WorldWideScience

Sample records for cellular neural networks

  1. Exponential Stability for Delayed Cellular Neural Networks

    Institute of Scientific and Technical Information of China (English)

    YANG Jin-xiang; ZHONG Shou-ming; YAN Ke-yu

    2005-01-01

    The exponential stability of the delayed cellular neural networks (DCNN's) is investigated. By dividing the network state variables into some parts according to the characters of the neural networks, some new sufficient conditions of exponential stability are derived via constructing a Liapunov function. It is shown that the conditions differ from previous ones. The new conditions, which are associated with some initial value, are represented by some blocks of the interconnection matrix.

  2. Stability of Stochastic Neutral Cellular Neural Networks

    Science.gov (United States)

    Chen, Ling; Zhao, Hongyong

    In this paper, we study a class of stochastic neutral cellular neural networks. By constructing a suitable Lyapunov functional and employing the nonnegative semi-martingale convergence theorem we give some sufficient conditions ensuring the almost sure exponential stability of the networks. The results obtained are helpful to design stability of networks when stochastic noise is taken into consideration. Finally, two examples are provided to show the correctness of our analysis.

  3. Boltzmann learning of parameters in cellular neural networks

    DEFF Research Database (Denmark)

    Hansen, Lars Kai

    1992-01-01

    The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified ...... by unsupervised adaptation of an image segmentation cellular network. The learning rule is applied to adaptive segmentation of satellite imagery......The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified...

  4. Global stability analysis on a class of cellular neural networks

    Institute of Scientific and Technical Information of China (English)

    ZHANG; Yi

    2001-01-01

    [1]Chua, L. O., Yang, L., Cellular neural networks: Theory, IEEE Trans. CAS, 1988, (10): 1257.[2]Chua, L. O., Yang, L., Cellular neural networks: Applications, IEEE Trans. CAS, 1988, (10): 1273.[3]Chua, L. O., Roska, T., The CNN paradigm, IEEE Trans. CAS-I, 1993, (3): 147.[4]Matsumoto, T. Chua, L. O., Suzuki, H., CNN cloning template: Connected component detector, IEEE Trans. CAS, 1990, (8): 633.[5]Cao, L, Sun, Y, Yu, J., A CNN-based signature verification system,Proc. ICONIP′95, Beijing, 1995, 913—916.[6]Roska, T., Chua, L. O., The CNN universal machine: An analogic array computer, IEEE Trans. CAS Ⅱ, 1993, (3): 163.[7]Chua, L. O., Roska, T., Stability of a class of nonreciprocal cellular neural networks, IEEE Trans. CAS, 1990, (3): 1520.[8]Roska, T., Wu, C. W., Balsi, M. Et al., Stability and dynamics of delay type general and cellular neural networks, IEEE Trans. CAS, 1992, (6): 487.[9]Roska, T., Wu, C. W., Chua, L. O., Stability of cellular neural networks with dominant nonlinear and delaytype templates, IEEE Trans. CAS, 1993, (4): 270.[10]Civalleri, P. P., On stability of cellular neural networks with delay, IEEE Trans. CAS-I, 1993, (3): 157.[11]Gilli, G., Stability of cellular neural network and delayed cellular neural networks with nonpositive templates and nonmonotonic output functions, IEEE Trans CAS-I, 1994, (8): 518.[12]Baldi, P., Atiya, A. F., How delays affect neural dynamics and learning, IEEE Trans. On Neural Networks, 1994, (4): 612.[13]Liao, X. X., Mathematic foundation of cellular neural networks (Ⅰ), Science in China, Ser. A, 1994, 37(9): 902.[14]Liao, X. X., Mathematic foundation of cellular neural networks (Ⅱ), Science in China, Ser. A, 1994, 37(9): 1037.[15]Zhang, Y., Global exponential stability and periodic solutions of delay Hopfild neural networks, International J. Sys. Sci., 1996, (2): 227.[16]Zhang Yi, Zhong, S. M., Li, Z. L., Periodic solutions and global

  5. Cellular neural networks for the stereo matching problem

    Energy Technology Data Exchange (ETDEWEB)

    Taraglio, S. [ENEA, Centro Ricerche Casaccia, Rome (Italy). Dipt. Innovazione; Zanela, A. [Rome Univ. `La Sapienza` (Italy). Dipt. di Fisica

    1997-03-01

    The applicability of the Cellular Neural Network (CNN) paradigm to the problem of recovering information on the tridimensional structure of the environment is investigated. The approach proposed is the stereo matching of video images. The starting point of this work is the Zhou-Chellappa neural network implementation for the same problem. The CNN based system we present here yields the same results as the previous approach, but without the many existing drawbacks.

  6. Template learning of cellular neural network using genetic programming.

    Science.gov (United States)

    Radwan, Elsayed; Tazaki, Eiichiro

    2004-08-01

    A new learning algorithm for space invariant Uncoupled Cellular Neural Network is introduced. Learning is formulated as an optimization problem. Genetic Programming has been selected for creating new knowledge because they allow the system to find new rules both near to good ones and far from them, looking for unknown good control actions. According to the lattice Cellular Neural Network architecture, Genetic Programming will be used in deriving the Cloning Template. Exploration of any stable domain is possible by the current approach. Details of the algorithm are discussed and several application results are shown.

  7. Global asymptotic stability of cellular neural networks with multiple delays

    Institute of Scientific and Technical Information of China (English)

    2006-01-01

    Global asymptotic stability (GAS) is discussed for cellular neural networks (CNN) with multiple time delays. Several criteria are proposed to ascertain the uniqueness and global asymptotic stability of the equilibrium point for the CNN with delays. These criteria can eliminate the difference between the neuronal excitatory and inhibitory effects. Two examples are presented to demonstrate the effectiveness of the criteria.

  8. Incorporating scale invariance into the cellular associative neural network

    OpenAIRE

    Burles, Nathan; O'Keefe, Simon; Austin, James

    2014-01-01

    This paper describes an improvement to the Cellular Associative Neural Network, an architecture based on the distributed model of a cellular automaton, allowing it to perform scale invariant pattern matching. The use of tensor products and superposition of patterns allows the system to recall patterns at multiple resolutions simultaneously. Our experimental results show that the architecture is capable of scale invariant pattern matching, but that further investigation is needed to reduce the...

  9. On Hardware Implementation of Discrete-Time Cellular Neural Networks

    OpenAIRE

    Malki, Suleyman

    2008-01-01

    Cellular Neural Networks are characterized by simplicity of operation. The network consists of a large number of nonlinear processing units; called cells; that are equally spread in the space. Each cell has a simple function (sequence of multiply-add followed by a single discrimination) that takes an element of a topographic map and then interacts with all cells within a specified sphere of interest through direct connections. Due to their intrinsic parallel computing power, CNNs have attract...

  10. Integration of Neural Networks and Cellular Automata for Urban Planning

    Institute of Scientific and Technical Information of China (English)

    Anthony Gar-on Yeh; LI Xia

    2004-01-01

    This paper presents a new type of cellular automata (CA) model for the simulation of alternative land development using neural networks for urban planning. CA models can be regarded as a planning tool because they can generate alternative urban growth. Alternative development patterns can be formed by using different sets of parameter values in CA simulation. A critical issue is how to define parameter values for realistic and idealized simulation. This paper demonstrates that neural networks can simplify CA models but generate more plausible results. The simulation is based on a simple three-layer network with an output neuron to generate conversion probability. No transition rules are required for the simulation. Parameter values are automatically obtained from the training of network by using satellite remote sensing data. Original training data can be assessed and modified according to planning objectives. Alternative urban patterns can be easily formulated by using the modified training data sets rather than changing the model.

  11. Global stability analysis on a class of cellular neural networks

    Institute of Scientific and Technical Information of China (English)

    2001-01-01

    The existence, uniqueness, globally exponential stability andspeed of exponential convergence for a class of cellular neural networks are investigated. The existence of a unique equilibrium is proved under very concise conditions, and theorems for estimating the global convergence speed approaching the equilibrium and criteria for its globally exponential stability are derived, Considering synapse time delay, by constructing appropriate Lyapunov functional, the existence of a unique equilibrium and its global stability for the delayed network are also proved. The results, which do not require the cloning template to be symmetric, are easy to use in network design.

  12. PERIODIC SOLUTIONS TO FUZZY CELLULAR NEURAL NETWORKS WITH DISTRIBUTED DELAYS

    Institute of Scientific and Technical Information of China (English)

    2008-01-01

    In this paper, a class of fuzzy cellular neural networks with distributed delays is discussed. By employing fixed point theorem and inequality techniques, some sufficient conditions are obtained to ensure the existence and global exponential stability of periodic solutions to the systems. Without assuming the global Lipschitz conditions of activation functions, our results are novel and reduce the limitation of previous known results. Moreover, an example is given to illustrate the effectiveness of our resu...

  13. Chaotic phenomena in Josephson circuits coupled quantum cellular neural networks

    Institute of Scientific and Technical Information of China (English)

    Wang Sen; Cai Li; Li Qin; Wu Gang

    2007-01-01

    In this paper the nonlinear dynamical behaviour of a quantum cellular neural network (QCNN) by coupling Josephson circuits was investigated and it was shown that the QCNN using only two of them can cause the onset of chaotic oscillation. The theoretical analysis and simulation for the two Josephson-circuits-coupled QCNN have been done by using the amplitude and phase as state variables. The complex chaotic behaviours can be observed and then proved by calculating Lyapunov exponents. The study provides valuable information about QCNNs for future application in high-parallel signal processing and novel chaotic generators.

  14. Controllability of time-varying cellular neural networks

    Directory of Open Access Journals (Sweden)

    Wadie Aziz

    2005-11-01

    Full Text Available In this work, we consider the model of Cellular Neural Network (CNN introduced by Chua and Yang in 1988, but with the cloning templates $omega$-periodic in time. By imposing periodic boundary conditions the matrices involved in the system become circulant and $omega$-periodic. We show some results on the controllability of the linear model using a Theorem by Brunovsky for the case of linear and $omega$-periodic system. Also we use this approach in image detection, specifically foreground, background and contours of figures in different scales of grey.

  15. Neural networks and cellular automata in experimental high energy physics

    International Nuclear Information System (INIS)

    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

  16. Cellular Neural Networks for NP-Hard Optimization

    Directory of Open Access Journals (Sweden)

    Mária Ercsey-Ravasz

    2009-02-01

    Full Text Available A cellular neural/nonlinear network (CNN is used for NP-hard optimization. We prove that a CNN in which the parameters of all cells can be separately controlled is the analog correspondent of a two-dimensional Ising-type (Edwards-Anderson spin-glass system. Using the properties of CNN, we show that one single operation (template always yields a local minimum of the spin-glass energy function. This way, a very fast optimization method, similar to simulated annealing, can be built. Estimating the simulation time needed on CNN-based computers, and comparing it with the time needed on normal digital computers using the simulated annealing algorithm, the results are astonishing. CNN computers could be faster than digital computers already at 10×10 lattice sizes. The local control of the template parameters was already partially realized on some of the hardwares, we think this study could further motivate their development in this direction.

  17. Medical image segmentation based on cellular neural network

    Institute of Scientific and Technical Information of China (English)

    2001-01-01

    The application of cellular neural network (CNN) has made great progress in image processing. When the selected objects extraction (SOE) CNN is applied to gray scale images, its effects depend on the choice of initial points. In this paper, we take medical images as an example to analyze this limitation. Then an improved algorithm is proposed in which we can segment any gray level objects regardless of the limitation stated above. We also use the gradient information and contour detection CNN to determine the contour and ensure the veracity of segmentation effectively. Finally, we apply the improved algorithm to tumor segmentation of the human brain MR image. The experimental results show that the algorithm is practical and effective.

  18. Spatio-Temporal Dynamics in Cellular Neural Networks

    Directory of Open Access Journals (Sweden)

    Liviu GORAS

    2009-07-01

    Full Text Available Analog Parallel Architectures like Cellular Neural Networks (CNN’s have been thoroughly studied not only for their potential in high-speed image processing applications but also for their rich and exciting spatio-temporal dynamics. An interesting behavior such architectures can exhibit is spatio-temporal filtering and pattern formation, aspects that will be discussed in this work for a general structure consisting of linear cells locally and homogeneously connected within a specified neighborhood. The results are generalizations of those regarding Turing pattern formation in CNN’s. Using linear cells (or piecewise linear cells working in the central linear part of their characteristic allows the use of the decoupling technique – a powerful technique that gives significant insight into the dynamics of the CNN. The roles of the cell structure as well as that of the connection template are discussed and models for the spatial modes dynamics are made as well.

  19. Cellular neural networks for motion estimation and obstacle detection

    Directory of Open Access Journals (Sweden)

    D. Feiden

    2003-01-01

    Full Text Available Obstacle detection is an important part of Video Processing because it is indispensable for a collision prevention of autonomously navigating moving objects. For example, vehicles driving without human guidance need a robust prediction of potential obstacles, like other vehicles or pedestrians. Most of the common approaches of obstacle detection so far use analytical and statistical methods like motion estimation or generation of maps. In the first part of this contribution a statistical algorithm for obstacle detection in monocular video sequences is presented. The proposed procedure is based on a motion estimation and a planar world model which is appropriate to traffic scenes. The different processing steps of the statistical procedure are a feature extraction, a subsequent displacement vector estimation and a robust estimation of the motion parameters. Since the proposed procedure is composed of several processing steps, the error propagation of the successive steps often leads to inaccurate results. In the second part of this contribution it is demonstrated, that the above mentioned problems can be efficiently overcome by using Cellular Neural Networks (CNN. It will be shown, that a direct obstacle detection algorithm can be easily performed, based only on CNN processing of the input images. Beside the enormous computing power of programmable CNN based devices, the proposed method is also very robust in comparison to the statistical method, because is shows much less sensibility to noisy inputs. Using the proposed approach of obstacle detection in planar worlds, a real time processing of large input images has been made possible.

  20. Periodic solutions of nonautonomous cellular neural networks with impulses

    International Nuclear Information System (INIS)

    Sufficient conditions are obtained for the existence and global exponential stability of a unique periodic solution of a class of neural networks with impulses by using Mawhin's continuation theorem of coincidence degree theory and constructing Lyapunov functions. An illustrative example is given to demonstrate the effectiveness of the obtained results

  1. On the Global Dissipativity of a Class of Cellular Neural Networks with Multipantograph Delays

    Directory of Open Access Journals (Sweden)

    Liqun Zhou

    2011-01-01

    Full Text Available For the first time the global dissipativity of a class of cellular neural networks with multipantograph delays is studied. On the one hand, some delay-dependent sufficient conditions are obtained by directly constructing suitable Lyapunov functionals; on the other hand, firstly the transformation transforms the cellular neural networks with multipantograph delays into the cellular neural networks with constant delays and variable coefficients, and then constructing Lyapunov functionals, some delay-independent sufficient conditions are given. These new sufficient conditions can ensure global dissipativity together with their sets of attraction and can be applied to design global dissipative cellular neural networks with multipantograph delays and easily checked in practice by simple algebraic methods. An example is given to illustrate the correctness of the results.

  2. Boundedness and exponential stability for nonautonomous cellular neural networks with reaction-diffusion terms

    Energy Technology Data Exchange (ETDEWEB)

    Lou Xuyang [Research Center of Control Science and Engineering, Southern Yangtze University, 1800 Lihu Road, Wuxi, Jiangsu 214122 (China); Cui Baotong [Research Center of Control Science and Engineering, Southern Yangtze University, 1800 Lihu Road, Wuxi, Jiangsu 214122 (China)]. E-mail: btcui@sohu.com

    2007-07-15

    Employing Lyapunov functional method, we analyze the ultimate boundedness and global exponential stability of a class of reaction-diffusion cellular neural networks with time-varying delays. Some new criteria are obtained to ensure ultimate boundedness and global exponential stability of delayed reaction-diffusion cellular neural networks (DRCNNs). Without assuming that the activation functions f {sub ijl}(.) are bounded, the results extend and improve the earlier publications.

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

    OpenAIRE

    Kang Xie; Yixian Yang; Yang Xin; Guangsheng Xia

    2015-01-01

    According to the problems of current distributed architecture intrusion detection systems (DIDS), a new online distributed intrusion detection model based on cellular neural network (CNN) was proposed, in which discrete-time CNN (DTCNN) was used as weak classifier in each local node and state-controlled CNN (SCCNN) was used as global detection method, respectively. We further proposed a new method for design template parameters of SCCNN via solving Linear Matrix Inequality. Experimental resul...

  4. THE EXISTENCE OF ALMOST PERIODIC SOLUTION FOR CELLULAR NEURAL NETWORKS WITH VARIABLE COEFFICIENTS AND DELAYS

    Institute of Scientific and Technical Information of China (English)

    XieHuiqin; WangQuanyi

    2005-01-01

    In this paper, we study the problem of almost periodic solution for the cellular neural networks with variable coefficients and delays. By ingeniously importing real parameters di > 0 (i = 1, 2,…, n)which can be adjusted, weestablish some sufficient conditions which ensure the neural networks exist a unique almost periodic solution, and all other solutions exponentially converge to such an almost periodic solution.

