are used to generate several realizations of physical properties in the sub-surface, these methods are based on the variogram analysis and limited to measures correlation between variables at two locations only. In this paper, we propose a simulation of properties based on supervised Neural network training at the existing drilling data set. The major advantage is that this method does not require a preliminary geostatistical study and takes into account several points. As a result, the geological information and the diverse geophysical data can be combined easily. To do this, we used a neural network with multi-layer perceptron architecture like feed-forward, then we used the back-propagation algorithm with conjugate gradient technique to minimize the error of the network output. The learning process can create links between different variables, this relationship can be used for interpolation of the properties on the one hand, or to generate several possible distribution of physical properties on the other hand, changing at each time and a random value of the input neurons, which was kept constant until the period of learning. This method was tested on real data to simulate multiple realizations of the density and the magnetic susceptibility in three-dimensions at the mining camp of Val d'Or, Québec (Canada.

  3. Role of graph architecture in controlling dynamical networks with applications to neural systems

    Science.gov (United States)

    Kim, Jason Z.; Soffer, Jonathan M.; Kahn, Ari E.; Vettel, Jean M.; Pasqualetti, Fabio; Bassett, Danielle S.

    2018-01-01

    Networked systems display complex patterns of interactions between components. In physical networks, these interactions often occur along structural connections that link components in a hard-wired connection topology, supporting a variety of system-wide dynamical behaviours such as synchronization. Although descriptions of these behaviours are important, they are only a first step towards understanding and harnessing the relationship between network topology and system behaviour. Here, we use linear network control theory to derive accurate closed-form expressions that relate the connectivity of a subset of structural connections (those linking driver nodes to non-driver nodes) to the minimum energy required to control networked systems. To illustrate the utility of the mathematics, we apply this approach to high-resolution connectomes recently reconstructed from Drosophila, mouse, and human brains. We use these principles to suggest an advantage of the human brain in supporting diverse network dynamics with small energetic costs while remaining robust to perturbations, and to perform clinically accessible targeted manipulation of the brain's control performance by removing single edges in the network. Generally, our results ground the expectation of a control system's behaviour in its network architecture, and directly inspire new directions in network analysis and design via distributed control.

  4. Squeeze-SegNet: a new fast deep convolutional neural network for semantic segmentation

    Science.gov (United States)

    Nanfack, Geraldin; Elhassouny, Azeddine; Oulad Haj Thami, Rachid

    2018-04-01

    The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to classification tasks, nowadays with contributions from Scientific Communities who are embarking in this field, they have become very useful in higher level tasks such as object detection and pixel-wise semantic segmentation. Thus, brilliant ideas in the field of semantic segmentation with deep learning have completed the state of the art of accuracy, however this architectures become very difficult to apply in embedded systems as is the case for autonomous driving. We present a new Deep fully Convolutional Neural Network for pixel-wise semantic segmentation which we call Squeeze-SegNet. The architecture is based on Encoder-Decoder style. We use a SqueezeNet-like encoder and a decoder formed by our proposed squeeze-decoder module and upsample layer using downsample indices like in SegNet and we add a deconvolution layer to provide final multi-channel feature map. On datasets like Camvid or City-states, our net gets SegNet-level accuracy with less than 10 times fewer parameters than SegNet.

  5. Data center networks and network architecture

    Science.gov (United States)

    Esaki, Hiroshi

    2014-02-01

    This paper discusses and proposes the architectural framework, which is for data center networks. The data center networks require new technical challenges, and it would be good opportunity to change the functions, which are not need in current and future networks. Based on the observation and consideration on data center networks, this paper proposes; (i) Broadcast-free layer 2 network (i.e., emulation of broadcast at the end-node), (ii) Full-mesh point-to-point pipes, and (iii) IRIDES (Invitation Routing aDvertisement for path Engineering System).

  6. Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network

    Science.gov (United States)

    Zhu, Aichun; Wang, Tian; Snoussi, Hichem

    2018-03-01

    This paper addresses the problems of the graphical-based human pose estimation in still images, including the diversity of appearances and confounding background clutter. We present a new architecture for estimating human pose using a Convolutional Neural Network (CNN). Firstly, a Relative Mixture Deformable Model (RMDM) is defined by each pair of connected parts to compute the relative spatial information in the graphical model. Secondly, a Local Multi-Resolution Convolutional Neural Network (LMR-CNN) is proposed to train and learn the multi-scale representation of each body parts by combining different levels of part context. Thirdly, a LMR-CNN based hierarchical model is defined to explore the context information of limb parts. Finally, the experimental results demonstrate the effectiveness of the proposed deep learning approach for human pose estimation.

  7. Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network

    Directory of Open Access Journals (Sweden)

    Aichun Zhu

    2018-03-01

    Full Text Available This paper addresses the problems of the graphical-based human pose estimation in still images, including the diversity of appearances and confounding background clutter. We present a new architecture for estimating human pose using a Convolutional Neural Network (CNN. Firstly, a Relative Mixture Deformable Model (RMDM is defined by each pair of connected parts to compute the relative spatial information in the graphical model. Secondly, a Local Multi-Resolution Convolutional Neural Network (LMR-CNN is proposed to train and learn the multi-scale representation of each body parts by combining different levels of part context. Thirdly, a LMR-CNN based hierarchical model is defined to explore the context information of limb parts. Finally, the experimental results demonstrate the effectiveness of the proposed deep learning approach for human pose estimation.

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

    Science.gov (United States)

    Gafarov, F M; Gafarova, V R

    2016-09-01

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

  9. Quantifying loopy network architectures.

    Directory of Open Access Journals (Sweden)

    Eleni Katifori

    Full Text Available Biology presents many examples of planar distribution and structural networks having dense sets of closed loops. An archetype of this form of network organization is the vasculature of dicotyledonous leaves, which showcases a hierarchically-nested architecture containing closed loops at many different levels. Although a number of approaches have been proposed to measure aspects of the structure of such networks, a robust metric to quantify their hierarchical organization is still lacking. We present an algorithmic framework, the hierarchical loop decomposition, that allows mapping loopy networks to binary trees, preserving in the connectivity of the trees the architecture of the original graph. We apply this framework to investigate computer generated graphs, such as artificial models and optimal distribution networks, as well as natural graphs extracted from digitized images of dicotyledonous leaves and vasculature of rat cerebral neocortex. We calculate various metrics based on the asymmetry, the cumulative size distribution and the Strahler bifurcation ratios of the corresponding trees and discuss the relationship of these quantities to the architectural organization of the original graphs. This algorithmic framework decouples the geometric information (exact location of edges and nodes from the metric topology (connectivity and edge weight and it ultimately allows us to perform a quantitative statistical comparison between predictions of theoretical models and naturally occurring loopy graphs.

  10. Damage Level Prediction of Reinforced Concrete Building Based on Earthquake Time History Using Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Suryanita Reni

    2017-01-01

    Full Text Available The strong motion earthquake could cause the building damage in case of the building not considered in the earthquake design of the building. The study aims to predict the damage-level of building due to earthquake using Artificial Neural Networks method. The building model is a reinforced concrete building with ten floors and height between floors is 3.6 m. The model building received a load of the earthquake based on nine earthquake time history records. Each time history scaled to 0,5g, 0,75g, and 1,0g. The Artificial Neural Networks are designed in 4 architectural models using the MATLAB program. Model 1 used the displacement, velocity, and acceleration as input and Model 2 used the displacement only as the input. Model 3 used the velocity as input, and Model 4 used the acceleration just as input. The output of the Neural Networks is the damage level of the building with the category of Safe (1, Immediate Occupancy (2, Life Safety (3 or in a condition of Collapse Prevention (4. According to the results, Neural Network models have the prediction rate of the damage level between 85%-95%. Therefore, one of the solutions for analyzing the structural responses and the damage level promptly and efficiently when the earthquake occurred is by using Artificial Neural Network

  11. A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242

    Directory of Open Access Journals (Sweden)

    Ahmed R. J. Almusawi

    2016-01-01

    Full Text Available This paper presents a novel inverse kinematics solution for robotic arm based on artificial neural network (ANN architecture. The motion of robotic arm is controlled by the kinematics of ANN. A new artificial neural network approach for inverse kinematics is proposed. The novelty of the proposed ANN is the inclusion of the feedback of current joint angles configuration of robotic arm as well as the desired position and orientation in the input pattern of neural network, while the traditional ANN has only the desired position and orientation of the end effector in the input pattern of neural network. In this paper, a six DOF Denso robotic arm with a gripper is controlled by ANN. The comprehensive experimental results proved the applicability and the efficiency of the proposed approach in robotic motion control. The inclusion of current configuration of joint angles in ANN significantly increased the accuracy of ANN estimation of the joint angles output. The new controller design has advantages over the existing techniques for minimizing the position error in unconventional tasks and increasing the accuracy of ANN in estimation of robot’s joint angles.

