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

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.

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.

Introduction to neural networks in high energy physics

International Nuclear Information System (INIS)

Therhaag, J.

2013-01-01

Artificial neural networks are a well established tool in high energy physics, playing an important role in both online and offline data analysis. Nevertheless they are often perceived as black boxes which perform obscure operations beyond the control of the user, resulting in a skepticism against any results that may be obtained using them. The situation is not helped by common explanations which try to draw analogies between artificial neural networks and the human brain, for the brain is an even more complex black box itself. In this introductory text, I will take a problem-oriented approach to neural network techniques, showing how the fundamental concepts arise naturally from the demand to solve classification tasks which are frequently encountered in high energy physics. Particular attention is devoted to the question how probability theory can be used to control the complexity of neural networks. (authors)

A high-speed analog neural processor

NARCIS (Netherlands)

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

1994-01-01

Targeted at high-energy physics research applications, our special-purpose analog neural processor can classify up to 70 dimensional vectors within 50 nanoseconds. The decision-making process of the implemented feedforward neural network enables this type of computation to tolerate weight

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.

Open quantum generalisation of Hopfield neural networks

Science.gov (United States)

Rotondo, P.; Marcuzzi, M.; Garrahan, J. P.; Lesanovsky, I.; Müller, M.

2018-03-01

We propose a new framework to understand how quantum effects may impact on the dynamics of neural networks. We implement the dynamics of neural networks in terms of Markovian open quantum systems, which allows us to treat thermal and quantum coherent effects on the same footing. In particular, we propose an open quantum generalisation of the Hopfield neural network, the simplest toy model of associative memory. We determine its phase diagram and show that quantum fluctuations give rise to a qualitatively new non-equilibrium phase. This novel phase is characterised by limit cycles corresponding to high-dimensional stationary manifolds that may be regarded as a generalisation of storage patterns to the quantum domain.

View-invariant gait recognition method by three-dimensional convolutional neural network

Science.gov (United States)

Xing, Weiwei; Li, Ying; Zhang, Shunli

2018-01-01

Gait as an important biometric feature can identify a human at a long distance. View change is one of the most challenging factors for gait recognition. To address the cross view issues in gait recognition, we propose a view-invariant gait recognition method by three-dimensional (3-D) convolutional neural network. First, 3-D convolutional neural network (3DCNN) is introduced to learn view-invariant feature, which can capture the spatial information and temporal information simultaneously on normalized silhouette sequences. Second, a network training method based on cross-domain transfer learning is proposed to solve the problem of the limited gait training samples. We choose the C3D as the basic model, which is pretrained on the Sports-1M and then fine-tune C3D model to adapt gait recognition. In the recognition stage, we use the fine-tuned model to extract gait features and use Euclidean distance to measure the similarity of gait sequences. Sufficient experiments are carried out on the CASIA-B dataset and the experimental results demonstrate that our method outperforms many other methods.

Bioelectric signal classification using a recurrent probabilistic neural network with time-series discriminant component analysis.

Science.gov (United States)

Hayashi, Hideaki; Shima, Keisuke; Shibanoki, Taro; Kurita, Yuichi; Tsuji, Toshio

2013-01-01

This paper outlines a probabilistic neural network developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower-dimensional space using a set of orthogonal transformations and the calculation of posterior probabilities based on a continuous-density hidden Markov model that incorporates a Gaussian mixture model expressed in the reduced-dimensional space. The analysis can be incorporated into a neural network so that parameters can be obtained appropriately as network coefficients according to backpropagation-through-time-based training algorithm. The network is considered to enable high-accuracy classification of high-dimensional time-series patterns and to reduce the computation time taken for network training. In the experiments conducted during the study, the validity of the proposed network was demonstrated for EEG signals.

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.

Wood Modification at High Temperature and Pressurized Steam: a Relational Model of Mechanical Properties Based on a Neural Network

Directory of Open Access Journals (Sweden)

Hong Yang

2015-07-01

Full Text Available Thermally modified wood has high dimensional stability and biological durability.But if the process parameters of thermal modification are not appropriate, then there will be a decline in the physical properties of wood.A neural network algorithm was employed in this study to establish the relationship between the process parameters of high-temperature and high-pressure thermal modification and the mechanical properties of the wood. Three important parameters: temperature, relative humidity, and treatment time, were considered as the inputs to the neural network. Back propagation (BP neural network and radial basis function (RBF neural network models for prediction were built and compared. The comparison showed that the RBF neural network model had advantages in network structure, convergence speed, and generalization capacity. On this basis, the inverse model, reflecting the relationship between the process parameters and the mechanical properties of wood, was established. Given the desired mechanical properties of the wood, the thermal modification process parameters could be inversely optimized and predicted. The results indicated that the model has good learning ability and generalization capacity. This is of great importance for the theoretical and applicational studies of the thermal modification of wood.

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

Approximation model of three-dimensional power distribution in boiling water reactor using neural networks

International Nuclear Information System (INIS)

Kobayashi, Yoko; Aiyoshi, Eitaro

2001-01-01

Fast and accurate prediction of three-dimensional (3D) power distribution is essential in a boiling water reactor (BWR). The prediction method of 3D power distribution in BWR is developed using the neural network. Application of the neural network starts with selecting the learning algorithm. In the proposed method, we use the learning algorithms based on a class of Quasi-Newton optimization techniques called Self-Scaling Variable Metric (SSVM) methods. Prediction studies were done for a core of actual BWR plant with octant symmetry. Compared to classical Quasi-Newton methods, it is shown that the SSVM method reduces the number of iterations in the learning mode. The results of prediction demonstrate that the neural network can predict 3D power distribution of BWR reasonably well. The proposed method will be very useful for BWR loading pattern optimization problems where 3D power distribution for a huge number of loading patterns (LPs) must be performed. (author)

Face recognition: a convolutional neural-network approach.

Science.gov (United States)

Lawrence, S; Giles, C L; Tsoi, A C; Back, A D

1997-01-01

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

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

Music Signal Processing Using Vector Product Neural Networks

Science.gov (United States)

Fan, Z. C.; Chan, T. S.; Yang, Y. H.; Jang, J. S. R.

2017-05-01

We propose a novel neural network model for music signal processing using vector product neurons and dimensionality transformations. Here, the inputs are first mapped from real values into three-dimensional vectors then fed into a three-dimensional vector product neural network where the inputs, outputs, and weights are all three-dimensional values. Next, the final outputs are mapped back to the reals. Two methods for dimensionality transformation are proposed, one via context windows and the other via spectral coloring. Experimental results on the iKala dataset for blind singing voice separation confirm the efficacy of our model.

Artificial neural network based approach to transmission lines protection

International Nuclear Information System (INIS)

Joorabian, M.

1999-05-01

The aim of this paper is to present and accurate fault detection technique for high speed distance protection using artificial neural networks. The feed-forward multi-layer neural network with the use of supervised learning and the common training rule of error back-propagation is chosen for this study. Information available locally at the relay point is passed to a neural network in order for an assessment of the fault location to be made. However in practice there is a large amount of information available, and a feature extraction process is required to reduce the dimensionality of the pattern vectors, whilst retaining important information that distinguishes the fault point. The choice of features is critical to the performance of the neural networks learning and operation. A significant feature in this paper is that an artificial neural network has been designed and tested to enhance the precision of the adaptive capabilities for distance protection

Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval

Directory of Open Access Journals (Sweden)

Weixun Zhou

2017-05-01

Full Text Available Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNNs for high-resolution remote sensing image retrieval (HRRSIR. To this end, several effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, a CNN pre-trained on a different problem is treated as a feature extractor since there are no sufficiently-sized remote sensing datasets to train a CNN from scratch. In the second scheme, we investigate learning features that are specific to our problem by first fine-tuning the pre-trained CNN on a remote sensing dataset and then proposing a novel CNN architecture based on convolutional layers and a three-layer perceptron. The novel CNN has fewer parameters than the pre-trained and fine-tuned CNNs and can learn low dimensional features from limited labelled images. The schemes are evaluated on several challenging, publicly available datasets. The results indicate that the proposed schemes, particularly the novel CNN, achieve state-of-the-art performance.

SORN: a self-organizing recurrent neural network

Directory of Open Access Journals (Sweden)

Andreea Lazar

2009-10-01

Full Text Available Understanding the dynamics of recurrent neural networks is crucial for explaining how the brain processes information. In the neocortex, a range of different plasticity mechanisms are shaping recurrent networks into effective information processing circuits that learn appropriate representations for time-varying sensory stimuli. However, it has been difficult to mimic these abilities in artificial neural network models. Here we introduce SORN, a self-organizing recurrent network. It combines three distinct forms of local plasticity to learn spatio-temporal patterns in its input while maintaining its dynamics in a healthy regime suitable for learning. The SORN learns to encode information in the form of trajectories through its high-dimensional state space reminiscent of recent biological findings on cortical coding. All three forms of plasticity are shown to be essential for the network's success.

Statistical mechanics of complex neural systems and high dimensional data

International Nuclear Information System (INIS)

Advani, Madhu; Lahiri, Subhaneil; Ganguli, Surya

2013-01-01

Recent experimental advances in neuroscience have opened new vistas into the immense complexity of neuronal networks. This proliferation of data challenges us on two parallel fronts. First, how can we form adequate theoretical frameworks for understanding how dynamical network processes cooperate across widely disparate spatiotemporal scales to solve important computational problems? Second, how can we extract meaningful models of neuronal systems from high dimensional datasets? To aid in these challenges, we give a pedagogical review of a collection of ideas and theoretical methods arising at the intersection of statistical physics, computer science and neurobiology. We introduce the interrelated replica and cavity methods, which originated in statistical physics as powerful ways to quantitatively analyze large highly heterogeneous systems of many interacting degrees of freedom. We also introduce the closely related notion of message passing in graphical models, which originated in computer science as a distributed algorithm capable of solving large inference and optimization problems involving many coupled variables. We then show how both the statistical physics and computer science perspectives can be applied in a wide diversity of contexts to problems arising in theoretical neuroscience and data analysis. Along the way we discuss spin glasses, learning theory, illusions of structure in noise, random matrices, dimensionality reduction and compressed sensing, all within the unified formalism of the replica method. Moreover, we review recent conceptual connections between message passing in graphical models, and neural computation and learning. Overall, these ideas illustrate how statistical physics and computer science might provide a lens through which we can uncover emergent computational functions buried deep within the dynamical complexities of neuronal networks. (paper)

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

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.

Applications of neural networks in high energy physics

International Nuclear Information System (INIS)

Cutts, D.; Hoftun, J.S.; Nesic, D.; Sornborger, A.; Johnson, C.R.; Zeller, R.T.

1990-01-01

Neural network techniques provide promising solutions to pattern recognition problems in high energy physics. We discuss several applications of back propagation networks, and in particular describe the operation of an electron algorithm based on calorimeter energies. 5 refs., 5 figs., 1 tab

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

Science.gov (United States)

Huang, Chengdai; Cao, Jinde

2018-02-01

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

Detecting atrial fibrillation by deep convolutional neural networks.

Science.gov (United States)

Xia, Yong; Wulan, Naren; Wang, Kuanquan; Zhang, Henggui

2018-02-01

Atrial fibrillation (AF) is the most common cardiac arrhythmia. The incidence of AF increases with age, causing high risks of stroke and increased morbidity and mortality. Efficient and accurate diagnosis of AF based on the ECG is valuable in clinical settings and remains challenging. In this paper, we proposed a novel method with high reliability and accuracy for AF detection via deep learning. The short-term Fourier transform (STFT) and stationary wavelet transform (SWT) were used to analyze ECG segments to obtain two-dimensional (2-D) matrix input suitable for deep convolutional neural networks. Then, two different deep convolutional neural network models corresponding to STFT output and SWT output were developed. Our new method did not require detection of P or R peaks, nor feature designs for classification, in contrast to existing algorithms. Finally, the performances of the two models were evaluated and compared with those of existing algorithms. Our proposed method demonstrated favorable performances on ECG segments as short as 5 s. The deep convolutional neural network using input generated by STFT, presented a sensitivity of 98.34%, specificity of 98.24% and accuracy of 98.29%. For the deep convolutional neural network using input generated by SWT, a sensitivity of 98.79%, specificity of 97.87% and accuracy of 98.63% was achieved. The proposed method using deep convolutional neural networks shows high sensitivity, specificity and accuracy, and, therefore, is a valuable tool for AF detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Neural Network Classifier Based on Growing Hyperspheres

Czech Academy of Sciences Publication Activity Database

Jiřina Jr., Marcel; Jiřina, Marcel

2000-01-01

Roč. 10, č. 3 (2000), s. 417-428 ISSN 1210-0552. [Neural Network World 2000. Prague, 09.07.2000-12.07.2000] Grant - others:MŠMT ČR(CZ) VS96047; MPO(CZ) RP-4210 Institutional research plan: AV0Z1030915 Keywords : neural network * classifier * hyperspheres * big -dimensional data Subject RIV: BA - General Mathematics

Application of a neural network for reflectance spectrum classification

Science.gov (United States)

Yang, Gefei; Gartley, Michael

2017-05-01

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

Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data

Science.gov (United States)

Liu, Wanjun; Liang, Xuejian; Qu, Haicheng

2017-11-01

Hyperspectral image (HSI) classification is one of the most popular topics in remote sensing community. Traditional and deep learning-based classification methods were proposed constantly in recent years. In order to improve the classification accuracy and robustness, a dimensionality-varied convolutional neural network (DVCNN) was proposed in this paper. DVCNN was a novel deep architecture based on convolutional neural network (CNN). The input of DVCNN was a set of 3D patches selected from HSI which contained spectral-spatial joint information. In the following feature extraction process, each patch was transformed into some different 1D vectors by 3D convolution kernels, which were able to extract features from spectral-spatial data. The rest of DVCNN was about the same as general CNN and processed 2D matrix which was constituted by by all 1D data. So that the DVCNN could not only extract more accurate and rich features than CNN, but also fused spectral-spatial information to improve classification accuracy. Moreover, the robustness of network on water-absorption bands was enhanced in the process of spectral-spatial fusion by 3D convolution, and the calculation was simplified by dimensionality varied convolution. Experiments were performed on both Indian Pines and Pavia University scene datasets, and the results showed that the classification accuracy of DVCNN improved by 32.87% on Indian Pines and 19.63% on Pavia University scene than spectral-only CNN. The maximum accuracy improvement of DVCNN achievement was 13.72% compared with other state-of-the-art HSI classification methods, and the robustness of DVCNN on water-absorption bands noise was demonstrated.

Neural Based Orthogonal Data Fitting The EXIN Neural Networks

CERN Document Server

Cirrincione, Giansalvo

2008-01-01

Written by three leaders in the field of neural based algorithms, Neural Based Orthogonal Data Fitting proposes several neural networks, all endowed with a complete theory which not only explains their behavior, but also compares them with the existing neural and traditional algorithms. The algorithms are studied from different points of view, including: as a differential geometry problem, as a dynamic problem, as a stochastic problem, and as a numerical problem. All algorithms have also been analyzed on real time problems (large dimensional data matrices) and have shown accurate solutions. Wh

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.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU

Science.gov (United States)

Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version. PMID:29250109

High Performance Implementation of 3D Convolutional Neural Networks on a GPU.

Science.gov (United States)

Lan, Qiang; Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version.

Global stability of stochastic high-order neural networks with discrete and distributed delays

International Nuclear Information System (INIS)

Wang Zidong; Fang Jianan; Liu Xiaohui

2008-01-01

High-order neural networks can be considered as an expansion of Hopfield neural networks, and have stronger approximation property, faster convergence rate, greater storage capacity, and higher fault tolerance than lower-order neural networks. In this paper, the global asymptotic stability analysis problem is considered for a class of stochastic high-order neural networks with discrete and distributed time-delays. Based on an Lyapunov-Krasovskii functional and the stochastic stability analysis theory, several sufficient conditions are derived, which guarantee the global asymptotic convergence of the equilibrium point in the mean square. It is shown that the stochastic high-order delayed neural networks under consideration are globally asymptotically stable in the mean square if two linear matrix inequalities (LMIs) are feasible, where the feasibility of LMIs can be readily checked by the Matlab LMI toolbox. It is also shown that the main results in this paper cover some recently published works. A numerical example is given to demonstrate the usefulness of the proposed global stability criteria

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.

Convolutional neural network based side attack explosive hazard detection in three dimensional voxel radar

Science.gov (United States)

Brockner, Blake; Veal, Charlie; Dowdy, Joshua; Anderson, Derek T.; Williams, Kathryn; Luke, Robert; Sheen, David

2018-04-01

The identification followed by avoidance or removal of explosive hazards in past and/or present conflict zones is a serious threat for both civilian and military personnel. This is a challenging task as variability exists with respect to the objects, their environment and emplacement context, to name a few factors. A goal is the development of automatic or human-in-the-loop sensor technologies that leverage signal processing, data fusion and machine learning. Herein, we explore the detection of side attack explosive hazards (SAEHs) in three dimensional voxel space radar via different shallow and deep convolutional neural network (CNN) architectures. Dimensionality reduction is performed by using multiple projected images versus the raw three dimensional voxel data, which leads to noteworthy savings in input size and associated network hyperparameters. Last, we explore the accuracy and interpretation of solutions learned via random versus intelligent network weight initialization. Experiments are provided on a U.S. Army data set collected over different times, weather conditions, target types and concealments. Preliminary results indicate that deep learning can perform as good as, if not better, than a skilled domain expert, even in light of limited training data with a class imbalance.

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

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

High-dimensional neural network potentials for solvation: The case of protonated water clusters in helium

Science.gov (United States)

Schran, Christoph; Uhl, Felix; Behler, Jörg; Marx, Dominik

2018-03-01

The design of accurate helium-solute interaction potentials for the simulation of chemically complex molecules solvated in superfluid helium has long been a cumbersome task due to the rather weak but strongly anisotropic nature of the interactions. We show that this challenge can be met by using a combination of an effective pair potential for the He-He interactions and a flexible high-dimensional neural network potential (NNP) for describing the complex interaction between helium and the solute in a pairwise additive manner. This approach yields an excellent agreement with a mean absolute deviation as small as 0.04 kJ mol-1 for the interaction energy between helium and both hydronium and Zundel cations compared with coupled cluster reference calculations with an energetically converged basis set. The construction and improvement of the potential can be performed in a highly automated way, which opens the door for applications to a variety of reactive molecules to study the effect of solvation on the solute as well as the solute-induced structuring of the solvent. Furthermore, we show that this NNP approach yields very convincing agreement with the coupled cluster reference for properties like many-body spatial and radial distribution functions. This holds for the microsolvation of the protonated water monomer and dimer by a few helium atoms up to their solvation in bulk helium as obtained from path integral simulations at about 1 K.

Medical image segmentation by means of constraint satisfaction neural network

International Nuclear Information System (INIS)

Chen, C.T.; Tsao, C.K.; Lin, W.C.

1990-01-01

This paper applies the concept of constraint satisfaction neural network (CSNN) to the problem of medical image segmentation. Constraint satisfaction (or constraint propagation), the procedure to achieve global consistency through local computation, is an important paradigm in artificial intelligence. CSNN can be viewed as a three-dimensional neural network, with the two-dimensional image matrix as its base, augmented by various constraint labels for each pixel. These constraint labels can be interpreted as the connections and the topology of the neural network. Through parallel and iterative processes, the CSNN will approach a solution that satisfies the given constraints thus providing segmented regions with global consistency

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

Science.gov (United States)

Mills, Kyle; Tamblyn, Isaac

2018-03-01

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

Particle swarm optimization-based automatic parameter selection for deep neural networks and its applications in large-scale and high-dimensional data.

Science.gov (United States)

Ye, Fei

2017-01-01

In this paper, we propose a new automatic hyperparameter selection approach for determining the optimal network configuration (network structure and hyperparameters) for deep neural networks using particle swarm optimization (PSO) in combination with a steepest gradient descent algorithm. In the proposed approach, network configurations were coded as a set of real-number m-dimensional vectors as the individuals of the PSO algorithm in the search procedure. During the search procedure, the PSO algorithm is employed to search for optimal network configurations via the particles moving in a finite search space, and the steepest gradient descent algorithm is used to train the DNN classifier with a few training epochs (to find a local optimal solution) during the population evaluation of PSO. After the optimization scheme, the steepest gradient descent algorithm is performed with more epochs and the final solutions (pbest and gbest) of the PSO algorithm to train a final ensemble model and individual DNN classifiers, respectively. The local search ability of the steepest gradient descent algorithm and the global search capabilities of the PSO algorithm are exploited to determine an optimal solution that is close to the global optimum. We constructed several experiments on hand-written characters and biological activity prediction datasets to show that the DNN classifiers trained by the network configurations expressed by the final solutions of the PSO algorithm, employed to construct an ensemble model and individual classifier, outperform the random approach in terms of the generalization performance. Therefore, the proposed approach can be regarded an alternative tool for automatic network structure and parameter selection for deep neural networks.

Identification of Complex Dynamical Systems with Neural Networks (2/2)

CERN Multimedia

CERN. Geneva

2016-01-01

The identification and analysis of high dimensional nonlinear systems is obviously a challenging task. Neural networks have been proven to be universal approximators but this still leaves the identification task a hard one. To do it efficiently, we have to violate some of the rules of classical regression theory. Furthermore we should focus on the interpretation of the resulting model to overcome its black box character. First, we will discuss function approximation with 3 layer feedforward neural networks up to new developments in deep neural networks and deep learning. These nets are not only of interest in connection with image analysis but are a center point of the current artificial intelligence developments. Second, we will focus on the analysis of complex dynamical system in the form of state space models realized as recurrent neural networks. After the introduction of small open dynamical systems we will study dynamical systems on manifolds. Here manifold and dynamics have to be identified in parall...

Identification of Complex Dynamical Systems with Neural Networks (1/2)

CERN Multimedia

CERN. Geneva

2016-01-01

The identification and analysis of high dimensional nonlinear systems is obviously a challenging task. Neural networks have been proven to be universal approximators but this still leaves the identification task a hard one. To do it efficiently, we have to violate some of the rules of classical regression theory. Furthermore we should focus on the interpretation of the resulting model to overcome its black box character. First, we will discuss function approximation with 3 layer feedforward neural networks up to new developments in deep neural networks and deep learning. These nets are not only of interest in connection with image analysis but are a center point of the current artificial intelligence developments. Second, we will focus on the analysis of complex dynamical system in the form of state space models realized as recurrent neural networks. After the introduction of small open dynamical systems we will study dynamical systems on manifolds. Here manifold and dynamics have to be identified in parall...

Deep neural networks for texture classification-A theoretical analysis.

Science.gov (United States)

Basu, Saikat; Mukhopadhyay, Supratik; Karki, Manohar; DiBiano, Robert; Ganguly, Sangram; Nemani, Ramakrishna; Gayaka, Shreekant

2018-01-01

We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity. Copyright © 2017 Elsevier Ltd. All rights reserved.

Hybrid discrete-time neural networks.

Science.gov (United States)

Cao, Hongjun; Ibarz, Borja

2010-11-13

Hybrid dynamical systems combine evolution equations with state transitions. When the evolution equations are discrete-time (also called map-based), the result is a hybrid discrete-time system. A class of biological neural network models that has recently received some attention falls within this category: map-based neuron models connected by means of fast threshold modulation (FTM). FTM is a connection scheme that aims to mimic the switching dynamics of a neuron subject to synaptic inputs. The dynamic equations of the neuron adopt different forms according to the state (either firing or not firing) and type (excitatory or inhibitory) of their presynaptic neighbours. Therefore, the mathematical model of one such network is a combination of discrete-time evolution equations with transitions between states, constituting a hybrid discrete-time (map-based) neural network. In this paper, we review previous work within the context of these models, exemplifying useful techniques to analyse them. Typical map-based neuron models are low-dimensional and amenable to phase-plane analysis. In bursting models, fast-slow decomposition can be used to reduce dimensionality further, so that the dynamics of a pair of connected neurons can be easily understood. We also discuss a model that includes electrical synapses in addition to chemical synapses with FTM. Furthermore, we describe how master stability functions can predict the stability of synchronized states in these networks. The main results are extended to larger map-based neural networks.