  5. Global exponential stability of mixed discrete and distributively delayed cellular neural network

    Institute of Scientific and Technical Information of China (English)

    Yao Hong-Xing; Zhou Jia-Yan

    2011-01-01

    This paper concernes analysis for the global exponential stability of a class of recurrent neural networks with mixed discrete and distributed delays. It first proves the existence and uniqueness of the balance point, then by employing the Lyapunov-Krasovskii functional and Young inequality, it gives the sufficient condition of global exponential stability of cellular neural network with mixed discrete and distributed delays, in addition, the example is provided to illustrate the applicability of the result.

  6. Linear matrix inequality approach for synchronization control of fuzzy cellular neural networks with mixed time delays

    Institute of Scientific and Technical Information of China (English)

    P. Balasubramaniam; M. Kalpana; R. Rakkiyappan

    2012-01-01

    Fuzzy cellular neural networks (FCNNs) are special kinds of cellular neural networks (CNNs).Each cell in an FCNN contains fuzzy operating abilities.The entire network is governed by cellular computing laws.The design of FCNNs is based on fuzzy local rules.In this paper,a linear matrix inequality (LMI) approach for synchronization control of FCNNs with mixed delays is investigated.Mixed delays include discrete time-varying delays and unbounded distributed delays.A dynamic control scheme is proposed to achieve the synchronization between a drive network and a response network.By constructing the Lyapunov-Krasovskii functional which contains a triple-integral term and the free-weighting matrices method an improved delay-dependent stability criterion is derived in terms of LMIs.The controller can be easily obtained by solving the derived LMIs.A numerical example and its simulations are presented to illustrate the effectiveness of the proposed method.

  7. Almost periodic solution of shunting inhibitory cellular neural networks with time-varying delay

    Energy Technology Data Exchange (ETDEWEB)

    Huang Xia; Cao Jinde

    2003-07-28

    Several sufficient conditions are obtained for the existence of almost periodic solution and its attractivity of shunting inhibitory cellular neural networks with time-varying delay based on the fixed point method and Halanay inequality technique. Some previous results are improved and extended in this Letter and two examples are given to illustrate the effectiveness of the new results.

  8. Delay—Independent Stability in Cellular Neural Networks with Infinite Delay

    Institute of Scientific and Technical Information of China (English)

    ZHANGQiang; ZHENGJianguo; XUJin

    2003-01-01

    In this paper, we establish a new model for cellular neural networks which extends previously known models. By utilizing the Lyapunov function method and the method of inequality analysis, a sufficient condition en-suring the global asymptotic stability independent of de-lays for this model is derived. This condition improves some existed works of other researchers.

  9. Existence of Periodic Solutions for Shunting Inhibitory Cellular Neural Networks with Neutral Delays

    Directory of Open Access Journals (Sweden)

    Ninghua Chen

    2013-01-01

    Full Text Available This paper considers the existence of periodic solutions for shunting inhibitory cellular neural networks (SICNNs with neutral delays. By applying the theory of abstract continuation theorem of k-set contractive operator and some analysis technique, a new result on the existence of periodic solutions is obtained.

  10. Existence of Periodic Solutions for Shunting Inhibitory Cellular Neural Networks with Neutral Delays

    OpenAIRE

    Ninghua Chen

    2013-01-01

    This paper considers the existence of periodic solutions for shunting inhibitory cellular neural networks (SICNNs) with neutral delays. By applying the theory of abstract continuation theorem of k-set contractive operator and some analysis technique, a new result on the existence of periodic solutions is obtained.

  11. Existence and uniqueness of periodic solutions of nonautonomous cellular neural networks with impulses

    International Nuclear Information System (INIS)

    By using the continuation theorem of Mawhin's coincidence degree theory and some analysis techniques, some new sufficient conditions are obtained ensuring existence, uniqueness and global exponential stability of periodic solution of nonautonomous cellular neural networks with impulses. The results extend earlier ones where impulses are absent. Further, using numerical simulation method the influences of the impulsive perturbations on the inherent oscillation are investigated

  12. Cellular Neural Networks: A genetic algorithm for parameters optimization in artificial vision applications

    International Nuclear Information System (INIS)

    An optimization method for some of the CNN's (Cellular Neural Network) parameters, based on evolutionary strategies, is proposed. The new class of feedback template found is more effective in extracting features from the images that an autonomous vehicle acquires, than in the previous CNN's literature

  13. One-way hash function based on hyper-chaotic cellular neural network

    Institute of Scientific and Technical Information of China (English)

    Yang Qun-Ting; Gao Tie-Gang

    2008-01-01

    The design of an efficient one-way hash function with good performance is a hot spot in modern cryptography researches. In this paper, a hash function construction method based on cell neural network with hyper-chaos characteristics is proposed. First, the chaos sequence is gotten by iterating cellular neural network with Runge-Kutta algorithm, and then the chaos sequence is iterated with the message. The hash code is obtained through the corresponding transform of the latter chaos sequence. Simulation and analysis demonstrate that the new method has the merit of convenience, high sensitivity to initial values, good hash performance, especially the strong stability.

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

    Directory of Open Access Journals (Sweden)

    Kang Xie

    2015-01-01

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

  15. Learning emergence: adaptive cellular automata façade trained by artificial neural networks

    OpenAIRE

    Skavara, M. M. E.

    2009-01-01

    This thesis looks into the possibilities of controlling the emergent behaviour of Cellular Automata (CA) to achieve specific architectural goals. More explicitly, the objective is to develop a performing, adaptive building facade, which is fed with the history of its achievements and errors, to provide optimum light conditions in buildings’ interiors. To achieve that, an artificial Neural Network (NN) is implemented. However, can an artificial NN cope with the complexity of suc...

  16. Global Exponential Stability of Almost Periodic Solution of Cellular Neural Networks with Time-Varying Delays

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    In this paper, global exponential stability of almost periodic solution of cellular neural networks with time-varing delays (CNNVDs) is considered. By using the methods of the topological degree theory and generalized Halanay inequality, a few new applicable criteria are established for the existence and global exponential stability of almost periodic solution. Some previous results are improved and extended in this letter and one example is given to illustrate the effectiveness of the new results.

  17. Cellular neural network-based hybrid approach toward automatic image registration

    Science.gov (United States)

    Arun, Pattathal VijayaKumar; Katiyar, Sunil Kumar

    2013-01-01

    Image registration is a key component of various image processing operations that involve the analysis of different image data sets. Automatic image registration domains have witnessed the application of many intelligent methodologies over the past decade; however, inability to properly model object shape as well as contextual information has limited the attainable accuracy. A framework for accurate feature shape modeling and adaptive resampling using advanced techniques such as vector machines, cellular neural network (CNN), scale invariant feature transform (SIFT), coreset, and cellular automata is proposed. CNN has been found to be effective in improving feature matching as well as resampling stages of registration and complexity of the approach has been considerably reduced using coreset optimization. The salient features of this work are cellular neural network approach-based SIFT feature point optimization, adaptive resampling, and intelligent object modelling. Developed methodology has been compared with contemporary methods using different statistical measures. Investigations over various satellite images revealed that considerable success was achieved with the approach. This system has dynamically used spectral and spatial information for representing contextual knowledge using CNN-prolog approach. This methodology is also illustrated to be effective in providing intelligent interpretation and adaptive resampling.

  18. Image-processing algorithms realized by discrete-time cellular neural networks and their circuit implementations

    International Nuclear Information System (INIS)

    In this study, eight image tasks: connected component detection (CCD) with down, right, +45o and -45o directions, edge detection, shadow projection with left and right directions and point removal are analyzed. These tasks are solved using the binary input and binary output discrete-time cellular neural networks (DTCNNs) associated with suitable templates. Furthermore, the behavior of the DTCNNs can be realized using Boolean functions, and the corresponding equivalent logic circuits are derived. An 8 x 8 DTCNNs-based image-processing chip is implemented by the FPGA technology. A simulation of the chip developed for the CCD task is also presented

  19. Initial Object Segmentation for Video Object Plane GenerationUsing Cellular Neural Networks

    Institute of Scientific and Technical Information of China (English)

    王慧; 杨高波; 张兆杨

    2003-01-01

    MPEG-4 is a basic tool for interactivity and manipulation of video sequences. Video object segmentation is a key issue in defining the content of any video sequence, which is often divided into two steps: initial object segmentation and object tracking. In this paper, an initial object segmentation method for video object plane(VOP) generation using color information is proposed. Based on 3 by 3 linear templates, a cellular neural network (CNN) is used to implemented object segmentation. The Experimental results arepresented to verify the efficiency and robustness of this approach.

  20. Functional recognition imaging using artificial neural networks: applications to rapid cellular identification via broadband electromechanical response

    Energy Technology Data Exchange (ETDEWEB)

    Nikiforov, M P; Guo, S; Kalinin, S V; Jesse, S [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN 37831 (United States); Reukov, V V; Thompson, G L; Vertegel, A A, E-mail: sergei2@ornl.go [Department of Bioengineering, Clemson University, Clemson, SC 29634 (United States)

    2009-10-07

    Functional recognition imaging in scanning probe microscopy (SPM) using artificial neural network identification is demonstrated. This approach utilizes statistical analysis of complex SPM responses at a single spatial location to identify the target behavior, which is reminiscent of associative thinking in the human brain, obviating the need for analytical models. We demonstrate, as an example of recognition imaging, rapid identification of cellular organisms using the difference in electromechanical activity over a broad frequency range. Single-pixel identification of model Micrococcus lysodeikticus and Pseudomonas fluorescens bacteria is achieved, demonstrating the viability of the method.

  1. New color image encryption algorithm based on compound chaos mapping and hyperchaotic cellular neural network

    Science.gov (United States)

    Li, Jinqing; Bai, Fengming; Di, Xiaoqiang

    2013-01-01

    We propose an image encryption/decryption algorithm based on chaotic control parameter and hyperchaotic system with the composite permutation-diffusion structure. Compound chaos mapping is used to generate control parameters in the permutation stage. The high correlation between pixels is shuffled. In the diffusion stage, compound chaos mapping of different initial condition and control parameter generates the diffusion parameters, which are applied to hyperchaotic cellular neural networks. The diffusion key stream is obtained by this process and implements the pixels' diffusion. Compared with the existing methods, both simulation and statistical analysis of our proposed algorithm show that the algorithm has a good performance against attacks and meets the corresponding security level.

  2. Robust tracking by cellular automata and neural networks with nonlocal weights

    Science.gov (United States)

    Ososkov, Gennadii A.

    1995-04-01

    A modified rotor model of the Hopfield neural networks (HNN) is proposed for finding tracks in multiwire proportional chambers. That requires us to apply both raw data prefiltering by cellular automaton and HNN weights furnishing by a special robust multiplier. Then this model is developed to be applicable for a more general type of data and detectors. As an example, data processing of ionospheric measurements are considered. For handling tracks detected by high pressure drift chambers with their up-down ambiguity a modification of deformable templates method is proposed. A new concept of controlled HNN is proposed for solving the so-called track-match problem.

  3. Entire solutions of nonlinear cellular neural networks with distributed time delays

    International Nuclear Information System (INIS)

    The aim of this work is to study the existence of entire solutions of nonlinear cellular neural networks with distributed time delays (DCNN). The entire solutions are defined in the whole space and for all time t ∈ R. From Yu et al (2011 J. Diff. Eqns 251 630–50), we know that the DCNN model admits travelling front solutions. Combining the travelling front solutions with different wave speeds and a spatially independent solution of the DCNN model, we establish some new entire solutions to describe the interactions of travelling fronts. Various qualitative features of the entire solutions are also investigated in this work. (paper)

  4. New Results on Almost Periodic Solution of Shunting Inhibitory Cellular Neural Networks with Continuously Distributed Delays

    Institute of Scientific and Technical Information of China (English)

    Jing Liu; Pei-Yong Zhu

    2008-01-01

    In this paper, the existence, uniqueness and global attractivity are discussed on almost periodic solution of SICNNs (shunting inhibitory cellular neural networks) with continuously distributed delays. By using the fixed point theorem, differential inequality technique and Lyapunov functional method, giving the new ranges of parameters, several sufficient conditions are obtained to ensure the existence, uniqueness and global attractivity of almost periodic solution. Compared with the previous studies, our methods are more effective for almost periodic solution analysis of SICNNs with continuously distributed delays. Some existing results have been improved and extended. In order to show the effectiveness of the obtained results, an example is given in this paper.

  5. Noise-robust realization of Turing-complete cellular automata by using neural networks with pattern representation

    Science.gov (United States)

    Oku, Makito; Aihara, Kazuyuki

    2010-11-01

    A modularly-structured neural network model is considered. Each module, which we call a ‘cell’, consists of two parts: a Hopfield neural network model and a multilayered perceptron. An array of such cells is used to simulate the Rule 110 cellular automaton with high accuracy even when all the units of neural networks are replaced by stochastic binary ones. We also find that noise not only degrades but also facilitates computation if the outputs of multilayered perceptrons are below the threshold required to update the states of the cells, which is a stochastic resonance in computation.

  6. Stability analysis of switched cellular neural networks: A mode-dependent average dwell time approach.

    Science.gov (United States)

    Huang, Chuangxia; Cao, Jie; Cao, Jinde

    2016-10-01

    This paper addresses the exponential stability of switched cellular neural networks by using the mode-dependent average dwell time (MDADT) approach. This method is quite different from the traditional average dwell time (ADT) method in permitting each subsystem to have its own average dwell time. Detailed investigations have been carried out for two cases. One is that all subsystems are stable and the other is that stable subsystems coexist with unstable subsystems. By employing Lyapunov functionals, linear matrix inequalities (LMIs), Jessen-type inequality, Wirtinger-based inequality, reciprocally convex approach, we derived some novel and less conservative conditions on exponential stability of the networks. Comparing to ADT, the proposed MDADT show that the minimal dwell time of each subsystem is smaller and the switched system stabilizes faster. The obtained results extend and improve some existing ones. Moreover, the validness and effectiveness of these results are demonstrated through numerical simulations.

  7. Modeling of Trophospheric Ozone Concentrations Using Genetically Trained Multi-Level Cellular Neural Networks

    Institute of Scientific and Technical Information of China (English)

    H. Kurtulus OZCAN; Erdem BILGILI; Ulku SAHIN; O. Nuri UCAN; Cuma BAYAT

    2007-01-01

    Tropospheric ozone concentrations, which are an important air pollutant, are modeled by the use of an artificial intelligence structure. Data obtained from air pollution measurement stations in the city of Istanbul are utilized in constituting the model. A supervised algorithm for the evaluation of ozone concentration using a genetically trained multi-level cellular neural network (ML-CNN) is introduced, developed, and applied to real data. A genetic algorithm is used in the optimization of CNN templates. The model results and the actual measurement results are compared and statistically evaluated. It is observed that seasonal changes in ozone concentrations are reflected effectively by the concentrations estimated by the multilevel-CNN model structure, with a correlation value of 0.57 ascertained between actual and model results. It is shown that the multilevel-CNN modeling technique is as satisfactory as other modeling techniques in associating the data in a complex medium in air pollution applications.

  8. Global Detection of Live Virtual Machine Migration Based on Cellular Neural Networks

    Directory of Open Access Journals (Sweden)

    Kang Xie

    2014-01-01

    Full Text Available In order to meet the demands of operation monitoring of large scale, autoscaling, and heterogeneous virtual resources in the existing cloud computing, a new method of live virtual machine (VM migration detection algorithm based on the cellular neural networks (CNNs, is presented. Through analyzing the detection process, the parameter relationship of CNN is mapped as an optimization problem, in which improved particle swarm optimization algorithm based on bubble sort is used to solve the problem. Experimental results demonstrate that the proposed method can display the VM migration processing intuitively. Compared with the best fit heuristic algorithm, this approach reduces the processing time, and emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI implementation allowing the VM migration detection to be performed better.

  9. Modeling of trophospheric ozone concentrations using genetically trained multi-level cellular neural networks

    Science.gov (United States)

    Ozcan, H. Kurtulus; Bilgili, Erdem; Sahin, Ulku; Ucan, O. Nuri; Bayat, Cuma

    2007-09-01

    Tropospheric ozone concentrations, which are an important air pollutant, are modeled by the use of an artificial intelligence structure. Data obtained from air pollution measurement stations in the city of Istanbul are utilized in constituting the model. A supervised algorithm for the evaluation of ozone concentration using a genetically trained multi-level cellular neural network (ML-CNN) is introduced, developed, and applied to real data. A genetic algorithm is used in the optimization of CNN templates. The model results and the actual measurement results are compared and statistically evaluated. It is observed that seasonal changes in ozone concentrations are reflected effectively by the concentrations estimated by the multilevel-CNN model structure, with a correlation value of 0.57 ascertained between actual and model results. It is shown that the multilevel-CNN modeling technique is as satisfactory as other modeling techniques in associating the data in a complex medium in air pollution applications.