  12. A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242)

    Science.gov (United States)

    Dülger, L. Canan; Kapucu, Sadettin

    2016-01-01

    This paper presents a novel inverse kinematics solution for robotic arm based on artificial neural network (ANN) architecture. The motion of robotic arm is controlled by the kinematics of ANN. A new artificial neural network approach for inverse kinematics is proposed. The novelty of the proposed ANN is the inclusion of the feedback of current joint angles configuration of robotic arm as well as the desired position and orientation in the input pattern of neural network, while the traditional ANN has only the desired position and orientation of the end effector in the input pattern of neural network. In this paper, a six DOF Denso robotic arm with a gripper is controlled by ANN. The comprehensive experimental results proved the applicability and the efficiency of the proposed approach in robotic motion control. The inclusion of current configuration of joint angles in ANN significantly increased the accuracy of ANN estimation of the joint angles output. The new controller design has advantages over the existing techniques for minimizing the position error in unconventional tasks and increasing the accuracy of ANN in estimation of robot's joint angles. PMID:27610129

  13. A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242).

    Science.gov (United States)

    Almusawi, Ahmed R J; Dülger, L Canan; Kapucu, Sadettin

    2016-01-01

    This paper presents a novel inverse kinematics solution for robotic arm based on artificial neural network (ANN) architecture. The motion of robotic arm is controlled by the kinematics of ANN. A new artificial neural network approach for inverse kinematics is proposed. The novelty of the proposed ANN is the inclusion of the feedback of current joint angles configuration of robotic arm as well as the desired position and orientation in the input pattern of neural network, while the traditional ANN has only the desired position and orientation of the end effector in the input pattern of neural network. In this paper, a six DOF Denso robotic arm with a gripper is controlled by ANN. The comprehensive experimental results proved the applicability and the efficiency of the proposed approach in robotic motion control. The inclusion of current configuration of joint angles in ANN significantly increased the accuracy of ANN estimation of the joint angles output. The new controller design has advantages over the existing techniques for minimizing the position error in unconventional tasks and increasing the accuracy of ANN in estimation of robot's joint angles.

  14. A Low-Cost Maximum Power Point Tracking System Based on Neural Network Inverse Model Controller

    Directory of Open Access Journals (Sweden)

    Carlos Robles Algarín

    2018-01-01

    Full Text Available This work presents the design, modeling, and implementation of a neural network inverse model controller for tracking the maximum power point of a photovoltaic (PV module. A nonlinear autoregressive network with exogenous inputs (NARX was implemented in a serial-parallel architecture. The PV module mathematical modeling was developed, a buck converter was designed to operate in the continuous conduction mode with a switching frequency of 20 KHz, and the dynamic neural controller was designed using the Neural Network Toolbox from Matlab/Simulink (MathWorks, Natick, MA, USA, and it was implemented on an open-hardware Arduino Mega board. To obtain the reference signals for the NARX and determine the 65 W PV module behavior, a system made of a 0.8 W PV cell, a temperature sensor, a voltage sensor and a static neural network, was used. To evaluate performance a comparison with the P&O traditional algorithm was done in terms of response time and oscillations around the operating point. Simulation results demonstrated the superiority of neural controller over the P&O. Implementation results showed that approximately the same power is obtained with both controllers, but the P&O controller presents oscillations between 7 W and 10 W, in contrast to the inverse controller, which had oscillations between 1 W and 2 W.

  15. Enhancing neural-network performance via assortativity

    International Nuclear Information System (INIS)

    Franciscis, Sebastiano de; Johnson, Samuel; Torres, Joaquin J.

    2011-01-01

    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.

  16. Genetic algorithm for neural networks optimization

    Science.gov (United States)

    Setyawati, Bina R.; Creese, Robert C.; Sahirman, Sidharta

    2004-11-01

    This paper examines the forecasting performance of multi-layer feed forward neural networks in modeling a particular foreign exchange rates, i.e. Japanese Yen/US Dollar. The effects of two learning methods, Back Propagation and Genetic Algorithm, in which the neural network topology and other parameters fixed, were investigated. The early results indicate that the application of this hybrid system seems to be well suited for the forecasting of foreign exchange rates. The Neural Networks and Genetic Algorithm were programmed using MATLAB«.

  17. Neural Network Based Load Frequency Control for Restructuring ...

    African Journals Online (AJOL)

    Neural Network Based Load Frequency Control for Restructuring Power Industry. ... an artificial neural network (ANN) application of load frequency control (LFC) of a Multi-Area power system by using a neural network controller is presented.

  18. PREDIKSI FOREX MENGGUNAKAN MODEL NEURAL NETWORK

    Directory of Open Access Journals (Sweden)

    R. Hadapiningradja Kusumodestoni

    2015-11-01

    Full Text Available ABSTRAK Prediksi adalah salah satu teknik yang paling penting dalam menjalankan bisnis forex. Keputusan dalam memprediksi adalah sangatlah penting, karena dengan prediksi dapat membantu mengetahui nilai forex di waktu tertentu kedepan sehingga dapat mengurangi resiko kerugian. Tujuan dari penelitian ini dimaksudkan memprediksi bisnis fores menggunakan model neural network dengan data time series per 1 menit untuk mengetahui nilai akurasi prediksi sehingga dapat mengurangi resiko dalam menjalankan bisnis forex. Metode penelitian pada penelitian ini meliputi metode pengumpulan data kemudian dilanjutkan ke metode training, learning, testing menggunakan neural network. Setelah di evaluasi hasil penelitian ini menunjukan bahwa penerapan algoritma Neural Network mampu untuk memprediksi forex dengan tingkat akurasi prediksi 0.431 +/- 0.096 sehingga dengan prediksi ini dapat membantu mengurangi resiko dalam menjalankan bisnis forex. Kata kunci: prediksi, forex, neural network.

  19. Modeling by artificial neural networks. Application to the management of fuel in a nuclear power plant

    International Nuclear Information System (INIS)

    Gaudier, F.

    1999-01-01

    The determination of the family of optimum core loading patterns for Pressurized Water Reactors (PWRs) involves the assessment of the core attributes, such as the power peaking factor for thousands of candidate loading patterns. Despite the rapid advances in computer architecture, the direct calculation of these attributes by a neutronic code needs a lot of of time and memory. With the goal of reducing the calculation time and optimizing the loading pattern, we propose in this thesis a method based on ideas of neural and statistical learning to provide a feed forward neural network capable of calculating the power peaking corresponding to an eighth core PWR. We use statistical methods to deduct judicious inputs (reduction of the input space dimension) and neural methods to train the model (learning capabilities). Indeed, on one hand, a principal component analysis allows us to characterize more efficiently the fuel assemblies (neural model inputs) and the other hand, the introduction of the a priori knowledge allows us to reducing the number of freedom parameters in the neural network. The model was built using a multi layered perceptron trained with the standard back propagation algorithm. We introduced our neural network in the automatic optimization code FORMOSA, and on EDF real problems we showed an important saving in time. Finally, we propose an hybrid method which combining the best characteristics of the linear local approximator GPT (Generalized Perturbation Theory) and the artificial neural network. (author)

  20. Optical-Correlator Neural Network Based On Neocognitron

    Science.gov (United States)

    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.

  1. Nonequilibrium landscape theory of neural networks

    Science.gov (United States)

    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

  2. Nonequilibrium landscape theory of neural networks.

    Science.gov (United States)

    Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin

    2013-11-05

    The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape-flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments.

  3. Architectures of electro-optical packet switched networks

    DEFF Research Database (Denmark)

    Berger, Michael Stubert

    2004-01-01

    and examines possible architectures for future high capacity networks with high capacity nodes. It is assumed that optics will play a key role in this scenario, and in this respect, the European IST research project DAVID aimed at proposing viable architectures for optical packet switching, exploiting the best...... from optics and electronics. An overview of the DAVID network architecture is given, focusing on the MAN and WAN architecture as well as the MPLS based network hierarchy. A statistical model of the optical slot generation process is presented and utilised to evaluate delay vs. efficiency. Furthermore...... architecture for a buffered crossbar switch is presented. The architecture uses two levels of backpressure (flow control) with different constraints on round trip time. No additional scheduling complexity is introduced, and for the actual example shown, a reduction in memory of 75% was obtained at the cost...

  4. Neutron spectrometry and dosimetry by means of Bonner spheres system and artificial neural networks applying robust design of artificial neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Martinez B, M.R.; Ortiz R, J.M.; Vega C, H.R. [UAZ, Av. Ramon Lopez Velarde No. 801, 98000 Zacatecas (Mexico)

    2006-07-01

    An Artificial Neural Network has been designed, trained and tested to unfold neutron spectra and simultaneously to calculate equivalent doses. A set of 187 neutron spectra compiled by the International Atomic Energy Agency and 13 equivalent doses were used in the artificial neural network designed, trained and tested. In order to design the neural network was used the robust design of artificial neural networks methodology, which assures that the quality of the neural networks takes into account from the design stage. Unless previous works, here, for first time a group of neural networks were designed and trained to unfold 187 neutron spectra and at the same time to calculate 13 equivalent doses, starting from the count rates coming from the Bonner spheres system by using a systematic and experimental strategy. (Author)

  5. Neutron spectrometry and dosimetry by means of Bonner spheres system and artificial neural networks applying robust design of artificial neural networks

    International Nuclear Information System (INIS)

    Martinez B, M.R.; Ortiz R, J.M.; Vega C, H.R.