Self-organized critical neural networks

International Nuclear Information System (INIS)

Bornholdt, Stefan; Roehl, Torsten

2003-01-01

A mechanism for self-organization of the degree of connectivity in model neural networks is studied. Network connectivity is regulated locally on the basis of an order parameter of the global dynamics, which is estimated from an observable at the single synapse level. This principle is studied in a two-dimensional neural network with randomly wired asymmetric weights. In this class of networks, network connectivity is closely related to a phase transition between ordered and disordered dynamics. A slow topology change is imposed on the network through a local rewiring rule motivated by activity-dependent synaptic development: Neighbor neurons whose activity is correlated, on average develop a new connection while uncorrelated neighbors tend to disconnect. As a result, robust self-organization of the network towards the order disorder transition occurs. Convergence is independent of initial conditions, robust against thermal noise, and does not require fine tuning of parameters

Deformable image registration using convolutional neural networks

NARCIS (Netherlands)

Eppenhof, Koen A.J.; Lafarge, Maxime W.; Moeskops, Pim; Veta, Mitko; Pluim, Josien P.W.

2018-01-01

Deformable image registration can be time-consuming and often needs extensive parameterization to perform well on a specific application. We present a step towards a registration framework based on a three-dimensional convolutional neural network. The network directly learns transformations between

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.)

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

Science.gov (United States)

Bao, Gang; Zeng, Zhigang; Shen, Yanjun

2018-02-01

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

Tutorial on neural network applications in high energy physics: A 1992 perspective

International Nuclear Information System (INIS)

Denby, B.

1992-04-01

Feed forward and recurrent neural networks are introduced and related to standard data analysis tools. Tips are given on applications of neural nets to various areas of high energy physics. A review of applications within high energy physics and a summary of neural net hardware status are given

Particle swarm optimization-based automatic parameter selection for deep neural networks and its applications in large-scale and high-dimensional data

Science.gov (United States)

2017-01-01

In this paper, we propose a new automatic hyperparameter selection approach for determining the optimal network configuration (network structure and hyperparameters) for deep neural networks using particle swarm optimization (PSO) in combination with a steepest gradient descent algorithm. In the proposed approach, network configurations were coded as a set of real-number m-dimensional vectors as the individuals of the PSO algorithm in the search procedure. During the search procedure, the PSO algorithm is employed to search for optimal network configurations via the particles moving in a finite search space, and the steepest gradient descent algorithm is used to train the DNN classifier with a few training epochs (to find a local optimal solution) during the population evaluation of PSO. After the optimization scheme, the steepest gradient descent algorithm is performed with more epochs and the final solutions (pbest and gbest) of the PSO algorithm to train a final ensemble model and individual DNN classifiers, respectively. The local search ability of the steepest gradient descent algorithm and the global search capabilities of the PSO algorithm are exploited to determine an optimal solution that is close to the global optimum. We constructed several experiments on hand-written characters and biological activity prediction datasets to show that the DNN classifiers trained by the network configurations expressed by the final solutions of the PSO algorithm, employed to construct an ensemble model and individual classifier, outperform the random approach in terms of the generalization performance. Therefore, the proposed approach can be regarded an alternative tool for automatic network structure and parameter selection for deep neural networks. PMID:29236718

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.

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.

Parameter diagnostics of phases and phase transition learning by neural networks

Science.gov (United States)

Suchsland, Philippe; Wessel, Stefan

2018-05-01

We present an analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the convolutional filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks. In particular, we study the classification process of both fully-connected and convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.

High level cognitive information processing in neural networks

Science.gov (United States)

Barnden, John A.; Fields, Christopher A.

1992-01-01

Two related research efforts were addressed: (1) high-level connectionist cognitive modeling; and (2) local neural circuit modeling. The goals of the first effort were to develop connectionist models of high-level cognitive processes such as problem solving or natural language understanding, and to understand the computational requirements of such models. The goals of the second effort were to develop biologically-realistic model of local neural circuits, and to understand the computational behavior of such models. In keeping with the nature of NASA's Innovative Research Program, all the work conducted under the grant was highly innovative. For instance, the following ideas, all summarized, are contributions to the study of connectionist/neural networks: (1) the temporal-winner-take-all, relative-position encoding, and pattern-similarity association techniques; (2) the importation of logical combinators into connection; (3) the use of analogy-based reasoning as a bridge across the gap between the traditional symbolic paradigm and the connectionist paradigm; and (4) the application of connectionism to the domain of belief representation/reasoning. The work on local neural circuit modeling also departs significantly from the work of related researchers. In particular, its concentration on low-level neural phenomena that could support high-level cognitive processing is unusual within the area of biological local circuit modeling, and also serves to expand the horizons of the artificial neural net field.

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.

Application of neural networks to group technology

Science.gov (United States)

Caudell, Thomas P.; Smith, Scott D. G.; Johnson, G. C.; Wunsch, Donald C., II

1991-08-01

Adaptive resonance theory (ART) neural networks are being developed for application to the industrial engineering problem of group technology--the reuse of engineering designs. Two- and three-dimensional representations of engineering designs are input to ART-1 neural networks to produce groups or families of similar parts. These representations, in their basic form, amount to bit maps of the part, and can become very large when the part is represented in high resolution. This paper describes an enhancement to an algorithmic form of ART-1 that allows it to operate directly on compressed input representations and to generate compressed memory templates. The performance of this compressed algorithm is compared to that of the regular algorithm on real engineering designs and a significant savings in memory storage as well as a speed up in execution is observed. In additions, a `neural database'' system under development is described. This system demonstrates the feasibility of training an ART-1 network to first cluster designs into families, and then to recall the family when presented a similar design. This application is of large practical value to industry, making it possible to avoid duplication of design efforts.

Stimulus Sensitivity of a Spiking Neural Network Model

Science.gov (United States)

Chevallier, Julien

2018-02-01

Some recent papers relate the criticality of complex systems to their maximal capacity of information processing. In the present paper, we consider high dimensional point processes, known as age-dependent Hawkes processes, which have been used to model spiking neural networks. Using mean-field approximation, the response of the network to a stimulus is computed and we provide a notion of stimulus sensitivity. It appears that the maximal sensitivity is achieved in the sub-critical regime, yet almost critical for a range of biologically relevant parameters.

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.

Neural Networks for protein Structure Prediction

DEFF Research Database (Denmark)

Bohr, Henrik

1998-01-01

This is a review about neural network applications in bioinformatics. Especially the applications to protein structure prediction, e.g. prediction of secondary structures, prediction of surface structure, fold class recognition and prediction of the 3-dimensional structure of protein backbones...

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.

Three-dimensional fingerprint recognition by using convolution neural network

Science.gov (United States)

Tian, Qianyu; Gao, Nan; Zhang, Zonghua

2018-01-01

With the development of science and technology and the improvement of social information, fingerprint recognition technology has become a hot research direction and been widely applied in many actual fields because of its feasibility and reliability. The traditional two-dimensional (2D) fingerprint recognition method relies on matching feature points. This method is not only time-consuming, but also lost three-dimensional (3D) information of fingerprint, with the fingerprint rotation, scaling, damage and other issues, a serious decline in robustness. To solve these problems, 3D fingerprint has been used to recognize human being. Because it is a new research field, there are still lots of challenging problems in 3D fingerprint recognition. This paper presents a new 3D fingerprint recognition method by using a convolution neural network (CNN). By combining 2D fingerprint and fingerprint depth map into CNN, and then through another CNN feature fusion, the characteristics of the fusion complete 3D fingerprint recognition after classification. This method not only can preserve 3D information of fingerprints, but also solves the problem of CNN input. Moreover, the recognition process is simpler than traditional feature point matching algorithm. 3D fingerprint recognition rate by using CNN is compared with other fingerprint recognition algorithms. The experimental results show that the proposed 3D fingerprint recognition method has good recognition rate and robustness.

Boosted jet identification using particle candidates and deep neural networks

CERN Document Server

CMS Collaboration

2017-01-01

This note presents developments for the identification of hadronically decaying top quarks using deep neural networks in CMS. A new method that utilizes one dimensional convolutional neural networks based on jet constituent particles is proposed. Alternative methods using boosted decision trees based on jet observables are compared. The new method shows significant improvement in performance.

Multiple simultaneous fault diagnosis via hierarchical and single artificial neural networks

International Nuclear Information System (INIS)

Eslamloueyan, R.; Shahrokhi, M.; Bozorgmehri, R.

2003-01-01

Process fault diagnosis involves interpreting the current status of the plant given sensor reading and process knowledge. There has been considerable work done in this area with a variety of approaches being proposed for process fault diagnosis. Neural networks have been used to solve process fault diagnosis problems in chemical process, as they are well suited for recognizing multi-dimensional nonlinear patterns. In this work, the use of Hierarchical Artificial Neural Networks in diagnosing the multi-faults of a chemical process are discussed and compared with that of Single Artificial Neural Networks. The lower efficiency of Hierarchical Artificial Neural Networks , in comparison to Single Artificial Neural Networks, in process fault diagnosis is elaborated and analyzed. Also, the concept of a multi-level selection switch is presented and developed to improve the performance of hierarchical artificial neural networks. Simulation results indicate that application of multi-level selection switch increase the performance of the hierarchical artificial neural networks considerably

Three-Dimensional Terahertz Coded-Aperture Imaging Based on Matched Filtering and Convolutional Neural Network.

Science.gov (United States)

Chen, Shuo; Luo, Chenggao; Wang, Hongqiang; Deng, Bin; Cheng, Yongqiang; Zhuang, Zhaowen

2018-04-26

As a promising radar imaging technique, terahertz coded-aperture imaging (TCAI) can achieve high-resolution, forward-looking, and staring imaging by producing spatiotemporal independent signals with coded apertures. However, there are still two problems in three-dimensional (3D) TCAI. Firstly, the large-scale reference-signal matrix based on meshing the 3D imaging area creates a heavy computational burden, thus leading to unsatisfactory efficiency. Secondly, it is difficult to resolve the target under low signal-to-noise ratio (SNR). In this paper, we propose a 3D imaging method based on matched filtering (MF) and convolutional neural network (CNN), which can reduce the computational burden and achieve high-resolution imaging for low SNR targets. In terms of the frequency-hopping (FH) signal, the original echo is processed with MF. By extracting the processed echo in different spike pulses separately, targets in different imaging planes are reconstructed simultaneously to decompose the global computational complexity, and then are synthesized together to reconstruct the 3D target. Based on the conventional TCAI model, we deduce and build a new TCAI model based on MF. Furthermore, the convolutional neural network (CNN) is designed to teach the MF-TCAI how to reconstruct the low SNR target better. The experimental results demonstrate that the MF-TCAI achieves impressive performance on imaging ability and efficiency under low SNR. Moreover, the MF-TCAI has learned to better resolve the low-SNR 3D target with the help of CNN. In summary, the proposed 3D TCAI can achieve: (1) low-SNR high-resolution imaging by using MF; (2) efficient 3D imaging by downsizing the large-scale reference-signal matrix; and (3) intelligent imaging with CNN. Therefore, the TCAI based on MF and CNN has great potential in applications such as security screening, nondestructive detection, medical diagnosis, etc.

Microfluidic engineered high cell density three-dimensional neural cultures

Science.gov (United States)

Cullen, D. Kacy; Vukasinovic, Jelena; Glezer, Ari; La Placa, Michelle C.

2007-06-01

Three-dimensional (3D) neural cultures with cells distributed throughout a thick, bioactive protein scaffold may better represent neurobiological phenomena than planar correlates lacking matrix support. Neural cells in vivo interact within a complex, multicellular environment with tightly coupled 3D cell-cell/cell-matrix interactions; however, thick 3D neural cultures at cell densities approaching that of brain rapidly decay, presumably due to diffusion limited interstitial mass transport. To address this issue, we have developed a novel perfusion platform that utilizes forced intercellular convection to enhance mass transport. First, we demonstrated that in thick (>500 µm) 3D neural cultures supported by passive diffusion, cell densities =104 cells mm-3), continuous medium perfusion at 2.0-11.0 µL min-1 improved viability compared to non-perfused cultures (p death and matrix degradation. In perfused cultures, survival was dependent on proximity to the perfusion source at 2.00-6.25 µL min-1 (p 90% viability in both neuronal cultures and neuronal-astrocytic co-cultures. This work demonstrates the utility of forced interstitial convection in improving the survival of high cell density 3D engineered neural constructs and may aid in the development of novel tissue-engineered systems reconstituting 3D cell-cell/cell-matrix interactions.

Visual control of a robot manipulator using neural networks

International Nuclear Information System (INIS)

Kurazume, Ryo; Sekiguchi, Minoru; Nagata, Shigemi

1994-01-01

This paper describes a vision-motor fusion system using neural networks, consisting of multiple vision sensors and a manipulator, for grasping an object placed in a desired position and attitude in a three-dimensional workspace. The system does not need complicated vision sensor calibration and calculation of a transformation matrix, and can thus be easily constructed for grasping tasks. An experimental system with two TV cameras and a manipulator with six degrees of freedom grasped a connector suspended in a three-dimensional workspace with high accuracy. (author)

The image recognition based on neural network and Bayesian decision

Science.gov (United States)

Wang, Chugege

2018-04-01

The artificial neural network began in 1940, which is an important part of artificial intelligence. At present, it has become a hot topic in the fields of neuroscience, computer science, brain science, mathematics, and psychology. Thomas Bayes firstly reported the Bayesian theory in 1763. After the development in the twentieth century, it has been widespread in all areas of statistics. In recent years, due to the solution of the problem of high-dimensional integral calculation, Bayesian Statistics has been improved theoretically, which solved many problems that cannot be solved by classical statistics and is also applied to the interdisciplinary fields. In this paper, the related concepts and principles of the artificial neural network are introduced. It also summarizes the basic content and principle of Bayesian Statistics, and combines the artificial neural network technology and Bayesian decision theory and implement them in all aspects of image recognition, such as enhanced face detection method based on neural network and Bayesian decision, as well as the image classification based on the Bayesian decision. It can be seen that the combination of artificial intelligence and statistical algorithms has always been the hot research topic.

Dimensionality-varied deep convolutional neural network for spectral-spatial classification of hyperspectral data

Science.gov (United States)

Qu, Haicheng; Liang, Xuejian; Liang, Shichao; Liu, Wanjun

2018-01-01

Many methods of hyperspectral image classification have been proposed recently, and the convolutional neural network (CNN) achieves outstanding performance. However, spectral-spatial classification of CNN requires an excessively large model, tremendous computations, and complex network, and CNN is generally unable to use the noisy bands caused by water-vapor absorption. A dimensionality-varied CNN (DV-CNN) is proposed to address these issues. There are four stages in DV-CNN and the dimensionalities of spectral-spatial feature maps vary with the stages. DV-CNN can reduce the computation and simplify the structure of the network. All feature maps are processed by more kernels in higher stages to extract more precise features. DV-CNN also improves the classification accuracy and enhances the robustness to water-vapor absorption bands. The experiments are performed on data sets of Indian Pines and Pavia University scene. The classification performance of DV-CNN is compared with state-of-the-art methods, which contain the variations of CNN, traditional, and other deep learning methods. The experiment of performance analysis about DV-CNN itself is also carried out. The experimental results demonstrate that DV-CNN outperforms state-of-the-art methods for spectral-spatial classification and it is also robust to water-vapor absorption bands. Moreover, reasonable parameters selection is effective to improve classification accuracy.

Neural networks for the dimensionality reduction of GOME measurement vector in the estimation of ozone profiles

International Nuclear Information System (INIS)

Del Frate, F.; Iapaolo, M.; Casadio, S.; Godin-Beekmann, S.; Petitdidier, M.

2005-01-01

Dimensionality reduction can be of crucial importance in the application of inversion schemes to atmospheric remote sensing data. In this study the problem of dimensionality reduction in the retrieval of ozone concentration profiles from the radiance measurements provided by the instrument Global Ozone Monitoring Experiment (GOME) on board of ESA satellite ERS-2 is considered. By means of radiative transfer modelling, neural networks and pruning algorithms, a complete procedure has been designed to extract the GOME spectral ranges most crucial for the inversion. The quality of the resulting retrieval algorithm has been evaluated by comparing its performance to that yielded by other schemes and co-located profiles obtained with lidar measurements

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

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

Science.gov (United States)

Zhang, WenJun

2007-07-01

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

Deep Neural Network Detects Quantum Phase Transition

Science.gov (United States)

Arai, Shunta; Ohzeki, Masayuki; Tanaka, Kazuyuki

2018-03-01

We detect the quantum phase transition of a quantum many-body system by mapping the observed results of the quantum state onto a neural network. In the present study, we utilized the simplest case of a quantum many-body system, namely a one-dimensional chain of Ising spins with the transverse Ising model. We prepared several spin configurations, which were obtained using repeated observations of the model for a particular strength of the transverse field, as input data for the neural network. Although the proposed method can be employed using experimental observations of quantum many-body systems, we tested our technique with spin configurations generated by a quantum Monte Carlo simulation without initial relaxation. The neural network successfully identified the strength of transverse field only from the spin configurations, leading to consistent estimations of the critical point of our model Γc = J.

High Speed PAM -8 Optical Interconnects with Digital Equalization based on Neural Network

DEFF Research Database (Denmark)

Gaiarin, Simone; Pang, Xiaodan; Ozolins, Oskars

2016-01-01

We experimentally evaluate a high-speed optical interconnection link with neural network equalization. Enhanced equalization performances are shown comparing to standard linear FFE for an EML-based 32 GBd PAM-8 signal after 4-km SMF transmission.......We experimentally evaluate a high-speed optical interconnection link with neural network equalization. Enhanced equalization performances are shown comparing to standard linear FFE for an EML-based 32 GBd PAM-8 signal after 4-km SMF transmission....

Complex Environmental Data Modelling Using Adaptive General Regression Neural Networks

Science.gov (United States)

Kanevski, Mikhail

2015-04-01

The research deals with an adaptation and application of Adaptive General Regression Neural Networks (GRNN) to high dimensional environmental data. GRNN [1,2,3] are efficient modelling tools both for spatial and temporal data and are based on nonparametric kernel methods closely related to classical Nadaraya-Watson estimator. Adaptive GRNN, using anisotropic kernels, can be also applied for features selection tasks when working with high dimensional data [1,3]. In the present research Adaptive GRNN are used to study geospatial data predictability and relevant feature selection using both simulated and real data case studies. The original raw data were either three dimensional monthly precipitation data or monthly wind speeds embedded into 13 dimensional space constructed by geographical coordinates and geo-features calculated from digital elevation model. GRNN were applied in two different ways: 1) adaptive GRNN with the resulting list of features ordered according to their relevancy; and 2) adaptive GRNN applied to evaluate all possible models N [in case of wind fields N=(2^13 -1)=8191] and rank them according to the cross-validation error. In both cases training were carried out applying leave-one-out procedure. An important result of the study is that the set of the most relevant features depends on the month (strong seasonal effect) and year. The predictabilities of precipitation and wind field patterns, estimated using the cross-validation and testing errors of raw and shuffled data, were studied in detail. The results of both approaches were qualitatively and quantitatively compared. In conclusion, Adaptive GRNN with their ability to select features and efficient modelling of complex high dimensional data can be widely used in automatic/on-line mapping and as an integrated part of environmental decision support systems. 1. Kanevski M., Pozdnoukhov A., Timonin V. Machine Learning for Spatial Environmental Data. Theory, applications and software. EPFL Press

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

Selection of variables for neural network analysis. Comparisons of several methods with high energy physics data

International Nuclear Information System (INIS)

Proriol, J.

1994-01-01

Five different methods are compared for selecting the most important variables with a view to classifying high energy physics events with neural networks. The different methods are: the F-test, Principal Component Analysis (PCA), a decision tree method: CART, weight evaluation, and Optimal Cell Damage (OCD). The neural networks use the variables selected with the different methods. We compare the percentages of events properly classified by each neural network. The learning set and the test set are the same for all the neural networks. (author)

SCYNet. Testing supersymmetric models at the LHC with neural networks

Energy Technology Data Exchange (ETDEWEB)

Bechtle, Philip; Belkner, Sebastian; Hamer, Matthias [Universitaet Bonn, Bonn (Germany); Dercks, Daniel [Universitaet Hamburg, Hamburg (Germany); Keller, Tim; Kraemer, Michael; Sarrazin, Bjoern; Schuette-Engel, Jan; Tattersall, Jamie [RWTH Aachen University, Institute for Theoretical Particle Physics and Cosmology, Aachen (Germany)

2017-10-15

SCYNet (SUSY Calculating Yield Net) is a tool for testing supersymmetric models against LHC data. It uses neural network regression for a fast evaluation of the profile likelihood ratio. Two neural network approaches have been developed: one network has been trained using the parameters of the 11-dimensional phenomenological Minimal Supersymmetric Standard Model (pMSSM-11) as an input and evaluates the corresponding profile likelihood ratio within milliseconds. It can thus be used in global pMSSM-11 fits without time penalty. In the second approach, the neural network has been trained using model-independent signature-related objects, such as energies and particle multiplicities, which were estimated from the parameters of a given new physics model. (orig.)

Linear programming based on neural networks for radiotherapy treatment planning

International Nuclear Information System (INIS)

Xingen Wu; Limin Luo

2000-01-01

In this paper, we propose a neural network model for linear programming that is designed to optimize radiotherapy treatment planning (RTP). This kind of neural network can be easily implemented by using a kind of 'neural' electronic system in order to obtain an optimization solution in real time. We first give an introduction to the RTP problem and construct a non-constraint objective function for the neural network model. We adopt a gradient algorithm to minimize the objective function and design the structure of the neural network for RTP. Compared to traditional linear programming methods, this neural network model can reduce the time needed for convergence, the size of problems (i.e., the number of variables to be searched) and the number of extra slack and surplus variables needed. We obtained a set of optimized beam weights that result in a better dose distribution as compared to that obtained using the simplex algorithm under the same initial condition. The example presented in this paper shows that this model is feasible in three-dimensional RTP. (author)

Bounds on Rates of Variable-Basis and Neural-Network Approximation

Czech Academy of Sciences Publication Activity Database

Kůrková, Věra; Sanguineti, M.

2001-01-01

Roč. 47, č. 6 (2001), s. 2659-2665 ISSN 0018-9448 R&D Projects: GA ČR GA201/00/1482 Institutional research plan: AV0Z1030915 Keywords : approximation by variable-basis functions * bounds on rates of approximation * complexity of neural networks * high-dimensional optimal decision problems Subject RIV: BA - General Mathematics Impact factor: 2.077, year: 2001

High Dimensional Modulation and MIMO Techniques for Access Networks

DEFF Research Database (Denmark)

Binti Othman, Maisara

Exploration of advanced modulation formats and multiplexing techniques for next generation optical access networks are of interest as promising solutions for delivering multiple services to end-users. This thesis addresses this from two different angles: high dimensionality carrierless...... the capacity per wavelength of the femto-cell network. Bit rate up to 1.59 Gbps with fiber-wireless transmission over 1 m air distance is demonstrated. The results presented in this thesis demonstrate the feasibility of high dimensionality CAP in increasing the number of dimensions and their potentially......) optical access network. 2 X 2 MIMO RoF employing orthogonal frequency division multiplexing (OFDM) with 5.6 GHz RoF signaling over all-vertical cavity surface emitting lasers (VCSEL) WDM passive optical networks (PONs). We have employed polarization division multiplexing (PDM) to further increase...

High dimensional ICA analysis detects within-network functional connectivity damage of default mode and sensory motor networks in Alzheimer's disease

Directory of Open Access Journals (Sweden)

Ottavia eDipasquale

2015-02-01

Full Text Available High dimensional independent component analysis (ICA, compared to low dimensional ICA, allows performing a detailed parcellation of the resting state networks. The purpose of this study was to give further insight into functional connectivity (FC in Alzheimer’s disease (AD using high dimensional ICA. For this reason, we performed both low and high dimensional ICA analyses of resting state fMRI (rfMRI data of 20 healthy controls and 21 AD patients, focusing on the primarily altered default mode network (DMN and exploring the sensory motor network (SMN. As expected, results obtained at low dimensionality were in line with previous literature. Moreover, high dimensional results allowed us to observe either the presence of within-network disconnections and FC damage confined to some of the resting state sub-networks. Due to the higher sensitivity of the high dimensional ICA analysis, our results suggest that high-dimensional decomposition in sub-networks is very promising to better localize FC alterations in AD and that FC damage is not confined to the default mode network.

Discriminating lysosomal membrane protein types using dynamic neural network.