  10. Convergence and attractivity of memristor-based cellular neural networks with time delays.

    Science.gov (United States)

    Qin, Sitian; Wang, Jun; Xue, Xiaoping

    2015-03-01

    This paper presents theoretical results on the convergence and attractivity of memristor-based cellular neural networks (MCNNs) with time delays. Based on a realistic memristor model, an MCNN is modeled using a differential inclusion. The essential boundedness of its global solutions is proven. The state of MCNNs is further proven to be convergent to a critical-point set located in saturated region of the activation function, when the initial state locates in a saturated region. It is shown that the state convergence time period is finite and can be quantitatively estimated using given parameters. Furthermore, the positive invariance and attractivity of state in non-saturated regions are also proven. The simulation results of several numerical examples are provided to substantiate the results. PMID:25562569

  11. A novel memristive cellular neural network with time-variant templates

    Directory of Open Access Journals (Sweden)

    Xiaofang Hu

    2016-03-01

    Full Text Available A cellular neural network (CNN is a massively parallel analog array processor capable of solving various complex processing problems by using specific templates that characterize the synaptic connections. The hardware implementation and applications of CNN have attracted a great deal of attention. Recently, memristors with nanometer-scale and variable gradual conductance have been exploited to make compact and programmable electric synapses. This paper proposes and studies a novel memristive CNN (Mt-CNN with time-variant templates realized by memristor crossbar synaptic circuits. The template parameters are estimated analytically. The Mt-CNN provides a promising solution to hardware realization of real-time template updating processes, which can be used to effectively deal with various complicated problems of cascaded processing. Its effectiveness and advantages are demonstrated by practical examples of edge detection on noisy images.

  12. Periodic solution and chaotic strange attractor for shunting inhibitory cellular neural networks with impulses

    International Nuclear Information System (INIS)

    By using the continuation theorem of coincidence degree theory and constructing suitable Lyapunov functions, we study the existence, uniqueness, and global exponential stability of periodic solution for shunting inhibitory cellular neural networks with impulses, dxij/dt=-aijxij-ΣCkl(set-membershipsign)Nr(i,j)Cijklfij[xkl(t)]xij+Lij(t), t>0,t≠tk; Δxij(tk)=xij(tk+)-xij(tk-)=Ik[xij(tk)], k=1,2,... . Furthermore, the numerical simulation shows that our system can occur in many forms of complexities, including periodic oscillation and chaotic strange attractor. To the best of our knowledge, these results have been obtained for the first time. Some researchers have introduced impulses into their models, but analogous results have never been found.

  13. An Asynchronous Recurrent Network of Cellular Automaton-Based Neurons and Its Reproduction of Spiking Neural Network Activities.

    Science.gov (United States)

    Matsubara, Takashi; Torikai, Hiroyuki

    2016-04-01

    Modeling and implementation approaches for the reproduction of input-output relationships in biological nervous tissues contribute to the development of engineering and clinical applications. However, because of high nonlinearity, the traditional modeling and implementation approaches encounter difficulties in terms of generalization ability (i.e., performance when reproducing an unknown data set) and computational resources (i.e., computation time and circuit elements). To overcome these difficulties, asynchronous cellular automaton-based neuron (ACAN) models, which are described as special kinds of cellular automata that can be implemented as small asynchronous sequential logic circuits have been proposed. This paper presents a novel type of such ACAN and a theoretical analysis of its excitability. This paper also presents a novel network of such neurons, which can mimic input-output relationships of biological and nonlinear ordinary differential equation model neural networks. Numerical analyses confirm that the presented network has a higher generalization ability than other major modeling and implementation approaches. In addition, Field-Programmable Gate Array-implementations confirm that the presented network requires lower computational resources.

  14. An Evaluation of Cellular Neural Networks for the Automatic Identification of Cephalometric Landmarks on Digital Images

    Directory of Open Access Journals (Sweden)

    Rosalia Leonardi

    2009-01-01

    Full Text Available Several efforts have been made to completely automate cephalometric analysis by automatic landmark search. However, accuracy obtained was worse than manual identification in every study. The analogue-to-digital conversion of X-ray has been claimed to be the main problem. Therefore the aim of this investigation was to evaluate the accuracy of the Cellular Neural Networks approach for automatic location of cephalometric landmarks on softcopy of direct digital cephalometric X-rays. Forty-one, direct-digital lateral cephalometric radiographs were obtained by a Siemens Orthophos DS Ceph and were used in this study and 10 landmarks (N, A Point, Ba, Po, Pt, B Point, Pg, PM, UIE, LIE were the object of automatic landmark identification. The mean errors and standard deviations from the best estimate of cephalometric points were calculated for each landmark. Differences in the mean errors of automatic and manual landmarking were compared with a 1-way analysis of variance. The analyses indicated that the differences were very small, and they were found at most within 0.59 mm. Furthermore, only few of these differences were statistically significant, but differences were so small to be in most instances clinically meaningless. Therefore the use of X-ray files with respect to scanned X-ray improved landmark accuracy of automatic detection. Investigations on softcopy of digital cephalometric X-rays, to search more landmarks in order to enable a complete automatic cephalometric analysis, are strongly encouraged.

  15. Memristor-based cellular nonlinear/neural network: design, analysis, and applications.

    Science.gov (United States)

    Duan, Shukai; Hu, Xiaofang; Dong, Zhekang; Wang, Lidan; Mazumder, Pinaki

    2015-06-01

    Cellular nonlinear/neural network (CNN) has been recognized as a powerful massively parallel architecture capable of solving complex engineering problems by performing trillions of analog operations per second. The memristor was theoretically predicted in the late seventies, but it garnered nascent research interest due to the recent much-acclaimed discovery of nanocrossbar memories by engineers at the Hewlett-Packard Laboratory. The memristor is expected to be co-integrated with nanoscale CMOS technology to revolutionize conventional von Neumann as well as neuromorphic computing. In this paper, a compact CNN model based on memristors is presented along with its performance analysis and applications. In the new CNN design, the memristor bridge circuit acts as the synaptic circuit element and substitutes the complex multiplication circuit used in traditional CNN architectures. In addition, the negative differential resistance and nonlinear current-voltage characteristics of the memristor have been leveraged to replace the linear resistor in conventional CNNs. The proposed CNN design has several merits, for example, high density, nonvolatility, and programmability of synaptic weights. The proposed memristor-based CNN design operations for implementing several image processing functions are illustrated through simulation and contrasted with conventional CNNs. Monte-Carlo simulation has been used to demonstrate the behavior of the proposed CNN due to the variations in memristor synaptic weights. PMID:25069124

  16. A Proposal for Energy-Efficient Cellular Neural Network Based on Spintronic Devices

    Science.gov (United States)

    Pan, Chenyun; Naeemi, Azad

    2016-09-01

    Due to the massive parallel computing capability and outstanding image and signal processing performance, cellular neural network (CNN) is one promising type of non-Boolean computing system that can outperform the traditional digital logic computation and mitigate the physical scaling limit of the conventional CMOS technology. The CNN was originally implemented by VLSI analog technologies with operational amplifiers and operational transconductance amplifiers as neurons and synapses, respectively, which are power and area consuming. In this paper, we propose a hybrid structure to implement the CNN with magnetic components and CMOS peripherals with a complete driving and sensing circuitry. In addition, we propose a digitally programmable magnetic synapse that can achieve both positive and negative values of the templates. After rigorous performance analyses and comparisons, optimal energy is achieved based on various design parameters, including the driving voltage and the CMOS driving size. At a comparable footprint area and operation speed, a spintronic CNN is projected to achieve more than one order of magnitude energy reduction per operation compared to its CMOS counterpart.

  17. Synchronization of cellular neural networks of neutral type via dynamic feedback controller

    Energy Technology Data Exchange (ETDEWEB)

    Park, Ju H. [Robust Control and Nonlinear Dynamics Laboratory, Department of Electrical Engineering, Yeungnam University, 214-1 Dae-Dong, Kyongsan 712-749 (Korea, Republic of)], E-mail: jessie@ynu.ac.kr

    2009-11-15

    In this paper, we aim to study global synchronization for neural networks with neutral delay. A dynamic feedback control scheme is proposed to achieve the synchronization between drive network and response network. By utilizing the Lyapunov function and linear matrix inequalities (LMIs), we derive simple and efficient criterion in terms of LMIs for synchronization. The feedback controllers can be easily obtained by solving the derived LMIs.

  18. Global Exponential Stability of a Unique Almost Periodic Solution for Neutral-Type Cellular Neural Networks with Distributed Delays

    Directory of Open Access Journals (Sweden)

    Wenquan Wu

    2014-01-01

    Full Text Available This paper is concerned with the problem of the existence, uniqueness, and global exponential stability for neutral-type cellular neural networks with distributed delays. Based on fixed point theory and Lyapunov functional, several sufficient conditions are established for the existence, uniqueness, and global exponential stability of almost periodic solution for the above system. Finally, a simple example is given to illustrate the feasibility and effectiveness of our main results.

  19. Global Exponential Stability of a Unique Almost Periodic Solution for Neutral-Type Cellular Neural Networks with Distributed Delays

    OpenAIRE

    Wenquan Wu

    2014-01-01

    This paper is concerned with the problem of the existence, uniqueness, and global exponential stability for neutral-type cellular neural networks with distributed delays. Based on fixed point theory and Lyapunov functional, several sufficient conditions are established for the existence, uniqueness, and global exponential stability of almost periodic solution for the above system. Finally, a simple example is given to illustrate the feasibility and effectiveness of our main results.

  20. Application of Local Activity Theory of Cellular Neural Network with Two Ports to the Coupled Lorenz-Cell Model

    Institute of Scientific and Technical Information of China (English)

    MIN LeQuan; YU Na

    2002-01-01

    Some criteria for the local activity theory in two-port cellular neural network cells with three local state variables are applied to a coupled Lorenz-cell model. The numerical simulation exhibited that emergence may exist if the selected cell parameters are nearby or on the edge of chaos domain. The local activity theory has provided a new tool of studying the complexity of high dimensional coupled nonlinear physical systems.

  1. 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.

  2. Doubly Periodic Traveling Waves in a Cellular Neural Network with Linear Reaction

    Directory of Open Access Journals (Sweden)

    Lin JianJhong

    2009-01-01

    Full Text Available Szekeley observed that the dynamic pattern of the locomotion of salamanders can be explained by periodic vector sequences generated by logical neural networks. Such sequences can mathematically be described by "doubly periodic traveling waves" and therefore it is of interest to propose dynamic models that may produce such waves. One such dynamic network model is built here based on reaction-diffusion principles and a complete discussion is given for the existence of doubly periodic waves as outputs. Since there are 2 parameters in our model and 4 a priori unknown parameters involved in our search of solutions, our results are nontrivial. The reaction term in our model is a linear function and hence our results can also be interpreted as existence criteria for solutions of a nontrivial linear problem depending on 6 parameters.

  3. Robust Template Decomposition without Weight Restriction for Cellular Neural Networks Implementing Arbitrary Boolean Functions Using Support Vector Classifiers

    Directory of Open Access Journals (Sweden)

    Yih-Lon Lin

    2013-01-01

    Full Text Available If the given Boolean function is linearly separable, a robust uncoupled cellular neural network can be designed as a maximal margin classifier. On the other hand, if the given Boolean function is linearly separable but has a small geometric margin or it is not linearly separable, a popular approach is to find a sequence of robust uncoupled cellular neural networks implementing the given Boolean function. In the past research works using this approach, the control template parameters and thresholds are restricted to assume only a given finite set of integers, and this is certainly unnecessary for the template design. In this study, we try to remove this restriction. Minterm- and maxterm-based decomposition algorithms utilizing the soft margin and maximal margin support vector classifiers are proposed to design a sequence of robust templates implementing an arbitrary Boolean function. Several illustrative examples are simulated to demonstrate the efficiency of the proposed method by comparing our results with those produced by other decomposition methods with restricted weights.

  4. Periodic Solutions for Shunting Inhibitory Cellular Neural Networks of Neutral Type with Time-Varying Delays in the Leakage Term on Time Scales

    OpenAIRE

    Yongkun Li; Lei Wang; Yu Fei

    2014-01-01

    A class of shunting inhibitory cellular neural networks of neutral type with time-varying delays in the leakage term on time scales is proposed. Based on the exponential dichotomy of linear dynamic equations on time scales, fixed point theorems, and calculus on time scales we obtain some sufficient conditions for the existence and global exponential stability of periodic solutions for that class of neural networks. The results of this paper are completely new and complementary to the previous...

  5. Stability Analysis of a Class of Three-Neuron Delayed Cellular Neural Network

    Directory of Open Access Journals (Sweden)

    Poulami D. Gupta

    2010-01-01

    Full Text Available Problem statement: In this study linear stability of a class of three neuron cellular network with transmission delay had been studied. Approach: The model for the problem was first presented. The problem is then formulated analytically and numerical simulations pertaining to the model are carried out. Results: A necessary and sufficient condition for asymptotic stability of trivial steady state in the absence of delay is derived. Then a delay dependent sufficient condition for local asymptotic stability of trivial, steady state and sufficient condition for no stability switching of trivial steady for such a network are derived. Numerical simulation results of the model were presented. Conclusion/Recommendations: From numerical simulation, it appears that there may be a possibility of multiple steady states of the model. It may be possible to investigate the condition for the existence of periodic solutions of the non-linear model analytically.

  6. Neural Network Applications

    NARCIS (Netherlands)

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

    1995-01-01

    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

  7. The characteristics of nonlinear chaotic dynamics in quantum cellular neural networks

    Institute of Scientific and Technical Information of China (English)

    Wang Sen; Cai Li; Kang Qiang; Wu Gang; Li Qin

    2008-01-01

    With the polarization of quantum-dot cell and quantum phase serving as state variables, this paper does both theoretical analysis and simulation for the complex nonlinear dynamical behaviour of a three-cell-coupled Quantum Cel- lular Neural Network (QCNN), including equilibrium points, bifurcation and chaotic behaviour. Different phenomena, such as quasi-periodic, chaotic and hyper-chaotic states as well as bifurcations are revealed. The system's bifurcation and chaotic behaviour under the influence of the different coupling parameters are analysed. And it finds that the unbalanced ceils coupled QCNN is easy to cause chaotic oscillation and the system response enters into chaotic state from quasi-periodic state by quasi-period bifurcation; however, the balanced cells coupled QCNN also can be chaotic when coupling parameters is in some region. Additionally, both the unbalanced and balanced cells coupled QCNNs can possess hyper-chaotic behaviour. It provides valuable information about QCNNs for future application in high-parallel signal processing and novel ultra-small chaotic generators.

  8. A cardiac electrical activity model based on a cellular automata system in comparison with neural network model.

    Science.gov (United States)

    Khan, Muhammad Sadiq Ali; Yousuf, Sidrah

    2016-03-01

    Cardiac Electrical Activity is commonly distributed into three dimensions of Cardiac Tissue (Myocardium) and evolves with duration of time. The indicator of heart diseases can occur randomly at any time of a day. Heart rate, conduction and each electrical activity during cardiac cycle should be monitor non-invasively for the assessment of "Action Potential" (regular) and "Arrhythmia" (irregular) rhythms. Many heart diseases can easily be examined through Automata model like Cellular Automata concepts. This paper deals with the different states of cardiac rhythms using cellular automata with the comparison of neural network also provides fast and highly effective stimulation for the contraction of cardiac muscles on the Atria in the result of genesis of electrical spark or wave. The specific formulated model named as "States of automaton Proposed Model for CEA (Cardiac Electrical Activity)" by using Cellular Automata Methodology is commonly shows the three states of cardiac tissues conduction phenomena (i) Resting (Relax and Excitable state), (ii) ARP (Excited but Absolutely refractory Phase i.e. Excited but not able to excite neighboring cells) (iii) RRP (Excited but Relatively Refractory Phase i.e. Excited and able to excite neighboring cells). The result indicates most efficient modeling with few burden of computation and it is Action Potential during the pumping of blood in cardiac cycle. PMID:27087101

  9. Periodic Solutions for Shunting Inhibitory Cellular Neural Networks of Neutral Type with Time-Varying Delays in the Leakage Term on Time Scales

    Directory of Open Access Journals (Sweden)

    Yongkun Li

    2014-01-01

    Full Text Available A class of shunting inhibitory cellular neural networks of neutral type with time-varying delays in the leakage term on time scales is proposed. Based on the exponential dichotomy of linear dynamic equations on time scales, fixed point theorems, and calculus on time scales we obtain some sufficient conditions for the existence and global exponential stability of periodic solutions for that class of neural networks. The results of this paper are completely new and complementary to the previously known results even if the time scale =ℝ or ℤ. Moreover, we present illustrative numerical examples to show the feasibility of our results.

  10. Heterogeneous cellular networks

    CERN Document Server

    Hu, Rose Qingyang

    2013-01-01

    A timely publication providing coverage of radio resource management, mobility management and standardization in heterogeneous cellular networks The topic of heterogeneous cellular networks has gained momentum in industry and the research community, attracting the attention of standardization bodies such as 3GPP LTE and IEEE 802.16j, whose objectives are looking into increasing the capacity and coverage of the cellular networks. This book focuses on recent progresses,  covering the related topics including scenarios of heterogeneous network deployment, interference management i

  11. Holographic neural networks

    OpenAIRE

    Manger, R

    1998-01-01

    Holographic neural networks are a new and promising type of artificial neural networks. This article gives an overview of the holographic neural technology and its possibilities. The theoretical principles of holographic networks are first reviewed. Then, some other papers are presented, where holographic networks have been applied or experimentally evaluated. A case study dealing with currency exchange rate prediction is described in more detail.