    2006-01-01

    An Artificial Neural Network has been designed, trained and tested to unfold neutron spectra and simultaneously to calculate equivalent doses. A set of 187 neutron spectra compiled by the International Atomic Energy Agency and 13 equivalent doses were used in the artificial neural network designed, trained and tested. In order to design the neural network was used the robust design of artificial neural networks methodology, which assures that the quality of the neural networks takes into account from the design stage. Unless previous works, here, for first time a group of neural networks were designed and trained to unfold 187 neutron spectra and at the same time to calculate 13 equivalent doses, starting from the count rates coming from the Bonner spheres system by using a systematic and experimental strategy. (Author)

  6. Combinatorial structures and processing in neural blackboard architectures

    NARCIS (Netherlands)

    van der Velde, Frank; van der Velde, Frank; de Kamps, Marc; Besold, Tarek R.; d'Avila Garcez, Artur; Marcus, Gary F.; Miikkulainen, Risto

    2015-01-01

    We discuss and illustrate Neural Blackboard Architectures (NBAs) as the basis for variable binding and combinatorial processing the brain. We focus on the NBA for sentence structure. NBAs are based on the notion that conceptual representations are in situ, hence cannot be copied or transported.

  7. Neural networks within multi-core optic fibers.

    Science.gov (United States)

    Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael

    2016-07-07

    Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.

  8. An Incremental Time-delay Neural Network for Dynamical Recurrent Associative Memory

    Institute of Scientific and Technical Information of China (English)

    2002-01-01

    An incremental time-delay neural network based on synapse growth, which is suitable for dynamic control and learning of autonomous robots, is proposed to improve the learning and retrieving performance of dynamical recurrent associative memory architecture. The model allows steady and continuous establishment of associative memory for spatio-temporal regularities and time series in discrete sequence of inputs. The inserted hidden units can be taken as the long-term memories that expand the capacity of network and sometimes may fade away under certain condition. Preliminary experiment has shown that this incremental network may be a promising approach to endow autonomous robots with the ability of adapting to new data without destroying the learned patterns. The system also benefits from its potential chaos character for emergence.

  9. Distribution network fault section identification and fault location using artificial neural network

    DEFF Research Database (Denmark)

    Dashtdar, Masoud; Dashti, Rahman; Shaker, Hamid Reza

    2018-01-01

    In this paper, a method for fault location in power distribution network is presented. The proposed method uses artificial neural network. In order to train the neural network, a series of specific characteristic are extracted from the recorded fault signals in relay. These characteristics...... components of the sequences as well as three-phase signals could be obtained using statistics to extract the hidden features inside them and present them separately to train the neural network. Also, since the obtained inputs for the training of the neural network strongly depend on the fault angle, fault...... resistance, and fault location, the training data should be selected such that these differences are properly presented so that the neural network does not face any issues for identification. Therefore, selecting the signal processing function, data spectrum and subsequently, statistical parameters...

  10. Development of automated system based on neural network algorithm for detecting defects on molds installed on casting machines

    Science.gov (United States)

    Bazhin, V. Yu; Danilov, I. V.; Petrov, P. A.

    2018-05-01

    During the casting of light alloys and ligatures based on aluminum and magnesium, problems of the qualitative distribution of the metal and its crystallization in the mold arise. To monitor the defects of molds on the casting conveyor, a camera with a resolution of 780 x 580 pixels and a shooting rate of 75 frames per second was selected. Images of molds from casting machines were used as input data for neural network algorithm. On the preparation of a digital database and its analytical evaluation stage, the architecture of the convolutional neural network was chosen for the algorithm. The information flow from the local controller is transferred to the OPC server and then to the SCADA system of foundry. After the training, accuracy of neural network defect recognition was about 95.1% on a validation split. After the training, weight coefficients of the neural network were used on testing split and algorithm had identical accuracy with validation images. The proposed technical solutions make it possible to increase the efficiency of the automated process control system in the foundry by expanding the digital database.

  11. Adaptive optimization and control using neural networks

    Energy Technology Data Exchange (ETDEWEB)

    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.

  12. Neural Networks

    Directory of Open Access Journals (Sweden)

    Schwindling Jerome

    2010-04-01

    Full Text Available This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p. corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.

  13. A research on the application of software defined networking in satellite network architecture

    Science.gov (United States)

    Song, Huan; Chen, Jinqiang; Cao, Suzhi; Cui, Dandan; Li, Tong; Su, Yuxing

    2017-10-01

    Software defined network is a new type of network architecture, which decouples control plane and data plane of traditional network, has the feature of flexible configurations and is a direction of the next generation terrestrial Internet development. Satellite network is an important part of the space-ground integrated information network, while the traditional satellite network has the disadvantages of difficult network topology maintenance and slow configuration. The application of SDN technology in satellite network can solve these problems that traditional satellite network faces. At present, the research on the application of SDN technology in satellite network is still in the stage of preliminary study. In this paper, we start with introducing the SDN technology and satellite network architecture. Then we mainly introduce software defined satellite network architecture, as well as the comparison of different software defined satellite network architecture and satellite network virtualization. Finally, the present research status and development trend of SDN technology in satellite network are analyzed.

  14. Altered Synchronizations among Neural Networks in Geriatric Depression.

    Science.gov (United States)

    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.

  15. Neural Networks for the Beginner.

    Science.gov (United States)

    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…

  16. Systematic classification and identification of noise spectra using perception-based neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Racz, A.; Kiss, S. (KFKI-Atomic Energy Research Inst., Budapest (Hungary). Applied Reactor Physics Lab.)

    1994-01-01

    A general framework for the detection of gradually developing changes in a noise generating system is presented. The procedure is based on a new learning algorithm developed for neural networks with dynamically building architecture. The method has been tested by using almost a thousand noise spectra recorded from different detector types and from different detector positions. This work is part of a larger project, aimed at developing a noise diagnostic expert system. (author).

  17. Neural network-based model reference adaptive control system.

    Science.gov (United States)

    Patino, H D; Liu, D

    2000-01-01

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

  18. Mass reconstruction with a neural network

    International Nuclear Information System (INIS)

    Loennblad, L.; Peterson, C.; Roegnvaldsson, T.

    1992-01-01

    A feed-forward neural network method is developed for reconstructing the invariant mass of hadronic jets appearing in a calorimeter. The approach is illustrated in W→qanti q, where W-bosons are produced in panti p reactions at SPS collider energies. The neural network method yields results that are superior to conventional methods. This neural network application differs from the classification ones in the sense that an analog number (the mass) is computed by the network, rather than a binary decision being made. As a by-product our application clearly demonstrates the need for using 'intelligent' variables in instances when the amount of training instances is limited. (orig.)

  19. Hybrid architecture for building secure sensor networks

    Science.gov (United States)

    Owens, Ken R., Jr.; Watkins, Steve E.

    2012-04-01

    Sensor networks have various communication and security architectural concerns. Three approaches are defined to address these concerns for sensor networks. The first area is the utilization of new computing architectures that leverage embedded virtualization software on the sensor. Deploying a small, embedded virtualization operating system on the sensor nodes that is designed to communicate to low-cost cloud computing infrastructure in the network is the foundation to delivering low-cost, secure sensor networks. The second area focuses on securing the sensor. Sensor security components include developing an identification scheme, and leveraging authentication algorithms and protocols that address security assurance within the physical, communication network, and application layers. This function will primarily be accomplished through encrypting the communication channel and integrating sensor network firewall and intrusion detection/prevention components to the sensor network architecture. Hence, sensor networks will be able to maintain high levels of security. The third area addresses the real-time and high priority nature of the data that sensor networks collect. This function requires that a quality-of-service (QoS) definition and algorithm be developed for delivering the right data at the right time. A hybrid architecture is proposed that combines software and hardware features to handle network traffic with diverse QoS requirements.

  20. Inversion of a lateral log using neural networks

    International Nuclear Information System (INIS)

    Garcia, G.; Whitman, W.W.

    1992-01-01

    In this paper a technique using neural networks is demonstrated for the inversion of a lateral log. The lateral log is simulated by a finite difference method which in turn is used as an input to a backpropagation neural network. An initial guess earth model is generated from the neural network, which is then input to a Marquardt inversion. The neural network reacts to gross and subtle data features in actual logs and produces a response inferred from the knowledge stored in the network during a training process. The neural network inversion of lateral logs is tested on synthetic and field data. Tests using field data resulted in a final earth model whose simulated lateral is in good agreement with the actual log data

  1. Financial time series prediction using spiking neural networks.

    Science.gov (United States)

    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.