Science.gov (United States)

Tripathi, Vijay; Gupta, Dwijendra Kumar

2014-01-01

This work presents a dynamic artificial neural network methodology, which classifies the proteins into their classes from their sequences alone: the lysosomal membrane protein classes and the various other membranes protein classes. In this paper, neural networks-based lysosomal-associated membrane protein type prediction system is proposed. Different protein sequence representations are fused to extract the features of a protein sequence, which includes seven feature sets; amino acid (AA) composition, sequence length, hydrophobic group, electronic group, sum of hydrophobicity, R-group, and dipeptide composition. To reduce the dimensionality of the large feature vector, we applied the principal component analysis. The probabilistic neural network, generalized regression neural network, and Elman regression neural network (RNN) are used as classifiers and compared with layer recurrent network (LRN), a dynamic network. The dynamic networks have memory, i.e. its output depends not only on the input but the previous outputs also. Thus, the accuracy of LRN classifier among all other artificial neural networks comes out to be the highest. The overall accuracy of jackknife cross-validation is 93.2% for the data-set. These predicted results suggest that the method can be effectively applied to discriminate lysosomal associated membrane proteins from other membrane proteins (Type-I, Outer membrane proteins, GPI-Anchored) and Globular proteins, and it also indicates that the protein sequence representation can better reflect the core feature of membrane proteins than the classical AA composition.

Visualization of neural networks using saliency maps

DEFF Research Database (Denmark)

Mørch, Niels J.S.; Kjems, Ulrik; Hansen, Lars Kai

1995-01-01

The saliency map is proposed as a new method for understanding and visualizing the nonlinearities embedded in feedforward neural networks, with emphasis on the ill-posed case, where the dimensionality of the input-field by far exceeds the number of examples. Several levels of approximations...

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)

Neural network model for proton-proton collision at high energy

International Nuclear Information System (INIS)

El-Bakry, M.Y.; El-Metwally, K.A.

2003-01-01

Developments in artificial intelligence (AI) techniques and their applications to physics have made it feasible to develop and implement new modeling techniques for high-energy interactions. In particular, AI techniques of artificial neural networks (ANN) have recently been used to design and implement more effective models. The primary purpose of this paper is to model the proton-proton (p-p) collision using the ANN technique. Following a review of the conventional techniques and an introduction to the neural network, the paper presents simulation test results using an p-p based ANN model trained with experimental data. The p-p based ANN model calculates the multiplicity distribution of charged particles and the inelastic cross section of the p-p collision at high energies. The results amply demonstrate the feasibility of such new technique in extracting the collision features and prove its effectiveness

Reservoir characterization using artificial neural network; Neural network wo mochiita choryuso tokusei kaiseki

Energy Technology Data Exchange (ETDEWEB)

Shimada, N; Kozawa, T [Japan National Oil Corp., Tokyo (Japan); Nishikawa, N; Tani, A [Fuji Research Institute Corp., Tokyo (Japan)

1997-05-27

Neural network is used for the prediction of porosity and permeability using logging data as reservoir characteristics, and the validity of this method is verified. For the prediction of reservoir characteristics by the use of seismic survey data, composite seismic survey records obtained by density logging and acoustic logging are used to experiment the prediction of porosity and permeability continuous along lines of wells. A 3-output back propagation network is used for analysis. There is a possibility that this technique when optimized will improve on prediction accuracy. Furthermore, in the case of characteristics mapping, 3-dimensional seismic data is applied to a carbonate rock reservoir for predicting spatial porosity and permeability. This technique facilitates the comprehensive analysis of core data, well data, and seismic survey data, enabling the derivation of a high-precision spatial distribution of reservoir characteristics. Efforts will continue for further improvement on prediction accuracy. 6 refs., 7 figs., 3 tabs.

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)

Global Hopf bifurcation analysis on a BAM neural network with delays

Science.gov (United States)

Sun, Chengjun; Han, Maoan; Pang, Xiaoming

2007-01-01

A delayed differential equation that models a bidirectional associative memory (BAM) neural network with four neurons is considered. By using a global Hopf bifurcation theorem for FDE and a Bendixon's criterion for high-dimensional ODE, a group of sufficient conditions for the system to have multiple periodic solutions are obtained when the sum of delays is sufficiently large.

Global Hopf bifurcation analysis on a BAM neural network with delays

International Nuclear Information System (INIS)

Sun Chengjun; Han Maoan; Pang Xiaoming

2007-01-01

A delayed differential equation that models a bidirectional associative memory (BAM) neural network with four neurons is considered. By using a global Hopf bifurcation theorem for FDE and a Bendixon's criterion for high-dimensional ODE, a group of sufficient conditions for the system to have multiple periodic solutions are obtained when the sum of delays is sufficiently large

Generating Seismograms with Deep Neural Networks

Science.gov (United States)

Krischer, L.; Fichtner, A.

2017-12-01

The recent surge of successful uses of deep neural networks in computer vision, speech recognition, and natural language processing, mainly enabled by the availability of fast GPUs and extremely large data sets, is starting to see many applications across all natural sciences. In seismology these are largely confined to classification and discrimination tasks. In this contribution we explore the use of deep neural networks for another class of problems: so called generative models.Generative modelling is a branch of statistics concerned with generating new observed data samples, usually by drawing from some underlying probability distribution. Samples with specific attributes can be generated by conditioning on input variables. In this work we condition on seismic source (mechanism and location) and receiver (location) parameters to generate multi-component seismograms.The deep neural networks are trained on synthetic data calculated with Instaseis (http://instaseis.net, van Driel et al. (2015)) and waveforms from the global ShakeMovie project (http://global.shakemovie.princeton.edu, Tromp et al. (2010)). The underlying radially symmetric or smoothly three dimensional Earth structures result in comparatively small waveform differences from similar events or at close receivers and the networks learn to interpolate between training data samples.Of particular importance is the chosen misfit functional. Generative adversarial networks (Goodfellow et al. (2014)) implement a system in which two networks compete: the generator network creates samples and the discriminator network distinguishes these from the true training examples. Both are trained in an adversarial fashion until the discriminator can no longer distinguish between generated and real samples. We show how this can be applied to seismograms and in particular how it compares to networks trained with more conventional misfit metrics. Last but not least we attempt to shed some light on the black-box nature of

Simultaneous multichannel signal transfers via chaos in a recurrent neural network.

Science.gov (United States)

Soma, Ken-ichiro; Mori, Ryota; Sato, Ryuichi; Furumai, Noriyuki; Nara, Shigetoshi

2015-05-01

We propose neural network model that demonstrates the phenomenon of signal transfer between separated neuron groups via other chaotic neurons that show no apparent correlations with the input signal. The model is a recurrent neural network in which it is supposed that synchronous behavior between small groups of input and output neurons has been learned as fragments of high-dimensional memory patterns, and depletion of neural connections results in chaotic wandering dynamics. Computer experiments show that when a strong oscillatory signal is applied to an input group in the chaotic regime, the signal is successfully transferred to the corresponding output group, although no correlation is observed between the input signal and the intermediary neurons. Signal transfer is also observed when multiple signals are applied simultaneously to separate input groups belonging to different memory attractors. In this sense simultaneous multichannel communications are realized, and the chaotic neural dynamics acts as a signal transfer medium in which the signal appears to be hidden.

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...

Parameterized neural networks for high-energy physics

Energy Technology Data Exchange (ETDEWEB)

Baldi, Pierre; Sadowski, Peter [University of California, Department of Computer Science, Irvine, CA (United States); Cranmer, Kyle [NYU, Department of Physics, New York, NY (United States); Faucett, Taylor; Whiteson, Daniel [University of California, Department of Physics and Astronomy, Irvine, CA (United States)

2016-05-15

We investigate a new structure for machine learning classifiers built with neural networks and applied to problems in high-energy physics by expanding the inputs to include not only measured features but also physics parameters. The physics parameters represent a smoothly varying learning task, and the resulting parameterized classifier can smoothly interpolate between them and replace sets of classifiers trained at individual values. This simplifies the training process and gives improved performance at intermediate values, even for complex problems requiring deep learning. Applications include tools parameterized in terms of theoretical model parameters, such as the mass of a particle, which allow for a single network to provide improved discrimination across a range of masses. This concept is simple to implement and allows for optimized interpolatable results. (orig.)

Parameterized neural networks for high-energy physics

International Nuclear Information System (INIS)

Baldi, Pierre; Sadowski, Peter; Cranmer, Kyle; Faucett, Taylor; Whiteson, Daniel

2016-01-01

We investigate a new structure for machine learning classifiers built with neural networks and applied to problems in high-energy physics by expanding the inputs to include not only measured features but also physics parameters. The physics parameters represent a smoothly varying learning task, and the resulting parameterized classifier can smoothly interpolate between them and replace sets of classifiers trained at individual values. This simplifies the training process and gives improved performance at intermediate values, even for complex problems requiring deep learning. Applications include tools parameterized in terms of theoretical model parameters, such as the mass of a particle, which allow for a single network to provide improved discrimination across a range of masses. This concept is simple to implement and allows for optimized interpolatable results. (orig.)

Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas.

Science.gov (United States)

Chang, P; Grinband, J; Weinberg, B D; Bardis, M; Khy, M; Cadena, G; Su, M-Y; Cha, S; Filippi, C G; Bota, D; Baldi, P; Poisson, L M; Jain, R; Chow, D

2018-05-10

The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 ( IDH1 ) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase ( MGMT ) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training. © 2018 by American Journal of Neuroradiology.

Study on the forward-feed neural network used for the classification of high energy particles

International Nuclear Information System (INIS)

Luo Guangxuan; Dai Guiliang

1997-01-01

Neural network has been applied in the field of high energy physics experiment for the classification of particles and gained good results. The author emphasizes the systematic analysis of the fundamental principle of the forward-feed neural network and discusses the problems and solving methods in application

Automated detection of lung nodules with three-dimensional convolutional neural networks

Science.gov (United States)

Pérez, Gustavo; Arbeláez, Pablo

2017-11-01

Lung cancer is the cancer type with highest mortality rate worldwide. It has been shown that early detection with computer tomography (CT) scans can reduce deaths caused by this disease. Manual detection of cancer nodules is costly and time-consuming. We present a general framework for the detection of nodules in lung CT images. Our method consists of the pre-processing of a patient's CT with filtering and lung extraction from the entire volume using a previously calculated mask for each patient. From the extracted lungs, we perform a candidate generation stage using morphological operations, followed by the training of a three-dimensional convolutional neural network for feature representation and classification of extracted candidates for false positive reduction. We perform experiments on the publicly available LIDC-IDRI dataset. Our candidate extraction approach is effective to produce precise candidates with a recall of 99.6%. In addition, false positive reduction stage manages to successfully classify candidates and increases precision by a factor of 7.000.

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.

The use of global image characteristics for neural network pattern recognitions

Science.gov (United States)

Kulyas, Maksim O.; Kulyas, Oleg L.; Loshkarev, Aleksey S.

2017-04-01

The recognition system is observed, where the information is transferred by images of symbols generated by a television camera. For descriptors of objects the coefficients of two-dimensional Fourier transformation generated in a special way. For solution of the task of classification the one-layer neural network trained on reference images is used. Fast learning of a neural network with a single neuron calculation of coefficients is applied.

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.

Stochastic synchronization of coupled neural networks with intermittent control

International Nuclear Information System (INIS)

Yang Xinsong; Cao Jinde

2009-01-01

In this Letter, we study the exponential stochastic synchronization problem for coupled neural networks with stochastic noise perturbations. Based on Lyapunov stability theory, inequality techniques, the properties of Weiner process, and adding different intermittent controllers, several sufficient conditions are obtained to ensure exponential stochastic synchronization of coupled neural networks with or without coupling delays under stochastic perturbations. These stochastic synchronization criteria are expressed in terms of several lower-dimensional linear matrix inequalities (LMIs) and can be easily verified. Moreover, the results of this Letter are applicable to both directed and undirected weighted networks. A numerical example and its simulations are offered to show the effectiveness of our new results.

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.

Flood routing modelling with Artificial Neural Networks

Directory of Open Access Journals (Sweden)

R. Peters

2006-01-01

Full Text Available For the modelling of the flood routing in the lower reaches of the Freiberger Mulde river and its tributaries the one-dimensional hydrodynamic modelling system HEC-RAS has been applied. Furthermore, this model was used to generate a database to train multilayer feedforward networks. To guarantee numerical stability for the hydrodynamic modelling of some 60 km of streamcourse an adequate resolution in space requires very small calculation time steps, which are some two orders of magnitude smaller than the input data resolution. This leads to quite high computation requirements seriously restricting the application – especially when dealing with real time operations such as online flood forecasting. In order to solve this problem we tested the application of Artificial Neural Networks (ANN. First studies show the ability of adequately trained multilayer feedforward networks (MLFN to reproduce the model performance.

Deformable image registration using convolutional neural networks

Science.gov (United States)

Eppenhof, Koen A. J.; Lafarge, Maxime W.; Moeskops, Pim; Veta, Mitko; Pluim, Josien P. W.

2018-03-01

Deformable image registration can be time-consuming and often needs extensive parameterization to perform well on a specific application. We present a step towards a registration framework based on a three-dimensional convolutional neural network. The network directly learns transformations between pairs of three-dimensional images. The outputs of the network are three maps for the x, y, and z components of a thin plate spline transformation grid. The network is trained on synthetic random transformations, which are applied to a small set of representative images for the desired application. Training therefore does not require manually annotated ground truth deformation information. The methodology is demonstrated on public data sets of inspiration-expiration lung CT image pairs, which come with annotated corresponding landmarks for evaluation of the registration accuracy. Advantages of this methodology are its fast registration times and its minimal parameterization.

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.

Coordinated three-dimensional motion of the head and torso by dynamic neural networks.

Science.gov (United States)

Kim, J; Hemami, H

1998-01-01

The problem of trajectory tracking control of a three dimensional (3D) model of the human upper torso and head is considered. The torso and the head are modeled as two rigid bodies connected at one point, and the Newton-Euler method is used to derive the nonlinear differential equations that govern the motion of the system. The two-link system is driven by six pairs of muscle like actuators that possess physiologically inspired alpha like and gamma like inputs, and spindle like and Golgi tendon organ like outputs. These outputs are utilized as reflex feedback for stability and stiffness control, in a long loop feedback for the purpose of estimating the state of the system (somesthesis), and as part of the input to the controller. Ideal delays of different duration are included in the feedforward and feedback paths of the system to emulate such delays encountered in physiological systems. Dynamical neural networks are trained to learn effective control of the desired maneuvers of the system. The feasibility of the controller is demonstrated by computer simulation of the successful execution of the desired maneuvers. This work demonstrates the capabilities of neural circuits in controlling highly nonlinear systems with multidelays in their feedforward and feedback paths. The ultimate long range goal of this research is toward understanding the working of the central nervous system in controlling movement. It is an interdisciplinary effort relying on mechanics, biomechanics, neuroscience, system theory, physiology and anatomy, and its short range relevance to rehabilitation must be noted.

On global exponential stability of high-order neural networks with time-varying delays

International Nuclear Information System (INIS)

Zhang Baoyong; Xu Shengyuan; Li Yongmin; Chu Yuming

2007-01-01

This Letter investigates the problem of stability analysis for a class of high-order neural networks with time-varying delays. The delays are bounded but not necessarily differentiable. Based on the Lyapunov stability theory together with the linear matrix inequality (LMI) approach and the use of Halanay inequality, sufficient conditions guaranteeing the global exponential stability of the equilibrium point of the considered neural networks are presented. Two numerical examples are provided to demonstrate the effectiveness of the proposed stability criteria

On global exponential stability of high-order neural networks with time-varying delays

Energy Technology Data Exchange (ETDEWEB)

Zhang Baoyong [School of Automation, Nanjing University of Science and Technology, Nanjing 210094, Jiangsu (China)]. E-mail: baoyongzhang@yahoo.com.cn; Xu Shengyuan [School of Automation, Nanjing University of Science and Technology, Nanjing 210094, Jiangsu (China)]. E-mail: syxu02@yahoo.com.cn; Li Yongmin [School of Automation, Nanjing University of Science and Technology, Nanjing 210094, Jiangsu (China) and Department of Mathematics, Huzhou Teacher' s College, Huzhou 313000, Zhejiang (China)]. E-mail: ymlwww@163.com; Chu Yuming [Department of Mathematics, Huzhou Teacher' s College, Huzhou 313000, Zhejiang (China)

2007-06-18

This Letter investigates the problem of stability analysis for a class of high-order neural networks with time-varying delays. The delays are bounded but not necessarily differentiable. Based on the Lyapunov stability theory together with the linear matrix inequality (LMI) approach and the use of Halanay inequality, sufficient conditions guaranteeing the global exponential stability of the equilibrium point of the considered neural networks are presented. Two numerical examples are provided to demonstrate the effectiveness of the proposed stability criteria.

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...

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

OpenAIRE

Li, Yuhong; Zhang, Xiaofan; Chen, Deming

2018-01-01

We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density maps. The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace po...

Hardware implementation of stochastic spiking neural networks.

Science.gov (United States)

Rosselló, Josep L; Canals, Vincent; Morro, Antoni; Oliver, Antoni

2012-08-01

Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.

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.

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

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....

Heat transfer prediction in a square porous medium using artificial neural network

Science.gov (United States)

Ahamad, N. Ameer; Athani, Abdulgaphur; Badruddin, Irfan Anjum

2018-05-01

Heat transfer in porous media has been investigated extensively because of its applications in various important fields. Neural network approach is applied to analyze steady two dimensional free convection flows through a porous medium fixed in a square cavity. The backpropagation neural network is trained and used to predict the heat transfer. The results are compared with available information in the literature. It is found that the heat transfer increases with increase in Rayleigh number. It is further found that the local Nusselt number decreases along the height of cavity. The neural network is found to predict the heat transfer behavior accurately for given parameters.

Real-space mapping of topological invariants using artificial neural networks

Science.gov (United States)

Carvalho, D.; García-Martínez, N. A.; Lado, J. L.; Fernández-Rossier, J.

2018-03-01

Topological invariants allow one to characterize Hamiltonians, predicting the existence of topologically protected in-gap modes. Those invariants can be computed by tracing the evolution of the occupied wave functions under twisted boundary conditions. However, those procedures do not allow one to calculate a topological invariant by evaluating the system locally, and thus require information about the wave functions in the whole system. Here we show that artificial neural networks can be trained to identify the topological order by evaluating a local projection of the density matrix. We demonstrate this for two different models, a one-dimensional topological superconductor and a two-dimensional quantum anomalous Hall state, both with spatially modulated parameters. Our neural network correctly identifies the different topological domains in real space, predicting the location of in-gap states. By combining a neural network with a calculation of the electronic states that uses the kernel polynomial method, we show that the local evaluation of the invariant can be carried out by evaluating a local quantity, in particular for systems without translational symmetry consisting of tens of thousands of atoms. Our results show that supervised learning is an efficient methodology to characterize the local topology of a system.

Artificial neural networks in prediction of mechanical behavior of concrete at high temperature

International Nuclear Information System (INIS)

Mukherjee, A.; Nag Biswas, S.

1997-01-01

The behavior of concrete structures that are exposed to extreme thermo-mechanical loading is an issue of great importance in nuclear engineering. The mechanical behavior of concrete at high temperature is non-linear. The properties that regulate its response are highly temperature dependent and extremely complex. In addition, the constituent materials, e.g. aggregates, influence the response significantly. Attempts have been made to trace the stress-strain curve through mathematical models and rheological models. However, it has been difficult to include all the contributing factors in the mathematical model. This paper examines a new programming paradigm, artificial neural networks, for the problem. Implementing a feedforward network and backpropagation algorithm the stress-strain relationship of the material is captured. The neural networks for the prediction of uniaxial behavior of concrete at high temperature has been presented here. The results of the present investigation are very encouraging. (orig.)

Multiple Linear Regression Model Based on Neural Network and Its Application in the MBR Simulation

Directory of Open Access Journals (Sweden)

Chunqing Li

2012-01-01

Full Text Available The computer simulation of the membrane bioreactor MBR has become the research focus of the MBR simulation. In order to compensate for the defects, for example, long test period, high cost, invisible equipment seal, and so forth, on the basis of conducting in-depth study of the mathematical model of the MBR, combining with neural network theory, this paper proposed a three-dimensional simulation system for MBR wastewater treatment, with fast speed, high efficiency, and good visualization. The system is researched and developed with the hybrid programming of VC++ programming language and OpenGL, with a multifactor linear regression model of affecting MBR membrane fluxes based on neural network, applying modeling method of integer instead of float and quad tree recursion. The experiments show that the three-dimensional simulation system, using the above models and methods, has the inspiration and reference for the future research and application of the MBR simulation technology.

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.

Fast analysis of spectral data using neural networks

International Nuclear Information System (INIS)

Roach, C.M.

1992-01-01

Fast analysis techniques are highly desirable in experiments where measurements are recorded at high rates. In fusion experiments the processing required to obtain plasma parameters is usually orders of magnitude slower than the data acquisition. Spectroscopic diagnostics suffer greatly from this problem. The extraction of plasma parameters from a measured spectrum typically corresponds to a nonlinear mapping between distinct multi-dimensional spaces. Where no analytic expression for the mapping exists, conventional analysis methods (e.g. least squares) are usually iterative and therefore slow. With this concern in mind a fast spectral analysis method involving neural networks has been investigated. (author) 6 refs., 3 figs

Control of beam halo-chaos using neural network self-adaptation method

International Nuclear Information System (INIS)

Fang Jinqing; Huang Guoxian; Luo Xiaoshu

2004-11-01

Taking the advantages of neural network control method for nonlinear complex systems, control of beam halo-chaos in the periodic focusing channels (network) of high intensity accelerators is studied by feed-forward back-propagating neural network self-adaptation method. The envelope radius of high-intensity proton beam is reached to the matching beam radius by suitably selecting the control structure of neural network and the linear feedback coefficient, adjusted the right-coefficient of neural network. The beam halo-chaos is obviously suppressed and shaking size is much largely reduced after the neural network self-adaptation control is applied. (authors)

Applications of neural networks to the studies of phase transitions of two-dimensional Potts models

Science.gov (United States)

Li, C.-D.; Tan, D.-R.; Jiang, F.-J.

2018-04-01

We study the phase transitions of two-dimensional (2D) Q-states Potts models on the square lattice, using the first principles Monte Carlo (MC) simulations as well as the techniques of neural networks (NN). We demonstrate that the ideas from NN can be adopted to study these considered phase transitions efficiently. In particular, even with a simple NN constructed in this investigation, we are able to obtain the relevant information of the nature of these phase transitions, namely whether they are first order or second order. Our results strengthen the potential applicability of machine learning in studying various states of matters. Subtlety of applying NN techniques to investigate many-body systems is briefly discussed as well.

Complex-valued neural networks advances and applications

CERN Document Server

Hirose, Akira

2013-01-01

Presents the latest advances in complex-valued neural networks by demonstrating the theory in a wide range of applications Complex-valued neural networks is a rapidly developing neural network framework that utilizes complex arithmetic, exhibiting specific characteristics in its learning, self-organizing, and processing dynamics. They are highly suitable for processing complex amplitude, composed of amplitude and phase, which is one of the core concepts in physical systems to deal with electromagnetic, light, sonic/ultrasonic waves as well as quantum waves, namely, electron and

Maximally resolved anharmonic OH vibrational spectrum of the water/ZnO(101 \\xAF 0) interface from a high-dimensional neural network potential

Science.gov (United States)

Quaranta, Vanessa; Hellström, Matti; Behler, Jörg; Kullgren, Jolla; Mitev, Pavlin D.; Hermansson, Kersti

2018-06-01

Unraveling the atomistic details of solid/liquid interfaces, e.g., by means of vibrational spectroscopy, is of vital importance in numerous applications, from electrochemistry to heterogeneous catalysis. Water-oxide interfaces represent a formidable challenge because a large variety of molecular and dissociated water species are present at the surface. Here, we present a comprehensive theoretical analysis of the anharmonic OH stretching vibrations at the water/ZnO(101 ¯ 0) interface as a prototypical case. Molecular dynamics simulations employing a reactive high-dimensional neural network potential based on density functional theory calculations have been used to sample the interfacial structures. In the second step, one-dimensional potential energy curves have been generated for a large number of configurations to solve the nuclear Schrödinger equation. We find that (i) the ZnO surface gives rise to OH frequency shifts up to a distance of about 4 Å from the surface; (ii) the spectrum contains a number of overlapping signals arising from different chemical species, with the frequencies decreasing in the order ν(adsorbed hydroxide) > ν(non-adsorbed water) > ν(surface hydroxide) > ν(adsorbed water); (iii) stretching frequencies are strongly influenced by the hydrogen bond pattern of these interfacial species. Finally, we have been able to identify substantial correlations between the stretching frequencies and hydrogen bond lengths for all species.