  12. A 181 GOPS AKAZE Accelerator Employing Discrete-Time Cellular Neural Networks for Real-Time Feature Extraction.

    Science.gov (United States)

    Jiang, Guangli; Liu, Leibo; Zhu, Wenping; Yin, Shouyi; Wei, Shaojun

    2015-01-01

    This paper proposes a real-time feature extraction VLSI architecture for high-resolution images based on the accelerated KAZE algorithm. Firstly, a new system architecture is proposed. It increases the system throughput, provides flexibility in image resolution, and offers trade-offs between speed and scaling robustness. The architecture consists of a two-dimensional pipeline array that fully utilizes computational similarities in octaves. Secondly, a substructure (block-serial discrete-time cellular neural network) that can realize a nonlinear filter is proposed. This structure decreases the memory demand through the removal of data dependency. Thirdly, a hardware-friendly descriptor is introduced in order to overcome the hardware design bottleneck through the polar sample pattern; a simplified method to realize rotation invariance is also presented. Finally, the proposed architecture is designed in TSMC 65 nm CMOS technology. The experimental results show a performance of 127 fps in full HD resolution at 200 MHz frequency. The peak performance reaches 181 GOPS and the throughput is double the speed of other state-of-the-art architectures. PMID:26404305

  13. 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.

  14. Mapping the spatiotemporal dynamics of calcium signaling in cellular neural networks using optical flow

    CERN Document Server

    Buibas, Marius; Nizar, Krystal; Silva, Gabriel A

    2009-01-01

    An optical flow gradient algorithm was applied to spontaneously forming networks of neurons and glia in culture imaged by fluorescence optical microscopy in order to map functional calcium signaling with single pixel resolution. Optical flow estimates the direction and speed of motion of objects in an image between subsequent frames in a recorded digital sequence of images (i.e. a movie). Computed vector field outputs by the algorithm were able to track the spatiotemporal dynamics of calcium signaling patterns. We begin by briefly reviewing the mathematics of the optical flow algorithm, describe how to solve for the displacement vectors, and how to measure their reliability. We then compare computed flow vectors with manually estimated vectors for the progression of a calcium signal recorded from representative astrocyte cultures. Finally, we applied the algorithm to preparations of primary astrocytes and hippocampal neurons and to the rMC-1 Muller glial cell line in order to illustrate the capability of the ...

  15. Global Exponential Stability of Almost Periodic Solution for Neutral-Type Cohen-Grossberg Shunting Inhibitory Cellular Neural Networks with Distributed Delays and Impulses

    OpenAIRE

    Lijun Xu; Qi Jiang; Guodong Gu

    2016-01-01

    A kind of neutral-type Cohen-Grossberg shunting inhibitory cellular neural networks with distributed delays and impulses is considered. Firstly, by using the theory of impulsive differential equations and the contracting mapping principle, the existence and uniqueness of the almost periodic solution for the above system are obtained. Secondly, by constructing a suitable Lyapunov functional, the global exponential stability of the unique almost periodic solution is also investigated. The work ...

  16. Nanostructured cellular networks.

    Science.gov (United States)

    Moriarty, P; Taylor, M D R; Brust, M

    2002-12-01

    Au nanocrystals spin-coated onto silicon from toluene form cellular networks. A quantitative statistical crystallography analysis shows that intercellular correlations drive the networks far from statistical equilibrium. Spin-coating from hexane does not produce cellular structure, yet a strong correlation is retained in the positions of nanocrystal aggregates. Mechanisms based on Marangoni convection alone cannot account for the variety of patterns observed, and we argue that spinodal decomposition plays an important role in foam formation.

  17. Modeling land use and land cover changes in a vulnerable coastal region using artificial neural networks and cellular automata.

    Science.gov (United States)

    Qiang, Yi; Lam, Nina S N

    2015-03-01

    As one of the most vulnerable coasts in the continental USA, the Lower Mississippi River Basin (LMRB) region has endured numerous hazards over the past decades. The sustainability of this region has drawn great attention from the international, national, and local communities, wanting to understand how the region as a system develops under intense interplay between the natural and human factors. A major problem in this deltaic region is significant land loss over the years due to a combination of natural and human factors. The main scientific and management questions are what factors contribute to the land use land cover (LULC) changes in this region, can we model the changes, and how would the LULC look like in the future given the current factors? This study analyzed the LULC changes of the region between 1996 and 2006 by utilizing an artificial neural network (ANN) to derive the LULC change rules from 15 human and natural variables. The rules were then used to simulate future scenarios in a cellular automation model. A stochastic element was added in the model to represent factors that were not included in the current model. The analysis was conducted for two sub-regions in the study area for comparison. The results show that the derived ANN models could simulate the LULC changes with a high degree of accuracy (above 92 % on average). A total loss of 263 km(2) in wetlands from 2006 to 2016 was projected, whereas the trend of forest loss will cease. These scenarios provide useful information to decision makers for better planning and management of the region.

  18. Chaotic diagonal recurrent neural network

    Institute of Scientific and Technical Information of China (English)

    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 andlearning 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.

  19. Environment Aware Cellular Networks

    KAUST Repository

    Ghazzai, Hakim

    2015-02-01

    The unprecedented rise of mobile user demand over the years have led to an enormous growth of the energy consumption of wireless networks as well as the greenhouse gas emissions which are estimated currently to be around 70 million tons per year. This significant growth of energy consumption impels network companies to pay huge bills which represent around half of their operating expenditures. Therefore, many service providers, including mobile operators, are looking for new and modern green solutions to help reduce their expenses as well as the level of their CO2 emissions. Base stations are the most power greedy element in cellular networks: they drain around 80% of the total network energy consumption even during low traffic periods. Thus, there is a growing need to develop more energy-efficient techniques to enhance the green performance of future 4G/5G cellular networks. Due to the problem of traffic load fluctuations in cellular networks during different periods of the day and between different areas (shopping or business districts and residential areas), the base station sleeping strategy has been one of the main popular research topics in green communications. In this presentation, we present several practical green techniques that provide significant gains for mobile operators. Indeed, combined with the base station sleeping strategy, these techniques achieve not only a minimization of the fossil fuel consumption but also an enhancement of mobile operator profits. We start with an optimized cell planning method that considers varying spatial and temporal user densities. We then use the optimal transport theory in order to define the cell boundaries such that the network total transmit power is reduced. Afterwards, we exploit the features of the modern electrical grid, the smart grid, as a new tool of power management for cellular networks and we optimize the energy procurement from multiple energy retailers characterized by different prices and pollutant

  20. Global Exponential Stability of Almost Periodic Solution for Neutral-Type Cohen-Grossberg Shunting Inhibitory Cellular Neural Networks with Distributed Delays and Impulses

    Directory of Open Access Journals (Sweden)

    Lijun Xu

    2016-01-01

    Full Text Available A kind of neutral-type Cohen-Grossberg shunting inhibitory cellular neural networks with distributed delays and impulses is considered. Firstly, by using the theory of impulsive differential equations and the contracting mapping principle, the existence and uniqueness of the almost periodic solution for the above system are obtained. Secondly, by constructing a suitable Lyapunov functional, the global exponential stability of the unique almost periodic solution is also investigated. The work in this paper improves and extends some results in recent years. As an application, an example and numerical simulations are presented to demonstrate the feasibility and effectiveness of the main results.

  1. Global Exponential Stability of Almost Periodic Solution for Neutral-Type Cohen-Grossberg Shunting Inhibitory Cellular Neural Networks with Distributed Delays and Impulses

    Science.gov (United States)

    Xu, Lijun; Jiang, Qi; Gu, Guodong

    2016-01-01

    A kind of neutral-type Cohen-Grossberg shunting inhibitory cellular neural networks with distributed delays and impulses is considered. Firstly, by using the theory of impulsive differential equations and the contracting mapping principle, the existence and uniqueness of the almost periodic solution for the above system are obtained. Secondly, by constructing a suitable Lyapunov functional, the global exponential stability of the unique almost periodic solution is also investigated. The work in this paper improves and extends some results in recent years. As an application, an example and numerical simulations are presented to demonstrate the feasibility and effectiveness of the main results. PMID:27190502

  2. 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

  3. 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...

  4. 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.

  5. 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....

  6. Critical Branching Neural Networks

    Science.gov (United States)

    Kello, Christopher T.

    2013-01-01

    It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…

  7. The Future of Neural Networks

    OpenAIRE

    Lakra, Sachin; T. V. Prasad; G. Ramakrishna

    2012-01-01

    The paper describes some recent developments in neural networks and discusses the applicability of neural networks in the development of a machine that mimics the human brain. The paper mentions a new architecture, the pulsed neural network that is being considered as the next generation of neural networks. The paper also explores the use of memristors in the development of a brain-like computer called the MoNETA. A new model, multi/infinite dimensional neural networks, are a recent developme...

  8. Neural Networks in Data Mining

    OpenAIRE

    Priyanka Gaur

    2012-01-01

    The application of neural networks in the data mining is very wide. Although neural networks may have complex structure, long training time, and uneasily understandable representation of results, neural networks have high acceptance ability for noisy data and high accuracy and are preferable in data mining. In this paper the data mining based on neural networks is researched in detail, and the key technology and ways to achieve the data mining based on neural networks are also researched.

  9. Neural networks and graph theory

    Institute of Scientific and Technical Information of China (English)

    许进; 保铮

    2002-01-01

    The relationships between artificial neural networks and graph theory are considered in detail. The applications of artificial neural networks to many difficult problems of graph theory, especially NP-complete problems, and the applications of graph theory to artificial neural networks are discussed. For example graph theory is used to study the pattern classification problem on the discrete type feedforward neural networks, and the stability analysis of feedback artificial neural networks etc.

  10. Introduction to neural networks

    International Nuclear Information System (INIS)

    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

  11. Stochastic asymptotical synchronization of chaotic Markovian jumping fuzzy cellular neural networks with mixed delays and the Wiener process based on sampled-data control

    Institute of Scientific and Technical Information of China (English)

    M.Kalpana; P.Balasubramaniam

    2013-01-01

    We investigate the stochastic asymptotical synchronization of chaotic Markovian jumping fuzzy cellular neural networks (MJFCNNs) with discrete,unbounded distributed delays,and the Wiener process based on sampled-data control using the linear matrix inequality (LMI) approach.The Lyapunov-Krasovskii functional combined with the input delay approach as well as the free-weighting matrix approach is employed to derive several sufficient criteria in terms of LMIs to ensure that the delayed MJFCNNs with the Wiener process is stochastic asymptotical synchronous.Restrictions (e.g.,time derivative is smaller than one) are removed to obtain a proposed sampled-data controller.Finally,a numerical example is provided to demonstrate the reliability of the derived results.

  12. Multiuser Cellular Network

    CERN Document Server

    Bao, Yi; Chen, Ming

    2011-01-01

    Modern radio communication is faced with a problem about how to distribute restricted frequency to users in a certain space. Since our task is to minimize the number of repeaters, a natural idea is enlarging coverage area. However, coverage has restrictions. First, service area has to be divided economically as repeater's coverage is limited. In this paper, our fundamental method is to adopt seamless cellular network division. Second, underlying physics content in frequency distribution problem is interference between two close frequencies. Consequently, we choose a proper frequency width of 0.1MHz and a relevantly reliable setting to apply one frequency several times. We make a few general assumptions to simplify real situation. For instance, immobile users yield to homogenous distribution; repeaters can receive and transmit information in any given frequency in duplex operation; coverage is mainly decided by antenna height. Two models are built up to solve 1000 users and 10000 users situations respectively....

  13. Study of bridge crack diagnosis based on cellular neural network%基于细胞神经网络的桥梁裂痕诊断研究

    Institute of Scientific and Technical Information of China (English)

    张福新; 李国东

    2014-01-01

    In order to detecting the bridge crack, we come up with a fixed way of bridge rift image detection by using cellular neural networks. By image processing, building rift networks and details networks and adding the model of similarity rift networks. It can avoid the problem that can not accurately detect crack by only taking the crack feature value. The experiment proved that fixed crack detect computing is easy to do, more accurate to detect the cracks on the road and can reach the standard level of current detect technique.%为了更好的监测桥梁裂痕,文章提出了一种改进的细胞神经网络桥梁裂痕图像识别方法。该方法通过一定的图像处理,建立裂痕网络和细节网络,同时增加了裂痕相似网络模型,避免了仅对裂痕特征提取信息不能准确识别裂痕的问题。实验证明,改进的裂痕识别算法实现简单,识别桥梁裂痕准确率高,达到了实时识别技术的要求。

  14. Neural networks in seismic discrimination

    Energy Technology Data Exchange (ETDEWEB)

    Dowla, F.U.

    1995-01-01

    Neural networks are powerful and elegant computational tools that can be used in the analysis of geophysical signals. At Lawrence Livermore National Laboratory, we have developed neural networks to solve problems in seismic discrimination, event classification, and seismic and hydrodynamic yield estimation. Other researchers have used neural networks for seismic phase identification. We are currently developing neural networks to estimate depths of seismic events using regional seismograms. In this paper different types of network architecture and representation techniques are discussed. We address the important problem of designing neural networks with good generalization capabilities. Examples of neural networks for treaty verification applications are also described.

  15. MIMO Communication for Cellular Networks

    CERN Document Server

    Huang, Howard; Venkatesan, Sivarama

    2012-01-01

    As the theoretical foundations of multiple-antenna techniques evolve and as these multiple-input multiple-output (MIMO) techniques become essential for providing high data rates in wireless systems, there is a growing need to understand the performance limits of MIMO in practical networks. To address this need, MIMO Communication for Cellular Networks presents a systematic description of MIMO technology classes and a framework for MIMO system design that takes into account the essential physical-layer features of practical cellular networks. In contrast to works that focus on the theoretical performance of abstract MIMO channels, MIMO Communication for Cellular Networks emphasizes the practical performance of realistic MIMO systems. A unified set of system simulation results highlights relative performance gains of different MIMO techniques and provides insights into how best to use multiple antennas in cellular networks under various conditions. MIMO Communication for Cellular Networks describes single-user,...

  16. Rule Extraction:Using Neural Networks or for Neural Networks?

    Institute of Scientific and Technical Information of China (English)

    Zhi-Hua Zhou

    2004-01-01

    In the research of rule extraction from neural networks, fidelity describes how well the rules mimic the behavior of a neural network while accuracy describes how well the rules can be generalized. This paper identifies the fidelity-accuracy dilemma. It argues to distinguish rule extraction using neural networks and rule extraction for neural networks according to their different goals, where fidelity and accuracy should be excluded from the rule quality evaluation framework, respectively.

  17. 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....

  18. Electronic Neural Networks

    Science.gov (United States)

    Lambe, John; Moopen, Alexander; Thakoor, Anilkumar P.

    1988-01-01

    Memory based on neural network models content-addressable and fault-tolerant. System includes electronic equivalent of synaptic network; particular, matrix of programmable binary switching elements over which data distributed. Switches programmed in parallel by outputs of serial-input/parallel-output shift registers. Input and output terminals of bank of high-gain nonlinear amplifiers connected in nonlinear-feedback configuration by switches and by memory-prompting shift registers.

  19. Artificial neural network modelling

    CERN Document Server

    Samarasinghe, Sandhya

    2016-01-01

    This book covers theoretical aspects as well as recent innovative applications of Artificial Neural networks (ANNs) in natural, environmental, biological, social, industrial and automated systems. It presents recent results of ANNs in modelling small, large and complex systems under three categories, namely, 1) Networks, Structure Optimisation, Robustness and Stochasticity 2) Advances in Modelling Biological and Environmental Systems and 3) Advances in Modelling Social and Economic Systems. The book aims at serving undergraduates, postgraduates and researchers in ANN computational modelling. .

  20. Quantum Neural Networks

    CERN Document Server

    Gupta, S; Gupta, Sanjay

    2002-01-01

    This paper initiates the study of quantum computing within the constraints of using a polylogarithmic ($O(\\log^k n), k\\geq 1$) number of qubits and a polylogarithmic number of computation steps. The current research in the literature has focussed on using a polynomial number of qubits. A new mathematical model of computation called \\emph{Quantum Neural Networks (QNNs)} is defined, building on Deutsch's model of quantum computational network. The model introduces a nonlinear and irreversible gate, similar to the speculative operator defined by Abrams and Lloyd. The precise dynamics of this operator are defined and while giving examples in which nonlinear Schr\\"{o}dinger's equations are applied, we speculate on its possible implementation. The many practical problems associated with the current model of quantum computing are alleviated in the new model. It is shown that QNNs of logarithmic size and constant depth have the same computational power as threshold circuits, which are used for modeling neural network...

  1. Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Kapil Nahar

    2012-12-01

    Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems. Ann’s, like people, learn by example.

  2. Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Kapil Nahar

    2012-12-01

    Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information.The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems.Ann’s, like people, learn by example.

  3. Neural networks for triggering

    Energy Technology Data Exchange (ETDEWEB)

    Denby, B. (Fermi National Accelerator Lab., Batavia, IL (USA)); Campbell, M. (Michigan Univ., Ann Arbor, MI (USA)); Bedeschi, F. (Istituto Nazionale di Fisica Nucleare, Pisa (Italy)); Chriss, N.; Bowers, C. (Chicago Univ., IL (USA)); Nesti, F. (Scuola Normale Superiore, Pisa (Italy))

    1990-01-01

    Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab.

  4. Space-Time Neural Networks

    Science.gov (United States)

    Villarreal, James A.; Shelton, Robert O.

    1992-01-01

    Concept of space-time neural network affords distributed temporal memory enabling such network to model complicated dynamical systems mathematically and to recognize temporally varying spatial patterns. Digital filters replace synaptic-connection weights of conventional back-error-propagation neural network.