  2. Neural Networks in Mobile Robot Motion

    Directory of Open Access Journals (Sweden)

    Danica Janglová

    2004-03-01

    Full Text Available This paper deals with a path planning and intelligent control of an autonomous robot which should move safely in partially structured environment. This environment may involve any number of obstacles of arbitrary shape and size; some of them are allowed to move. We describe our approach to solving the motion-planning problem in mobile robot control using neural networks-based technique. Our method of the construction of a collision-free path for moving robot among obstacles is based on two neural networks. The first neural network is used to determine the “free” space using ultrasound range finder data. The second neural network “finds” a safe direction for the next robot section of the path in the workspace while avoiding the nearest obstacles. Simulation examples of generated path with proposed techniques will be presented.

  3. International Conference on Artificial Neural Networks (ICANN)

    CERN Document Server

    Mladenov, Valeri; Kasabov, Nikola; Artificial Neural Networks : Methods and Applications in Bio-/Neuroinformatics

    2015-01-01

    The book reports on the latest theories on artificial neural networks, with a special emphasis on bio-neuroinformatics methods. It includes twenty-three papers selected from among the best contributions on bio-neuroinformatics-related issues, which were presented at the International Conference on Artificial Neural Networks, held in Sofia, Bulgaria, on September 10-13, 2013 (ICANN 2013). The book covers a broad range of topics concerning the theory and applications of artificial neural networks, including recurrent neural networks, super-Turing computation and reservoir computing, double-layer vector perceptrons, nonnegative matrix factorization, bio-inspired models of cell communities, Gestalt laws, embodied theory of language understanding, saccadic gaze shifts and memory formation, and new training algorithms for Deep Boltzmann Machines, as well as dynamic neural networks and kernel machines. It also reports on new approaches to reinforcement learning, optimal control of discrete time-delay systems, new al...

  4. Development of efficiency module of organization of Arctic sea cargo transportation with application of neural network technologies

    Science.gov (United States)

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

    2018-05-01

    The analysis of software intended for organizing and managing the processes of sea cargo transportation has been carried out. The shortcomings of information resources are presented, for the organization of work in the Arctic and Subarctic regions of the Far East: the lack of decision support systems, the lack of factor analysis to calculate the time and cost of delivery. The architecture of the module for calculating the effectiveness of the organization of sea cargo transportation has been developed. The simulation process has been considered, which is based on the neural network. The main classification factors with their weighting coefficients have been identified. The architecture of the neural network has been developed to calculate the efficiency of the organization of sea cargo transportation in Arctic conditions. The architecture of the intellectual system of organization of sea cargo transportation has been developed, taking into account the difficult navigation conditions in the Arctic. Its implementation will allow one to provide the management of the shipping company with predictive analytics; to support decision-making; to calculate the most efficient delivery route; to provide on demand online transportation forecast, to minimize the shipping cost, delays in transit, and risks to cargo safety.

  5. Classifying medical relations in clinical text via convolutional neural networks.

    Science.gov (United States)

    He, Bin; Guan, Yi; Dai, Rui

    2018-05-16

    Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method. Copyright © 2018. Published by Elsevier B.V.

  6. Application of Neural Networks for classification of Patau, Edwards, Down, Turner and Klinefelter Syndrome based on first trimester maternal serum screening data, ultrasonographic findings and patient demographics.

    Science.gov (United States)

    Catic, Aida; Gurbeta, Lejla; Kurtovic-Kozaric, Amina; Mehmedbasic, Senad; Badnjevic, Almir

    2018-02-13

    The usage of Artificial Neural Networks (ANNs) for genome-enabled classifications and establishing genome-phenotype correlations have been investigated more extensively over the past few years. The reason for this is that ANNs are good approximates of complex functions, so classification can be performed without the need for explicitly defined input-output model. This engineering tool can be applied for optimization of existing methods for disease/syndrome classification. Cytogenetic and molecular analyses are the most frequent tests used in prenatal diagnostic for the early detection of Turner, Klinefelter, Patau, Edwards and Down syndrome. These procedures can be lengthy, repetitive; and often employ invasive techniques so a robust automated method for classifying and reporting prenatal diagnostics would greatly help the clinicians with their routine work. The database consisted of data collected from 2500 pregnant woman that came to the Institute of Gynecology, Infertility and Perinatology "Mehmedbasic" for routine antenatal care between January 2000 and December 2016. During first trimester all women were subject to screening test where values of maternal serum pregnancy-associated plasma protein A (PAPP-A) and free beta human chorionic gonadotropin (β-hCG) were measured. Also, fetal nuchal translucency thickness and the presence or absence of the nasal bone was observed using ultrasound. The architectures of linear feedforward and feedback neural networks were investigated for various training data distributions and number of neurons in hidden layer. Feedback neural network architecture out performed feedforward neural network architecture in predictive ability for all five aneuploidy prenatal syndrome classes. Feedforward neural network with 15 neurons in hidden layer achieved classification sensitivity of 92.00%. Classification sensitivity of feedback (Elman's) neural network was 99.00%. Average accuracy of feedforward neural network was 89.6% and for

  7. Proposed Network Intrusion Detection System ‎In Cloud Environment Based on Back ‎Propagation Neural Network

    Directory of Open Access Journals (Sweden)

    Shawq Malik Mehibs

    2017-12-01

    Full Text Available Cloud computing is distributed architecture, providing computing facilities and storage resource as a service over the internet. This low-cost service fulfills the basic requirements of users. Because of the open nature and services introduced by cloud computing intruders impersonate legitimate users and misuse cloud resource and services. To detect intruders and suspicious activities in and around the cloud computing environment, intrusion detection system used to discover the illegitimate users and suspicious action by monitors different user activities on the network .this work proposed based back propagation artificial neural network to construct t network intrusion detection in the cloud environment. The proposed module evaluated with kdd99 dataset the experimental results shows promising approach to detect attack with high detection rate and low false alarm rate

  8. Interpretable neural networks with BP-SOM

    NARCIS (Netherlands)

    Weijters, A.J.M.M.; Bosch, van den A.P.J.; Pobil, del A.P.; Mira, J.; Ali, M.

    1998-01-01

    Artificial Neural Networks (ANNS) are used successfully in industry and commerce. This is not surprising since neural networks are especially competitive for complex tasks for which insufficient domain-specific knowledge is available. However, interpretation of models induced by ANNS is often

  9. Adaptive nonlinear control using input normalized neural networks

    International Nuclear Information System (INIS)

    Leeghim, Henzeh; Seo, In Ho; Bang, Hyo Choong

    2008-01-01

    An adaptive feedback linearization technique combined with the neural network is addressed to control uncertain nonlinear systems. The neural network-based adaptive control theory has been widely studied. However, the stability analysis of the closed-loop system with the neural network is rather complicated and difficult to understand, and sometimes unnecessary assumptions are involved. As a result, unnecessary assumptions for stability analysis are avoided by using the neural network with input normalization technique. The ultimate boundedness of the tracking error is simply proved by the Lyapunov stability theory. A new simple update law as an adaptive nonlinear control is derived by the simplification of the input normalized neural network assuming the variation of the uncertain term is sufficiently small

  10. Runoff Modelling in Urban Storm Drainage by Neural Networks

    DEFF Research Database (Denmark)

    Rasmussen, Michael R.; Brorsen, Michael; Schaarup-Jensen, Kjeld

    1995-01-01

    A neural network is used to simulate folw and water levels in a sewer system. The calibration of th neural network is based on a few measured events and the network is validated against measureed events as well as flow simulated with the MOUSE model (Lindberg and Joergensen, 1986). The neural...... network is used to compute flow or water level at selected points in the sewer system, and to forecast the flow from a small residential area. The main advantages of the neural network are the build-in self calibration procedure and high speed performance, but the neural network cannot be used to extract...... knowledge of the runoff process. The neural network was found to simulate 150 times faster than e.g. the MOUSE model....

  11. Neural networks in economic modelling : An empirical study

    NARCIS (Netherlands)

    Verkooijen, W.J.H.

    1996-01-01

    This dissertation addresses the statistical aspects of neural networks and their usability for solving problems in economics and finance. Neural networks are discussed in a framework of modelling which is generally accepted in econometrics. Within this framework a neural network is regarded as a

  12. Reconstruction of Micropattern Detector Signals using Convolutional Neural Networks

    Science.gov (United States)

    Flekova, L.; Schott, M.

    2017-10-01

    Micropattern gaseous detector (MPGD) technologies, such as GEMs or MicroMegas, are particularly suitable for precision tracking and triggering in high rate environments. Given their relatively low production costs, MPGDs are an exemplary candidate for the next generation of particle detectors. Having acknowledged these advantages, both the ATLAS and CMS collaborations at the LHC are exploiting these new technologies for their detector upgrade programs in the coming years. When MPGDs are utilized for triggering purposes, the measured signals need to be precisely reconstructed within less than 200 ns, which can be achieved by the usage of FPGAs. In this work, we present a novel approach to identify reconstructed signals, their timing and the corresponding spatial position on the detector. In particular, we study the effect of noise and dead readout strips on the reconstruction performance. Our approach leverages the potential of convolutional neural network (CNNs), which have recently manifested an outstanding performance in a range of modeling tasks. The proposed neural network architecture of our CNN is designed simply enough, so that it can be modeled directly by an FPGA and thus provide precise information on reconstructed signals already in trigger level.