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.

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

Comparing the accuracy of high-dimensional neural network potentials and the systematic molecular fragmentation method: A benchmark study for all-trans alkanes

Energy Technology Data Exchange (ETDEWEB)

Gastegger, Michael; Kauffmann, Clemens; Marquetand, Philipp, E-mail: philipp.marquetand@univie.ac.at [Institute of Theoretical Chemistry, Faculty of Chemistry, University of Vienna, Währinger Straße 17, Vienna (Austria); Behler, Jörg [Lehrstuhl für Theoretische Chemie, Ruhr-Universität Bochum, Universitätsstraße 150, Bochum (Germany)

2016-05-21

Many approaches, which have been developed to express the potential energy of large systems, exploit the locality of the atomic interactions. A prominent example is the fragmentation methods in which the quantum chemical calculations are carried out for overlapping small fragments of a given molecule that are then combined in a second step to yield the system’s total energy. Here we compare the accuracy of the systematic molecular fragmentation approach with the performance of high-dimensional neural network (HDNN) potentials introduced by Behler and Parrinello. HDNN potentials are similar in spirit to the fragmentation approach in that the total energy is constructed as a sum of environment-dependent atomic energies, which are derived indirectly from electronic structure calculations. As a benchmark set, we use all-trans alkanes containing up to eleven carbon atoms at the coupled cluster level of theory. These molecules have been chosen because they allow to extrapolate reliable reference energies for very long chains, enabling an assessment of the energies obtained by both methods for alkanes including up to 10 000 carbon atoms. We find that both methods predict high-quality energies with the HDNN potentials yielding smaller errors with respect to the coupled cluster reference.

Comparing the accuracy of high-dimensional neural network potentials and the systematic molecular fragmentation method: A benchmark study for all-trans alkanes

International Nuclear Information System (INIS)

Gastegger, Michael; Kauffmann, Clemens; Marquetand, Philipp; Behler, Jörg

2016-01-01

Many approaches, which have been developed to express the potential energy of large systems, exploit the locality of the atomic interactions. A prominent example is the fragmentation methods in which the quantum chemical calculations are carried out for overlapping small fragments of a given molecule that are then combined in a second step to yield the system’s total energy. Here we compare the accuracy of the systematic molecular fragmentation approach with the performance of high-dimensional neural network (HDNN) potentials introduced by Behler and Parrinello. HDNN potentials are similar in spirit to the fragmentation approach in that the total energy is constructed as a sum of environment-dependent atomic energies, which are derived indirectly from electronic structure calculations. As a benchmark set, we use all-trans alkanes containing up to eleven carbon atoms at the coupled cluster level of theory. These molecules have been chosen because they allow to extrapolate reliable reference energies for very long chains, enabling an assessment of the energies obtained by both methods for alkanes including up to 10 000 carbon atoms. We find that both methods predict high-quality energies with the HDNN potentials yielding smaller errors with respect to the coupled cluster reference.

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

Detection of high-grade small bowel obstruction on conventional radiography with convolutional neural networks.

Science.gov (United States)

Cheng, Phillip M; Tejura, Tapas K; Tran, Khoa N; Whang, Gilbert

2018-05-01

The purpose of this pilot study is to determine whether a deep convolutional neural network can be trained with limited image data to detect high-grade small bowel obstruction patterns on supine abdominal radiographs. Grayscale images from 3663 clinical supine abdominal radiographs were categorized into obstructive and non-obstructive categories independently by three abdominal radiologists, and the majority classification was used as ground truth; 74 images were found to be consistent with small bowel obstruction. Images were rescaled and randomized, with 2210 images constituting the training set (39 with small bowel obstruction) and 1453 images constituting the test set (35 with small bowel obstruction). Weight parameters for the final classification layer of the Inception v3 convolutional neural network, previously trained on the 2014 Large Scale Visual Recognition Challenge dataset, were retrained on the training set. After training, the neural network achieved an AUC of 0.84 on the test set (95% CI 0.78-0.89). At the maximum Youden index (sensitivity + specificity-1), the sensitivity of the system for small bowel obstruction is 83.8%, with a specificity of 68.1%. The results demonstrate that transfer learning with convolutional neural networks, even with limited training data, may be used to train a detector for high-grade small bowel obstruction gas patterns on supine radiographs.

Artificial neural networks for dynamic monitoring of simulated-operating parameters of high temperature gas cooled engineering test reactor (HTTR)

International Nuclear Information System (INIS)

Seker, Serhat; Tuerkcan, Erdinc; Ayaz, Emine; Barutcu, Burak

2003-01-01

This paper addresses to the problem of utilisation of the artificial neural networks (ANNs) for detecting anomalies as well as physical parameters of a nuclear power plant during power operation in real time. Three different types of neural network algorithms were used namely, feed-forward neural network (back-propagation, BP) and two types of recurrent neural networks (RNN). The data used in this paper were gathered from the simulation of the power operation of the Japan's High Temperature Engineering Testing Reactor (HTTR). For the wide range of power operation, 56 signals were generated by the reactor dynamic simulation code for several hours of normal power operation at different power ramps between 30 and 100% nominal power. Paper will compare the outcomes of different neural networks and presents the neural network system and the determination of physical parameters from the simulated operating data

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.

Neural network approach to time-dependent dividing surfaces in classical reaction dynamics

Science.gov (United States)

Schraft, Philippe; Junginger, Andrej; Feldmaier, Matthias; Bardakcioglu, Robin; Main, Jörg; Wunner, Günter; Hernandez, Rigoberto

2018-04-01

In a dynamical system, the transition between reactants and products is typically mediated by an energy barrier whose properties determine the corresponding pathways and rates. The latter is the flux through a dividing surface (DS) between the two corresponding regions, and it is exact only if it is free of recrossings. For time-independent barriers, the DS can be attached to the top of the corresponding saddle point of the potential energy surface, and in time-dependent systems, the DS is a moving object. The precise determination of these direct reaction rates, e.g., using transition state theory, requires the actual construction of a DS for a given saddle geometry, which is in general a demanding methodical and computational task, especially in high-dimensional systems. In this paper, we demonstrate how such time-dependent, global, and recrossing-free DSs can be constructed using neural networks. In our approach, the neural network uses the bath coordinates and time as input, and it is trained in a way that its output provides the position of the DS along the reaction coordinate. An advantage of this procedure is that, once the neural network is trained, the complete information about the dynamical phase space separation is stored in the network's parameters, and a precise distinction between reactants and products can be made for all possible system configurations, all times, and with little computational effort. We demonstrate this general method for two- and three-dimensional systems and explain its straightforward extension to even more degrees of freedom.

A Comparison of Machine Learning Methods in a High-Dimensional Classification Problem

Directory of Open Access Journals (Sweden)

Zekić-Sušac Marijana

2014-09-01

Full Text Available Background: Large-dimensional data modelling often relies on variable reduction methods in the pre-processing and in the post-processing stage. However, such a reduction usually provides less information and yields a lower accuracy of the model. Objectives: The aim of this paper is to assess the high-dimensional classification problem of recognizing entrepreneurial intentions of students by machine learning methods. Methods/Approach: Four methods were tested: artificial neural networks, CART classification trees, support vector machines, and k-nearest neighbour on the same dataset in order to compare their efficiency in the sense of classification accuracy. The performance of each method was compared on ten subsamples in a 10-fold cross-validation procedure in order to assess computing sensitivity and specificity of each model. Results: The artificial neural network model based on multilayer perceptron yielded a higher classification rate than the models produced by other methods. The pairwise t-test showed a statistical significance between the artificial neural network and the k-nearest neighbour model, while the difference among other methods was not statistically significant. Conclusions: Tested machine learning methods are able to learn fast and achieve high classification accuracy. However, further advancement can be assured by testing a few additional methodological refinements in machine learning methods.

Predicting typhoon-induced storm surge tide with a two-dimensional hydrodynamic model and artificial neural network model

Science.gov (United States)

Chen, W.-B.; Liu, W.-C.; Hsu, M.-H.

2012-12-01

Precise predictions of storm surges during typhoon events have the necessity for disaster prevention in coastal seas. This paper explores an artificial neural network (ANN) model, including the back propagation neural network (BPNN) and adaptive neuro-fuzzy inference system (ANFIS) algorithms used to correct poor calculations with a two-dimensional hydrodynamic model in predicting storm surge height during typhoon events. The two-dimensional model has a fine horizontal resolution and considers the interaction between storm surges and astronomical tides, which can be applied for describing the complicated physical properties of storm surges along the east coast of Taiwan. The model is driven by the tidal elevation at the open boundaries using a global ocean tidal model and is forced by the meteorological conditions using a cyclone model. The simulated results of the hydrodynamic model indicate that this model fails to predict storm surge height during the model calibration and verification phases as typhoons approached the east coast of Taiwan. The BPNN model can reproduce the astronomical tide level but fails to modify the prediction of the storm surge tide level. The ANFIS model satisfactorily predicts both the astronomical tide level and the storm surge height during the training and verification phases and exhibits the lowest values of mean absolute error and root-mean-square error compared to the simulated results at the different stations using the hydrodynamic model and the BPNN model. Comparison results showed that the ANFIS techniques could be successfully applied in predicting water levels along the east coastal of Taiwan during typhoon events.

Optical supervised filtering technique based on Hopfield neural network

Science.gov (United States)

Bal, Abdullah

2004-11-01

Hopfield neural network is commonly preferred for optimization problems. In image segmentation, conventional Hopfield neural networks (HNN) are formulated as a cost-function-minimization problem to perform gray level thresholding on the image histogram or the pixels' gray levels arranged in a one-dimensional array [R. Sammouda, N. Niki, H. Nishitani, Pattern Rec. 30 (1997) 921-927; K.S. Cheng, J.S. Lin, C.W. Mao, IEEE Trans. Med. Imag. 15 (1996) 560-567; C. Chang, P. Chung, Image and Vision comp. 19 (2001) 669-678]. In this paper, a new high speed supervised filtering technique is proposed for image feature extraction and enhancement problems by modifying the conventional HNN. The essential improvement in this technique is to use 2D convolution operation instead of weight-matrix multiplication. Thereby, neural network based a new filtering technique has been obtained that is required just 3 × 3 sized filter mask matrix instead of large size weight coefficient matrix. Optical implementation of the proposed filtering technique is executed easily using the joint transform correlator. The requirement of non-negative data for optical implementation is provided by bias technique to convert the bipolar data to non-negative data. Simulation results of the proposed optical supervised filtering technique are reported for various feature extraction problems such as edge detection, corner detection, horizontal and vertical line extraction, and fingerprint enhancement.

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

Decoding small surface codes with feedforward neural networks

Science.gov (United States)

Varsamopoulos, Savvas; Criger, Ben; Bertels, Koen

2018-01-01

Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.

A web-based system for neural network based classification in temporomandibular joint osteoarthritis.

Science.gov (United States)

de Dumast, Priscille; Mirabel, Clément; Cevidanes, Lucia; Ruellas, Antonio; Yatabe, Marilia; Ioshida, Marcos; Ribera, Nina Tubau; Michoud, Loic; Gomes, Liliane; Huang, Chao; Zhu, Hongtu; Muniz, Luciana; Shoukri, Brandon; Paniagua, Beatriz; Styner, Martin; Pieper, Steve; Budin, Francois; Vimort, Jean-Baptiste; Pascal, Laura; Prieto, Juan Carlos

2018-07-01

The purpose of this study is to describe the methodological innovations of a web-based system for storage, integration and computation of biomedical data, using a training imaging dataset to remotely compute a deep neural network classifier of temporomandibular joint osteoarthritis (TMJOA). This study imaging dataset consisted of three-dimensional (3D) surface meshes of mandibular condyles constructed from cone beam computed tomography (CBCT) scans. The training dataset consisted of 259 condyles, 105 from control subjects and 154 from patients with diagnosis of TMJ OA. For the image analysis classification, 34 right and left condyles from 17 patients (39.9 ± 11.7 years), who experienced signs and symptoms of the disease for less than 5 years, were included as the testing dataset. For the integrative statistical model of clinical, biological and imaging markers, the sample consisted of the same 17 test OA subjects and 17 age and sex matched control subjects (39.4 ± 15.4 years), who did not show any sign or symptom of OA. For these 34 subjects, a standardized clinical questionnaire, blood and saliva samples were also collected. The technological methodologies in this study include a deep neural network classifier of 3D condylar morphology (ShapeVariationAnalyzer, SVA), and a flexible web-based system for data storage, computation and integration (DSCI) of high dimensional imaging, clinical, and biological data. The DSCI system trained and tested the neural network, indicating 5 stages of structural degenerative changes in condylar morphology in the TMJ with 91% close agreement between the clinician consensus and the SVA classifier. The DSCI remotely ran with a novel application of a statistical analysis, the Multivariate Functional Shape Data Analysis, that computed high dimensional correlations between shape 3D coordinates, clinical pain levels and levels of biological markers, and then graphically displayed the computation results. The findings of this

Permeability Estimation of Rock Reservoir Based on PCA and Elman Neural Networks

Science.gov (United States)

Shi, Ying; Jian, Shaoyong

2018-03-01

an intelligent method which based on fuzzy neural networks with PCA algorithm, is proposed to estimate the permeability of rock reservoir. First, the dimensionality reduction process is utilized for these parameters by principal component analysis method. Further, the mapping relationship between rock slice characteristic parameters and permeability had been found through fuzzy neural networks. The estimation validity and reliability for this method were tested with practical data from Yan’an region in Ordos Basin. The result showed that the average relative errors of permeability estimation for this method is 6.25%, and this method had the better convergence speed and more accuracy than other. Therefore, by using the cheap rock slice related information, the permeability of rock reservoir can be estimated efficiently and accurately, and it is of high reliability, practicability and application prospect.

Computation of optimal transport and related hedging problems via penalization and neural networks

OpenAIRE

Eckstein, Stephan; Kupper, Michael

2018-01-01

This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks. The core idea is to penalize the optimization problem in its dual formulation and reduce it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function. We present numerical examples from optimal transport, martingale optimal transport, portfolio optimization under uncertainty and generative adversa...

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.

High Performance Data mining by Genetic Neural Network

Directory of Open Access Journals (Sweden)

Dadmehr Rahbari

2013-10-01

Full Text Available Data mining in computer science is the process of discovering interesting and useful patterns and relationships in large volumes of data. Most methods for mining problems is based on artificial intelligence algorithms. Neural network optimization based on three basic parameters topology, weights and the learning rate is a powerful method. We introduce optimal method for solving this problem. In this paper genetic algorithm with mutation and crossover operators change the network structure and optimized that. Dataset used for our work is stroke disease with twenty features that optimized number of that achieved by new hybrid algorithm. Result of this work is very well incomparison with other similar method. Low present of error show that our method is our new approach to efficient, high-performance data mining problems is introduced.

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.

Global existence of periodic solutions on a simplified BAM neural network model with delays

International Nuclear Information System (INIS)

Zheng Baodong; Zhang Yazhuo; Zhang Chunrui

2008-01-01

A simplified n-dimensional BAM neural network model with delays is considered. Some results of Hopf bifurcations occurring at the zero equilibrium as the delay increases are exhibited. Global existence of periodic solutions are established using a global Hopf bifurcation result of Wu [Wu J. Symmetric functional-differential equations and neural networks with memory. Trans Am Math Soc 1998;350:4799-838], and a Bendixson criterion for higher dimensional ordinary differential equations due to Li and Muldowney [Li MY, Muldowney J. On Bendixson's criterion. J Differ Equations 1994;106:27-39]. Finally, computer simulations are performed to illustrate the analytical results found

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)

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

A Comparison of Machine Learning Methods in a High-Dimensional Classification Problem

OpenAIRE

Zekić-Sušac, Marijana; Pfeifer, Sanja; Šarlija, Nataša

2014-01-01

Background: Large-dimensional data modelling often relies on variable reduction methods in the pre-processing and in the post-processing stage. However, such a reduction usually provides less information and yields a lower accuracy of the model. Objectives: The aim of this paper is to assess the high-dimensional classification problem of recognizing entrepreneurial intentions of students by machine learning methods. Methods/Approach: Four methods were tested: artificial neural networks, CART ...

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.

A neural network to predict symptomatic lung injury

International Nuclear Information System (INIS)

Munley, M.T.; Lo, J.Y.

1999-01-01

A nonlinear neural network that simultaneously uses pre-radiotherapy (RT) biological and physical data was developed to predict symptomatic lung injury. The input data were pre-RT pulmonary function, three-dimensional treatment plan doses and demographics. The output was a single value between 0 (asymptomatic) and 1 (symptomatic) to predict the likelihood that a particular patient would become symptomatic. The network was trained on data from 97 patients for 400 iterations with the goal to minimize the mean-squared error. Statistical analysis was performed on the resulting network to determine the model's accuracy. Results from the neural network were compared with those given by traditional linear discriminate analysis and the dose-volume histogram reduction (DVHR) scheme of Kutcher. Receiver-operator characteristic (ROC) analysis was performed on the resulting network which had Az=0.833±0.04. (Az is the area under the ROC curve.) Linear discriminate multivariate analysis yielded an Az=0.813±0.06. The DVHR method had Az=0.521±0.08. The network was also used to rank the significance of the input variables. Future studies will be conducted to improve network accuracy and to include functional imaging data. (author)

Neural networks and cellular automata in experimental high energy physics

Energy Technology Data Exchange (ETDEWEB)

Denby, B

1988-06-01

Within the past few years, two novel computing techniques, cellular automata and neural networks, have shown considerable promise in the solution of problems of a very high degree of complexity, such as turbulent fluid flow, image processing, and pattern recognition. Many of the problems faced in experimental high energy physics are also of this nature. Track reconstruction in wire chambers and cluster finding in cellular calorimeters, for instance, involve pattern recognition and high combinatorial complexity since many combinations of hits or cells must be considered in order to arrive at the final tracks or clusters. Here we examine in what way connective network methods can be applied to some of the problems of experimental high energy physics. It is found that such problems as track and cluster finding adapt naturally to these approaches. When large scale hard-wired connective networks become available, it will be possible to realize solutions to such problems in a fraction of the time required by traditional methods. For certain types of problems, faster solutions are already possible using model networks implemented on vector or other massively parallel machines. It should also be possible, using existing technology, to build simplified networks that will allow detailed reconstructed event information to be used in fast trigger decisions.

Neural networks and cellular automata in experimental high energy physics

International Nuclear Information System (INIS)

Denby, B.

1987-11-01

Within the past few years, two novel computing techniques, cellular automata and neural networks, have shown considerable promise in the solution of problems of a very high degree of complexity, such as turbulent fluid flow, image processing, and pattern recognition. Many of the problems faced in experimental high energy physics are also of this nature. Track reconstruction in wire chambers and cluster finding in cellular calorimeters, for instance, involve pattern recognition and high combinatorial complexity since many combinations of hits or cells must be considered in order to arrive at the final tracks or clusters. Here we examine in what way connective network methods can be applied to some of the problems of experimental high physics. It is found that such problems as track and cluster finding adapt naturally to these approaches. When large scale hardwired connective networks become available, it will be possible to realize solutions to such problems in a fraction of the time required by traditional methods. For certain types of problems, faster solutions are already possible using model networks implemented on vector or other massively parallel machines. It should also be possible, using existing technology, to build simplified networks that will allow detailed reconstructed event information to be used in fast trigger decisions

Neural networks and cellular automata in experimental high energy physics

International Nuclear Information System (INIS)

Denby, B.

1988-01-01

Within the past few years, two novel computing techniques, cellular automata and neural networks, have shown considerable promise in the solution of problems of a very high degree of complexity, such as turbulent fluid flow, image processing, and pattern recognition. Many of the problems faced in experimental high energy physics are also of this nature. Track reconstruction in wire chambers and cluster finding in cellular calorimeters, for instance, involve pattern recognition and high combinatorial complexity since many combinations of hits or cells must be considered in order to arrive at the final tracks or clusters. Here we examine in what way connective network methods can be applied to some of the problems of experimental high energy physics. It is found that such problems as track and cluster finding adapt naturally to these approaches. When large scale hard-wired connective networks become available, it will be possible to realize solutions to such problems in a fraction of the time required by traditional methods. For certain types of problems, faster solutions are already possible using model networks implemented on vector or other massively parallel machines. It should also be possible, using existing technology, to build simplified networks that will allow detailed reconstructed event information to be used in fast trigger decisions. (orig.)

Three-dimensional object recognitions from two-dimensional images using wavelet transforms and neural networks

Science.gov (United States)

Deschenes, Sylvain; Sheng, Yunlong; Chevrette, Paul C.

1998-03-01

3D object classification from 2D IR images is shown. The wavelet transform is used for edge detection. Edge tracking is used for removing noise effectively int he wavelet transform. The invariant Fourier descriptor is used to describe the contour curves. Invariance under out-of-plane rotation is achieved by the feature space trajectory neural network working as a classifier.

Neural networks for event filtering at D/O/

International Nuclear Information System (INIS)

Cutts, D.; Hoftun, J.S.; Sornborger, A.; Johnson, C.R.; Zeller, R.T.

1989-01-01

Neural networks may provide important tools for pattern recognition in high energy physics. We discuss an initial exploration of these techniques, presenting the result of network simulations of several filter algorithms. The D0 data acquisition system, a MicroVAX farm, will perform critical event selection; we describe a possible implementation of neural network algorithms in this system. 7 refs., 4 figs

Network Reconstruction From High-Dimensional Ordinary Differential Equations.

Science.gov (United States)

Chen, Shizhe; Shojaie, Ali; Witten, Daniela M

2017-01-01

We consider the task of learning a dynamical system from high-dimensional time-course data. For instance, we might wish to estimate a gene regulatory network from gene expression data measured at discrete time points. We model the dynamical system nonparametrically as a system of additive ordinary differential equations. Most existing methods for parameter estimation in ordinary differential equations estimate the derivatives from noisy observations. This is known to be challenging and inefficient. We propose a novel approach that does not involve derivative estimation. We show that the proposed method can consistently recover the true network structure even in high dimensions, and we demonstrate empirical improvement over competing approaches. Supplementary materials for this article are available online.

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

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.

Stability of a neural network model with small-world connections

International Nuclear Information System (INIS)

Li Chunguang; Chen Guanrong

2003-01-01

Small-world networks are highly clustered networks with small distances among the nodes. There are many biological neural networks that present this kind of connection. There are no special weightings in the connections of most existing small-world network models. However, this kind of simply connected model cannot characterize biological neural networks, in which there are different weights in synaptic connections. In this paper, we present a neural network model with weighted small-world connections and further investigate the stability of this model

Dynamic analysis of high-order Cohen-Grossberg neural networks with time delay

International Nuclear Information System (INIS)

Chen Zhang; Zhao Donghua; Ruan Jiong

2007-01-01

In this paper, a class of high-order Cohen-Grossberg neural networks with time delay is studied. Several sufficient conditions are obtained for global asymptotic stability and global exponential stability using Lyapunov and LMI method. Finally, two examples are given to illustrate the effectiveness of our method

Topology influences performance in the associative memory neural networks

International Nuclear Information System (INIS)

Lu Jianquan; He Juan; Cao Jinde; Gao Zhiqiang

2006-01-01

To explore how topology affects performance within Hopfield-type associative memory neural networks (AMNNs), we studied the computational performance of the neural networks with regular lattice, random, small-world, and scale-free structures. In this Letter, we found that the memory performance of neural networks obtained through asynchronous updating from 'larger' nodes to 'smaller' nodes are better than asynchronous updating in random order, especially for the scale-free topology. The computational performance of associative memory neural networks linked by the above-mentioned network topologies with the same amounts of nodes (neurons) and edges (synapses) were studied respectively. Along with topologies becoming more random and less locally disordered, we will see that the performance of associative memory neural network is quite improved. By comparing, we show that the regular lattice and random network form two extremes in terms of patterns stability and retrievability. For a network, its patterns stability and retrievability can be largely enhanced by adding a random component or some shortcuts to its structured component. According to the conclusions of this Letter, we can design the associative memory neural networks with high performance and minimal interconnect requirements

Cultured Neural Networks: Optimization of Patterned Network Adhesiveness and Characterization of their Neural Activity

Directory of Open Access Journals (Sweden)

W. L. C. Rutten

2006-01-01

Full Text Available One type of future, improved neural interface is the “cultured probe”. It is a hybrid type of neural information transducer or prosthesis, for stimulation and/or recording of neural activity. It would consist of a microelectrode array (MEA on a planar substrate, each electrode being covered and surrounded by a local circularly confined network (“island” of cultured neurons. The main purpose of the local networks is that they act as biofriendly intermediates for collateral sprouts from the in vivo system, thus allowing for an effective and selective neuron–electrode interface. As a secondary purpose, one may envisage future information processing applications of these intermediary networks. In this paper, first, progress is shown on how substrates can be chemically modified to confine developing networks, cultured from dissociated rat cortex cells, to “islands” surrounding an electrode site. Additional coating of neurophobic, polyimide-coated substrate by triblock-copolymer coating enhances neurophilic-neurophobic adhesion contrast. Secondly, results are given on neuronal activity in patterned, unconnected and connected, circular “island” networks. For connected islands, the larger the island diameter (50, 100 or 150 μm, the more spontaneous activity is seen. Also, activity may show a very high degree of synchronization between two islands. For unconnected islands, activity may start at 22 days in vitro (DIV, which is two weeks later than in unpatterned networks.