  5. 多比例时滞细胞神经网络的全局一致渐近稳定性%Global Uniform Asymptotic Stability of Cellular Neural Networks with Mutli-Porportional Delays

    Institute of Scientific and Technical Information of China (English)

    周立群

    2013-01-01

    对一类具多比例时滞细胞神经网络进行研究,利用变换zi (t)=yi (et ),将具多比例时滞细胞神经网络变换成变系数常时滞的细胞神经网络。通过构造合适的Lyapunov泛函,给出了几个保证该系统全局一致渐近稳定的时滞独立的充分条件,并给出例子验证所得结论的正确性。%A class of cellular neural networks with multi-proportional delays is studied in this paper. The transformation zi (t)=yi (et ) transforms cellular neural networks with multi-proportional delays into cellular neural networks with variable coefficient and constant delays, and then constructing Lyapunov functionals, some delay-independent sufficient conditions are given. These new sufficient conditions can ensure global uniform asymptotic stability of this system. An example is given to illustrate the correctness of obtained results.

  6. via dynamic neural networks

    Directory of Open Access Journals (Sweden)

    J. Reyes-Reyes

    2000-01-01

    Full Text Available In this paper, an adaptive technique is suggested to provide the passivity property for a class of partially known SISO nonlinear systems. A simple Dynamic Neural Network (DNN, containing only two neurons and without any hidden-layers, is used to identify the unknown nonlinear system. By means of a Lyapunov-like analysis the new learning law for this DNN, guarantying both successful identification and passivation effects, is derived. Based on this adaptive DNN model, an adaptive feedback controller, serving for wide class of nonlinear systems with an a priori incomplete model description, is designed. Two typical examples illustrate the effectiveness of the suggested approach.

  7. Interacting neural networks.

    Science.gov (United States)

    Metzler, R; Kinzel, W; Kanter, I

    2000-08-01

    Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random. PMID:11088736

  8. Analysis of neural networks

    CERN Document Server

    Heiden, Uwe

    1980-01-01

    The purpose of this work is a unified and general treatment of activity in neural networks from a mathematical pOint of view. Possible applications of the theory presented are indica­ ted throughout the text. However, they are not explored in de­ tail for two reasons : first, the universal character of n- ral activity in nearly all animals requires some type of a general approach~ secondly, the mathematical perspicuity would suffer if too many experimental details and empirical peculiarities were interspersed among the mathematical investigation. A guide to many applications is supplied by the references concerning a variety of specific issues. Of course the theory does not aim at covering all individual problems. Moreover there are other approaches to neural network theory (see e.g. Poggio-Torre, 1978) based on the different lev­ els at which the nervous system may be viewed. The theory is a deterministic one reflecting the average be­ havior of neurons or neuron pools. In this respect the essay is writt...

  9. 忆阻细胞神经网络及图像去噪和边缘提取中的应用%On Memristive Cellular Neural Network and Its Applications in Noise Removal and Edge Extraction

    Institute of Scientific and Technical Information of China (English)

    高士咏; 段书凯; 王丽丹

    2011-01-01

    结合忆阻器的记忆特征和细胞神经网络高效并行处理能力,将忆阻器作为可编程连接权值,提出了一种具有忆阻器特性的细胞神经网络.计算机仿真验证了提出的忆阻细胞神经网络用于图像去噪和边缘提取的有效性.%The 4th fundamental circuit element-memristor has received significant attention since a real device was recently demonstrated for the first time.The study on memristors will bring about a revolution in circuit theory and even a change in our lifestyle.The hybrid of the CNN(cellular neural network) scheme and the memristor will greatly expand the applications of the memristor.In this paper,we consider using memristors to implement the neighborhood connections of a CNN base on the memory characteristics of memristors and cellular neural network,which is parallel and highly efficient in data processing.This proposed scheme is a special cellular neural network with the property of the memristor.A series of computer simulations have verified the effectiveness of the proposed scheme in noise removal and edge extraction.

  10. 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....

  11. Artificial neural networks in NDT

    International Nuclear Information System (INIS)

    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)

  12. Neural networks in astronomy.

    Science.gov (United States)

    Tagliaferri, Roberto; Longo, Giuseppe; Milano, Leopoldo; Acernese, Fausto; Barone, Fabrizio; Ciaramella, Angelo; De Rosa, Rosario; Donalek, Ciro; Eleuteri, Antonio; Raiconi, Giancarlo; Sessa, Salvatore; Staiano, Antonino; Volpicelli, Alfredo

    2003-01-01

    In the last decade, the use of neural networks (NN) and of other soft computing methods has begun to spread also in the astronomical community which, due to the required accuracy of the measurements, is usually reluctant to use automatic tools to perform even the most common tasks of data reduction and data mining. The federation of heterogeneous large astronomical databases which is foreseen in the framework of the astrophysical virtual observatory and national virtual observatory projects, is, however, posing unprecedented data mining and visualization problems which will find a rather natural and user friendly answer in artificial intelligence tools based on NNs, fuzzy sets or genetic algorithms. This review is aimed to both astronomers (who often have little knowledge of the methodological background) and computer scientists (who often know little about potentially interesting applications), and therefore will be structured as follows: after giving a short introduction to the subject, we shall summarize the methodological background and focus our attention on some of the most interesting fields of application, namely: object extraction and classification, time series analysis, noise identification, and data mining. Most of the original work described in the paper has been performed in the framework of the AstroNeural collaboration (Napoli-Salerno).

  13. 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...

  14. Medical diagnosis using neural network

    CERN Document Server

    Kamruzzaman, S M; Siddiquee, Abu Bakar; Mazumder, Md Ehsanul Hoque

    2010-01-01

    This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. This paper describes a modified feedforward neural network constructive algorithm (MFNNCA), a new algorithm for medical diagnosis. The new constructive algorithm with backpropagation; offer an approach for the incremental construction of near-minimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. The MFNNCA was tested on several benchmarking classification problems including the cancer, heart disease and diabetes. Experimental results show that the MFNNCA can produce optimal neural networ...

  15. New Markov-Shannon Entropy models to assess connectivity quality in complex networks: from molecular to cellular pathway, Parasite-Host, Neural, Industry, and Legal-Social networks.

    Science.gov (United States)

    Riera-Fernández, Pablo; Munteanu, Cristian R; Escobar, Manuel; Prado-Prado, Francisco; Martín-Romalde, Raquel; Pereira, David; Villalba, Karen; Duardo-Sánchez, Aliuska; González-Díaz, Humberto

    2012-01-21

    Graph and Complex Network theory is expanding its application to different levels of matter organization such as molecular, biological, technological, and social networks. A network is a set of items, usually called nodes, with connections between them, which are called links or edges. There are many different experimental and/or theoretical methods to assign node-node links depending on the type of network we want to construct. Unfortunately, the use of a method for experimental reevaluation of the entire network is very expensive in terms of time and resources; thus the development of cheaper theoretical methods is of major importance. In addition, different methods to link nodes in the same type of network are not totally accurate in such a way that they do not always coincide. In this sense, the development of computational methods useful to evaluate connectivity quality in complex networks (a posteriori of network assemble) is a goal of major interest. In this work, we report for the first time a new method to calculate numerical quality scores S(L(ij)) for network links L(ij) (connectivity) based on the Markov-Shannon Entropy indices of order k-th (θ(k)) for network nodes. The algorithm may be summarized as follows: (i) first, the θ(k)(j) values are calculated for all j-th nodes in a complex network already constructed; (ii) A Linear Discriminant Analysis (LDA) is used to seek a linear equation that discriminates connected or linked (L(ij)=1) pairs of nodes experimentally confirmed from non-linked ones (L(ij)=0); (iii) the new model is validated with external series of pairs of nodes; (iv) the equation obtained is used to re-evaluate the connectivity quality of the network, connecting/disconnecting nodes based on the quality scores calculated with the new connectivity function. This method was used to study different types of large networks. The linear models obtained produced the following results in terms of overall accuracy for network reconstruction

  16. New Markov-Shannon Entropy models to assess connectivity quality in complex networks: from molecular to cellular pathway, Parasite-Host, Neural, Industry, and Legal-Social networks.

    Science.gov (United States)

    Riera-Fernández, Pablo; Munteanu, Cristian R; Escobar, Manuel; Prado-Prado, Francisco; Martín-Romalde, Raquel; Pereira, David; Villalba, Karen; Duardo-Sánchez, Aliuska; González-Díaz, Humberto

    2012-01-21

    Graph and Complex Network theory is expanding its application to different levels of matter organization such as molecular, biological, technological, and social networks. A network is a set of items, usually called nodes, with connections between them, which are called links or edges. There are many different experimental and/or theoretical methods to assign node-node links depending on the type of network we want to construct. Unfortunately, the use of a method for experimental reevaluation of the entire network is very expensive in terms of time and resources; thus the development of cheaper theoretical methods is of major importance. In addition, different methods to link nodes in the same type of network are not totally accurate in such a way that they do not always coincide. In this sense, the development of computational methods useful to evaluate connectivity quality in complex networks (a posteriori of network assemble) is a goal of major interest. In this work, we report for the first time a new method to calculate numerical quality scores S(L(ij)) for network links L(ij) (connectivity) based on the Markov-Shannon Entropy indices of order k-th (θ(k)) for network nodes. The algorithm may be summarized as follows: (i) first, the θ(k)(j) values are calculated for all j-th nodes in a complex network already constructed; (ii) A Linear Discriminant Analysis (LDA) is used to seek a linear equation that discriminates connected or linked (L(ij)=1) pairs of nodes experimentally confirmed from non-linked ones (L(ij)=0); (iii) the new model is validated with external series of pairs of nodes; (iv) the equation obtained is used to re-evaluate the connectivity quality of the network, connecting/disconnecting nodes based on the quality scores calculated with the new connectivity function. This method was used to study different types of large networks. The linear models obtained produced the following results in terms of overall accuracy for network reconstruction

  17. Initial Object Segmentation for Video Object Plane Generation Using Cellular Neural Networks%在视频对象平面生成中使用细胞神经网络进行初始对象的分割

    Institute of Scientific and Technical Information of China (English)

    王慧; 杨高波; 张兆扬

    2003-01-01

    MPEG-4 is a basic tool for interactivity and manipulation of video sequences. Video object segmentation is a key issue indefining the content of any video sequence, which is often divided into two steps: initial object segmentation and object tracking. Inthis paper, an initial object segmentation method for video object plane(VOP) generation using color information is proposed. Based on3 by 3 linear templates, a cellular neural network (CNN) is used to implemented object segmentation, The Experimental results arepresented to verify the efficiency and robustness of this approach.

  18. Neural networks and statistical learning

    CERN Document Server

    Du, Ke-Lin

    2014-01-01

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

  19. Neural Networks Of VLSI Components

    Science.gov (United States)

    Eberhardt, Silvio P.

    1991-01-01

    Concept for design of electronic neural network calls for assembly of very-large-scale integrated (VLSI) circuits of few standard types. Each VLSI chip, which contains both analog and digital circuitry, used in modular or "building-block" fashion by interconnecting it in any of variety of ways with other chips. Feedforward neural network in typical situation operates under control of host computer and receives inputs from, and sends outputs to, other equipment.

  20. What are artificial neural networks?

    DEFF Research Database (Denmark)

    Krogh, Anders

    2008-01-01

    Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb......Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb...

  1. Neural Networks for Fingerprint Recognition

    OpenAIRE

    Baldi, Pierre; Chauvin, Yves

    1993-01-01

    After collecting a data base of fingerprint images, we design a neural network algorithm for fingerprint recognition. When presented with a pair of fingerprint images, the algorithm outputs an estimate of the probability that the two images originate from the same finger. In one experiment, the neural network is trained using a few hundred pairs of images and its performance is subsequently tested using several thousand pairs of images originated from a subset of the database corresponding to...

  2. Neural Networks and Photometric Redshifts

    OpenAIRE

    Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo

    2002-01-01

    We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy...

  3. Correlational Neural Networks.

    Science.gov (United States)

    Chandar, Sarath; Khapra, Mitesh M; Larochelle, Hugo; Ravindran, Balaraman

    2016-02-01

    Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)-based approaches and autoencoder (AE)-based approaches. CCA-based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE-based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA-based approaches outperform AE-based approaches for the task of transfer learning, they are not as scalable as the latter. In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than AE and CCA with respect to its ability to learn correlated common representations. We employ CorrNet for several cross-language tasks and show that the representations learned using it perform better than the ones learned using other state-of-the-art approaches. PMID:26654210

  4. Cellular recurrent deep network for image registration

    Science.gov (United States)

    Alam, M.; Vidyaratne, L.; Iftekharuddin, Khan M.

    2015-09-01

    Image registration using Artificial Neural Network (ANN) remains a challenging learning task. Registration can be posed as a two-step problem: parameter estimation and actual alignment/transformation using the estimated parameters. To date ANN based image registration techniques only perform the parameter estimation, while affine equations are used to perform the actual transformation. In this paper, we propose a novel deep ANN based image rigid registration that combines parameter estimation and transformation as a simultaneous learning task. Our previous work shows that a complex universal approximator known as Cellular Simultaneous Recurrent Network (CSRN) can successfully approximate affine transformations with known transformation parameters. This study introduces a deep ANN that combines a feed forward network with a CSRN to perform full rigid registration. Layer wise training is used to pre-train feed forward network for parameter estimation and followed by a CSRN for image transformation respectively. The deep network is then fine-tuned to perform the final registration task. Our result shows that the proposed deep ANN architecture achieves comparable registration accuracy to that of image affine transformation using CSRN with known parameters. We also demonstrate the efficacy of our novel deep architecture by a performance comparison with a deep clustered MLP.

  5. Preliminary Analysis of the efficacy of Artificial neural Network (ANN) and Cellular Automaton (CA) based Land Use Models in Urban Land-Use Planning

    Science.gov (United States)

    Harun, R.

    2013-05-01

    This research provides an opportunity of collaboration between urban planners and modellers by providing a clear theoretical foundations on the two most widely used urban land use models, and assessing the effectiveness of applying the models in urban planning context. Understanding urban land cover change is an essential element for sustainable urban development as it affects ecological functioning in urban ecosystem. Rapid urbanization due to growing inclination of people to settle in urban areas has increased the complexities in predicting that at what shape and size cities will grow. The dynamic changes in the spatial pattern of urban landscapes has exposed the policy makers and environmental scientists to great challenge. But geographic science has grown in symmetry to the advancements in computer science. Models and tools are developed to support urban planning by analyzing the causes and consequences of land use changes and project the future. Of all the different types of land use models available in recent days, it has been found by researchers that the most frequently used models are Cellular Automaton (CA) and Artificial Neural Networks (ANN) models. But studies have demonstrated that the existing land use models have not been able to meet the needs of planners and policy makers. There are two primary causes identified behind this prologue. First, there is inadequate understanding of the fundamental theories and application of the models in urban planning context i.e., there is a gap in communication between modellers and urban planners. Second, the existing models exclude many key drivers in the process of simplification of the complex urban system that guide urban spatial pattern. Thus the models end up being effective in assessing the impacts of certain land use policies, but cannot contribute in new policy formulation. This paper is an attempt to increase the knowledge base of planners on the most frequently used land use model and also assess the

  6. 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...

  7. Phase Transitions of Neural Networks

    OpenAIRE

    Kinzel, Wolfgang

    1997-01-01

    The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This is demonstrated for a few examples: Perceptron, associative memory, learning from examples, generalization, multilayer networks, structure recognition, Bayesian estimate, on-line training, noise estimation and time series generation.

  8. Linear matrix inequality approach to exponential synchronization of a class of chaotic neural networks with time-varying delays

    Institute of Scientific and Technical Information of China (English)

    Wu Wei; Cui Bao-Tong

    2007-01-01

    In this paper, a synchronization scheme for a class of chaotic neural networks with time-varying delays is presented.This class of chaotic neural networks covers several well-known neural network, such a Hopfield neural networks, cellular neural networks, and bidirectional associative memory networks. The obtained criteria are expressed in terms of linear matrix inequalities, thus they can be efficiently verified. A comparison between our results and the previous results shows that our results are less restrictive.

  9. Pattern Recognition Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Santaji Ghorpade

    2010-12-01

    Full Text Available Face Recognition has been identified as one of the attracting research areas and it has drawn the attention of many researchers due to its varying applications such as security systems, medical systems,entertainment, etc. Face recognition is the preferred mode of identification by humans: it is natural,robust and non-intrusive. A wide variety of systems requires reliable personal recognition schemes to either confirm or determine the identity of an individual requesting their services. The purpose of such schemes is to ensure that the rendered services are accessed only by a legitimate user and no one else.Examples of such applications include secure access to buildings, computer systems, laptops, cellular phones, and ATMs. In the absence of robust personal recognition schemes, these systems are vulnerable to the wiles of an impostor.In this paper we have developed and illustrated a recognition system for human faces using a novel Kohonen self-organizing map (SOM or Self-Organizing Feature Map (SOFM based retrieval system.SOM has good feature extracting property due to its topological ordering. The Facial Analytics results for the 400 images of AT&T database reflects that the face recognition rate using one of the neural network algorithm SOM is 85.5% for 40 persons.