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

    Science.gov (United States)

    Testolin, Alberto; Zorzi, Marco

    2016-01-01

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

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

    Science.gov (United States)

    Takiyama, Ken

    2017-12-01

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

  15. Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities.

    Science.gov (United States)

    Ghafoorian, Mohsen; Karssemeijer, Nico; Heskes, Tom; van Uden, Inge W M; Sanchez, Clara I; Litjens, Geert; de Leeuw, Frank-Erik; van Ginneken, Bram; Marchiori, Elena; Platel, Bram

    2017-07-11

    The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).

  16. A fuzzy neural network for sensor signal estimation

    International Nuclear Information System (INIS)

    Na, Man Gyun

    2000-01-01

    In this work, a fuzzy neural network is used to estimate the relevant sensor signal using other sensor signals. Noise components in input signals into the fuzzy neural network are removed through the wavelet denoising technique. Principal component analysis (PCA) is used to reduce the dimension of an input space without losing a significant amount of information. A lower dimensional input space will also usually reduce the time necessary to train a fuzzy-neural network. Also, the principal component analysis makes easy the selection of the input signals into the fuzzy neural network. The fuzzy neural network parameters are optimized by two learning methods. A genetic algorithm is used to optimize the antecedent parameters of the fuzzy neural network and a least-squares algorithm is used to solve the consequent parameters. The proposed algorithm was verified through the application to the pressurizer water level and the hot-leg flowrate measurements in pressurized water reactors

  17. Multistability in bidirectional associative memory neural networks

    International Nuclear Information System (INIS)

    Huang Gan; Cao Jinde

    2008-01-01

    In this Letter, the multistability issue is studied for Bidirectional Associative Memory (BAM) neural networks. Based on the existence and stability analysis of the neural networks with or without delay, it is found that the 2n-dimensional networks can have 3 n equilibria and 2 n equilibria of them are locally exponentially stable, where each layer of the BAM network has n neurons. Furthermore, the results has been extended to (n+m)-dimensional BAM neural networks, where there are n and m neurons on the two layers respectively. Finally, two numerical examples are presented to illustrate the validity of our results

  18. Multistability in bidirectional associative memory neural networks

    Science.gov (United States)

    Huang, Gan; Cao, Jinde

    2008-04-01

    In this Letter, the multistability issue is studied for Bidirectional Associative Memory (BAM) neural networks. Based on the existence and stability analysis of the neural networks with or without delay, it is found that the 2 n-dimensional networks can have 3 equilibria and 2 equilibria of them are locally exponentially stable, where each layer of the BAM network has n neurons. Furthermore, the results has been extended to (n+m)-dimensional BAM neural networks, where there are n and m neurons on the two layers respectively. Finally, two numerical examples are presented to illustrate the validity of our results.

  19. Machine Learning Topological Invariants with Neural Networks

    Science.gov (United States)

    Zhang, Pengfei; Shen, Huitao; Zhai, Hui

    2018-02-01

    In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators. After training with Hamiltonians of one-dimensional insulators with chiral symmetry, the neural network can predict their topological winding numbers with nearly 100% accuracy, even for Hamiltonians with larger winding numbers that are not included in the training data. These results show a remarkable success that the neural network can capture the global and nonlinear topological features of quantum phases from local inputs. By opening up the neural network, we confirm that the network does learn the discrete version of the winding number formula. We also make a couple of remarks regarding the role of the symmetry and the opposite effect of regularization techniques when applying machine learning to physical systems.

  20. Using Weightless Neural Networks for Vergence Control in an Artificial Vision System

    Directory of Open Access Journals (Sweden)

    Karin S. Komati

    2003-01-01

    Full Text Available This paper presents a methodology we have developed and used to implement an artificial binocular vision system capable of emulating the vergence of eye movements. This methodology involves using weightless neural networks (WNNs as building blocks of artificial vision systems. Using the proposed methodology, we have designed several architectures of WNN-based artificial vision systems, in which images captured by virtual cameras are used for controlling the position of the ‘foveae’ of these cameras (high-resolution region of the images captured. Our best architecture is able to control the foveae vergence movements with average error of only 3.58 image pixels, which is equivalent to an angular error of approximately 0.629°.

  1. Time series prediction with simple recurrent neural networks ...

    African Journals Online (AJOL)

    A hybrid of the two called Elman-Jordan (or Multi-recurrent) neural network is also being used. In this study, we evaluated the performance of these neural networks on three established bench mark time series prediction problems. Results from the experiments showed that Jordan neural network performed significantly ...

  2. Quantum neural networks: Current status and prospects for development

    Science.gov (United States)

    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.

  3. Neural network modeling for near wall turbulent flow

    International Nuclear Information System (INIS)

    Milano, Michele; Koumoutsakos, Petros

    2002-01-01

    A neural network methodology is developed in order to reconstruct the near wall field in a turbulent flow by exploiting flow fields provided by direct numerical simulations. The results obtained from the neural network methodology are compared with the results obtained from prediction and reconstruction using proper orthogonal decomposition (POD). Using the property that the POD is equivalent to a specific linear neural network, a nonlinear neural network extension is presented. It is shown that for a relatively small additional computational cost nonlinear neural networks provide us with improved reconstruction and prediction capabilities for the near wall velocity fields. Based on these results advantages and drawbacks of both approaches are discussed with an outlook toward the development of near wall models for turbulence modeling and control

  4. Application of neural networks in CRM systems

    Directory of Open Access Journals (Sweden)

    Bojanowska Agnieszka

    2017-01-01

    Full Text Available The central aim of this study is to investigate how to apply artificial neural networks in Customer Relationship Management (CRM. The paper presents several business applications of neural networks in software systems designed to aid CRM, e.g. in deciding on the profitability of building a relationship with a given customer. Furthermore, a framework for a neural-network based CRM software tool is developed. Building beneficial relationships with customers is generating considerable interest among various businesses, and is often mentioned as one of the crucial objectives of enterprises, next to their key aim: to bring satisfactory profit. There is a growing tendency among businesses to invest in CRM systems, which together with an organisational culture of a company aid managing customer relationships. It is the sheer amount of gathered data as well as the need for constant updating and analysis of this breadth of information that may imply the suitability of neural networks for the application in question. Neural networks exhibit considerably higher computational capabilities than sequential calculations because the solution to a problem is obtained without the need for developing a special algorithm. In the majority of presented CRM applications neural networks constitute and are presented as a managerial decision-taking optimisation tool.

  5. An application of neural networks to process and materials control

    International Nuclear Information System (INIS)

    Howell, J.A.; Whiteson, R.

    1991-01-01

    Process control consists of two basic elements: a model of the process and knowledge of the desired control algorithm. In some cases the level of the control algorithm is merely supervisory, as in an alarm-reporting or anomaly-detection system. If the model of the process is known, then a set of equations may often be solved explicitly to provide the control algorithm. Otherwise, the model has to be discovered through empirical studies. Neural networks have properties that make them useful in this application. They can learn (make internal models from experience or observations). The problem of anomaly detection in materials control systems fits well into this general control framework. To successfully model a process with a neutral network, a good set of observables must be chosen. These observables must in some sense adequately span the space of representable events, so that a signature metric can be built for normal operation. In this way, a non-normal event, one that does not fit within the signature, can be detected. In this paper, we discuss the issues involved in applying a neural network model to anomaly detection in materials control systems. These issues include data selection and representation, network architecture, prediction of events, the use of simulated data, and software tools. 10 refs., 4 figs., 1 tab

  6. Local Dynamics in Trained Recurrent Neural Networks.

    Science.gov (United States)

    Rivkind, Alexander; Barak, Omri

    2017-06-23

    Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.

  7. Local Dynamics in Trained Recurrent Neural Networks

    Science.gov (United States)

    Rivkind, Alexander; Barak, Omri

    2017-06-01

    Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.