Construction of an interatomic potential for zinc oxide surfaces by high-dimensional neural networks

Energy Technology Data Exchange (ETDEWEB)

Artrith, Nongnuch; Morawietz, Tobias; Behler, Joerg [Lehrstuhl fuer Theoretische Chemie, Ruhr-Universitaet Bochum, D-44780 Bochum (Germany)

2011-07-01

Zinc oxide (ZnO) is a technologically important material with many applications, e.g. in heterogeneous catalysis. For theoretical studies of the structural properties of ZnO surfaces, defects, and crystal structures it is necessary to simulate large systems over long time-scales with sufficient accuracy. Often, the required system size is not accessible by computationally rather demanding density-functional theory (DFT) calculations. Recently, artificial Neural Networks (NN) trained to first principles data have shown to provide accurate potential-energy surfaces (PESs) for condensed systems. We present the construction and analysis of a NN PES for ZnO. The structural and energetic properties of bulk ZnO and ZnO surfaces are investigated using this potential and compared to DFT calculations.

Neural network CT image reconstruction method for small amount of projection data

International Nuclear Information System (INIS)

Ma, X.F.; Fukuhara, M.; Takeda, T.

2000-01-01

This paper presents a new method for two-dimensional image reconstruction by using a multi-layer neural network. Though a conventionally used object function of such a neural network is composed of a sum of squared errors of the output data, we define an object function composed of a sum of squared residuals of an integral equation. By employing an appropriate numerical line integral for this integral equation, we can construct a neural network which can be used for CT image reconstruction for cases with small amount of projection data. We applied this method to some model problems and obtained satisfactory results. This method is especially useful for analyses of laboratory experiments or field observations where only a small amount of projection data is available in comparison with the well-developed medical applications

Neural network CT image reconstruction method for small amount of projection data

CERN Document Server

Ma, X F; Takeda, T

2000-01-01

This paper presents a new method for two-dimensional image reconstruction by using a multi-layer neural network. Though a conventionally used object function of such a neural network is composed of a sum of squared errors of the output data, we define an object function composed of a sum of squared residuals of an integral equation. By employing an appropriate numerical line integral for this integral equation, we can construct a neural network which can be used for CT image reconstruction for cases with small amount of projection data. We applied this method to some model problems and obtained satisfactory results. This method is especially useful for analyses of laboratory experiments or field observations where only a small amount of projection data is available in comparison with the well-developed medical applications.

Neural networks for link prediction in realistic biomedical graphs: a multi-dimensional evaluation of graph embedding-based approaches.

Science.gov (United States)

Crichton, Gamal; Guo, Yufan; Pyysalo, Sampo; Korhonen, Anna

2018-05-21

Link prediction in biomedical graphs has several important applications including predicting Drug-Target Interactions (DTI), Protein-Protein Interaction (PPI) prediction and Literature-Based Discovery (LBD). It can be done using a classifier to output the probability of link formation between nodes. Recently several works have used neural networks to create node representations which allow rich inputs to neural classifiers. Preliminary works were done on this and report promising results. However they did not use realistic settings like time-slicing, evaluate performances with comprehensive metrics or explain when or why neural network methods outperform. We investigated how inputs from four node representation algorithms affect performance of a neural link predictor on random- and time-sliced biomedical graphs of real-world sizes (∼ 6 million edges) containing information relevant to DTI, PPI and LBD. We compared the performance of the neural link predictor to those of established baselines and report performance across five metrics. In random- and time-sliced experiments when the neural network methods were able to learn good node representations and there was a negligible amount of disconnected nodes, those approaches outperformed the baselines. In the smallest graph (∼ 15,000 edges) and in larger graphs with approximately 14% disconnected nodes, baselines such as Common Neighbours proved a justifiable choice for link prediction. At low recall levels (∼ 0.3) the approaches were mostly equal, but at higher recall levels across all nodes and average performance at individual nodes, neural network approaches were superior. Analysis showed that neural network methods performed well on links between nodes with no previous common neighbours; potentially the most interesting links. Additionally, while neural network methods benefit from large amounts of data, they require considerable amounts of computational resources to utilise them. Our results indicate

Using function approximation to determine neural network accuracy

International Nuclear Information System (INIS)

Wichman, R.F.; Alexander, J.

2013-01-01

Many, if not most, control processes demonstrate nonlinear behavior in some portion of their operating range and the ability of neural networks to model non-linear dynamics makes them very appealing for control. Control of high reliability safety systems, and autonomous control in process or robotic applications, however, require accurate and consistent control and neural networks are only approximators of various functions so their degree of approximation becomes important. In this paper, the factors affecting the ability of a feed-forward back-propagation neural network to accurately approximate a non-linear function are explored. Compared to pattern recognition using a neural network for function approximation provides an easy and accurate method for determining the network's accuracy. In contrast to other techniques, we show that errors arising in function approximation or curve fitting are caused by the neural network itself rather than scatter in the data. A method is proposed that provides improvements in the accuracy achieved during training and resulting ability of the network to generalize after training. Binary input vectors provided a more accurate model than with scalar inputs and retraining using a small number of the outlier x,y pairs improved generalization. (author)

CNNcon: improved protein contact maps prediction using cascaded neural networks.

Directory of Open Access Journals (Sweden)

Wang Ding

Full Text Available BACKGROUNDS: Despite continuing progress in X-ray crystallography and high-field NMR spectroscopy for determination of three-dimensional protein structures, the number of unsolved and newly discovered sequences grows much faster than that of determined structures. Protein modeling methods can possibly bridge this huge sequence-structure gap with the development of computational science. A grand challenging problem is to predict three-dimensional protein structure from its primary structure (residues sequence alone. However, predicting residue contact maps is a crucial and promising intermediate step towards final three-dimensional structure prediction. Better predictions of local and non-local contacts between residues can transform protein sequence alignment to structure alignment, which can finally improve template based three-dimensional protein structure predictors greatly. METHODS: CNNcon, an improved multiple neural networks based contact map predictor using six sub-networks and one final cascade-network, was developed in this paper. Both the sub-networks and the final cascade-network were trained and tested with their corresponding data sets. While for testing, the target protein was first coded and then input to its corresponding sub-networks for prediction. After that, the intermediate results were input to the cascade-network to finish the final prediction. RESULTS: The CNNcon can accurately predict 58.86% in average of contacts at a distance cutoff of 8 Å for proteins with lengths ranging from 51 to 450. The comparison results show that the present method performs better than the compared state-of-the-art predictors. Particularly, the prediction accuracy keeps steady with the increase of protein sequence length. It indicates that the CNNcon overcomes the thin density problem, with which other current predictors have trouble. This advantage makes the method valuable to the prediction of long length proteins. As a result, the effective

Neural networks for sensor validation and plant-wide monitoring

International Nuclear Information System (INIS)

Eryurek, E.

1991-08-01

The feasibility of using neural networks to characterize one or more variables as a function of other than related variables has been studied. Neural network or parallel distributed processing is found to be highly suitable for the development of relationships among various parameters. A sensor failure detection is studied, and it is shown that neural network models can be used to estimate the sensor readings during the absence of a sensor. (author). 4 refs.; 3 figs

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.

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)

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.

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...

Use of neural network based auto-associative memory as a data compressor for pre-processing optical emission spectra in gas thermometry with the help of neural network

International Nuclear Information System (INIS)

Dolenko, S.A.; Filippov, A.V.; Pal, A.F.; Persiantsev, I.G.; Serov, A.O.

2003-01-01

Determination of temperature from optical emission spectra is an inverse problem that is often very difficult to solve, especially when substantial noise is present. One of the means that can be used to solve such a problem is a neural network trained on the results of modeling of spectra at different temperatures (Dolenko, et al., in: I.C. Parmee (Ed.), Adaptive Computing in Design and Manufacture, Springer, London, 1998, p. 345). Reducing the dimensionality of the input data prior to application of neural network can increase the accuracy and stability of temperature determination. In this study, such pre-processing is performed with another neural network working as an auto-associative memory with a narrow bottleneck in the hidden layer. The improvement in the accuracy and stability of temperature determination in presence of noise is demonstrated on model spectra similar to those recorded in a DC-discharge CVD reactor

Three-dimensional neural cultures produce networks that mimic native brain activity.

Science.gov (United States)

Bourke, Justin L; Quigley, Anita F; Duchi, Serena; O'Connell, Cathal D; Crook, Jeremy M; Wallace, Gordon G; Cook, Mark J; Kapsa, Robert M I

2018-02-01

Development of brain function is critically dependent on neuronal networks organized through three dimensions. Culture of central nervous system neurons has traditionally been limited to two dimensions, restricting growth patterns and network formation to a single plane. Here, with the use of multichannel extracellular microelectrode arrays, we demonstrate that neurons cultured in a true three-dimensional environment recapitulate native neuronal network formation and produce functional outcomes more akin to in vivo neuronal network activity. Copyright © 2017 John Wiley & Sons, Ltd.

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

Neural networks, D0, and the SSC

International Nuclear Information System (INIS)

Barter, C.; Cutts, D.; Hoftun, J.S.; Partridge, R.A.; Sornborger, A.T.; Johnson, C.T.; Zeller, R.T.

1989-01-01

We outline several exploratory studies involving neural network simulations applied to pattern recognition in high energy physics. We describe the D0 data acquisition system and a natual means by which algorithms derived from neural networks techniques may be incorporated into recently developed hardware associated with the D0 MicroVAX farm nodes. Such applications to the event filtering needed by SSC detectors look interesting. 10 refs., 11 figs

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.

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

Development of Fast-Running Simulation Methodology Using Neural Networks for Load Follow Operation

International Nuclear Information System (INIS)

Seong, Seung-Hwan; Park, Heui-Youn; Kim, Dong-Hoon; Suh, Yong-Suk; Hur, Seop; Koo, In-Soo; Lee, Un-Chul; Jang, Jin-Wook; Shin, Yong-Chul

2002-01-01

A new fast-running analytic model has been developed for analyzing the load follow operation. The new model was based on the neural network theory, which has the capability of modeling the input/output relationships of a nonlinear system. The new model is made up of two error back-propagation neural networks and procedures to calculate core parameters, such as the distributions and density of xenon in a quasi-steady-state core like load follow operation. One neural network is designed to retrieve the axial offset of power distribution, and the other is for reactivity corresponding to a given core condition. The training data sets for learning the neural networks in the new model are generated with a three-dimensional nodal code and, also, the measured data of the first-day test of load follow operation. Using the new model, the simulation results of the 5-day load follow test in a pressurized water reactor show a good agreement between the simulation data and the actual measured data. Required computing time for simulating a load follow operation is comparable to that of a fast-running lumped model. Moreover, the new model does not require additional engineering factors to compensate for the difference between the actual measurements and analysis results because the neural network has the inherent learning capability of neural networks to new situations

Efficient computation in adaptive artificial spiking neural networks

NARCIS (Netherlands)

D. Zambrano (Davide); R.B.P. Nusselder (Roeland); H.S. Scholte; S.M. Bohte (Sander)

2017-01-01

textabstractArtificial Neural Networks (ANNs) are bio-inspired models of neural computation that have proven highly effective. Still, ANNs lack a natural notion of time, and neural units in ANNs exchange analog values in a frame-based manner, a computationally and energetically inefficient form of

The Use of Three-Dimensional Convolutional Neural Networks to Interpret LiDAR for Forest Inventory

Directory of Open Access Journals (Sweden)

Elias Ayrey

2018-04-01

Full Text Available As light detection and ranging (LiDAR technology becomes more available, it has become common to use these datasets to generate remotely sensed forest inventories across landscapes. Traditional methods for generating these inventories employ the use of height and proportion metrics to measure LiDAR returns and relate these back to field data using predictive models. Here, we employ a three-dimensional convolutional neural network (CNN, a deep learning technique that scans the LiDAR data and automatically generates useful features for predicting forest attributes. We test the accuracy in estimating forest attributes using the three-dimensional implementations of different CNN models commonly used in the field of image recognition. Using the best performing model architecture, we compared CNN performance to models developed using traditional height metrics. The results of this comparison show that CNNs produced 12% less prediction error when estimating biomass, 6% less in estimating tree count, and 2% less when estimating the percentage of needleleaf trees. We conclude that using CNNs can be a more accurate means of interpreting LiDAR data for forest inventories compared to standard approaches.

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

Designing neural networks that process mean values of random variables

International Nuclear Information System (INIS)

Barber, Michael J.; Clark, John W.

2014-01-01

We develop a class of neural networks derived from probabilistic models posed in the form of Bayesian networks. Making biologically and technically plausible assumptions about the nature of the probabilistic models to be represented in the networks, we derive neural networks exhibiting standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the relevant random variables, that can pool multiple sources of evidence, and that deal appropriately with ambivalent, inconsistent, or contradictory evidence. - Highlights: • High-level neural computations are specified by Bayesian belief networks of random variables. • Probability densities of random variables are encoded in activities of populations of neurons. • Top-down algorithm generates specific neural network implementation of given computation. • Resulting “neural belief networks” process mean values of random variables. • Such networks pool multiple sources of evidence and deal properly with inconsistent evidence

Designing neural networks that process mean values of random variables

Energy Technology Data Exchange (ETDEWEB)

Barber, Michael J. [AIT Austrian Institute of Technology, Innovation Systems Department, 1220 Vienna (Austria); Clark, John W. [Department of Physics and McDonnell Center for the Space Sciences, Washington University, St. Louis, MO 63130 (United States); Centro de Ciências Matemáticas, Universidade de Madeira, 9000-390 Funchal (Portugal)

2014-06-13

We develop a class of neural networks derived from probabilistic models posed in the form of Bayesian networks. Making biologically and technically plausible assumptions about the nature of the probabilistic models to be represented in the networks, we derive neural networks exhibiting standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the relevant random variables, that can pool multiple sources of evidence, and that deal appropriately with ambivalent, inconsistent, or contradictory evidence. - Highlights: • High-level neural computations are specified by Bayesian belief networks of random variables. • Probability densities of random variables are encoded in activities of populations of neurons. • Top-down algorithm generates specific neural network implementation of given computation. • Resulting “neural belief networks” process mean values of random variables. • Such networks pool multiple sources of evidence and deal properly with inconsistent evidence.

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.

Image Fusion Based on the Self-Organizing Feature Map Neural Networks

Institute of Scientific and Technical Information of China (English)

ZHANG Zhaoli; SUN Shenghe

2001-01-01

This paper presents a new image datafusion scheme based on the self-organizing featuremap (SOFM) neural networks.The scheme consists ofthree steps:(1) pre-processing of the images,whereweighted median filtering removes part of the noisecomponents corrupting the image,(2) pixel clusteringfor each image using two-dimensional self-organizingfeature map neural networks,and (3) fusion of the im-ages obtained in Step (2) utilizing fuzzy logic,whichsuppresses the residual noise components and thusfurther improves the image quality.It proves thatsuch a three-step combination offers an impressive ef-fectiveness and performance improvement,which isconfirmed by simulations involving three image sen-sors (each of which has a different noise structure).

Bio-inspired spiking neural network for nonlinear systems control.

Science.gov (United States)

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

2018-08-01

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

A comparative study of two neural networks for document retrieval

International Nuclear Information System (INIS)

Hui, S.C.; Goh, A.

1997-01-01

In recent years there has been specific interest in adopting advanced computer techniques in the field of document retrieval. This interest is generated by the fact that classical methods such as the Boolean search, the vector space model or even probabilistic retrieval cannot handle the increasing demands of end-users in satisfying their needs. The most recent attempt is the application of the neural network paradigm as a means of providing end-users with a more powerful retrieval mechanism. Neural networks are not only good pattern matchers but also highly versatile and adaptable. In this paper, we demonstrate how to apply two neural networks, namely Adaptive Resonance Theory and Fuzzy Kohonen Neural Network, for document retrieval. In addition, a comparison of these two neural networks based on performance is also given

Network traffic anomaly prediction using Artificial Neural Network

Science.gov (United States)

Ciptaningtyas, Hening Titi; Fatichah, Chastine; Sabila, Altea

2017-03-01

As the excessive increase of internet usage, the malicious software (malware) has also increase significantly. Malware is software developed by hacker for illegal purpose(s), such as stealing data and identity, causing computer damage, or denying service to other user[1]. Malware which attack computer or server often triggers network traffic anomaly phenomena. Based on Sophos's report[2], Indonesia is the riskiest country of malware attack and it also has high network traffic anomaly. This research uses Artificial Neural Network (ANN) to predict network traffic anomaly based on malware attack in Indonesia which is recorded by Id-SIRTII/CC (Indonesia Security Incident Response Team on Internet Infrastructure/Coordination Center). The case study is the highest malware attack (SQL injection) which has happened in three consecutive years: 2012, 2013, and 2014[4]. The data series is preprocessed first, then the network traffic anomaly is predicted using Artificial Neural Network and using two weight update algorithms: Gradient Descent and Momentum. Error of prediction is calculated using Mean Squared Error (MSE) [7]. The experimental result shows that MSE for SQL Injection is 0.03856. So, this approach can be used to predict network traffic anomaly.

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...

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...

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.

Prediction of compression strength of high performance concrete using artificial neural networks

International Nuclear Information System (INIS)

Torre, A; Moromi, I; Garcia, F; Espinoza, P; Acuña, L

2015-01-01

High-strength concrete is undoubtedly one of the most innovative materials in construction. Its manufacture is simple and is carried out starting from essential components (water, cement, fine and aggregates) and a number of additives. Their proportions have a high influence on the final strength of the product. This relations do not seem to follow a mathematical formula and yet their knowledge is crucial to optimize the quantities of raw materials used in the manufacture of concrete. Of all mechanical properties, concrete compressive strength at 28 days is most often used for quality control. Therefore, it would be important to have a tool to numerically model such relationships, even before processing. In this aspect, artificial neural networks have proven to be a powerful modeling tool especially when obtaining a result with higher reliability than knowledge of the relationships between the variables involved in the process. This research has designed an artificial neural network to model the compressive strength of concrete based on their manufacturing parameters, obtaining correlations of the order of 0.94

Controlled neural network application in track-match problem

International Nuclear Information System (INIS)

Baginyan, S.A.; Ososkov, G.A.

1993-01-01

Track-match problem of high energy physics (HEP) data handling is formulated in terms of incidence matrices. The corresponding Hopfield neural network is developed to solve this type of constraint satisfaction problems (CSP). A special concept of the controlled neural network is proposed as a basis of an algorithm for the effective CSP solution. Results of comparable calculations show the very high performance of this algorithm against conventional search procedures. 8 refs.; 1 fig.; 1 tab

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

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.

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....

Constructing general partial differential equations using polynomial and neural networks.

Science.gov (United States)

Zjavka, Ladislav; Pedrycz, Witold

2016-01-01

Sum fraction terms can approximate multi-variable functions on the basis of discrete observations, replacing a partial differential equation definition with polynomial elementary data relation descriptions. Artificial neural networks commonly transform the weighted sum of inputs to describe overall similarity relationships of trained and new testing input patterns. Differential polynomial neural networks form a new class of neural networks, which construct and solve an unknown general partial differential equation of a function of interest with selected substitution relative terms using non-linear multi-variable composite polynomials. The layers of the network generate simple and composite relative substitution terms whose convergent series combinations can describe partial dependent derivative changes of the input variables. This regression is based on trained generalized partial derivative data relations, decomposed into a multi-layer polynomial network structure. The sigmoidal function, commonly used as a nonlinear activation of artificial neurons, may transform some polynomial items together with the parameters with the aim to improve the polynomial derivative term series ability to approximate complicated periodic functions, as simple low order polynomials are not able to fully make up for the complete cycles. The similarity analysis facilitates substitutions for differential equations or can form dimensional units from data samples to describe real-world problems. Copyright © 2015 Elsevier Ltd. All rights reserved.

Neural networks: Application to medical imaging

Science.gov (United States)

Clarke, Laurence P.

1994-01-01

The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.

Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank

OpenAIRE

Zhao, Liang; Liao, Siyu; Wang, Yanzhi; Li, Zhe; Tang, Jian; Pan, Victor; Yuan, Bo

2017-01-01

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as LDR neural networks, can achieve significant reduction in space and computational complexity while retaining high accuracy. We formally study LDR matrices in deep learning. First, we prove the universal approximation property of LDR neural networks with a ...

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

Microstructural characterization of materials by neural network technique

Energy Technology Data Exchange (ETDEWEB)

Barat, P. [Variable Energy Cyclotron Centre, 1/AF Bidhan Nagar, Kolkata 700064 (India); Chatterjee, A., E-mail: arnomitra@veccal.ernet.i [Variable Energy Cyclotron Centre, 1/AF Bidhan Nagar, Kolkata 700064 (India); Mukherjee, P.; Gayathri, N. [Variable Energy Cyclotron Centre, 1/AF Bidhan Nagar, Kolkata 700064 (India); Jayakumar, T.; Raj, Baldev [Indira Gandhi Centre for Atomic Research, Kalpakkam 603102 (India)

2010-11-15

Ultrasonic signals received by pulse echo technique from plane parallel Zircaloy 2 samples of fixed thickness and of three different microstructures, were subjected to signal analysis, as conventional parameters like velocity and attenuation could not reliably discriminate them. The signals, obtained from these samples, were first sampled and digitized. Modified Karhunen Loeve Transform was used to reduce their dimensionality. A multilayered feed forward Artificial Neural Network was trained using a few signals in their reduced domain from the three different microstructures. The rest of the signals from the three samples with different microstructures were classified satisfactorily using this network.

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.

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....

Characterization of differentially expressed genes using high-dimensional co-expression networks

DEFF Research Database (Denmark)

Coelho Goncalves de Abreu, Gabriel; Labouriau, Rodrigo S.

2010-01-01

We present a technique to characterize differentially expressed genes in terms of their position in a high-dimensional co-expression network. The set-up of Gaussian graphical models is used to construct representations of the co-expression network in such a way that redundancy and the propagation...... that allow to make effective inference in problems with high degree of complexity (e.g. several thousands of genes) and small number of observations (e.g. 10-100) as typically occurs in high throughput gene expression studies. Taking advantage of the internal structure of decomposable graphical models, we...... construct a compact representation of the co-expression network that allows to identify the regions with high concentration of differentially expressed genes. It is argued that differentially expressed genes located in highly interconnected regions of the co-expression network are less informative than...