  10. Multigradient for Neural Networks for Equalizers

    Directory of Open Access Journals (Sweden)

    Chulhee Lee

    2003-06-01

    Full Text Available Recently, a new training algorithm, multigradient, has been published for neural networks and it is reported that the multigradient outperforms the backpropagation when neural networks are used as a classifier. When neural networks are used as an equalizer in communications, they can be viewed as a classifier. In this paper, we apply the multigradient algorithm to train the neural networks that are used as equalizers. Experiments show that the neural networks trained using the multigradient noticeably outperforms the neural networks trained by the backpropagation.

  11. Video Compression Using Neural Network

    Directory of Open Access Journals (Sweden)

    Sangeeta Mishra

    2012-08-01

    Full Text Available Apart from the existing technology on image compression represented by series of JPEG, MPEG and H.26x standards, new technology such as neural networks and genetic algorithms are being developed to explore the future of image coding. Successful applications of neural networks to basic propagation algorithm have now become well established and other aspects of neural network involvement in this technology. In this paper different algorithms were implemented like gradient descent back propagation, gradient descent with momentum back propagation, gradient descent with adaptive learning back propagation, gradient descent with momentum and adaptive learning back propagation and Levenberg-Marquardt algorithm. The size of original video clip is 25MB and after compression it becomes 21.3MB giving the compression ratio as 85.2% and compression factor of 1.174. It was observed that the size remains same after compression but the difference is in the clarity.

  12. Relations Between Wavelet Network and Feedforward Neural Network

    Institute of Scientific and Technical Information of China (English)

    刘志刚; 何正友; 钱清泉

    2002-01-01

    A comparison of construction forms and base functions is made between feedforward neural network and wavelet network. The relations between them are studied from the constructions of wavelet functions or dilation functions in wavelet network by different activation functions in feedforward neural network. It is concluded that some wavelet function is equal to the linear combination of several neurons in feedforward neural network.

  13. Ocean wave forecasting using recurrent neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Prabaharan, N.

    , merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper describes an artificial neural network, namely recurrent neural network with rprop update algorithm and is applied for wave forecasting. Measured ocean waves off...

  14. Generalization performance of regularized neural network models

    DEFF Research Database (Denmark)

    Larsen, Jan; Hansen, Lars Kai

    1994-01-01

    Architecture optimization is a fundamental problem of neural network modeling. The optimal architecture is defined as the one which minimizes the generalization error. This paper addresses estimation of the generalization performance of regularized, complete neural network models. Regularization...

  15. Neural Networks for Flight Control

    Science.gov (United States)

    Jorgensen, Charles C.

    1996-01-01

    Neural networks are being developed at NASA Ames Research Center to permit real-time adaptive control of time varying nonlinear systems, enhance the fault-tolerance of mission hardware, and permit online system reconfiguration. In general, the problem of controlling time varying nonlinear systems with unknown structures has not been solved. Adaptive neural control techniques show considerable promise and are being applied to technical challenges including automated docking of spacecraft, dynamic balancing of the space station centrifuge, online reconfiguration of damaged aircraft, and reducing cost of new air and spacecraft designs. Our experiences have shown that neural network algorithms solved certain problems that conventional control methods have been unable to effectively address. These include damage mitigation in nonlinear reconfiguration flight control, early performance estimation of new aircraft designs, compensation for damaged planetary mission hardware by using redundant manipulator capability, and space sensor platform stabilization. This presentation explored these developments in the context of neural network control theory. The discussion began with an overview of why neural control has proven attractive for NASA application domains. The more important issues in control system development were then discussed with references to significant technical advances in the literature. Examples of how these methods have been applied were given, followed by projections of emerging application needs and directions.

  16. Neural Network Adaptations to Hardware Implementations

    OpenAIRE

    Moerland, Perry,; Fiesler,Emile

    1997-01-01

    In order to take advantage of the massive parallelism offered by artificial neural networks, hardware implementations are essential.However, most standard neural network models are not very suitable for implementation in hardware and adaptations are needed. In this section an overview is given of the various issues that are encountered when mapping an ideal neural network model onto a compact and reliable neural network hardware implementation, like quantization, handling nonuniformities and ...

  17. Neural Network Adaptations to Hardware Implementations

    OpenAIRE

    Moerland, Perry,; Fiesler,Emile; Beale, R

    1997-01-01

    In order to take advantage of the massive parallelism offered by artificial neural networks, hardware implementations are essential. However, most standard neural network models are not very suitable for implementation in hardware and adaptations are needed. In this section an overview is given of the various issues that are encountered when mapping an ideal neural network model onto a compact and reliable neural network hardware implementation, like quantization, handling nonuniformities and...

  18. Building a Chaotic Proved Neural Network

    CERN Document Server

    Bahi, Jacques M; Salomon, Michel

    2011-01-01

    Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different architectures are trained to exhibit a chaotical behavior.

  19. Neural Network based Consumption Forecasting

    DEFF Research Database (Denmark)

    Madsen, Per Printz

    2016-01-01

    This paper describe a Neural Network based method for consumption forecasting. This work has been financed by the The ENCOURAGE project. The aims of The ENCOURAGE project is to develop embedded intelligence and integration technologies that will directly optimize energy use in buildings and enable...

  20. Artificial neural networks in medicine

    Energy Technology Data Exchange (ETDEWEB)

    Keller, P.E.

    1994-07-01

    This Technology Brief provides an overview of artificial neural networks (ANN). A definition and explanation of an ANN is given and situations in which an ANN is used are described. ANN applications to medicine specifically are then explored and the areas in which it is currently being used are discussed. Included are medical diagnostic aides, biochemical analysis, medical image analysis and drug development.

  1. Medical Imaging with Neural Networks

    International Nuclear Information System (INIS)

    The objective of this paper is to provide an overview of the recent developments in the use of artificial neural networks in medical imaging. The areas of medical imaging that are covered include : ultrasound, magnetic resonance, nuclear medicine and radiological (including computerized tomography). (authors)

  2. Aphasia Classification Using Neural Networks

    DEFF Research Database (Denmark)

    Axer, H.; Jantzen, Jan; Berks, G.;

    2000-01-01

    A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests...

  3. Model Of Neural Network With Creative Dynamics

    Science.gov (United States)

    Zak, Michail; Barhen, Jacob

    1993-01-01

    Paper presents analysis of mathematical model of one-neuron/one-synapse neural network featuring coupled activation and learning dynamics and parametrical periodic excitation. Demonstrates self-programming, partly random behavior of suitable designed neural network; believed to be related to spontaneity and creativity of biological neural networks.

  4. Analysis of Neural Networks through Base Functions

    NARCIS (Netherlands)

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

    2002-01-01

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

  5. 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...

  6. 细胞神经网络在重力异常分异中的研究及应用%Study and application of gravity anomaly separation by cellular neural networks

    Institute of Scientific and Technical Information of China (English)

    李超; 江玉乐; 胡明科; 蒋亚东; 郑成

    2015-01-01

    This article describes the separation of the mining of ore bodies and rock gravity anomalies by the cellular neural network method.First the principle and algorithm of CNN method were elaborated,a pseudo-BP algorithm was used to train the weights of neural network,using the global error function derivative method to derive corrected formula of weights,and how to train the network connection weight based on target gravity anomalies in the particular geological conditions were dis-cussed.Secondly,in order to achieve data format and requirements of the CNN processing,do some pretreatment about the gravity anomaly data.Furthermore,since there is no known gravity data in the region as target output in the network training, so set the corresponding subsurface structure model according to the relevant geological map.The superimposed anomaly and the ore anomaly was forward modeled by the “point element”method,and obtained the targeted connection weights by training the network,to fractionate the region gravity anomaly.The results of application show that the neural network well highlight the high anomaly of the mining area and ore body boundary.As long as the appropriate network connection weights are chosen, lateral stacking anomalies can be separated.So the CNN method can serve to separate out the mining of ore bodies and rock gravity anomalies.%介绍采用细胞神经网络CNN(cellular neural network)方法,对铬铁矿区内的矿体和围岩的重力异常进行分异。首先阐述了CNN方法的原理和算法,采用拟BP学习算法训练网络的权值,用全局误差函数求导方法推导权值的修正公式,讨论了如何根据目标异常训练适合该地质条件的网络的连接权值;其次将重力异常数据预处理,以达到适合 CNN 方法处理的数据格式和要求;最后由于该矿区内没有已知的重力数据作为网络训练的目标输出,根据相关地质图设置相应的地下构造模型。利用“点元

  7. 具分布时滞和脉冲的Cohen-Grossberg SICNNs的概周期解%Almost Periodic Solutions for Cohen-Grossberg Shunting Inhibitory Cellular Neural Networks with Distributed Delays and Impulses

    Institute of Scientific and Technical Information of China (English)

    农秀丽; 杨莉

    2014-01-01

    研究一类具分布时滞和脉冲的Cohen-Grossberg SICNNs模型。利用不动点定理,得到一些保证所考虑模型存在概周期解的充分条件,并举例说明了所得结果的可行性。%In this paper, a class of Cohen-Grossberg Shunting Inhibitory cellular neural net-works with distributed delays and impulses are considered. Some criteria for the exis-tence of nonzero almost period⁃ic solutions are established by Banach fixed point theorem.Moreover, an example is employed to illus⁃trate our feasible results.

  8. Neural Networks and Photometric Redshifts

    CERN Document Server

    Tagliaferri, R; Andreon, S; Capozziello, S; Donalek, C; Giordano, G; Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo

    2002-01-01

    We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy of the results, turned out to be the most effective. In the best experiment, the implemented network reached an accuracy of 0.020 (interquartile error) in the range 0

  9. 基于神经网络模型的双混沌 Hash 函数构造%A Dual Chaotic Hash Function Based on Cellular Neural Network

    Institute of Scientific and Technical Information of China (English)

    刘慧; 赵耿; 白健

    2014-01-01

    高效快速的单向Hash函数是当前安全技术研究的热点。文章采用神经网络结构构造了一种Hash函数,由Logistic映射和Chebyshev映射结合起来的双混沌系统产生该神经网络的参数,将明文信息逐块进行处理,并最终通过异或产生128 bit的Hash值。经实验数据和仿真分析可知:文章提出的方案满足单向Hash函数所要求的混乱和置换特性,并且具有很好的弱碰撞性和初值敏感性;另外,该方案结构简单容易实现。%The Hash function with high speed and efifciency has been a hotspot of security. In this paper, a new Hash function based on cellular neural network was proposed. The parameters of the cellular neural network were produced by a unique system which combined the Logistic map with the Chebyshev map. The function can handle the plaintext by the block, and the ifnal 128 Hash value is the xor of every block’s Hash value. The experimental data and simulated analysis show that the proposed algorithm can satisfy the requirements of a secure hash function, and it has some good properties such as diffusion, confusion, weak collision and sensitivity to initial conditions. What’s more, the construction of the scheme can be achieved easily.

  10. Software-Defined Cellular Mobile Network Solutions

    Institute of Scientific and Technical Information of China (English)

    Jiandong Li; Peng Liu; Hongyan Li

    2014-01-01

    The emergency relating to software-defined networking (SDN), especially in terms of the prototype associated with OpenFlow, pro-vides new possibilities for innovating on network design. Researchers have started to extend SDN to cellular networks. Such new programmable architecture is beneficial to the evolution of mobile networks and allows operators to provide better services. The typical cellular network comprises radio access network (RAN) and core network (CN); hence, the technique roadmap diverges in two ways. In this paper, we investigate SoftRAN, the latest SDN solution for RAN, and SoftCell and MobileFlow, the latest solu-tions for CN. We also define a series of control functions for CROWD. Unlike in the other literature, we emphasize only software-defined cellular network solutions and specifications in order to provide possible research directions.

  11. Photon spectrometry utilizing neural networks

    International Nuclear Information System (INIS)

    Having in mind the time spent on the uneventful work of characterization of the radiation beams used in a ionizing radiation metrology laboratory, the Metrology Service of the Centro Regional de Ciencias Nucleares do Nordeste - CRCN-NE verified the applicability of artificial intelligence (artificial neural networks) to perform the spectrometry in photon fields. For this, was developed a multilayer neural network, as an application for the classification of patterns in energy, associated with a thermoluminescent dosimetric system (TLD-700 and TLD-600). A set of dosimeters was initially exposed to various well known medium energies, between 40 keV and 1.2 MeV, coinciding with the beams determined by ISO 4037 standard, for the dose of 10 mSv in the quantity Hp(10), on a chest phantom (ISO slab phantom) with the purpose of generating a set of training data for the neural network. Subsequently, a new set of dosimeters irradiated in unknown energies was presented to the network with the purpose to test the method. The methodology used in this work was suitable for application in the classification of energy beams, having obtained 100% of the classification performed. (authors)

  12. Cellular mechanisms of posterior neural tube morphogenesis in the zebrafish.

    Science.gov (United States)

    Harrington, Michael J; Chalasani, Kavita; Brewster, Rachel

    2010-03-01

    The zebrafish is a well established model system for studying neural development, yet neurulation remains poorly understood in this organism. In particular, the morphogenetic movements that shape the posterior neural tube (PNT) have not been described. Using tools for imaging neural tissue and tracking the behavior of cells in real time, we provide the first comprehensive analysis of the cellular events shaping the PNT. We observe that this tissue is formed in a stepwise manner, beginning with merging of presumptive neural domains in the tailbud (Stage 1); followed by neural convergence and infolding to shape the neural rod (Stage 2); and continued elongation of the PNT, in absence of further convergence (Stage 3). We further demonstrate that cell proliferation plays only a minimal role in PNT elongation. Overall, these mechanisms resemble those previously described in anterior regions, suggesting that, in contrast to amniotes, neurulation is a fairly uniform process in zebrafish.

  13. Fuzzy logic systems are equivalent to feedforward neural networks

    Institute of Scientific and Technical Information of China (English)

    李洪兴

    2000-01-01

    Fuzzy logic systems and feedforward neural networks are equivalent in essence. First, interpolation representations of fuzzy logic systems are introduced and several important conclusions are given. Then three important kinds of neural networks are defined, i.e. linear neural networks, rectangle wave neural networks and nonlinear neural networks. Then it is proved that nonlinear neural networks can be represented by rectangle wave neural networks. Based on the results mentioned above, the equivalence between fuzzy logic systems and feedforward neural networks is proved, which will be very useful for theoretical research or applications on fuzzy logic systems or neural networks by means of combining fuzzy logic systems with neural networks.

  14. 时滞依赖的变延时细胞神经网络的指数稳定性%Delay-dependent Exponential Stability for Cellular Neural Networks with Time-varying Delays

    Institute of Scientific and Technical Information of China (English)

    梁金玲; 黄霞

    2005-01-01

    Stability analysis of cellular neural networks (CNNs)has been an important topic in the neuralnetwork field since it has great significance for many applications. The qualitative analysis of the neurodynamics has attracted considerable attention thus far[1~7]. In electronic implementation of neural networks,many problems such as switching delays, integration, and communication delays have arisen. In such a case, a delay parameter must be introduced into the system model. Study of neural dynamics with consideration of delays becomes particularly important in manufacturing high quality microelectronic neural networks. Global stability of delayed cellular neural networks (DCNNs) has been extensively studied[1~11]. Sufficient conditions[5,9,12,13] for global stability of DCNNs have been proposed, but the output of the cell is a piecewise linear function and the time-delay is constant. A wider adaptive range without assuming the output of the cell to be piecewise linear function[10,13] is introduced and the time-delay terms of DCNNs are also constant.Based on the Lyapunov stability theorem as well as some facts about the negative definiteness and inequality of matrices, a new sufficient condition is presented for the existence of a unique equilibrium point and its global exponential stability of the delayed CNNs. This condition imposes constraints on the size of the delay parameter. An illustrative example and its numerical simulation is also given to show the effectiveness of our results.%细胞神经网络(CNNs)由于有许多重要的应用价值,所以它的稳定性分析一直是神经网络领域里的一个重要课题.近年来,神经动力系统的定性分析吸引了众多学者的关注[1-7].在神经网络的电子器件实现中,出现了许多问题,诸如:转换延时,积分器,连接延时等.在这种情况下,在系统模型中一定要引进一个延时参数.要制造高质量的微电子神经网络,研究带有延时的神经动

  15. Neural Networks Methodology and Applications

    CERN Document Server

    Dreyfus, Gérard

    2005-01-01

    Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts ands seemlessly edited to present a coherent and comprehensive, yet not redundant, practically-oriented...

  16. Learning with heterogeneous neural networks

    OpenAIRE

    Belanche Muñoz, Luis Antonio

    2011-01-01

    This chapter studies a class of neuron models that computes a user-defined similarity function between inputs and weights. The neuron transfer function is formed by composition of an adapted logistic function with the quasi-linear mean of the partial input-weight similarities. The neuron model is capable of dealing directly with mixtures of continuous as well as discrete quantities, among other data types and there is provision for missing values. An artificial neural network using these n...

  17. Process Neural Networks Theory and Applications

    CERN Document Server

    He, Xingui

    2010-01-01

    "Process Neural Networks - Theory and Applications" proposes the concept and model of a process neural network for the first time, showing how it expands the mapping relationship between the input and output of traditional neural networks, and enhancing the expression capability for practical problems, with broad applicability to solving problems relating to process in practice. Some theoretical problems such as continuity, functional approximation capability, and computing capability, are strictly proved. The application methods, network construction principles, and optimization alg

  18. The LILARTI neural network system

    Energy Technology Data Exchange (ETDEWEB)

    Allen, J.D. Jr.; Schell, F.M.; Dodd, C.V.