  8. Neural attractor network for application in visual field data classification

    International Nuclear Information System (INIS)

    Fink, Wolfgang

    2004-01-01

    The purpose was to introduce a novel method for computer-based classification of visual field data derived from perimetric examination, that may act as a ' counsellor', providing an independent 'second opinion' to the diagnosing physician. The classification system consists of a Hopfield-type neural attractor network that obtains its input data from perimetric examination results. An iterative relaxation process determines the states of the neurons dynamically. Therefore, even 'noisy' perimetric output, e.g., early stages of a disease, may eventually be classified correctly according to the predefined idealized visual field defect (scotoma) patterns, stored as attractors of the network, that are found with diseases of the eye, optic nerve and the central nervous system. Preliminary tests of the classification system on real visual field data derived from perimetric examinations have shown a classification success of over 80%. Some of the main advantages of the Hopfield-attractor-network-based approach over feed-forward type neural networks are: (1) network architecture is defined by the classification problem; (2) no training is required to determine the neural coupling strengths; (3) assignment of an auto-diagnosis confidence level is possible by means of an overlap parameter and the Hamming distance. In conclusion, the novel method for computer-based classification of visual field data, presented here, furnishes a valuable first overview and an independent 'second opinion' in judging perimetric examination results, pointing towards a final diagnosis by a physician. It should not be considered a substitute for the diagnosing physician. Thanks to the worldwide accessibility of the Internet, the classification system offers a promising perspective towards modern computer-assisted diagnosis in both medicine and tele-medicine, for example and in particular, with respect to non-ophthalmic clinics or in communities where perimetric expertise is not readily available

  9. Two-stage neural-network-based technique for Urdu character two-dimensional shape representation, classification, and recognition

    Science.gov (United States)

    Megherbi, Dalila B.; Lodhi, S. M.; Boulenouar, A. J.

    2001-03-01

    This work is in the field of automated document processing. This work addresses the problem of representation and recognition of Urdu characters using Fourier representation and a Neural Network architecture. In particular, we show that a two-stage Neural Network scheme is used here to make classification of 36 Urdu characters into seven sub-classes namely subclasses characterized by seven proposed and defined fuzzy features specifically related to Urdu characters. We show that here Fourier Descriptors and Neural Network provide a remarkably simple way to draw definite conclusions from vague, ambiguous, noisy or imprecise information. In particular, we illustrate the concept of interest regions and describe a framing method that provides a way to make the proposed technique for Urdu characters recognition robust and invariant to scaling and translation. We also show that a given character rotation is dealt with by using the Hotelling transform. This transform is based upon the eigenvalue decomposition of the covariance matrix of an image, providing a method of determining the orientation of the major axis of an object within an image. Finally experimental results are presented to show the power and robustness of the proposed two-stage Neural Network based technique for Urdu character recognition, its fault tolerance, and high recognition accuracy.

  10. Mode Choice Modeling Using Artificial Neural Networks

    OpenAIRE

    Edara, Praveen Kumar

    2003-01-01

    Artificial intelligence techniques have produced excellent results in many diverse fields of engineering. Techniques such as neural networks and fuzzy systems have found their way into transportation engineering. In recent years, neural networks are being used instead of regression techniques for travel demand forecasting purposes. The basic reason lies in the fact that neural networks are able to capture complex relationships and learn from examples and also able to adapt when new data becom...

  11. Neutron spectrometry with artificial neural networks

    International Nuclear Information System (INIS)

    Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Rodriguez, J.M.; Mercado S, G.A.; Iniguez de la Torre Bayo, M.P.; Barquero, R.; Arteaga A, T.

    2005-01-01

    An artificial neural network has been designed to obtain the neutron spectra from the Bonner spheres spectrometer's count rates. The neural network was trained using 129 neutron spectra. These include isotopic neutron sources; reference and operational spectra from accelerators and nuclear reactors, spectra from mathematical functions as well as few energy groups and monoenergetic spectra. The spectra were transformed from lethargy to energy distribution and were re-bin ned to 31 energy groups using the MCNP 4C code. Re-binned spectra and UTA4 response matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and the respective spectrum was used as output during neural network training. After training the network was tested with the Bonner spheres count rates produced by a set of neutron spectra. This set contains data used during network training as well as data not used. Training and testing was carried out in the Mat lab program. To verify the network unfolding performance the original and unfolded spectra were compared using the χ 2 -test and the total fluence ratios. The use of Artificial Neural Networks to unfold neutron spectra in neutron spectrometry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

  12. A neural network construction method for surrogate modeling of physics-based analysis

    Science.gov (United States)

    Sung, Woong Je

    In this thesis existing methodologies related to the developmental methods of neural networks have been surveyed and their approaches to network sizing and structuring are carefully observed. This literature review covers the constructive methods, the pruning methods, and the evolutionary methods and questions about the basic assumption intrinsic to the conventional neural network learning paradigm, which is primarily devoted to optimization of connection weights (or synaptic strengths) for the pre-determined connection structure of the network. The main research hypothesis governing this thesis is that, without breaking a prevailing dichotomy between weights and connectivity of the network during learning phase, the efficient design of a task-specific neural network is hard to achieve because, as long as connectivity and weights are searched by separate means, a structural optimization of the neural network requires either repetitive re-training procedures or computationally expensive topological meta-search cycles. The main contribution of this thesis is designing and testing a novel learning mechanism which efficiently learns not only weight parameters but also connection structure from a given training data set, and positioning this learning mechanism within the surrogate modeling practice. In this work, a simple and straightforward extension to the conventional error Back-Propagation (BP) algorithm has been formulated to enable a simultaneous learning for both connectivity and weights of the Generalized Multilayer Perceptron (GMLP) in supervised learning tasks. A particular objective is to achieve a task-specific network having reasonable generalization performance with a minimal training time. The dichotomy between architectural design and weight optimization is reconciled by a mechanism establishing a new connection for a neuron pair which has potentially higher error-gradient than one of the existing connections. Interpreting an instance of the absence of

  13. Neural network and its application to CT imaging

    Energy Technology Data Exchange (ETDEWEB)

    Nikravesh, M.; Kovscek, A.R.; Patzek, T.W. [Lawrence Berkeley National Lab., CA (United States)] [and others

    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.

  14. Artificial neural networks in neutron dosimetry

    Energy Technology Data Exchange (ETDEWEB)

    Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Mercado, G.A.; Perales M, W.A.; Robles R, J.A. [Unidades Academicas de Estudios Nucleares, UAZ, A.P. 336, 98000 Zacatecas (Mexico); Gallego, E.; Lorente, A. [Depto. de Ingenieria Nuclear, Universidad Politecnica de Madrid, (Spain)

    2005-07-01

    An artificial neural network has been designed to obtain the neutron doses using only the Bonner spheres spectrometer's count rates. Ambient, personal and effective neutron doses were included. 187 neutron spectra were utilized to calculate the Bonner count rates and the neutron doses. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra, UTA4 response matrix and fluence-to-dose coefficients were used to calculate the count rates in Bonner spheres spectrometer and the doses. Count rates were used as input and the respective doses were used as output during neural network training. Training and testing was carried out in Mat lab environment. The artificial neural network performance was evaluated using the {chi}{sup 2}- test, where the original and calculated doses were compared. The use of Artificial Neural Networks in neutron dosimetry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

  15. Artificial neural networks in neutron dosimetry

    International Nuclear Information System (INIS)

    Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Mercado, G.A.; Perales M, W.A.; Robles R, J.A.; Gallego, E.; Lorente, A.

    2005-01-01

    An artificial neural network has been designed to obtain the neutron doses using only the Bonner spheres spectrometer's count rates. Ambient, personal and effective neutron doses were included. 187 neutron spectra were utilized to calculate the Bonner count rates and the neutron doses. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra, UTA4 response matrix and fluence-to-dose coefficients were used to calculate the count rates in Bonner spheres spectrometer and the doses. Count rates were used as input and the respective doses were used as output during neural network training. Training and testing was carried out in Mat lab environment. The artificial neural network performance was evaluated using the χ 2 - test, where the original and calculated doses were compared. The use of Artificial Neural Networks in neutron dosimetry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

  16. Artificial neural network as the tool in prediction rheological features of raw minced meat.

    Science.gov (United States)

    Balejko, Jerzy A; Nowak, Zbigniew; Balejko, Edyta

    2012-01-01

    The aim of the study was to elaborate a method of modelling and forecasting rheological features which could be applied to raw minced meat at the stage of mixture preparation with a given ingredient composition. The investigated material contained pork and beef meat, pork fat, fat substitutes, ice and curing mixture in various proportions. Seven texture parameters were measured for each sample of raw minced meat. The data obtained were processed using the artificial neural network module in Statistica 9.0 software. The model that reached the lowest training error was a multi-layer perceptron MLP with three neural layers and architecture 7:7-11-7:7. Correlation coefficients between the experimental and calculated values in training, verification and testing subsets were similar and rather high (around 0.65) which indicated good network performance. High percentage of the total variance explained in PCA analysis (73.5%) indicated that the percentage composition of raw minced meat can be successfully used in the prediction of its rheological features. Statistical analysis of the results revealed, that artificial neural network model is able to predict rheological parameters and thus a complete texture profile of raw minced meat.

  17. EEG signal classification based on artificial neural networks and amplitude spectra features

    Science.gov (United States)

    Chojnowski, K.; FrÄ czek, J.

    BCI (called Brain-Computer Interface) is an interface that allows direct communication between human brain and an external device. It bases on EEG signal collection, processing and classification. In this paper a complete BCI system is presented which classifies EEG signal using artificial neural networks. For this purpose we used a multi-layered perceptron architecture trained with the RProp algorithm. Furthermore a simple multi-threaded method for automatic network structure optimizing was shown. We presented the results of our system in the opening and closing eyes recognition task. We also showed how our system could be used for controlling devices basing on imaginary hand movements.