Reduced-Order Modeling for Flutter/LCO Using Recurrent Artificial Neural Network

Science.gov (United States)

Yao, Weigang; Liou, Meng-Sing

2012-01-01

The present study demonstrates the efficacy of a recurrent artificial neural network to provide a high fidelity time-dependent nonlinear reduced-order model (ROM) for flutter/limit-cycle oscillation (LCO) modeling. An artificial neural network is a relatively straightforward nonlinear method for modeling an input-output relationship from a set of known data, for which we use the radial basis function (RBF) with its parameters determined through a training process. The resulting RBF neural network, however, is only static and is not yet adequate for an application to problems of dynamic nature. The recurrent neural network method [1] is applied to construct a reduced order model resulting from a series of high-fidelity time-dependent data of aero-elastic simulations. Once the RBF neural network ROM is constructed properly, an accurate approximate solution can be obtained at a fraction of the cost of a full-order computation. The method derived during the study has been validated for predicting nonlinear aerodynamic forces in transonic flow and is capable of accurate flutter/LCO simulations. The obtained results indicate that the present recurrent RBF neural network is accurate and efficient for nonlinear aero-elastic system analysis

Classifying Wheat Hyperspectral Pixels of Healthy Heads and Fusarium Head Blight Disease Using a Deep Neural Network in the Wild Field

Directory of Open Access Journals (Sweden)

Xiu Jin

2018-03-01

Full Text Available Classification of healthy and diseased wheat heads in a rapid and non-destructive manner for the early diagnosis of Fusarium head blight disease research is difficult. Our work applies a deep neural network classification algorithm to the pixels of hyperspectral image to accurately discern the disease area. The spectra of hyperspectral image pixels in a manually selected region of interest are preprocessed via mean removal to eliminate interference, due to the time interval and the environment. The generalization of the classification model is considered, and two improvements are made to the model framework. First, the pixel spectra data are reshaped into a two-dimensional data structure for the input layer of a Convolutional Neural Network (CNN. After training two types of CNNs, the assessment shows that a two-dimensional CNN model is more efficient than a one-dimensional CNN. Second, a hybrid neural network with a convolutional layer and bidirectional recurrent layer is reconstructed to improve the generalization of the model. When considering the characteristics of the dataset and models, the confusion matrices that are based on the testing dataset indicate that the classification model is effective for background and disease classification of hyperspectral image pixels. The results of the model show that the two-dimensional convolutional bidirectional gated recurrent unit neural network (2D-CNN-BidGRU has an F1 score and accuracy of 0.75 and 0.743, respectively, for the total testing dataset. A comparison of all the models shows that the hybrid neural network of 2D-CNN-BidGRU is the best at preventing over-fitting and optimize the generalization. Our results illustrate that the hybrid structure deep neural network is an excellent classification algorithm for healthy and Fusarium head blight diseased classification in the field of hyperspectral imagery.

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.

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

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.

Classifying the molecular functions of Rab GTPases in membrane trafficking using deep convolutional neural networks.

Science.gov (United States)

Le, Nguyen-Quoc-Khanh; Ho, Quang-Thai; Ou, Yu-Yen

2018-06-13

Deep learning has been increasingly used to solve a number of problems with state-of-the-art performance in a wide variety of fields. In biology, deep learning can be applied to reduce feature extraction time and achieve high levels of performance. In our present work, we apply deep learning via two-dimensional convolutional neural networks and position-specific scoring matrices to classify Rab protein molecules, which are main regulators in membrane trafficking for transferring proteins and other macromolecules throughout the cell. The functional loss of specific Rab molecular functions has been implicated in a variety of human diseases, e.g., choroideremia, intellectual disabilities, cancer. Therefore, creating a precise model for classifying Rabs is crucial in helping biologists understand the molecular functions of Rabs and design drug targets according to such specific human disease information. We constructed a robust deep neural network for classifying Rabs that achieved an accuracy of 99%, 99.5%, 96.3%, and 97.6% for each of four specific molecular functions. Our approach demonstrates superior performance to traditional artificial neural networks. Therefore, from our proposed study, we provide both an effective tool for classifying Rab proteins and a basis for further research that can improve the performance of biological modeling using deep neural networks. Copyright © 2018 Elsevier Inc. All rights reserved.

TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions

Science.gov (United States)

2017-01-01

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. Availability: weilab.math.msu.edu/TDL/ PMID:28749969

Probabilistic Wind Power Forecasting with Hybrid Artificial Neural Networks

DEFF Research Database (Denmark)

Wan, Can; Song, Yonghua; Xu, Zhao

2016-01-01

probabilities of prediction errors provide an alternative yet effective solution. This article proposes a hybrid artificial neural network approach to generate prediction intervals of wind power. An extreme learning machine is applied to conduct point prediction of wind power and estimate model uncertainties...... via a bootstrap technique. Subsequently, the maximum likelihood estimation method is employed to construct a distinct neural network to estimate the noise variance of forecasting results. The proposed approach has been tested on multi-step forecasting of high-resolution (10-min) wind power using...... actual wind power data from Denmark. The numerical results demonstrate that the proposed hybrid artificial neural network approach is effective and efficient for probabilistic forecasting of wind power and has high potential in practical applications....

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.

Sequential and parallel image restoration: neural network implementations.

Science.gov (United States)

Figueiredo, M T; Leitao, J N

1994-01-01

Sequential and parallel image restoration algorithms and their implementations on neural networks are proposed. For images degraded by linear blur and contaminated by additive white Gaussian noise, maximum a posteriori (MAP) estimation and regularization theory lead to the same high dimension convex optimization problem. The commonly adopted strategy (in using neural networks for image restoration) is to map the objective function of the optimization problem into the energy of a predefined network, taking advantage of its energy minimization properties. Departing from this approach, we propose neural implementations of iterative minimization algorithms which are first proved to converge. The developed schemes are based on modified Hopfield (1985) networks of graded elements, with both sequential and parallel updating schedules. An algorithm supported on a fully standard Hopfield network (binary elements and zero autoconnections) is also considered. Robustness with respect to finite numerical precision is studied, and examples with real images are presented.

Efficient Cancer Detection Using Multiple Neural Networks.

Science.gov (United States)

Shell, John; Gregory, William D

2017-01-01

The inspection of live excised tissue specimens to ascertain malignancy is a challenging task in dermatopathology and generally in histopathology. We introduce a portable desktop prototype device that provides highly accurate neural network classification of malignant and benign tissue. The handheld device collects 47 impedance data samples from 1 Hz to 32 MHz via tetrapolar blackened platinum electrodes. The data analysis was implemented with six different backpropagation neural networks (BNN). A data set consisting of 180 malignant and 180 benign breast tissue data files in an approved IRB study at the Aurora Medical Center, Milwaukee, WI, USA, were utilized as a neural network input. The BNN structure consisted of a multi-tiered consensus approach autonomously selecting four of six neural networks to determine a malignant or benign classification. The BNN analysis was then compared with the histology results with consistent sensitivity of 100% and a specificity of 100%. This implementation successfully relied solely on statistical variation between the benign and malignant impedance data and intricate neural network configuration. This device and BNN implementation provides a novel approach that could be a valuable tool to augment current medical practice assessment of the health of breast, squamous, and basal cell carcinoma and other excised tissue without requisite tissue specimen expertise. It has the potential to provide clinical management personnel with a fast non-invasive accurate assessment of biopsied or sectioned excised tissue in various clinical settings.

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...

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

Global exponential stability of neutral high-order stochastic Hopfield neural networks with Markovian jump parameters and mixed time delays.

Science.gov (United States)

Huang, Haiying; Du, Qiaosheng; Kang, Xibing

2013-11-01

In this paper, a class of neutral high-order stochastic Hopfield neural networks with Markovian jump parameters and mixed time delays is investigated. The jumping parameters are modeled as a continuous-time finite-state Markov chain. At first, the existence of equilibrium point for the addressed neural networks is studied. By utilizing the Lyapunov stability theory, stochastic analysis theory and linear matrix inequality (LMI) technique, new delay-dependent stability criteria are presented in terms of linear matrix inequalities to guarantee the neural networks to be globally exponentially stable in the mean square. Numerical simulations are carried out to illustrate the main results. © 2013 ISA. Published by ISA. All rights reserved.

A qualitative numerical study of high dimensional dynamical systems

Science.gov (United States)

Albers, David James

Since Poincare, the father of modern mathematical dynamical systems, much effort has been exerted to achieve a qualitative understanding of the physical world via a qualitative understanding of the functions we use to model the physical world. In this thesis, we construct a numerical framework suitable for a qualitative, statistical study of dynamical systems using the space of artificial neural networks. We analyze the dynamics along intervals in parameter space, separating the set of neural networks into roughly four regions: the fixed point to the first bifurcation; the route to chaos; the chaotic region; and a transition region between chaos and finite-state neural networks. The study is primarily with respect to high-dimensional dynamical systems. We make the following general conclusions as the dimension of the dynamical system is increased: the probability of the first bifurcation being of type Neimark-Sacker is greater than ninety-percent; the most probable route to chaos is via a cascade of bifurcations of high-period periodic orbits, quasi-periodic orbits, and 2-tori; there exists an interval of parameter space such that hyperbolicity is violated on a countable, Lebesgue measure 0, "increasingly dense" subset; chaos is much more likely to persist with respect to parameter perturbation in the chaotic region of parameter space as the dimension is increased; moreover, as the number of positive Lyapunov exponents is increased, the likelihood that any significant portion of these positive exponents can be perturbed away decreases with increasing dimension. The maximum Kaplan-Yorke dimension and the maximum number of positive Lyapunov exponents increases linearly with dimension. The probability of a dynamical system being chaotic increases exponentially with dimension. The results with respect to the first bifurcation and the route to chaos comment on previous results of Newhouse, Ruelle, Takens, Broer, Chenciner, and Iooss. Moreover, results regarding the high-dimensional

On the synchronization of neural networks containing time-varying delays and sector nonlinearity

International Nuclear Information System (INIS)

Yan, J.-J.; Lin, J.-S.; Hung, M.-L.; Liao, T.-L.

2007-01-01

We present a systematic design procedure for synchronization of neural networks subject to time-varying delays and sector nonlinearity in the control input. Based on the drive-response concept and the Lyapunov stability theorem, a memoryless decentralized control law is proposed which guarantees exponential synchronization even when input nonlinearity is present. The supplementary requirement that the time-derivative of time-varying delays must be smaller than one is released for the proposed control scheme. A four-dimensional Hopfield neural network with time-varying delays is presented as the illustrative example to demonstrate the effectiveness of the proposed synchronization scheme

Cotton genotypes selection through artificial neural networks.

Science.gov (United States)

Júnior, E G Silva; Cardoso, D B O; Reis, M C; Nascimento, A F O; Bortolin, D I; Martins, M R; Sousa, L B

2017-09-27

Breeding programs currently use statistical analysis to assist in the identification of superior genotypes at various stages of a cultivar's development. Differently from these analyses, the computational intelligence approach has been little explored in genetic improvement of cotton. Thus, this study was carried out with the objective of presenting the use of artificial neural networks as auxiliary tools in the improvement of the cotton to improve fiber quality. To demonstrate the applicability of this approach, this research was carried out using the evaluation data of 40 genotypes. In order to classify the genotypes for fiber quality, the artificial neural networks were trained with replicate data of 20 genotypes of cotton evaluated in the harvests of 2013/14 and 2014/15, regarding fiber length, uniformity of length, fiber strength, micronaire index, elongation, short fiber index, maturity index, reflectance degree, and fiber quality index. This quality index was estimated by means of a weighted average on the determined score (1 to 5) of each characteristic of the HVI evaluated, according to its industry standards. The artificial neural networks presented a high capacity of correct classification of the 20 selected genotypes based on the fiber quality index, so that when using fiber length associated with the short fiber index, fiber maturation, and micronaire index, the artificial neural networks presented better results than using only fiber length and previous associations. It was also observed that to submit data of means of new genotypes to the neural networks trained with data of repetition, provides better results of classification of the genotypes. When observing the results obtained in the present study, it was verified that the artificial neural networks present great potential to be used in the different stages of a genetic improvement program of the cotton, aiming at the improvement of the fiber quality of the future cultivars.

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

Top tagging with deep neural networks [Vidyo

CERN Multimedia

CERN. Geneva

2017-01-01

Recent literature on deep neural networks for top tagging has focussed on image based techniques or multivariate approaches using high level jet substructure variables. Here, we take a sequential approach to this task by using anordered sequence of energy deposits as training inputs. Unlike previous approaches, this strategy does not result in a loss of information during pixelization or the calculation of high level features. We also propose new preprocessing methods that do not alter key physical quantities such as jet mass. We compare the performance of this approach to standard tagging techniques and present results evaluating the robustness of the neural network to pileup.

Land Cover Change Detection using Neural Network and Grid Cells Techniques

Science.gov (United States)

Bagan, H.; Li, Z.; Tangud, T.; Yamagata, Y.

2017-12-01

In recent years, many advanced neural network methods have been applied in land cover classification, each of which has both strengths and limitations. In which, the self-organizing map (SOM) neural network method have been used to solve remote sensing data classification problems and have shown potential for efficient classification of remote sensing data. In SOM, both the distribution and the topology of features of the input layer are identified by using an unsupervised, competitive, neighborhood learning method. The high-dimensional data are then projected onto a low-dimensional map (competitive layer), usually as a two-dimensional map. The neurons (nodes) in the competitive layer are arranged by topological order in the input space. Spatio-temporal analyses of land cover change based on grid cells have demonstrated that gridded data are useful for obtaining spatial and temporal information about areas that are smaller than municipal scale and are uniform in size. Analysis based on grid cells has many advantages: grid cells all have the same size allowing for easy comparison; grids integrate easily with other scientific data; grids are stable over time and thus facilitate the modelling and analysis of very large multivariate spatial data sets. This study chose time-series MODIS and Landsat images as data sources, applied SOM neural network method to identify the land utilization in Inner Mongolia Autonomous Region of China. Then the results were integrated into grid cell to get the dynamic change maps. Land cover change using MODIS data in Inner Mongolia showed that urban area increased more than fivefold in recent 15 years, along with the growth of mining area. In terms of geographical distribution, the most obvious place of urban expansion is Ordos in southwest Inner Mongolia. The results using Landsat images from 1986 to 2014 in northeastern part of the Inner Mongolia show degradation in grassland from 1986 to 2014. Grid-cell-based spatial correlation

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

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....

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

Communication: Fitting potential energy surfaces with fundamental invariant neural network

Energy Technology Data Exchange (ETDEWEB)

Shao, Kejie; Chen, Jun; Zhao, Zhiqiang; Zhang, Dong H., E-mail: zhangdh@dicp.ac.cn [State Key Laboratory of Molecular Reaction Dynamics and Center for Theoretical Computational Chemistry, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian 116023, People’s Republic of China and University of Chinese Academy of Sciences, Beijing 100049, People’s Republic of China. (China)

2016-08-21

A more flexible neural network (NN) method using the fundamental invariants (FIs) as the input vector is proposed in the construction of potential energy surfaces for molecular systems involving identical atoms. Mathematically, FIs finitely generate the permutation invariant polynomial (PIP) ring. In combination with NN, fundamental invariant neural network (FI-NN) can approximate any function to arbitrary accuracy. Because FI-NN minimizes the size of input permutation invariant polynomials, it can efficiently reduce the evaluation time of potential energy, in particular for polyatomic systems. In this work, we provide the FIs for all possible molecular systems up to five atoms. Potential energy surfaces for OH{sub 3} and CH{sub 4} were constructed with FI-NN, with the accuracy confirmed by full-dimensional quantum dynamic scattering and bound state calculations.

Three-dimensional neural differentiation of embryonic stem cells with ACM induction in microfibrous matrices in bioreactors.

Science.gov (United States)

Liu, Ning; Ouyang, Anli; Li, Yan; Yang, Shang-Tian

2013-01-01

The clinical use of pluripotent stem cell (PSC)-derived neural cells requires an efficient differentiation process for mass production in a bioreactor. Toward this goal, neural differentiation of murine embryonic stem cells (ESCs) in three-dimensional (3D) polyethylene terephthalate microfibrous matrices was investigated in this study. To streamline the process and provide a platform for process integration, the neural differentiation of ESCs was induced with astrocyte-conditioned medium without the formation of embryoid bodies, starting from undifferentiated ESC aggregates expanded in a suspension bioreactor. The 3D neural differentiation was able to generate a complex neural network in the matrices. When compared to 2D differentiation, 3D differentiation in microfibrous matrices resulted in a higher percentage of nestin-positive cells (68% vs. 54%) and upregulated gene expressions of nestin, Nurr1, and tyrosine hydroxylase. High purity of neural differentiation in 3D microfibrous matrix was also demonstrated in a spinner bioreactor with 74% nestin + cells. This study demonstrated the feasibility of a scalable process based on 3D differentiation in microfibrous matrices for the production of ESC-derived neural cells. © 2013 American Institute of Chemical Engineers.

Numeral eddy current sensor modelling based on genetic neural network

International Nuclear Information System (INIS)

Yu Along

2008-01-01

This paper presents a method used to the numeral eddy current sensor modelling based on the genetic neural network to settle its nonlinear problem. The principle and algorithms of genetic neural network are introduced. In this method, the nonlinear model parameters of the numeral eddy current sensor are optimized by genetic neural network (GNN) according to measurement data. So the method remains both the global searching ability of genetic algorithm and the good local searching ability of neural network. The nonlinear model has the advantages of strong robustness, on-line modelling and high precision. The maximum nonlinearity error can be reduced to 0.037% by using GNN. However, the maximum nonlinearity error is 0.075% using the least square method

Neural networks for predicting breeding values and genetic gains

Directory of Open Access Journals (Sweden)

Gabi Nunes Silva

2014-12-01

Full Text Available Analysis using Artificial Neural Networks has been described as an approach in the decision-making process that, although incipient, has been reported as presenting high potential for use in animal and plant breeding. In this study, we introduce the procedure of using the expanded data set for training the network. Wealso proposed using statistical parameters to estimate the breeding value of genotypes in simulated scenarios, in addition to the mean phenotypic value in a feed-forward back propagation multilayer perceptron network. After evaluating artificial neural network configurations, our results showed its superiority to estimates based on linear models, as well as its applicability in the genetic value prediction process. The results further indicated the good generalization performance of the neural network model in several additional validation experiments.

Topological probability and connection strength induced activity in complex neural networks

International Nuclear Information System (INIS)

Du-Qu, Wei; Bo, Zhang; Dong-Yuan, Qiu; Xiao-Shu, Luo

2010-01-01

Recent experimental evidence suggests that some brain activities can be assigned to small-world networks. In this work, we investigate how the topological probability p and connection strength C affect the activities of discrete neural networks with small-world (SW) connections. Network elements are described by two-dimensional map neurons (2DMNs) with the values of parameters at which no activity occurs. It is found that when the value of p is smaller or larger, there are no active neurons in the network, no matter what the value of connection strength is; for a given appropriate connection strength, there is an intermediate range of topological probability where the activity of 2DMN network is induced and enhanced. On the other hand, for a given intermediate topological probability level, there exists an optimal value of connection strength such that the frequency of activity reaches its maximum. The possible mechanism behind the action of topological probability and connection strength is addressed based on the bifurcation method. Furthermore, the effects of noise and transmission delay on the activity of neural network are also studied. (general)

The Ripple Pond: Enabling Spiking Networks to See

Directory of Open Access Journals (Sweden)

Saeed eAfshar

2013-11-01

Full Text Available We present the biologically inspired Ripple Pond Network (RPN, a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for information processing, using dimensional collapse of imagery information into amenable temporal patterns and the use of asynchronous frames for information binding.

The ripple pond: enabling spiking networks to see.

Science.gov (United States)

Afshar, Saeed; Cohen, Gregory K; Wang, Runchun M; Van Schaik, André; Tapson, Jonathan; Lehmann, Torsten; Hamilton, Tara J

2013-01-01

We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns (TP) suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilizing the spatial properties of physically embedded neural networks and propagating waves of activity therein for information processing, using dimensional collapse of imagery information into amenable TP and the use of asynchronous frames for information binding.

ACO-Initialized Wavelet Neural Network for Vibration Fault Diagnosis of Hydroturbine Generating Unit

OpenAIRE

Xiao, Zhihuai; He, Xinying; Fu, Xiangqian; Malik, O. P.

2015-01-01

Considering the drawbacks of traditional wavelet neural network, such as low convergence speed and high sensitivity to initial parameters, an ant colony optimization- (ACO-) initialized wavelet neural network is proposed in this paper for vibration fault diagnosis of a hydroturbine generating unit. In this method, parameters of the wavelet neural network are initialized by the ACO algorithm, and then the wavelet neural network is trained by the gradient descent algorithm. Amplitudes of the fr...

A neural network approach to the study of internal energy flow in molecular systems

International Nuclear Information System (INIS)

Sumpter, B.G.; Getino, C.; Noid, D.W.

1992-01-01

Neural networks are used to develop a new technique for efficient analysis of data obtained from molecular-dynamics calculations and is applied to the study of mode energy flow in molecular systems. The methodology is based on teaching an appropriate neural network the relationship between phase-space points along a classical trajectory and mode energies for stretch, bend, and torsion vibrations. Results are discussed for reactive and nonreactive classical trajectories of hydrogen peroxide (H 2 O 2 ) on a semiempirical potential-energy surface. The neural-network approach is shown to produce reasonably accurate values for the mode energies, with average errors between 1% and 12%, and is applicable to any region within the 24-dimensional phase space of H 2 O 2 . In addition, the generic knowledge learned by the neural network allows calculations to be made for other molecular systems. Results are discussed for a series of tetratomic molecules: H 2 X 2 , X=C, N, O, Si, S, or Se, and preliminary results are given for energy flow predictions in macromolecules

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

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

Application of artificial neural networks in fault diagnosis for 10MW high-temperature gas-cooled reactor

International Nuclear Information System (INIS)

Li Hui; Wang Ruipian; Hu Shouyin

2003-01-01

This paper makes researches on 10 MW High-Temperature Gas-Cooled Reactor fault diagnosis system using Artificial Neural Network, and uses the tendency value and real value of the data under the accidents to train and test two BP networks respectively. The final diagnostic result is the combination of the results of the two networks. The compound system can enhance the accuracy and adaptability of the diagnosis compared to the single network system

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.

Classification of Company Performance using Weighted Probabilistic Neural Network

Science.gov (United States)

Yasin, Hasbi; Waridi Basyiruddin Arifin, Adi; Warsito, Budi

2018-05-01

Classification of company performance can be judged by looking at its financial status, whether good or bad state. Classification of company performance can be achieved by some approach, either parametric or non-parametric. Neural Network is one of non-parametric methods. One of Artificial Neural Network (ANN) models is Probabilistic Neural Network (PNN). PNN consists of four layers, i.e. input layer, pattern layer, addition layer, and output layer. The distance function used is the euclidean distance and each class share the same values as their weights. In this study used PNN that has been modified on the weighting process between the pattern layer and the addition layer by involving the calculation of the mahalanobis distance. This model is called the Weighted Probabilistic Neural Network (WPNN). The results show that the company's performance modeling with the WPNN model has a very high accuracy that reaches 100%.

A neural-network potential through charge equilibration for WS2: From clusters to sheets

Science.gov (United States)

Hafizi, Roohollah; Ghasemi, S. Alireza; Hashemifar, S. Javad; Akbarzadeh, Hadi

2017-12-01

In the present work, we use a machine learning method to construct a high-dimensional potential for tungsten disulfide using a charge equilibration neural-network technique. A training set of stoichiometric WS2 clusters is prepared in the framework of density functional theory. After training the neural-network potential, the reliability and transferability of the potential are verified by performing a crystal structure search on bulk phases of WS2 and by plotting energy-area curves of two different monolayers. Then, we use the potential to investigate various triangular nano-clusters and nanotubes of WS2. In the case of nano-structures, we argue that 2H atomic configurations with sulfur rich edges are thermodynamically more stable than the other investigated configurations. We also studied a number of WS2 nanotubes which revealed that 1T tubes with armchair chirality exhibit lower bending stiffness.

A Neural Network Approach to Muon Triggering in ATLAS

CERN Document Server

Livneh, Ran; CERN. Geneva

2007-01-01

The extremely high rate of events that will be produced in the future Large Hadron Collider requires the triggering mechanism to make precise decisions in a few nano-seconds. This poses a complicated inverse problem, arising from the inhomogeneous nature of the magnetic fields in ATLAS. This thesis presents a study of an application of Artificial Neural Networks to the muon triggering problem in the ATLAS end-cap. A comparison with realistic results from the ATLAS first level trigger simulation was in favour of the neural network, but this is mainly due to superior resolution available off-line. Other options for applying a neural network to this problem are discussed.

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.

Reinforcement learning on slow features of high-dimensional input streams.