    1992-10-01

    The material of this Technical Memorandum is intended to provide the reader with conceptual and technical background information on the LILARTI neural network system of detail sufficient to confer an understanding of the LILARTI method as it is presently allied and to facilitate application of the method to problems beyond the scope of this document. Of particular importance in this regard are the descriptive sections and the Appendices which include operating instructions, partial listings of program output and data files, and network construction information.

  19. 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

  20. Neural network modeling of emotion

    Science.gov (United States)

    Levine, Daniel S.

    2007-03-01

    This article reviews the history and development of computational neural network modeling of cognitive and behavioral processes that involve emotion. The exposition starts with models of classical conditioning dating from the early 1970s. Then it proceeds toward models of interactions between emotion and attention. Then models of emotional influences on decision making are reviewed, including some speculative (not and not yet simulated) models of the evolution of decision rules. Through the late 1980s, the neural networks developed to model emotional processes were mainly embodiments of significant functional principles motivated by psychological data. In the last two decades, network models of these processes have become much more detailed in their incorporation of known physiological properties of specific brain regions, while preserving many of the psychological principles from the earlier models. Most network models of emotional processes so far have dealt with positive and negative emotion in general, rather than specific emotions such as fear, joy, sadness, and anger. But a later section of this article reviews a few models relevant to specific emotions: one family of models of auditory fear conditioning in rats, and one model of induced pleasure enhancing creativity in humans. Then models of emotional disorders are reviewed. The article concludes with philosophical statements about the essential contributions of emotion to intelligent behavior and the importance of quantitative theories and models to the interdisciplinary enterprise of understanding the interactions of emotion, cognition, and behavior.

  1. Neural networks and MIMD-multiprocessors

    Science.gov (United States)

    Vanhala, Jukka; Kaski, Kimmo

    1990-01-01

    Two artificial neural network models are compared. They are the Hopfield Neural Network Model and the Sparse Distributed Memory model. Distributed algorithms for both of them are designed and implemented. The run time characteristics of the algorithms are analyzed theoretically and tested in practice. The storage capacities of the networks are compared. Implementations are done using a distributed multiprocessor system.

  2. Neural-Network Computer Transforms Coordinates

    Science.gov (United States)

    Josin, Gary M.

    1990-01-01

    Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.

  3. Salience-Affected Neural Networks

    CERN Document Server

    Remmelzwaal, Leendert A; Ellis, George F R

    2010-01-01

    We present a simple neural network model which combines a locally-connected feedforward structure, as is traditionally used to model inter-neuron connectivity, with a layer of undifferentiated connections which model the diffuse projections from the human limbic system to the cortex. This new layer makes it possible to model global effects such as salience, at the same time as the local network processes task-specific or local information. This simple combination network displays interactions between salience and regular processing which correspond to known effects in the developing brain, such as enhanced learning as a result of heightened affect. The cortex biases neuronal responses to affect both learning and memory, through the use of diffuse projections from the limbic system to the cortex. Standard ANNs do not model this non-local flow of information represented by the ascending systems, which are a significant feature of the structure of the brain, and although they do allow associational learning with...

  4. Fast Algorithms for Convolutional Neural Networks

    OpenAIRE

    Lavin, Andrew; Gray, Scott

    2015-01-01

    Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing resources. The success of convolutional neural networks in these situations is limited by how fast we can compute them. Conventional FFT based convolution is fast for large filters, but state of the art convolutional neural networks use small, 3x3 filters. We ...

  5. 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.

  6. Information Theory for Analyzing Neural Networks

    OpenAIRE

    Sørngård, Bård

    2014-01-01

    The goal of this thesis was to investigate how information theory could be used to analyze artificial neural networks. For this purpose, two problems, a classification problem and a controller problem were considered. The classification problem was solved with a feedforward neural network trained with backpropagation, the controller problem was solved with a continuous-time recurrent neural network optimized with evolution.Results from the classification problem shows that mutual information ...

  7. Sequential optimizing investing strategy with neural networks

    OpenAIRE

    Ryo Adachi; Akimichi Takemura

    2010-01-01

    In this paper we propose an investing strategy based on neural network models combined with ideas from game-theoretic probability of Shafer and Vovk. Our proposed strategy uses parameter values of a neural network with the best performance until the previous round (trading day) for deciding the investment in the current round. We compare performance of our proposed strategy with various strategies including a strategy based on supervised neural network models and show that our procedure is co...

  8. Artificial neural networks in nuclear medicine

    International Nuclear Information System (INIS)

    An analysis of the accessible literature on the diagnostic applicability of artificial neural networks in coronary artery disease and pulmonary embolism appears to be comparative to the diagnosis of experienced doctors dealing with nuclear medicine. Differences in the employed models of artificial neural networks indicate a constant search for the most optimal parameters, which could guarantee the ultimate accuracy in neural network activity. The diagnostic potential within systems containing artificial neural networks proves this calculation tool to be an independent or/and an additional device for supporting a doctor's diagnosis of artery disease and pulmonary embolism. (author)

  9. 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

  10. Application of neural networks in coastal engineering

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.

    neural networks, J of computer aided civil and infrastructural engineering, (UK), 13, 113-120. Deo, MC and Naidu, CS (1999) Real time wave forecasting using neural networks, Ocean Engineering, 26, 191-203. Deo, MC, Gondane, DS and Kumar, VS (2002...) An application of artificial neural networks in tide-forecasting. Ocean Engineering, 29, pp 1003-1022 MandaI,S; Subba Rao and Chackraborty, l\\TV (2002) Hindcasting cyclonic waves using neural network. International Conference SHOT 2002, lIT Kharagpur, 18...

  11. Neural networks for nuclear spectroscopy

    Energy Technology Data Exchange (ETDEWEB)

    Keller, P.E.; Kangas, L.J.; Hashem, S.; Kouzes, R.T. [Pacific Northwest Lab., Richland, WA (United States)] [and others

    1995-12-31

    In this paper two applications of artificial neural networks (ANNs) in nuclear spectroscopy analysis are discussed. In the first application, an ANN assigns quality coefficients to alpha particle energy spectra. These spectra are used to detect plutonium contamination in the work environment. The quality coefficients represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with quality coefficients by an expert and used to train the ANN expert system. Our investigation shows that the expert knowledge of spectral quality can be transferred to an ANN system. The second application combines a portable gamma-ray spectrometer with an ANN. In this system the ANN is used to automatically identify, radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perception and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perception for this application. Both networks have a linear response and are useful in determining the composition of an unknown sample when the spectrum of the unknown is a linear superposition of known spectra. One feature of this technique is that it uses the whole spectrum in the identification process instead of only the individual photo-peaks. For this reason, it is potentially more useful for processing data from lower resolution gamma-ray spectrometers. This approach has been tested with data generated by Monte Carlo simulations and with field data from sodium iodide and Germanium detectors. With the ANN approach, the intense computation takes place during the training process. Once the network is trained, normal operation consists of propagating the data through the network, which results in rapid identification of samples. This approach is useful in situations that require fast response where precise quantification is less important.

  12. The existence and global attractivity of almost periodic sequence solution of discrete-time neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Huang Zhenkun [Department of Mathematics, School of Sciences, Zhejiang University, Hangzhou, Zhejiang 310027 (China) and School of Sciences, Jimei University, Xiamen, Fujian 361021 (China)]. E-mail: huangdoc@tom.com; Wang Xinghua [Department of Mathematics, School of Sciences, Zhejiang University, Hangzhou, Zhejiang 310027 (China); Gao Feng [School of Sciences, Jimei University, Xiamen, Fujian 361021 (China)

    2006-02-06

    In this Letter, we discuss discrete-time analogue of a continuous-time cellular neural network. Sufficient conditions are obtained for the existence of a unique almost periodic sequence solution which is globally attractive. Our results demonstrate dynamics of the formulated discrete-time analogue as mathematical models for the continuous-time cellular neural network in almost periodic case. Finally, a computer simulation illustrates the suitability of our discrete-time analogue as numerical algorithms in simulating the continuous-time cellular neural network conveniently.

  13. Neural Network Controlled Visual Saccades

    Science.gov (United States)

    Johnson, Jeffrey D.; Grogan, Timothy A.

    1989-03-01

    The paper to be presented will discuss research on a computer vision system controlled by a neural network capable of learning through classical (Pavlovian) conditioning. Through the use of unconditional stimuli (reward and punishment) the system will develop scan patterns of eye saccades necessary to differentiate and recognize members of an input set. By foveating only those portions of the input image that the system has found to be necessary for recognition the drawback of computational explosion as the size of the input image grows is avoided. The model incorporates many features found in animal vision systems, and is governed by understandable and modifiable behavior patterns similar to those reported by Pavlov in his classic study. These behavioral patterns are a result of a neuronal model, used in the network, explicitly designed to reproduce this behavior.

  14. 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...

  15. Video Traffic Prediction Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Miloš Oravec

    2008-10-01

    Full Text Available In this paper, we consider video stream prediction for application in services likevideo-on-demand, videoconferencing, video broadcasting, etc. The aim is to predict thevideo stream for an efficient bandwidth allocation of the video signal. Efficient predictionof traffic generated by multimedia sources is an important part of traffic and congestioncontrol procedures at the network edges. As a tool for the prediction, we use neuralnetworks – multilayer perceptron (MLP, radial basis function networks (RBF networksand backpropagation through time (BPTT neural networks. At first, we briefly introducetheoretical background of neural networks, the prediction methods and the differencebetween them. We propose also video time-series processing using moving averages.Simulation results for each type of neural network together with final comparisons arepresented. For comparison purposes, also conventional (non-neural prediction isincluded. The purpose of our work is to construct suitable neural networks for variable bitrate video prediction and evaluate them. We use video traces from [1].

  16. Neural Networks for Emotion Classification

    CERN Document Server

    Sun, Yafei

    2011-01-01

    It is argued that for the computer to be able to interact with humans, it needs to have the communication skills of humans. One of these skills is the ability to understand the emotional state of the person. This thesis describes a neural network-based approach for emotion classification. We learn a classifier that can recognize six basic emotions with an average accuracy of 77% over the Cohn-Kanade database. The novelty of this work is that instead of empirically selecting the parameters of the neural network, i.e. the learning rate, activation function parameter, momentum number, the number of nodes in one layer, etc. we developed a strategy that can automatically select comparatively better combination of these parameters. We also introduce another way to perform back propagation. Instead of using the partial differential of the error function, we use optimal algorithm; namely Powell's direction set to minimize the error function. We were also interested in construction an authentic emotion databases. This...

  17. Artificial neural networks in neurosurgery.

    Science.gov (United States)

    Azimi, Parisa; Mohammadi, Hasan Reza; Benzel, Edward C; Shahzadi, Sohrab; Azhari, Shirzad; Montazeri, Ali

    2015-03-01

    Artificial neural networks (ANNs) effectively analyze non-linear data sets. The aimed was A review of the relevant published articles that focused on the application of ANNs as a tool for assisting clinical decision-making in neurosurgery. A literature review of all full publications in English biomedical journals (1993-2013) was undertaken. The strategy included a combination of key words 'artificial neural networks', 'prognostic', 'brain', 'tumor tracking', 'head', 'tumor', 'spine', 'classification' and 'back pain' in the title and abstract of the manuscripts using the PubMed search engine. The major findings are summarized, with a focus on the application of ANNs for diagnostic and prognostic purposes. Finally, the future of ANNs in neurosurgery is explored. A total of 1093 citations were identified and screened. In all, 57 citations were found to be relevant. Of these, 50 articles were eligible for inclusion in this review. The synthesis of the data showed several applications of ANN in neurosurgery, including: (1) diagnosis and assessment of disease progression in low back pain, brain tumours and primary epilepsy; (2) enhancing clinically relevant information extraction from radiographic images, intracranial pressure processing, low back pain and real-time tumour tracking; (3) outcome prediction in epilepsy, brain metastases, lumbar spinal stenosis, lumbar disc herniation, childhood hydrocephalus, trauma mortality, and the occurrence of symptomatic cerebral vasospasm in patients with aneurysmal subarachnoid haemorrhage; (4) the use in the biomechanical assessments of spinal disease. ANNs can be effectively employed for diagnosis, prognosis and outcome prediction in neurosurgery.

  18. The Laplacian spectrum of neural networks

    Directory of Open Access Journals (Sweden)

    Siemon ede Lange

    2014-01-01

    Full Text Available 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.

  19. Optimising the topology of complex neural networks

    CERN Document Server

    Jiang, Fei; Schoenauer, Marc

    2007-01-01

    In this paper, we study instances of complex neural networks, i.e. neural netwo rks with complex topologies. We use Self-Organizing Map neural networks whose n eighbourhood relationships are defined by a complex network, to classify handwr itten digits. We show that topology has a small impact on performance and robus tness to neuron failures, at least at long learning times. Performance may howe ver be increased (by almost 10%) by artificial evolution of the network topo logy. In our experimental conditions, the evolved networks are more random than their parents, but display a more heterogeneous degree distribution.

  20. Optimizing neural network forecast by immune algorithm

    Institute of Scientific and Technical Information of China (English)

    YANG Shu-xia; LI Xiang; LI Ning; YANG Shang-dong

    2006-01-01

    Considering multi-factor influence, a forecasting model was built. The structure of BP neural network was designed, and immune algorithm was applied to optimize its network structure and weight. After training the data of power demand from the year 1980 to 2005 in China, a nonlinear network model was obtained on the relationship between power demand and the factors which had impacts on it, and thus the above proposed method was verified. Meanwhile, the results were compared to those of neural network optimized by genetic algorithm. The results show that this method is superior to neural network optimized by genetic algorithm and is one of the effective ways of time series forecast.

  1. A new formulation for feedforward neural networks.

    Science.gov (United States)

    Razavi, Saman; Tolson, Bryan A

    2011-10-01

    Feedforward neural network is one of the most commonly used function approximation techniques and has been applied to a wide variety of problems arising from various disciplines. However, neural networks are black-box models having multiple challenges/difficulties associated with training and generalization. This paper initially looks into the internal behavior of neural networks and develops a detailed interpretation of the neural network functional geometry. Based on this geometrical interpretation, a new set of variables describing neural networks is proposed as a more effective and geometrically interpretable alternative to the traditional set of network weights and biases. Then, this paper develops a new formulation for neural networks with respect to the newly defined variables; this reformulated neural network (ReNN) is equivalent to the common feedforward neural network but has a less complex error response surface. To demonstrate the learning ability of ReNN, in this paper, two training methods involving a derivative-based (a variation of backpropagation) and a derivative-free optimization algorithms are employed. Moreover, a new measure of regularization on the basis of the developed geometrical interpretation is proposed to evaluate and improve the generalization ability of neural networks. The value of the proposed geometrical interpretation, the ReNN approach, and the new regularization measure are demonstrated across multiple test problems. Results show that ReNN can be trained more effectively and efficiently compared to the common neural networks and the proposed regularization measure is an effective indicator of how a network would perform in terms of generalization.

  2. Drift chamber tracking with neural networks

    International Nuclear Information System (INIS)

    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

  3. Drift chamber tracking with neural networks

    Energy Technology Data Exchange (ETDEWEB)

    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.

  4. Coherence resonance in bursting neural networks

    Science.gov (United States)

    Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J.

    2015-10-01

    Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal—a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.

  5. Coherence resonance in bursting neural networks.

    Science.gov (United States)

    Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J

    2015-10-01

    Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal-a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.

  6. Tension and robustness in multitasking cellular networks.

    Directory of Open Access Journals (Sweden)

    Jeffrey V Wong

    Full Text Available Cellular networks multitask by exhibiting distinct, context-dependent dynamics. However, network states (parameters that generate a particular dynamic are often sub-optimal for others, defining a source of "tension" between them. Though multitasking is pervasive, it is not clear where tension arises, what consequences it has, and how it is resolved. We developed a generic computational framework to examine the source and consequences of tension between pairs of dynamics exhibited by the well-studied RB-E2F switch regulating cell cycle entry. We found that tension arose from task-dependent shifts in parameters associated with network modules. Although parameter sets common to distinct dynamics did exist, tension reduced both their accessibility and resilience to perturbation, indicating a trade-off between "one-size-fits-all" solutions and robustness. With high tension, robustness can be preserved by dynamic shifting of modules, enabling the network to toggle between tasks, and by increasing network complexity, in this case by gene duplication. We propose that tension is a general constraint on the architecture and operation of multitasking biological networks. To this end, our work provides a framework to quantify the extent of tension between any network dynamics and how it affects network robustness. Such analysis would suggest new ways to interfere with network elements to elucidate the design principles of cellular networks.

  7. Radiation Behavior of Analog Neural Network Chip

    Science.gov (United States)

    Langenbacher, H.; Zee, F.; Daud, T.; Thakoor, A.

    1996-01-01

    A neural network experiment conducted for the Space Technology Research Vehicle (STRV-1) 1-b launched in June 1994. Identical sets of analog feed-forward neural network chips was used to study and compare the effects of space and ground radiation on the chips. Three failure mechanisms are noted.

  8. Adaptive Neurons For Artificial Neural Networks

    Science.gov (United States)

    Tawel, Raoul

    1990-01-01

    Training time decreases dramatically. In improved mathematical model of neural-network processor, temperature of neurons (in addition to connection strengths, also called weights, of synapses) varied during supervised-learning phase of operation according to mathematical formalism and not heuristic rule. Evidence that biological neural networks also process information at neuronal level.