  18. Artificial neural networks for plasma spectroscopy analysis

    International Nuclear Information System (INIS)

    Morgan, W.L.; Larsen, J.T.; Goldstein, W.H.

    1992-01-01

    Artificial neural networks have been applied to a variety of signal processing and image recognition problems. Of the several common neural models the feed-forward, back-propagation network is well suited for the analysis of scientific laboratory data, which can be viewed as a pattern recognition problem. The authors present a discussion of the basic neural network concepts and illustrate its potential for analysis of experiments by applying it to the spectra of laser produced plasmas in order to obtain estimates of electron temperatures and densities. Although these are high temperature and density plasmas, the neural network technique may be of interest in the analysis of the low temperature and density plasmas characteristic of experiments and devices in gaseous electronics

  19. Dynamic training algorithm for dynamic neural networks

    International Nuclear Information System (INIS)

    Tan, Y.; Van Cauwenberghe, A.; Liu, Z.

    1996-01-01

    The widely used backpropagation algorithm for training neural networks based on the gradient descent has a significant drawback of slow convergence. A Gauss-Newton method based recursive least squares (RLS) type algorithm with dynamic error backpropagation is presented to speed-up the learning procedure of neural networks with local recurrent terms. Finally, simulation examples concerning the applications of the RLS type algorithm to identification of nonlinear processes using a local recurrent neural network are also included in this paper

  20. Neural Networks for Non-linear Control

    DEFF Research Database (Denmark)

    Sørensen, O.

    1994-01-01

    This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....

  1. A neural network model of ventriloquism effect and aftereffect.

    Science.gov (United States)

    Magosso, Elisa; Cuppini, Cristiano; Ursino, Mauro

    2012-01-01

    Presenting simultaneous but spatially discrepant visual and auditory stimuli induces a perceptual translocation of the sound towards the visual input, the ventriloquism effect. General explanation is that vision tends to dominate over audition because of its higher spatial reliability. The underlying neural mechanisms remain unclear. We address this question via a biologically inspired neural network. The model contains two layers of unimodal visual and auditory neurons, with visual neurons having higher spatial resolution than auditory ones. Neurons within each layer communicate via lateral intra-layer synapses; neurons across layers are connected via inter-layer connections. The network accounts for the ventriloquism effect, ascribing it to a positive feedback between the visual and auditory neurons, triggered by residual auditory activity at the position of the visual stimulus. Main results are: i) the less localized stimulus is strongly biased toward the most localized stimulus and not vice versa; ii) amount of the ventriloquism effect changes with visual-auditory spatial disparity; iii) ventriloquism is a robust behavior of the network with respect to parameter value changes. Moreover, the model implements Hebbian rules for potentiation and depression of lateral synapses, to explain ventriloquism aftereffect (that is, the enduring sound shift after exposure to spatially disparate audio-visual stimuli). By adaptively changing the weights of lateral synapses during cross-modal stimulation, the model produces post-adaptive shifts of auditory localization that agree with in-vivo observations. The model demonstrates that two unimodal layers reciprocally interconnected may explain ventriloquism effect and aftereffect, even without the presence of any convergent multimodal area. The proposed study may provide advancement in understanding neural architecture and mechanisms at the basis of visual-auditory integration in the spatial realm.

  2. Learning representations for the early detection of sepsis with deep neural networks.

    Science.gov (United States)

    Kam, Hye Jin; Kim, Ha Young

    2017-10-01

    Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns. Copyright © 2017 Elsevier Ltd. All rights reserved.

  3. Modelling of solar energy potential in Nigeria using an artificial neural network model

    International Nuclear Information System (INIS)

    Fadare, D.A.

    2009-01-01

    In this study, an artificial neural network (ANN) based model for prediction of solar energy potential in Nigeria (lat. 4-14 o N, log. 2-15 o E) was developed. Standard multilayered, feed-forward, back-propagation neural networks with different architecture were designed using neural toolbox for MATLAB. Geographical and meteorological data of 195 cities in Nigeria for period of 10 years (1983-1993) from the NASA geo-satellite database were used for the training and testing the network. Meteorological and geographical data (latitude, longitude, altitude, month, mean sunshine duration, mean temperature, and relative humidity) were used as inputs to the network, while the solar radiation intensity was used as the output of the network. The results show that the correlation coefficients between the ANN predictions and actual mean monthly global solar radiation intensities for training and testing datasets were higher than 90%, thus suggesting a high reliability of the model for evaluation of solar radiation in locations where solar radiation data are not available. The predicted solar radiation values from the model were given in form of monthly maps. The monthly mean solar radiation potential in northern and southern regions ranged from 7.01-5.62 to 5.43-3.54 kW h/m 2 day, respectively. A graphical user interface (GUI) was developed for the application of the model. The model can be used easily for estimation of solar radiation for preliminary design of solar applications.

  4. Using neural networks to describe tracer correlations

    Directory of Open Access Journals (Sweden)

    D. J. Lary

    2004-01-01

    Full Text Available 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 methane 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 coefficient between simulated and training values 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.

  5. Inverting radiometric measurements with a neural network

    Science.gov (United States)

    Measure, Edward M.; Yee, Young P.; Balding, Jeff M.; Watkins, Wendell R.

    1992-02-01

    A neural network scheme for retrieving remotely sensed vertical temperature profiles was applied to observed ground based radiometer measurements. The neural network used microwave radiance measurements and surface measurements of temperature and pressure as inputs. Because the microwave radiometer is capable of measuring 4 oxygen channels at 5 different elevation angles (9, 15, 25, 40, and 90 degs), 20 microwave measurements are potentially available. Because these measurements have considerable redundancy, a neural network was experimented with, accepting as inputs microwave measurements taken at 53.88 GHz, 40 deg; 57.45 GHz, 40 deg; and 57.45, 90 deg. The primary test site was located at White Sands Missile Range (WSMR), NM. Results are compared with measurements made simultaneously with balloon borne radiosonde instruments and with radiometric temperature retrievals made using more conventional retrieval algorithms. The neural network was trained using a Widrow-Hoff delta rule procedure. Functions of date to include season dependence in the retrieval process and functions of time to include diurnal effects were used as inputs to the neural network.

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

    Science.gov (United States)

    Kim, Lok-Won

    2018-05-01

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

  7. Future Network Architectures

    DEFF Research Database (Denmark)

    Wessing, Henrik; Bozorgebrahimi, Kurosh; Belter, Bartosz

    2015-01-01

    This study identifies key requirements for NRENs towards future network architectures that become apparent as users become more mobile and have increased expectations in terms of availability of data. In addition, cost saving requirements call for federated use of, in particular, the optical...

  8. A neutron spectrum unfolding computer code based on artificial neural networks

    Science.gov (United States)

    Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

    2014-02-01

    The Bonner Spheres Spectrometer consists of a thermal neutron sensor placed at the center of a number of moderating polyethylene spheres of different diameters. From the measured readings, information can be derived about the spectrum of the neutron field where measurements were made. Disadvantages of the Bonner system are the weight associated with each sphere and the need to sequentially irradiate the spheres, requiring long exposure periods. Provided a well-established response matrix and adequate irradiation conditions, the most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Intelligence, mainly Artificial Neural Networks, have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This code is called Neutron Spectrometry and Dosimetry with Artificial Neural networks unfolding code that was designed in a graphical interface. The core of the code is an embedded neural network architecture previously optimized using the robust design of artificial neural networks methodology. The main features of the code are: easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, for unfolding the neutron spectrum, only seven rate counts measured with seven Bonner spheres are required; simultaneously the code calculates 15 dosimetric quantities as well as the total flux for radiation protection purposes. This code generates a full report with all information of the unfolding in

  9. A design philosophy for multi-layer neural networks with applications to robot control

    Science.gov (United States)

    Vadiee, Nader; Jamshidi, MO

    1989-01-01

    A system is proposed which receives input information from many sensors that may have diverse scaling, dimension, and data representations. The proposed system tolerates sensory information with faults. The proposed self-adaptive processing technique has great promise in integrating the techniques of artificial intelligence and neural networks in an attempt to build a more intelligent computing environment. The proposed architecture can provide a detailed decision tree based on the input information, information stored in a long-term memory, and the adapted rule-based knowledge. A mathematical model for analysis will be obtained to validate the cited hypotheses. An extensive software program will be developed to simulate a typical example of pattern recognition problem. It is shown that the proposed model displays attention, expectation, spatio-temporal, and predictory behavior which are specific to the human brain. The anticipated results of this research project are: (1) creation of a new dynamic neural network structure, and (2) applications to and comparison with conventional multi-layer neural network structures. The anticipated benefits from this research are vast. The model can be used in a neuro-computer architecture as a building block which can perform complicated, nonlinear, time-varying mapping from a multitude of input excitory classes to an output or decision environment. It can be used for coordinating different sensory inputs and past experience of a dynamic system and actuating signals. The commercial applications of this project can be the creation of a special-purpose neuro-computer hardware which can be used in spatio-temporal pattern recognitions in such areas as air defense systems, e.g., target tracking, and recognition. Potential robotics-related applications are trajectory planning, inverse dynamics computations, hierarchical control, task-oriented control, and collision avoidance.