Directory of Open Access Journals (Sweden)

Robert Legenstein

Full Text Available Humans and animals are able to learn complex behaviors based on a massive stream of sensory information from different modalities. Early animal studies have identified learning mechanisms that are based on reward and punishment such that animals tend to avoid actions that lead to punishment whereas rewarded actions are reinforced. However, most algorithms for reward-based learning are only applicable if the dimensionality of the state-space is sufficiently small or its structure is sufficiently simple. Therefore, the question arises how the problem of learning on high-dimensional data is solved in the brain. In this article, we propose a biologically plausible generic two-stage learning system that can directly be applied to raw high-dimensional input streams. The system is composed of a hierarchical slow feature analysis (SFA network for preprocessing and a simple neural network on top that is trained based on rewards. We demonstrate by computer simulations that this generic architecture is able to learn quite demanding reinforcement learning tasks on high-dimensional visual input streams in a time that is comparable to the time needed when an explicit highly informative low-dimensional state-space representation is given instead of the high-dimensional visual input. The learning speed of the proposed architecture in a task similar to the Morris water maze task is comparable to that found in experimental studies with rats. This study thus supports the hypothesis that slowness learning is one important unsupervised learning principle utilized in the brain to form efficient state representations for behavioral learning.

Aspects of artificial neural networks - with applications in high energy physics

International Nuclear Information System (INIS)

Roegnvaldsson, T.S.

1994-02-01

Different aspects of artificial neural networks are studied and discussed. They are demonstrated to be powerful general purpose algorithms, applicable to many different problem areas like pattern recognition, function fitting and prediction. Multi-layer perceptron (MPL) models are shown to out perform previous standard approaches on both off-line and on-line analysis tasks in high energy physics, like quark flavour tagging and mass reconstruction, as well as being powerful tools for prediction tasks. It is also demonstrated how a self-organizing network can be employed to extract information from data, for instance to track down origins of unexpected model discrepancies. Furthermore, it is proved that the MPL is more efficient than the learning vector quantization technique on classification problems, by producing smoother discrimination surfaces, and that an MPL network should be trained with a noisy updating schedule if the Hessian is ill-conditioned - A result that is especially important for MPL network with more than just one hidden layer. 81 refs, 6 figs

Classification Technique for Ultrasonic Weld Inspection Signals using a Neural Network based on 2-dimensional fourier Transform and Principle Component Analysis

International Nuclear Information System (INIS)

Kim, Jae Joon

2004-01-01

Neural network-based signal classification systems are increasingly used in the analysis of large volumes of data obtained in NDE applications. Ultrasonic inspection methods on the other hand are commonly used in the nondestructive evaluation of welds to detect flaws. An important characteristic of ultrasonic inspection is the ability to identify the type of discontinuity that gives rise to a peculiar signal. Standard techniques rely on differences in individual A-scans to classify the signals. This paper proposes an ultrasonic signal classification technique based on the information tying in the neighboring signals. The approach is based on a 2-dimensional Fourier transform and the principal component analysis to generate a reduced dimensional feature vector for classification. Results of applying the technique to data obtained from the inspection of actual steel welds are presented

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

An Improved Neural Network Training Algorithm for Wi-Fi Fingerprinting Positioning

Directory of Open Access Journals (Sweden)

Esmond Mok

2013-09-01

Full Text Available Ubiquitous positioning provides continuous positional information in both indoor and outdoor environments for a wide spectrum of location based service (LBS applications. With the rapid development of the low-cost and high speed data communication, Wi-Fi networks in many metropolitan cities, strength of signals propagated from the Wi-Fi access points (APs namely received signal strength (RSS have been cleverly adopted for indoor positioning. In this paper, a Wi-Fi positioning algorithm based on neural network modeling of Wi-Fi signal patterns is proposed. This algorithm is based on the correlation between the initial parameter setting for neural network training and output of the mean square error to obtain better modeling of the nonlinear highly complex Wi-Fi signal power propagation surface. The test results show that this neural network based data processing algorithm can significantly improve the neural network training surface to achieve the highest possible accuracy of the Wi-Fi fingerprinting positioning method.

Analysis of the experimental positron lifetime spectra by neural networks

International Nuclear Information System (INIS)

Avdic, S.; Chakarova, R.; Pazsit, I.

2003-01-01

This paper deals with the analysis of experimental positron lifetime spectra in polymer materials by using various algorithms of neural networks. A method based on the use of artificial neural networks for unfolding the mean lifetime and intensity of the spectral components of simulated positron lifetime spectra was previously suggested and tested on simulated data [Pazsit et al., Applied Surface Science, 149 (1998), 97]. In this work, the applicability of the method to the analysis of experimental positron spectra has been verified in the case of spectra from polymer materials with three components. It has been demonstrated that the backpropagation neural network can determine the spectral parameters with a high accuracy and perform the decomposition of lifetimes which differ by 10% or more. The backpropagation network has not been suitable for the identification of both the parameters and the number of spectral components. Therefore, a separate artificial neural network module has been designed to solve the classification problem. Module types based on self-organizing map and learning vector quantization algorithms have been tested. The learning vector quantization algorithm was found to have better performance and reliability. A complete artificial neural network analysis tool of positron lifetime spectra has been constructed to include a spectra classification module and parameter evaluation modules for spectra with a different number of components. In this way, both flexibility and high resolution can be achieved. (author)

A neural network device for on-line particle identification in cosmic ray experiments

International Nuclear Information System (INIS)

Scrimaglio, R.; Finetti, N.; D'Altorio, L.; Rantucci, E.; Raso, M.; Segreto, E.; Tassoni, A.; Cardarilli, G.C.

2004-01-01

On-line particle identification is one of the main goals of many experiments in space both for rare event studies and for optimizing measurements along the orbital trajectory. Neural networks can be a useful tool for signal processing and real time data analysis in such experiments. In this document we report on the performances of a programmable neural device which was developed in VLSI analog/digital technology. Neurons and synapses were accomplished by making use of Operational Transconductance Amplifier (OTA) structures. In this paper we report on the results of measurements performed in order to verify the agreement of the characteristic curves of each elementary cell with simulations and on the device performances obtained by implementing simple neural structures on the VLSI chip. A feed-forward neural network (Multi-Layer Perceptron, MLP) was implemented on the VLSI chip and trained to identify particles by processing the signals of two-dimensional position-sensitive Si detectors. The radiation monitoring device consisted of three double-sided silicon strip detectors. From the analysis of a set of simulated data it was found that the MLP implemented on the neural device gave results comparable with those obtained with the standard method of analysis confirming that the implemented neural network could be employed for real time particle identification

Inhibition delay increases neural network capacity through Stirling transform

Science.gov (United States)

Nogaret, Alain; King, Alastair

2018-03-01

Inhibitory neural networks are found to encode high volumes of information through delayed inhibition. We show that inhibition delay increases storage capacity through a Stirling transform of the minimum capacity which stabilizes locally coherent oscillations. We obtain both the exact and asymptotic formulas for the total number of dynamic attractors. Our results predict a (ln2) -N-fold increase in capacity for an N -neuron network and demonstrate high-density associative memories which host a maximum number of oscillations in analog neural devices.

High-precision position estimation in PET using artificial neural networks

Energy Technology Data Exchange (ETDEWEB)

Mateo, F. [Digital Systems Design Group (DSD), Instituto de las Tecnologias de la Informacion y de las Comunicaciones Avanzadas (ITACA), Universidad Politecnica de Valencia, Camino de Vera s/n, 46022 Valencia (Spain)], E-mail: fermaji@upvnet.upv.es; Aliaga, R.J.; Ferrando, N.; Martinez, J.D.; Herrero, V.; Lerche, Ch.W.; Colom, R.J.; Monzo, J.M.; Sebastia, A.; Gadea, R. [Digital Systems Design Group (DSD), Instituto de las Tecnologias de la Informacion y de las Comunicaciones Avanzadas (ITACA), Universidad Politecnica de Valencia, Camino de Vera s/n, 46022 Valencia (Spain)

2009-06-01

Traditionally, the most popular technique to predict the impact position of gamma photons on a PET detector has been Anger's logic. However, it introduces nonlinearities that compress the light distribution, reducing the useful field of view and the spatial resolution, especially at the edges of the scintillator crystal. In this work, we make use of neural networks to address a bias-corrected position estimation from real stimulus obtained from a 2D PET system setup. The preprocessing and data acquisition were performed by separate custom boards, especially designed for this application. The results show that neural networks yield a more uniform field of view while improving the systematic error and the spatial resolution. Therefore, they stand as a better performing and readily available alternative to classic positioning methods.

High-precision position estimation in PET using artificial neural networks

International Nuclear Information System (INIS)

Mateo, F.; Aliaga, R.J.; Ferrando, N.; Martinez, J.D.; Herrero, V.; Lerche, Ch.W.; Colom, R.J.; Monzo, J.M.; Sebastia, A.; Gadea, R.

2009-01-01

Traditionally, the most popular technique to predict the impact position of gamma photons on a PET detector has been Anger's logic. However, it introduces nonlinearities that compress the light distribution, reducing the useful field of view and the spatial resolution, especially at the edges of the scintillator crystal. In this work, we make use of neural networks to address a bias-corrected position estimation from real stimulus obtained from a 2D PET system setup. The preprocessing and data acquisition were performed by separate custom boards, especially designed for this application. The results show that neural networks yield a more uniform field of view while improving the systematic error and the spatial resolution. Therefore, they stand as a better performing and readily available alternative to classic positioning methods.

Analysis of JET charge exchange spectra using neural networks

International Nuclear Information System (INIS)

Svensson, J.; Hellermann, M. von; Koenig, R.W.T.

1999-01-01

Active charge exchange spectra representing the local interaction of injected neutral beams and fully stripped impurity ions are hard to analyse due to strong blending with passive emission from the plasma edge. As a result, the deduced plasma parameters (e.g. ion temperature, rotation velocity, impurity density) cannot always be determined unambiguously. Also, the speed of the analysis is limited by the time consuming nonlinear least-squares minimization procedure. In practice, semi-manual analysis is necessary and fast, automatic analysis, based on currently used techniques, does not seem feasible. In this paper the development of a robust and accurate analysis procedure based on multi-layer perceptron (MLP) neural networks is described. This procedure is fully automatic and fast, thus enabling a real-time analysis of charge exchange spectra. Accuracy has been increased in several ways as compared to earlier straightforward neural network implementations and is comparable to a standard least-squares based analysis. Robustness is achieved by using a combination of different confidence measures. A novel technique for the creation of training data, suitable for high-dimensional inverse problems has been developed and used extensively. A new method for fast calculation of error bars directly from the hidden neurons in a MLP network is also described, and used as part of the confidence calculations. For demonstration purposes, a real-time ion temperature profile diagnostic based on this work has been implemented. (author)

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.

FUZZY NEURAL NETWORK FOR OBJECT IDENTIFICATION ON INTEGRATED CIRCUIT LAYOUTS

Directory of Open Access Journals (Sweden)

A. A. Doudkin

2015-01-01

Full Text Available Fuzzy neural network model based on neocognitron is proposed to identify layout objects on images of topological layers of integrated circuits. Testing of the model on images of real chip layouts was showed a highеr degree of identification of the proposed neural network in comparison to base neocognitron.

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.

Application of artificial neural network to search for gravitational-wave signals associated with short gamma-ray bursts

International Nuclear Information System (INIS)

Kim, Kyungmin; Lee, Hyun Kyu; Harry, Ian W; Hodge, Kari A; Kim, Young-Min; Lee, Chang-Hwan; Oh, John J; Oh, Sang Hoon; Son, Edwin J

2015-01-01

We apply a machine learning algorithm, the artificial neural network, to the search for gravitational-wave signals associated with short gamma-ray bursts (GRBs). The multi-dimensional samples consisting of data corresponding to the statistical and physical quantities from the coherent search pipeline are fed into the artificial neural network to distinguish simulated gravitational-wave signals from background noise artifacts. Our result shows that the data classification efficiency at a fixed false alarm probability (FAP) is improved by the artificial neural network in comparison to the conventional detection statistic. Specifically, the distance at 50% detection probability at a fixed false positive rate is increased about 8%–14% for the considered waveform models. We also evaluate a few seconds of the gravitational-wave data segment using the trained networks and obtain the FAP. We suggest that the artificial neural network can be a complementary method to the conventional detection statistic for identifying gravitational-wave signals related to the short GRBs. (paper)

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«.

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.

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.

Automatic Seismic-Event Classification with Convolutional Neural Networks.

Science.gov (United States)

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

2017-12-01

Active volcanoes exhibit a wide range of seismic signals, providing vast amounts of unlabelled volcano-seismic data that can be analyzed through the lens of artificial intelligence. However, obtaining high-quality labelled data is time-consuming and expensive. Deep neural networks can process data in their raw form, compute high-level features and provide a better representation of the input data distribution. These systems can be deployed to classify seismic data at scale, enhance current early-warning systems and build extensive seismic catalogs. In this research, we aim to classify spectrograms from seven different seismic events registered at "Volcán de Fuego" (Colima, Mexico), during four eruptive periods. Our approach is based on convolutional neural networks (CNNs), a sub-type of deep neural networks that can exploit grid structure from the data. Volcano-seismic signals can be mapped into a grid-like structure using the spectrogram: a representation of the temporal evolution in terms of time and frequency. Spectrograms were computed from the data using Hamming windows with 4 seconds length, 2.5 seconds overlapping and 128 points FFT resolution. Results are compared to deep neural networks, random forest and SVMs. Experiments show that CNNs can exploit temporal and frequency information, attaining a classification accuracy of 93%, similar to deep networks 91% but outperforming SVM and random forest. These results empirically show that CNNs are powerful models to classify a wide range of volcano-seismic signals, and achieve good generalization. Furthermore, volcano-seismic spectrograms contains useful discriminative information for the CNN, as higher layers of the network combine high-level features computed for each frequency band, helping to detect simultaneous events in time. Being at the intersection of deep learning and geophysics, this research enables future studies of how CNNs can be used in volcano monitoring to accurately determine the detection and

Robust stabilization of burn conditions in subignited fusion reactors using artificial neural networks

International Nuclear Information System (INIS)

Vitela, E. Javier; Martinell, J. Julio

2000-01-01

In this work it is shown that robust burn control in long pulse operations of thermonuclear reactors can be successfully achieved with artificial neural networks. The results reported here correspond to a volume averaged zero-dimensional nonlinear model of a subignited fusion device using the design parameters of the tokamak EDA-ITER group. A Radial Basis Neural Network (RBNN) was trained to provide feedback stabilization at a fixed operating point independently of any particular scaling law that the reactor confinement time may follow. A numerically simulated transient is used to illustrate the stabilization capabilities of the resulting RBNN when the reactor follows an ELMy scaling law corrupted with Gaussian noise. (author)

Application of a Shallow Neural Network to Short-Term Stock Trading

OpenAIRE

Madahar, Abhinav; Ma, Yuze; Patel, Kunal

2017-01-01

Machine learning is increasingly prevalent in stock market trading. Though neural networks have seen success in computer vision and natural language processing, they have not been as useful in stock market trading. To demonstrate the applicability of a neural network in stock trading, we made a single-layer neural network that recommends buying or selling shares of a stock by comparing the highest high of 10 consecutive days with that of the next 10 days, a process repeated for the stock's ye...

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.

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.

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

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.

Permutation invariant polynomial neural network approach to fitting potential energy surfaces. II. Four-atom systems

Energy Technology Data Exchange (ETDEWEB)

Li, Jun; Jiang, Bin; Guo, Hua, E-mail: hguo@unm.edu [Department of Chemistry and Chemical Biology, University of New Mexico, Albuquerque, New Mexico 87131 (United States)

2013-11-28

A rigorous, general, and simple method to fit global and permutation invariant potential energy surfaces (PESs) using neural networks (NNs) is discussed. This so-called permutation invariant polynomial neural network (PIP-NN) method imposes permutation symmetry by using in its input a set of symmetry functions based on PIPs. For systems with more than three atoms, it is shown that the number of symmetry functions in the input vector needs to be larger than the number of internal coordinates in order to include both the primary and secondary invariant polynomials. This PIP-NN method is successfully demonstrated in three atom-triatomic reactive systems, resulting in full-dimensional global PESs with average errors on the order of meV. These PESs are used in full-dimensional quantum dynamical calculations.

Feed forward neural networks modeling for K-P interactions

International Nuclear Information System (INIS)

El-Bakry, M.Y.

2003-01-01

Artificial intelligence techniques involving neural networks became vital modeling tools where model dynamics are difficult to track with conventional techniques. The paper make use of the feed forward neural networks (FFNN) to model the charged multiplicity distribution of K-P interactions at high energies. The FFNN was trained using experimental data for the multiplicity distributions at different lab momenta. Results of the FFNN model were compared to that generated using the parton two fireball model and the experimental data. The proposed FFNN model results showed good fitting to the experimental data. The neural network model performance was also tested at non-trained space and was found to be in good agreement with the experimental data

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

Science.gov (United States)

Soltic, Snjezana; Kasabov, Nikola

2010-12-01

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

ACO-Initialized Wavelet Neural Network for Vibration Fault Diagnosis of Hydroturbine Generating Unit

Directory of Open Access Journals (Sweden)

Zhihuai Xiao

2015-01-01

Full Text Available Considering the drawbacks of traditional wavelet neural network, such as low convergence speed and high sensitivity to initial parameters, an ant colony optimization- (ACO- initialized wavelet neural network is proposed in this paper for vibration fault diagnosis of a hydroturbine generating unit. In this method, parameters of the wavelet neural network are initialized by the ACO algorithm, and then the wavelet neural network is trained by the gradient descent algorithm. Amplitudes of the frequency components of the hydroturbine generating unit vibration signals are used as feature vectors for wavelet neural network training to realize mapping relationship from vibration features to fault types. A real vibration fault diagnosis case result of a hydroturbine generating unit shows that the proposed method has faster convergence speed and stronger generalization ability than the traditional wavelet neural network and ACO wavelet neural network. Thus it can provide an effective solution for online vibration fault diagnosis of a hydroturbine generating unit.

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)

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)

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.

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.

A reverse engineering algorithm for neural networks, applied to the subthalamopallidal network of basal ganglia.

Science.gov (United States)

Floares, Alexandru George

2008-01-01

Modeling neural networks with ordinary differential equations systems is a sensible approach, but also very difficult. This paper describes a new algorithm based on linear genetic programming which can be used to reverse engineer neural networks. The RODES algorithm automatically discovers the structure of the network, including neural connections, their signs and strengths, estimates its parameters, and can even be used to identify the biophysical mechanisms involved. The algorithm is tested on simulated time series data, generated using a realistic model of the subthalamopallidal network of basal ganglia. The resulting ODE system is highly accurate, and results are obtained in a matter of minutes. This is because the problem of reverse engineering a system of coupled differential equations is reduced to one of reverse engineering individual algebraic equations. The algorithm allows the incorporation of common domain knowledge to restrict the solution space. To our knowledge, this is the first time a realistic reverse engineering algorithm based on linear genetic programming has been applied to neural networks.

A multi-scale convolutional neural network for phenotyping high-content cellular images.

Science.gov (United States)

Godinez, William J; Hossain, Imtiaz; Lazic, Stanley E; Davies, John W; Zhang, Xian

2017-07-01

Identifying phenotypes based on high-content cellular images is challenging. Conventional image analysis pipelines for phenotype identification comprise multiple independent steps, with each step requiring method customization and adjustment of multiple parameters. Here, we present an approach based on a multi-scale convolutional neural network (M-CNN) that classifies, in a single cohesive step, cellular images into phenotypes by using directly and solely the images' pixel intensity values. The only parameters in the approach are the weights of the neural network, which are automatically optimized based on training images. The approach requires no a priori knowledge or manual customization, and is applicable to single- or multi-channel images displaying single or multiple cells. We evaluated the classification performance of the approach on eight diverse benchmark datasets. The approach yielded overall a higher classification accuracy compared with state-of-the-art results, including those of other deep CNN architectures. In addition to using the network to simply obtain a yes-or-no prediction for a given phenotype, we use the probability outputs calculated by the network to quantitatively describe the phenotypes. This study shows that these probability values correlate with chemical treatment concentrations. This finding validates further our approach and enables chemical treatment potency estimation via CNNs. The network specifications and solver definitions are provided in Supplementary Software 1. william_jose.godinez_navarro@novartis.com or xian-1.zhang@novartis.com. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Application of neural networks to prediction of phase transport characteristics in high-pressure two-phase turbulent bubbly flows

International Nuclear Information System (INIS)

Yang, A.-S.; Kuo, T.-C.; Ling, P.-H.

2003-01-01

The phase transport phenomenon of the high-pressure two-phase turbulent bubbly flow involves complicated interfacial interactions of the mass, momentum, and energy transfer processes between phases, revealing that an enormous effort is required in characterizing the liquid-gas flow behavior. Nonetheless, the instantaneous information of bubbly flow properties is often desired for many industrial applications. This investigation aims to demonstrate the successful use of neural networks in the real-time determination of two-phase flow properties at elevated pressures. Three back-propagation neural networks, trained with the simulation results of a comprehensive theoretical model, are established to predict the transport characteristics (specifically the distributions of void-fraction and axial liquid-gas velocities) of upward turbulent bubbly pipe flows at pressures covering 3.5-7.0 MPa. Comparisons of the predictions with the test target vectors indicate that the averaged root-mean-squared (RMS) error for each one of three back-propagation neural networks is within 4.59%. In addition, this study appraises the effects of different network parameters, including the number of hidden nodes, the type of transfer function, the number of training pairs, the learning rate-increasing ratio, the learning rate-decreasing ratio, and the momentum value, on the training quality of neural networks.

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.

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...

Artificial neural network applications in the calibration of spark-ignition engines: An overview

Directory of Open Access Journals (Sweden)

Richard Fiifi Turkson

2016-09-01

Full Text Available Emission legislation has become progressively tighter, making the development of new internal combustion engines very challenging. New engine technologies for complying with these regulations introduce an exponential dependency between the number of test combinations required for obtaining optimum results and the time and cost outlays. This makes the calibration task very expensive and virtually impossible to carry out. The potential use of trained neural networks in combination with Design of Experiments (DoE methods for engine calibration has been a subject of research activities in recent times. This is because artificial neural networks, compared with other data-driven modeling techniques, perform better in satisfying a majority of the modeling requirements for engine calibration including the curse of dimensionality; the use of DoE for obtaining few measurements as practicable, with the aim of reducing engine calibration costs; the required flexibility that allows model parameters to be optimized to avoid overfitting; and the facilitation of automated online optimization during the engine calibration process that eliminates the need for user intervention. The purpose of this review is to give an overview of the various applications of neural networks in the calibration of spark-ignition engines. The identified and discussed applications include system identification for rapid prototyping, virtual sensing, use of neural networks as look-up table surrogates, emerging control strategies and On-Board Diagnostic (OBD applications. The demerits of neural networks, future possibilities and alternatives were also discussed.

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.

Target recognition based on convolutional neural network

Science.gov (United States)

Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

2017-11-01

One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.

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.

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…

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.

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.)

Derivation of a correlation for Drag coefficient in two-dimensional bounded supercavitating flows, using artificial neural networks

Energy Technology Data Exchange (ETDEWEB)

Shafaghat, R.; Hosseinalipour, S.M.; Derakhshani, S.M.E. [Iran University of Science and Technology, Department of Mechanical Engineering, Tehran (Iran)

2010-07-15

Artificial neural networks (ANNs) are used as a new approach for the determination of the relations between drag coefficient and Cavitation Number with cavity geometry in supercavitating flows which have been most widely used in the hydrodynamics researches. Also the result of the ANNs as a cost function potentially will be used in an optimization algorithm. Instead of complex differential equations and limited experimental data, faster and simpler solutions were obtained using equations derived from the ANN model. For training of the ANN the numerical results are used that are obtained from a boundary element method (BEM). At this problem, a two-dimensional supercavitation potential inviscid flow pasts a symmetric two-dimensional cavitator, which is placed perpendicular to the flow in a channel of infinite width and immediately a cavity is formed behind the cavitator. It was found that the coefficient of multiple determination (R{sup 2}-value) between the actual and ANN predicted data is equal to about 0.9998 for the drag coefficient and Cavitation number. As seen from the obtained results, the calculated cavity geometry for all drag coefficients and Cavitation Numbers are obviously within acceptable limits. (orig.)

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

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.

DataHigh: graphical user interface for visualizing and interacting with high-dimensional neural activity

Science.gov (United States)

Cowley, Benjamin R.; Kaufman, Matthew T.; Butler, Zachary S.; Churchland, Mark M.; Ryu, Stephen I.; Shenoy, Krishna V.; Yu, Byron M.

2013-12-01

Objective. Analyzing and interpreting the activity of a heterogeneous population of neurons can be challenging, especially as the number of neurons, experimental trials, and experimental conditions increases. One approach is to extract a set of latent variables that succinctly captures the prominent co-fluctuation patterns across the neural population. A key problem is that the number of latent variables needed to adequately describe the population activity is often greater than 3, thereby preventing direct visualization of the latent space. By visualizing a small number of 2-d projections of the latent space or each latent variable individually, it is easy to miss salient features of the population activity. Approach. To address this limitation, we developed a Matlab graphical user interface (called DataHigh) that allows the user to quickly and smoothly navigate through a continuum of different 2-d projections of the latent space. We also implemented a suite of additional visualization tools (including playing out population activity timecourses as a movie and displaying summary statistics, such as covariance ellipses and average timecourses) and an optional tool for performing dimensionality reduction. Main results. To demonstrate the utility and versatility of DataHigh, we used it to analyze single-trial spike count and single-trial timecourse population activity recorded using a multi-electrode array, as well as trial-averaged population activity recorded using single electrodes. Significance. DataHigh was developed to fulfil a need for visualization in exploratory neural data analysis, which can provide intuition that is critical for building scientific hypotheses and models of population activity.

DataHigh: graphical user interface for visualizing and interacting with high-dimensional neural activity.

Science.gov (United States)

Cowley, Benjamin R; Kaufman, Matthew T; Butler, Zachary S; Churchland, Mark M; Ryu, Stephen I; Shenoy, Krishna V; Yu, Byron M

2013-12-01

Analyzing and interpreting the activity of a heterogeneous population of neurons can be challenging, especially as the number of neurons, experimental trials, and experimental conditions increases. One approach is to extract a set of latent variables that succinctly captures the prominent co-fluctuation patterns across the neural population. A key problem is that the number of latent variables needed to adequately describe the population activity is often greater than 3, thereby preventing direct visualization of the latent space. By visualizing a small number of 2-d projections of the latent space or each latent variable individually, it is easy to miss salient features of the population activity. To address this limitation, we developed a Matlab graphical user interface (called DataHigh) that allows the user to quickly and smoothly navigate through a continuum of different 2-d projections of the latent space. We also implemented a suite of additional visualization tools (including playing out population activity timecourses as a movie and displaying summary statistics, such as covariance ellipses and average timecourses) and an optional tool for performing dimensionality reduction. To demonstrate the utility and versatility of DataHigh, we used it to analyze single-trial spike count and single-trial timecourse population activity recorded using a multi-electrode array, as well as trial-averaged population activity recorded using single electrodes. DataHigh was developed to fulfil a need for visualization in exploratory neural data analysis, which can provide intuition that is critical for building scientific hypotheses and models of population activity.

DataHigh: Graphical user interface for visualizing and interacting with high-dimensional neural activity

Science.gov (United States)

Cowley, Benjamin R.; Kaufman, Matthew T.; Butler, Zachary S.; Churchland, Mark M.; Ryu, Stephen I.; Shenoy, Krishna V.; Yu, Byron M.

2014-01-01

Objective Analyzing and interpreting the activity of a heterogeneous population of neurons can be challenging, especially as the number of neurons, experimental trials, and experimental conditions increases. One approach is to extract a set of latent variables that succinctly captures the prominent co-fluctuation patterns across the neural population. A key problem is that the number of latent variables needed to adequately describe the population activity is often greater than three, thereby preventing direct visualization of the latent space. By visualizing a small number of 2-d projections of the latent space or each latent variable individually, it is easy to miss salient features of the population activity. Approach To address this limitation, we developed a Matlab graphical user interface (called DataHigh) that allows the user to quickly and smoothly navigate through a continuum of different 2-d projections of the latent space. We also implemented a suite of additional visualization tools (including playing out population activity timecourses as a movie and displaying summary statistics, such as covariance ellipses and average timecourses) and an optional tool for performing dimensionality reduction. Main results To demonstrate the utility and versatility of DataHigh, we used it to analyze single-trial spike count and single-trial timecourse population activity recorded using a multi-electrode array, as well as trial-averaged population activity recorded using single electrodes. Significance DataHigh was developed to fulfill a need for visualization in exploratory neural data analysis, which can provide intuition that is critical for building scientific hypotheses and models of population activity. PMID:24216250

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.

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...

Real time track finding in a drift chamber with a VLSI neural network

International Nuclear Information System (INIS)

Lindsey, C.S.; Denby, B.; Haggerty, H.; Johns, K.

1992-01-01

In a test setup, a hardware neural network determined track parameters of charged particles traversing a drift chamber. Voltages proportional to the drift times in 6 cells of the 3-layer chamber were inputs to the Intel ETANN neural network chip which had been trained to give the slope and intercept of tracks. We compare network track parameters to those obtained from off-line track fits. To our knowledge this is the first on-line application of a VLSI neural network to a high energy physics detector. This test explored the potential of the chip and the practical problems of using it in a real world setting. We compare the chip performance to a neural network simulation on a conventional computer. We discuss possible applications of the chip in high energy physics detector triggers. (orig.)

Modeling of High Temperature Oxidation Behavior of FeCrAl Alloy by using Artificial Neural Network

Energy Technology Data Exchange (ETDEWEB)

Kim, Jae Joon; Ryu, Ho Jin [KAIST, Daejeon (Korea, Republic of)

2016-10-15

Refractory alloys are candidate materials for replacing current zirconium-base cladding of light water reactors and they retain significant creep resistance and mechanical strength at high temperatures up to 1500 ℃ due to their high melting temperature. Thermal neutron cross sections of refractory metals are higher than that of zirconium, however the loss of neutron can be overcome by reducing cladding thickness which can be facilitated with enhanced mechanical properties. However, most refractory metals show the poor oxidation resistance at a high temperature. Oxidation behaviors of the various compositions of FeCrAl alloys in high temperature conditions were modeled by using Bayesian neural network. The automatic relevance determination (ARD) technique represented the influence of the composition of alloying elements on the oxidation resistance of FeCrAl alloys. This model can be utilized to understand the tendency of oxidation behavior along the composition of each element and prove the applicability of neural network modeling for the development of new cladding material of light water reactors.

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

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

Drug release control and system understanding of sucrose esters matrix tablets by artificial neural networks.

Science.gov (United States)

Chansanroj, Krisanin; Petrović, Jelena; Ibrić, Svetlana; Betz, Gabriele

2011-10-09

Artificial neural networks (ANNs) were applied for system understanding and prediction of drug release properties from direct compacted matrix tablets using sucrose esters (SEs) as matrix-forming agents for controlled release of a highly water soluble drug, metoprolol tartrate. Complexity of the system was presented through the effects of SE concentration and tablet porosity at various hydrophilic-lipophilic balance (HLB) values of SEs ranging from 0 to 16. Both effects contributed to release behaviors especially in the system containing hydrophilic SEs where swelling phenomena occurred. A self-organizing map neural network (SOM) was applied for visualizing interrelation among the variables and multilayer perceptron neural networks (MLPs) were employed to generalize the system and predict the drug release properties based on HLB value and concentration of SEs and tablet properties, i.e., tablet porosity, volume and tensile strength. Accurate prediction was obtained after systematically optimizing network performance based on learning algorithm of MLP. Drug release was mainly attributed to the effects of SEs, tablet volume and tensile strength in multi-dimensional interrelation whereas tablet porosity gave a small impact. Ability of system generalization and accurate prediction of the drug release properties proves the validity of SOM and MLPs for the formulation modeling of direct compacted matrix tablets containing controlled release agents of different material properties. Copyright © 2011 Elsevier B.V. All rights reserved.

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

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 ...

Orientation selective neural network for cosmic muon identification

International Nuclear Information System (INIS)

Abramowicz, H.; Tel Aviv Univ.; Horn, D.; Naftaly, U.; Sahar-Pikielny, C.

1997-01-01

We discuss a novel method for identification of a linear pattern of pixels on a two-dimensional grid. Motivated by principles employed by the visual cortex, we construct orientation selective neurons in a neural network that performs this task. The method is then applied to a sample of data collected with the ZEUS detector at HERA in order to identify cosmic muons that leave a linear pattern of signals in the segmented uranium-scintillator calorimeter. A two dimensional representation of the relevant part of the detector is used. The algorithm performs well in the presence of noise and pixels with limited efficiency. Given its architecture, this system becomes a good candidate for fast pattern recognition in parallel processing devices. (orig.)

Decorrelation of Neural-Network Activity by Inhibitory Feedback

Science.gov (United States)

Einevoll, Gaute T.; Diesmann, Markus

2012-01-01

Correlations in spike-train ensembles can seriously impair the encoding of information by their spatio-temporal structure. An inevitable source of correlation in finite neural networks is common presynaptic input to pairs of neurons. Recent studies demonstrate that spike correlations in recurrent neural networks are considerably smaller than expected based on the amount of shared presynaptic input. Here, we explain this observation by means of a linear network model and simulations of networks of leaky integrate-and-fire neurons. We show that inhibitory feedback efficiently suppresses pairwise correlations and, hence, population-rate fluctuations, thereby assigning inhibitory neurons the new role of active decorrelation. We quantify this decorrelation by comparing the responses of the intact recurrent network (feedback system) and systems where the statistics of the feedback channel is perturbed (feedforward system). Manipulations of the feedback statistics can lead to a significant increase in the power and coherence of the population response. In particular, neglecting correlations within the ensemble of feedback channels or between the external stimulus and the feedback amplifies population-rate fluctuations by orders of magnitude. The fluctuation suppression in homogeneous inhibitory networks is explained by a negative feedback loop in the one-dimensional dynamics of the compound activity. Similarly, a change of coordinates exposes an effective negative feedback loop in the compound dynamics of stable excitatory-inhibitory networks. The suppression of input correlations in finite networks is explained by the population averaged correlations in the linear network model: In purely inhibitory networks, shared-input correlations are canceled by negative spike-train correlations. In excitatory-inhibitory networks, spike-train correlations are typically positive. Here, the suppression of input correlations is not a result of the mere existence of correlations between

Review On Applications Of Neural Network To Computer Vision

Science.gov (United States)

Li, Wei; Nasrabadi, Nasser M.

1989-03-01

Neural network models have many potential applications to computer vision due to their parallel structures, learnability, implicit representation of domain knowledge, fault tolerance, and ability of handling statistical data. This paper demonstrates the basic principles, typical models and their applications in this field. Variety of neural models, such as associative memory, multilayer back-propagation perceptron, self-stabilized adaptive resonance network, hierarchical structured neocognitron, high order correlator, network with gating control and other models, can be applied to visual signal recognition, reinforcement, recall, stereo vision, motion, object tracking and other vision processes. Most of the algorithms have been simulated on com-puters. Some have been implemented with special hardware. Some systems use features, such as edges and profiles, of images as the data form for input. Other systems use raw data as input signals to the networks. We will present some novel ideas contained in these approaches and provide a comparison of these methods. Some unsolved problems are mentioned, such as extracting the intrinsic properties of the input information, integrating those low level functions to a high-level cognitive system, achieving invariances and other problems. Perspectives of applications of some human vision models and neural network models are analyzed.

Electrocardiogram (ECG Signal Modeling and Noise Reduction Using Hopfield Neural Networks

Directory of Open Access Journals (Sweden)

F. Bagheri

2013-02-01

Full Text Available The Electrocardiogram (ECG signal is one of the diagnosing approaches to detect heart disease. In this study the Hopfield Neural Network (HNN is applied and proposed for ECG signal modeling and noise reduction. The Hopfield Neural Network (HNN is a recurrent neural network that stores the information in a dynamic stable pattern. This algorithm retrieves a pattern stored in memory in response to the presentation of an incomplete or noisy version of that pattern. Computer simulation results show that this method can successfully model the ECG signal and remove high-frequency noise.

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.

Numerical experiments with neural networks

International Nuclear Information System (INIS)

Miranda, Enrique.

1990-01-01

Neural networks are highly idealized models which, in spite of their simplicity, reproduce some key features of the real brain. In this paper, they are introduced at a level adequate for an undergraduate computational physics course. Some relevant magnitudes are defined and evaluated numerically for the Hopfield model and a short term memory model. (Author)

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.

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.

A multivariate extension of mutual information for growing neural networks.

Science.gov (United States)

Ball, Kenneth R; Grant, Christopher; Mundy, William R; Shafer, Timothy J

2017-11-01

Recordings of neural network activity in vitro are increasingly being used to assess the development of neural network activity and the effects of drugs, chemicals and disease states on neural network function. The high-content nature of the data derived from such recordings can be used to infer effects of compounds or disease states on a variety of important neural functions, including network synchrony. Historically, synchrony of networks in vitro has been assessed either by determination of correlation coefficients (e.g. Pearson's correlation), by statistics estimated from cross-correlation histograms between pairs of active electrodes, and/or by pairwise mutual information and related measures. The present study examines the application of Normalized Multiinformation (NMI) as a scalar measure of shared information content in a multivariate network that is robust with respect to changes in network size. Theoretical simulations are designed to investigate NMI as a measure of complexity and synchrony in a developing network relative to several alternative approaches. The NMI approach is applied to these simulations and also to data collected during exposure of in vitro neural networks to neuroactive compounds during the first 12 days in vitro, and compared to other common measures, including correlation coefficients and mean firing rates of neurons. NMI is shown to be more sensitive to developmental effects than first order synchronous and nonsynchronous measures of network complexity. Finally, NMI is a scalar measure of global (rather than pairwise) mutual information in a multivariate network, and hence relies on less assumptions for cross-network comparisons than historical approaches. Copyright © 2017 Elsevier Ltd. All rights reserved.

Methodology for neural networks prototyping. Application to traffic control

Energy Technology Data Exchange (ETDEWEB)

Belegan, I.C.

1998-07-01

The work described in this report was carried out in the context of the European project ASTORIA (Advanced Simulation Toolbox for Real-World Industrial Application in Passenger Management and Adaptive Control), and concerns the development of an advanced toolbox for complex transportation systems. Our work was focused on the methodology for prototyping a set of neural networks corresponding to specific strategies for traffic control and congestion management. The tool used for prototyping is SNNS (Stuggart Neural Network Simulator), developed at the University of Stuggart, Institute for Parallel and Distributed High Performance Systems, and the real data from the field were provided by ZELT. This report is structured into six parts. The introduction gives some insights about traffic control and its approaches. The second chapter discusses the various control strategies existing. The third chapter is an introduction to the field of neural networks. The data analysis and pre-processing is described in the fourth chapter. In the fifth chapter, the methodology for prototyping the neural networks is presented. Finally, conclusions and further work are presented. (author) 14 refs.

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 ...

Generalized synthetic aperture radar automatic target recognition by convolutional neural network with joint use of two-dimensional principal component analysis and support vector machine

Science.gov (United States)

Zheng, Ce; Jiang, Xue; Liu, Xingzhao

2017-10-01

Convolutional neural network (CNN), as a vital part of the deep learning research field, has shown powerful potential for automatic target recognition (ATR) of synthetic aperture radar (SAR). However, the high complexity caused by the deep structure of CNN makes it difficult to generalize. An improved form of CNN with higher generalization capability and less probability of overfitting, which further improves the efficiency and robustness of the SAR ATR system, is proposed. The convolution layers of CNN are combined with a two-dimensional principal component analysis algorithm. Correspondingly, the kernel support vector machine is utilized as the classifier layer instead of the multilayer perceptron. The verification experiments are implemented using the moving and stationary target acquisition and recognition database, and the results validate the efficiency of the proposed method.

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

Science.gov (United States)

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

2013-09-01

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

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.

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

Science.gov (United States)

Bakanovskaya, L. N.

2016-08-01

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

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

Optimizing Markovian modeling of chaotic systems with recurrent neural networks

International Nuclear Information System (INIS)

Cechin, Adelmo L.; Pechmann, Denise R.; Oliveira, Luiz P.L. de

2008-01-01

In this paper, we propose a methodology for optimizing the modeling of an one-dimensional chaotic time series with a Markov Chain. The model is extracted from a recurrent neural network trained for the attractor reconstructed from the data set. Each state of the obtained Markov Chain is a region of the reconstructed state space where the dynamics is approximated by a specific piecewise linear map, obtained from the network. The Markov Chain represents the dynamics of the time series in its statistical essence. An application to a time series resulted from Lorenz system is included

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.

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.

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.

Numerical simulation of shower cooling tower based on artificial neural network

International Nuclear Information System (INIS)

Qi Xiaoni; Liu Zhenyan; Li Dandan

2008-01-01

This study was prompted by the need to design towers for applications in which, due to salt deposition on the packing and subsequent blockage, the use of tower packing is not practical. The cooling tower analyzed in this study is void of fill, named shower cooling tower (SCT). However, the present study focuses mostly on experimental investigation of the SCT, and no systematic numerical method is available. In this paper, we first developed a one dimensional model and analyzed the heat and mass transfer processes of the SCT; then we used the concept of artificial neural network (ANN) to propose a computer design tool that can help the designer evaluate the outlet water temperature from a given set of experimentally obtained data. For comparison purposes and accurate evaluation of the predictions, part of the experimental data was used to train the neural network and the remainder to test the model. The results predicted by the ANN model were compared with those of the standard model and the experimental data. The ANN model predicted the outlet water temperature with a MAE (mean absolute error) of 1.31%, whereas the standard one dimensional model showed a MAE of 9.42%

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

Science.gov (United States)

Zhu, Zhenyu; Wang, Rubin; Zhu, Fengyun

2018-01-01

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

Development of target-tracking algorithms using neural network

Energy Technology Data Exchange (ETDEWEB)

Park, Dong Sun; Lee, Joon Whaoan; Yoon, Sook; Baek, Seong Hyun; Lee, Myung Jae [Chonbuk National University, Chonjoo (Korea)

1998-04-01

The utilization of remote-control robot system in atomic power plants or nuclear-related facilities grows rapidly, to protect workers form high radiation environments. Such applications require complete stability of the robot system, so that precisely tracking the robot is essential for the whole system. This research is to accomplish the goal by developing appropriate algorithms for remote-control robot systems. A neural network tracking system is designed and experimented to trace a robot Endpoint. This model is aimed to utilized the excellent capabilities of neural networks; nonlinear mapping between inputs and outputs, learning capability, and generalization capability. The neural tracker consists of two networks for position detection and prediction. Tracking algorithms are developed and experimented for the two models. Results of the experiments show that both models are promising as real-time target-tracking systems for remote-control robot systems. (author). 10 refs., 47 figs.

Joint Multi-scale Convolution Neural Network for Scene Classification of High Resolution Remote Sensing Imagery

Directory of Open Access Journals (Sweden)

ZHENG Zhuo

2018-05-01

Full Text Available High resolution remote sensing imagery scene classification is important for automatic complex scene recognition, which is the key technology for military and disaster relief, etc. In this paper, we propose a novel joint multi-scale convolution neural network (JMCNN method using a limited amount of image data for high resolution remote sensing imagery scene classification. Different from traditional convolutional neural network, the proposed JMCNN is an end-to-end training model with joint enhanced high-level feature representation, which includes multi-channel feature extractor, joint multi-scale feature fusion and Softmax classifier. Multi-channel and scale convolutional extractors are used to extract scene middle features, firstly. Then, in order to achieve enhanced high-level feature representation in a limit dataset, joint multi-scale feature fusion is proposed to combine multi-channel and scale features using two feature fusions. Finally, enhanced high-level feature representation can be used for classification by Softmax. Experiments were conducted using two limit public UCM and SIRI datasets. Compared to state-of-the-art methods, the JMCNN achieved improved performance and great robustness with average accuracies of 89.3% and 88.3% on the two datasets.

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...

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)

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.

Multistability of neural networks with discontinuous non-monotonic piecewise linear activation functions and time-varying delays.

Science.gov (United States)

Nie, Xiaobing; Zheng, Wei Xing

2015-05-01

This paper is concerned with the problem of coexistence and dynamical behaviors of multiple equilibrium points for neural networks with discontinuous non-monotonic piecewise linear activation functions and time-varying delays. The fixed point theorem and other analytical tools are used to develop certain sufficient conditions that ensure that the n-dimensional discontinuous neural networks with time-varying delays can have at least 5(n) equilibrium points, 3(n) of which are locally stable and the others are unstable. The importance of the derived results is that it reveals that the discontinuous neural networks can have greater storage capacity than the continuous ones. Moreover, different from the existing results on multistability of neural networks with discontinuous activation functions, the 3(n) locally stable equilibrium points obtained in this paper are located in not only saturated regions, but also unsaturated regions, due to the non-monotonic structure of discontinuous activation functions. A numerical simulation study is conducted to illustrate and support the derived theoretical results. Copyright © 2015 Elsevier Ltd. All rights reserved.

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)

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)

Genetic algorithm-based neural network for accidents diagnosis of research reactors on FPGA

International Nuclear Information System (INIS)

Ghuname, A.A.A.

2012-01-01

The Nuclear Research Reactors plants are expected to be operated with high levels of reliability, availability and safety. In order to achieve and maintain system stability and assure satisfactory and safe operation, there is increasing demand for automated systems to detect and diagnose such failures. Artificial Neural Networks (ANNs) are one of the most popular solutions because of their parallel structure, high speed, and their ability to give easy solution to complicated problems. The genetic algorithms (GAs) which are search algorithms (optimization techniques), in recent years, have been used to find the optimum construction of a neural network for definite application, as one of the advantages of its usage. Nowadays, Field Programmable Gate Arrays (FPGAs) are being an important implementation method of neural networks due to their high performance and they can easily be made parallel. The VHDL, which stands for VHSIC (Very High Speed Integrated Circuits) Hardware Description Language, have been used to describe the design behaviorally in addition to schematic and other description languages. The description of designs in synthesizable language such as VHDL make them reusable and be implemented in upgradeable systems like the Nuclear Research Reactors plants. In this thesis, the work was carried out through three main parts.In the first part, the Nuclear Research Reactors accident's pattern recognition is tackled within the artificial neural network approach. Such patterns are introduced initially without noise. And, to increase the reliability of such neural network, the noise ratio up to 50% was added for training in order to ensure the recognition of these patterns if it introduced with noise.The second part is concerned with the construction of Artificial Neural Networks (ANNs) using Genetic algorithms (GAs) for the nuclear accidents diagnosis. MATLAB ANNs toolbox and GAs toolbox are employed to optimize an ANN for this purpose. The results obtained show

Statistical downscaling of precipitation using long short-term memory recurrent neural networks

Science.gov (United States)

Misra, Saptarshi; Sarkar, Sudeshna; Mitra, Pabitra

2017-11-01

Hydrological impacts of global climate change on regional scale are generally assessed by downscaling large-scale climatic variables, simulated by General Circulation Models (GCMs), to regional, small-scale hydrometeorological variables like precipitation, temperature, etc. In this study, we propose a new statistical downscaling model based on Recurrent Neural Network with Long Short-Term Memory which captures the spatio-temporal dependencies in local rainfall. The previous studies have used several other methods such as linear regression, quantile regression, kernel regression, beta regression, and artificial neural networks. Deep neural networks and recurrent neural networks have been shown to be highly promising in modeling complex and highly non-linear relationships between input and output variables in different domains and hence we investigated their performance in the task of statistical downscaling. We have tested this model on two datasets—one on precipitation in Mahanadi basin in India and the second on precipitation in Campbell River basin in Canada. Our autoencoder coupled long short-term memory recurrent neural network model performs the best compared to other existing methods on both the datasets with respect to temporal cross-correlation, mean squared error, and capturing the extremes.

Studying the Relationship between High-Latitude Geomagnetic Activity and Parameters of Interplanetary Magnetic Clouds with the Use of Artificial Neural Networks

Science.gov (United States)

Barkhatov, N. A.; Revunov, S. E.; Vorobjev, V. G.; Yagodkina, O. I.

2018-03-01

The cause-and-effect relations of the dynamics of high-latitude geomagnetic activity (in terms of the AL index) and the type of the magnetic cloud of the solar wind are studied with the use of artificial neural networks. A recurrent neural network model has been created based on the search for the optimal physically coupled input and output parameters characterizing the action of a plasma flux belonging to a certain magnetic cloud type on the magnetosphere. It has been shown that, with IMF components as input parameters of neural networks with allowance for a 90-min prehistory, it is possible to retrieve the AL sequence with an accuracy to 80%. The successful retrieval of the AL dynamics by the used data indicates the presence of a close nonlinear connection of the AL index with cloud parameters. The created neural network models can be applied with high efficiency to retrieve the AL index, both in periods of isolated magnetospheric substorms and in periods of the interaction between the Earth's magnetosphere and magnetic clouds of different types. The developed model of AL index retrieval can be used to detect magnetic clouds.