  10. Convolutional Neural Network for Image Recognition

    CERN Document Server

    Seifnashri, Sahand

    2015-01-01

    The aim of this project is to use machine learning techniques especially Convolutional Neural Networks for image processing. These techniques can be used for Quark-Gluon discrimination using calorimeters data, but unfortunately I didn’t manage to get the calorimeters data and I just used the Jet data fromminiaodsim(ak4 chs). The Jet data was not good enough for Convolutional Neural Network which is designed for ’image’ recognition. This report is made of twomain part, part one is mainly about implementing Convolutional Neural Network on unphysical data such as MNIST digits and CIFAR-10 dataset and part 2 is about the Jet data.

  11. Prediction of Groundwater Arsenic Contamination using Geographic Information System and Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Md. Moqbul Hossain

    2013-01-01

    Full Text Available Ground water arsenic contamination is a well known health and environmental problem in Bangladesh. Sources of this heavy metal are known to be geogenic, however, the processes of its release into groundwater are poorly understood phenomena. In quest of mitigation of the problem it is necessary to predict probable contamination before it causes any damage to human health. Hence our research has been carried out to find the factor relations of arsenic contamination and develop an arsenic contamination prediction model. Researchers have generally agreed that the elevated concentration of arsenic is affected by several factors such as soil reaction (pH, organic matter content, geology, iron content, etc. However, the variability of concentration within short lateral and vertical intervals, and the inter-relationships of variables among themselves, make the statistical analyses highly non-linear and difficult to converge with a meaningful relationship. Artificial Neural Networks (ANN comes in handy for such a black box type problem. This research uses Back propagation Neural Networks (BPNN to train and validate the data derived from Geographic Information System (GIS spatial distribution grids. The neural network architecture with (6-20-1 pattern was able to predict the arsenic concentration with reasonable accuracy.

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

    Science.gov (United States)

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

    2018-04-01

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

  13. Neural network classifier of attacks in IP telephony

    Science.gov (United States)

    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.

  14. A Neural Network-Based Interval Pattern Matcher

    Directory of Open Access Journals (Sweden)

    Jing Lu

    2015-07-01

    Full Text Available One of the most important roles in the machine learning area is to classify, and neural networks are very important classifiers. However, traditional neural networks cannot identify intervals, let alone classify them. To improve their identification ability, we propose a neural network-based interval matcher in our paper. After summarizing the theoretical construction of the model, we take a simple and a practical weather forecasting experiment, which show that the recognizer accuracy reaches 100% and that is promising.

  15. Artificial Neural Networks and the Mass Appraisal of Real Estate

    Directory of Open Access Journals (Sweden)

    Gang Zhou

    2018-03-01

    Full Text Available With the rapid development of computer, artificial intelligence and big data technology, artificial neural networks have become one of the most powerful machine learning algorithms. In the practice, most of the applications of artificial neural networks use back propagation neural network and its variation. Besides the back propagation neural network, various neural networks have been developing in order to improve the performance of standard models. Though neural networks are well known method in the research of real estate, there is enormous space for future research in order to enhance their function. Some scholars combine genetic algorithm, geospatial information, support vector machine model, particle swarm optimization with artificial neural networks to appraise the real estate, which is helpful for the existing appraisal technology. The mass appraisal of real estate in this paper includes the real estate valuation in the transaction and the tax base valuation in the real estate holding. In this study we focus on the theoretical development of artificial neural networks and mass appraisal of real estate, artificial neural networks model evolution and algorithm improvement, artificial neural networks practice and application, and review the existing literature about artificial neural networks and mass appraisal of real estate. Finally, we provide some suggestions for the mass appraisal of China's real estate.

  16. Introduction to neural networks with electric power applications

    International Nuclear Information System (INIS)

    Wildberger, A.M.; Hickok, K.A.

    1990-01-01

    This is an introduction to the general field of neural networks with emphasis on prospects for their application in the power industry. It is intended to provide enough background information for its audience to begin to follow technical developments in neural networks and to recognize those which might impact on electric power engineering. Beginning with a brief discussion of natural and artificial neurons, the characteristics of neural networks in general and how they learn, neural networks are compared with other modeling tools such as simulation and expert systems in order to provide guidance in selecting appropriate applications. In the power industry, possible applications include plant control, dispatching, and maintenance scheduling. In particular, neural networks are currently being investigated for enhancements to the Thermal Performance Advisor (TPA) which General Physics Corporation (GP) has developed to improve the efficiency of electric power generation

  17. Controlling the dynamics of multi-state neural networks

    International Nuclear Information System (INIS)

    Jin, Tao; Zhao, Hong

    2008-01-01

    In this paper, we first analyze the distribution of local fields (DLF) which is induced by the memory patterns in the Q-Ising model. It is found that the structure of the DLF is closely correlated with the network dynamics and the system performance. However, the design rule adopted in the Q-Ising model, like the other rules adopted for multi-state neural networks with associative memories, cannot be applied to directly control the DLF for a given set of memory patterns, and thus cannot be applied to further study the relationships between the structure of the DLF and the dynamics of the network. We then extend a design rule, which was presented recently for designing binary-state neural networks, to make it suitable for designing general multi-state neural networks. This rule is able to control the structure of the DLF as expected. We show that controlling the DLF not only can affect the dynamic behaviors of the multi-state neural networks for a given set of memory patterns, but also can improve the storage capacity. With the change of the DLF, the network shows very rich dynamic behaviors, such as the 'chaos phase', the 'memory phase', and the 'mixture phase'. These dynamic behaviors are also observed in the binary-state neural networks; therefore, our results imply that they may be the universal behaviors of feedback neural networks

  18. Face recognition based on improved BP neural network

    Directory of Open Access Journals (Sweden)

    Yue Gaili

    2017-01-01

    Full Text Available In order to improve the recognition rate of face recognition, face recognition algorithm based on histogram equalization, PCA and BP neural network is proposed. First, the face image is preprocessed by histogram equalization. Then, the classical PCA algorithm is used to extract the features of the histogram equalization image, and extract the principal component of the image. And then train the BP neural network using the trained training samples. This improved BP neural network weight adjustment method is used to train the network because the conventional BP algorithm has the disadvantages of slow convergence, easy to fall into local minima and training process. Finally, the BP neural network with the test sample input is trained to classify and identify the face images, and the recognition rate is obtained. Through the use of ORL database face image simulation experiment, the analysis results show that the improved BP neural network face recognition method can effectively improve the recognition rate of face recognition.

  19. Control of autonomous robot using neural networks

    Science.gov (United States)

    Barton, Adam; Volna, Eva

    2017-07-01

    The aim of the article is to design a method of control of an autonomous robot using artificial neural networks. The introductory part describes control issues from the perspective of autonomous robot navigation and the current mobile robots controlled by neural networks. The core of the article is the design of the controlling neural network, and generation and filtration of the training set using ART1 (Adaptive Resonance Theory). The outcome of the practical part is an assembled Lego Mindstorms EV3 robot solving the problem of avoiding obstacles in space. To verify models of an autonomous robot behavior, a set of experiments was created as well as evaluation criteria. The speed of each motor was adjusted by the controlling neural network with respect to the situation in which the robot was found.

  20. Neutron spectrometry using artificial neural networks

    International Nuclear Information System (INIS)

    Vega-Carrillo, Hector Rene; Martin Hernandez-Davila, Victor; Manzanares-Acuna, Eduardo; Mercado Sanchez, Gema A.; Pilar Iniguez de la Torre, Maria; Barquero, Raquel; Palacios, Francisco; Mendez Villafane, Roberto; Arteaga Arteaga, Tarcicio; Manuel Ortiz Rodriguez, Jose

    2006-01-01

    An artificial neural network has been designed to obtain neutron spectra from Bonner spheres spectrometer count rates. The neural network was trained using 129 neutron spectra. These include spectra from isotopic neutron sources; reference and operational spectra from accelerators and nuclear reactors, spectra based on mathematical functions as well as few energy groups and monoenergetic spectra. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. The re-binned spectra and the UTA4 response matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and their respective spectra were used as output during the neural network training. After training, the network was tested with the Bonner spheres count rates produced by folding a set of neutron spectra with the response matrix. This set contains data used during network training as well as data not used. Training and testing was carried out using the Matlab ( R) program. To verify the network unfolding performance, the original and unfolded spectra were compared using the root mean square error. The use of artificial neural networks to unfold neutron spectra in neutron spectrometry is an alternative procedure that overcomes the drawbacks associated with this ill-conditioned problem