  9. Self-organization of neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Clark, J.W.; Winston, J.V.; Rafelski, J.

    1984-05-14

    The plastic development of a neural-network model operating autonomously in discrete time is described by the temporal modification of interneuronal coupling strengths according to momentary neural activity. A simple algorithm (brainwashing) is found which, applied to nets with initially quasirandom connectivity, leads to model networks with properties conducive to the simulation of memory and learning phenomena. 18 references, 2 figures.

  10. Self-organization of neural networks

    Science.gov (United States)

    Clark, John W.; Winston, Jeffrey V.; Rafelski, Johann

    1984-05-01

    The plastic development of a neural-network model operating autonomously in discrete time is described by the temporal modification of interneuronal coupling strengths according to momentary neural activity. A simple algorithm (“brainwashing”) is found which, applied to nets with initially quasirandom connectivity, leads to model networks with properties conductive to the simulation of memory and learning phenomena.

  11. Neural Networks for Non-linear Control

    DEFF Research Database (Denmark)

    Sørensen, O.

    1994-01-01

    This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....

  12. Secure Key Exchange using Neural Network

    OpenAIRE

    Vineeta Soni

    2014-01-01

    Any cryptographic system is used to exchange confidential information securely over the public channel without any leakage of information to the unauthorized users. Neural networks can be used to generate a common secret key because the processes involve in Cryptographic system requires large computational power and very complex. Moreover Diffi hellman key exchange is suffered from man-in –the middle attack. For overcome this problem neural networks can be used.Two neural netwo...

  13. Introduction to Concepts in Artificial Neural Networks

    Science.gov (United States)

    Niebur, Dagmar

    1995-01-01

    This introduction to artificial neural networks summarizes some basic concepts of computational neuroscience and the resulting models of artificial neurons. The terminology of biological and artificial neurons, biological and machine learning and neural processing is introduced. The concepts of supervised and unsupervised learning are explained with examples from the power system area. Finally, a taxonomy of different types of neurons and different classes of artificial neural networks is presented.

  14. Rule Extraction using Artificial Neural Networks

    CERN Document Server

    Kamruzzaman, S M

    2010-01-01

    Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can gain a better understanding of the solution. This paper presents an efficient algorithm to extract rules from artificial neural networks. We use two-phase training algorithm for backpropagation learning. In the first phase, the number of hidden nodes of the network is determined automatically in a constructive fashion by adding nodes one after another based on the performance of the network on training data. In the second phase, the number of relevant input units of the network is determined using pruning algorithm. The ...

  15. Firing rate dynamics in recurrent spiking neural networks with intrinsic and network heterogeneity.

    Science.gov (United States)

    Ly, Cheng

    2015-12-01

    Heterogeneity of neural attributes has recently gained a lot of attention and is increasing recognized as a crucial feature in neural processing. Despite its importance, this physiological feature has traditionally been neglected in theoretical studies of cortical neural networks. Thus, there is still a lot unknown about the consequences of cellular and circuit heterogeneity in spiking neural networks. In particular, combining network or synaptic heterogeneity and intrinsic heterogeneity has yet to be considered systematically despite the fact that both are known to exist and likely have significant roles in neural network dynamics. In a canonical recurrent spiking neural network model, we study how these two forms of heterogeneity lead to different distributions of excitatory firing rates. To analytically characterize how these types of heterogeneities affect the network, we employ a dimension reduction method that relies on a combination of Monte Carlo simulations and probability density function equations. We find that the relationship between intrinsic and network heterogeneity has a strong effect on the overall level of heterogeneity of the firing rates. Specifically, this relationship can lead to amplification or attenuation of firing rate heterogeneity, and these effects depend on whether the recurrent network is firing asynchronously or rhythmically firing. These observations are captured with the aforementioned reduction method, and furthermore simpler analytic descriptions based on this dimension reduction method are developed. The final analytic descriptions provide compact and descriptive formulas for how the relationship between intrinsic and network heterogeneity determines the firing rate heterogeneity dynamics in various settings.

  16. 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...

  17. Exponential synchronization of general chaotic delayed neural networks via hybrid feedback

    Institute of Scientific and Technical Information of China (English)

    2008-01-01

    This paper investigates the exponential synchronization problem of some chaotic delayed neural networks based on the proposed general neural network model, which is the interconnection of a linear delayed dynamic system and a bounded static nonlinear operator, and covers several well-known neural networks, such as Hopfield neural networks, cellular neural networks (CNNs), bidirectional associative memory (BAM) networks, recurrent multilayer perceptrons (RMLPs). By virtue of LyapunovKrasovskii stability theory and linear matrix inequality (LMI) technique, some exponential synchronization criteria are derived.Using the drive-response concept, hybrid feedback controllers are designed to synchronize two identical chaotic neural networks based on those synchronization criteria. Finally, detailed comparisons with existing results are made and numerical simulations are carried out to demonstrate the effectiveness of the established synchronization laws.

  18. Cognitive resource management for heterogeneous cellular networks

    CERN Document Server

    Liu, Yongkang

    2014-01-01

    This Springer Brief focuses on cognitive resource management in heterogeneous cellular networks (Het Net) with small cell deployment for the LTE-Advanced system. It introduces the Het Net features, presents practical approaches using cognitive radio technology in accommodating small cell data relay and optimizing resource allocation and examines the effectiveness of resource management among small cells given limited coordination bandwidth and wireless channel uncertainty. The authors introduce different network characteristics of small cell, investigate the mesh of small cell access points in

  19. Wavelet Neural Networks for Adaptive Equalization

    Institute of Scientific and Technical Information of China (English)

    JIANGMinghu; DENGBeixing; GIELENGeorges; ZHANGBo

    2003-01-01

    A structure based on the Wavelet neural networks (WNNs) is proposed for nonlinear channel equalization in a digital communication system. The construction algorithm of the Minimum error probability (MEP) is presented and applied as a performance criterion to update the parameter matrix of wavelet networks. Our experimental results show that performance of the proposed wavelet networks based on equalizer can significantly improve the neural modeling accuracy, perform quite well in compensating the nonlinear distortion introduced by the channel, and outperform the conventional neural networks in signal to noise ratio and channel non-llnearity.

  20. Sunspot prediction using neural networks

    Science.gov (United States)

    Villarreal, James; Baffes, Paul

    1990-01-01

    The earliest systematic observance of sunspot activity is known to have been discovered by the Chinese in 1382 during the Ming Dynasty (1368 to 1644) when spots on the sun were noticed by looking at the sun through thick, forest fire smoke. Not until after the 18th century did sunspot levels become more than a source of wonderment and curiosity. Since 1834 reliable sunspot data has been collected by the National Oceanic and Atmospheric Administration (NOAA) and the U.S. Naval Observatory. Recently, considerable effort has been placed upon the study of the effects of sunspots on the ecosystem and the space environment. The efforts of the Artificial Intelligence Section of the Mission Planning and Analysis Division of the Johnson Space Center involving the prediction of sunspot activity using neural network technologies are described.

  1. Subspace learning of neural networks

    CERN Document Server

    Cheng Lv, Jian; Zhou, Jiliu

    2010-01-01

    PrefaceChapter 1. Introduction1.1 Introduction1.1.1 Linear Neural Networks1.1.2 Subspace Learning1.2 Subspace Learning Algorithms1.2.1 PCA Learning Algorithms1.2.2 MCA Learning Algorithms1.2.3 ICA Learning Algorithms1.3 Methods for Convergence Analysis1.3.1 SDT Method1.3.2 DCT Method1.3.3 DDT Method1.4 Block Algorithms1.5 Simulation Data Set and Notation1.6 ConclusionsChapter 2. PCA Learning Algorithms with Constants Learning Rates2.1 Oja's PCA Learning Algorithms2.1.1 The Algorithms2.1.2 Convergence Issue2.2 Invariant Sets2.2.1 Properties of Invariant Sets2.2.2 Conditions for Invariant Sets2.

  2. Introduction to artificial neural networks.

    Science.gov (United States)

    Grossi, Enzo; Buscema, Massimo

    2007-12-01

    The coupling of computer science and theoretical bases such as nonlinear dynamics and chaos theory allows the creation of 'intelligent' agents, such as artificial neural networks (ANNs), able to adapt themselves dynamically to problems of high complexity. ANNs are able to reproduce the dynamic interaction of multiple factors simultaneously, allowing the study of complexity; they can also draw conclusions on individual basis and not as average trends. These tools can offer specific advantages with respect to classical statistical techniques. This article is designed to acquaint gastroenterologists with concepts and paradigms related to ANNs. The family of ANNs, when appropriately selected and used, permits the maximization of what can be derived from available data and from complex, dynamic, and multidimensional phenomena, which are often poorly predictable in the traditional 'cause and effect' philosophy. PMID:17998827

  3. Drift chamber tracking with neural networks

    International Nuclear Information System (INIS)

    With the very high event rates projected for experiments at the SSC and LHC, it is important to investigate new approaches to on line pattern recognition. The use of neural networks for pattern recognition. The use of neural networks for pattern recognition in high energy physics detectors has been an area of very active research. The authors discuss drift chamber tracking with a commercial analog 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

  4. Learning Processes of Layered Neural Networks

    OpenAIRE

    Fujiki, Sumiyoshi; Fujiki, Nahomi M.

    1995-01-01

    A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward neural network, and a learning equation similar to that of the Boltzmann machine algorithm is obtained. By applying a mean field approximation to the same stochastic feed-forward neural network, a deterministic analog feed-forward network is obtained and the back-propagation learning rule is re-derived.

  5. Research of The Deeper Neural Networks

    Directory of Open Access Journals (Sweden)

    Xiao You Rong

    2016-01-01

    Full Text Available Neural networks (NNs have powerful computational abilities and could be used in a variety of applications; however, training these networks is still a difficult problem. With different network structures, many neural models have been constructed. In this report, a deeper neural networks (DNNs architecture is proposed. The training algorithm of deeper neural network insides searching the global optimal point in the actual error surface. Before the training algorithm is designed, the error surface of the deeper neural network is analyzed from simple to complicated, and the features of the error surface is obtained. Based on these characters, the initialization method and training algorithm of DNNs is designed. For the initialization, a block-uniform design method is proposed which separates the error surface into some blocks and finds the optimal block using the uniform design method. For the training algorithm, the improved gradient-descent method is proposed which adds a penalty term into the cost function of the old gradient descent method. This algorithm makes the network have a great approximating ability and keeps the network state stable. All of these improve the practicality of the neural network.

  6. Coronary Artery Diagnosis Aided by Neural Network

    Science.gov (United States)

    Stefko, Kamil

    2007-01-01

    Coronary artery disease is due to atheromatous narrowing and subsequent occlusion of the coronary vessel. Application of optimised feed forward multi-layer back propagation neural network (MLBP) for detection of narrowing in coronary artery vessels is presented in this paper. The research was performed using 580 data records from traditional ECG exercise test confirmed by coronary arteriography results. Each record of training database included description of the state of a patient providing input data for the neural network. Level and slope of ST segment of a 12 lead ECG signal recorded at rest and after effort (48 floating point values) was the main component of input data for neural network was. Coronary arteriography results (verified the existence or absence of more than 50% stenosis of the particular coronary vessels) were used as a correct neural network training output pattern. More than 96% of cases were correctly recognised by especially optimised and a thoroughly verified neural network. Leave one out method was used for neural network verification so 580 data records could be used for training as well as for verification of neural network.

  7. 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.

  8. Mobility Prediction in Wireless Ad Hoc Networks using Neural Networks

    CERN Document Server

    Kaaniche, Heni

    2010-01-01

    Mobility prediction allows estimating the stability of paths in a mobile wireless Ad Hoc networks. Identifying stable paths helps to improve routing by reducing the overhead and the number of connection interruptions. In this paper, we introduce a neural network based method for mobility prediction in Ad Hoc networks. This method consists of a multi-layer and recurrent neural network using back propagation through time algorithm for training.

  9. Neural network for sonogram gap filling

    DEFF Research Database (Denmark)

    Klebæk, Henrik; Jensen, Jørgen Arendt; Hansen, Lars Kai

    1995-01-01

    a neural network for predicting mean frequency of the velocity signal and its variance. The neural network then predicts the evolution of the mean and variance in the gaps, and the sonogram and audio signal are reconstructed from these. The technique is applied on in-vivo data from the carotid artery....... The neural network is trained on part of the data and the network is pruned by the optimal brain damage procedure in order to reduce the number of parameters in the network, and thereby reduce the risk of overfitting. The neural predictor is compared to using a linear filter for the mean and variance time......In duplex imaging both an anatomical B-mode image and a sonogram are acquired, and the time for data acquisition is divided between the two images. This gives problems when rapid B-mode image display is needed, since there is not time for measuring the velocity data. Gaps then appear...

  10. Convolutional Neural Network for Image Recognition

    CERN Document Server

    Seifnashri, Sahand

    2015-01-01

    The aim of this project is to use machine learning techniques especially Convolutional Neural Networks for image processing. These techniques can be used for Quark-Gluon discrimination using calorimeters data, but unfortunately I didn’t manage to get the calorimeters data and I just used the Jet data fromminiaodsim(ak4 chs). The Jet data was not good enough for Convolutional Neural Network which is designed for ’image’ recognition. This report is made of twomain part, part one is mainly about implementing Convolutional Neural Network on unphysical data such as MNIST digits and CIFAR-10 dataset and part 2 is about the Jet data.

  11. Multispectral-image fusion using neural networks

    Science.gov (United States)

    Kagel, Joseph H.; Platt, C. A.; Donaven, T. W.; Samstad, Eric A.

    1990-08-01

    A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard a circuit card assembly and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations results and a description of the prototype system are presented. 1.

  12. Multispectral image fusion using neural networks

    Science.gov (United States)

    Kagel, J. H.; Platt, C. A.; Donaven, T. W.; Samstad, E. A.

    1990-01-01

    A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard, a circuit card assembly, and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations, results, and a description of the prototype system are presented.

  13. Hidden neural networks: application to speech recognition

    DEFF Research Database (Denmark)

    Riis, Søren Kamaric

    1998-01-01

    We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, and (2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how hidden neural networks...... (HNNs) with much fewer parameters than conventional HMMs and other hybrids can obtain comparable performance, and for the broad class task it is illustrated how the HNN can be applied as a purely transition based system, where acoustic context dependent transition probabilities are estimated by neural...... networks...

  14. Neural network based temporal video segmentation.

    Science.gov (United States)

    Cao, X; Suganthan, P N

    2002-01-01

    The organization of video information in video databases requires automatic temporal segmentation with minimal user interaction. As neural networks are capable of learning the characteristics of various video segments and clustering them accordingly, in this paper, a neural network based technique is developed to segment the video sequence into shots automatically and with a minimum number of user-defined parameters. We propose to employ growing neural gas (GNG) networks and integrate multiple frame difference features to efficiently detect shot boundaries in the video. Experimental results are presented to illustrate the good performance of the proposed scheme on real video sequences. PMID:12370954

  15. Estimation of Conditional Quantile using Neural Networks

    DEFF Research Database (Denmark)

    Kulczycki, P.; Schiøler, Henrik

    1999-01-01

    The problem of estimating conditional quantiles using neural networks is investigated here. A basic structure is developed using the methodology of kernel estimation, and a theory guaranteeing con-sistency on a mild set of assumptions is provided. The constructed structure constitutes a basis...... for the design of a variety of different neural networks, some of which are considered in detail. The task of estimating conditional quantiles is related to Bayes point estimation whereby a broad range of applications within engineering, economics and management can be suggested. Numerical results illustrating...... the capabilities of the elaborated neural network are also given....

  16. Nonequilibrium landscape theory of neural networks.

    Science.gov (United States)

    Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin

    2013-11-01

    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.

  17. Neural Network for Estimating Conditional Distribution

    DEFF Research Database (Denmark)

    Schiøler, Henrik; Kulczycki, P.

    Neural networks for estimating conditional distributions and their associated quantiles are investigated in this paper. A basic network structure is developed on the basis of kernel estimation theory, and consistency is proved from a mild set of assumptions. A number of applications within...... statistcs, decision theory and signal processing are suggested, and a numerical example illustrating the capabilities of the elaborated network is given...

  18. Diagnosis method utilizing neural networks

    International Nuclear Information System (INIS)

    Studies have been made on the technique of neural networks, which will be used to identify a cause of a small anomalous state in the reactor coolant system of the ATR (Advance Thermal Reactor). Three phases of analyses were carried out in this study. First, simulation for 100 seconds was made to determine how the plant parameters respond after the occurence of a transient decrease in reactivity, flow rate and temperature of feed water and increase in the steam flow rate and steam pressure, which would produce a decrease of water level in a steam drum of the ATR. Next, the simulation data was analysed utilizing an autoregressive model. From this analysis, a total of 36 coherency functions up to 0.5 Hz in each transient were computed among nine important and detectable plant parameters: neutron flux, flow rate of coolant, steam or feed water, water level in the steam drum, pressure and opening area of control valve in a steam pipe, feed water temperature and electrical power. Last, learning of neural networks composed of 96 input, 4-9 hidden and 5 output layer units was done by use of the generalized delta rule, namely a back-propagation algorithm. These convergent computations were continued as far as the difference between the desired outputs, 1 for direct cause or 0 for four other ones and actual outputs reached less than 10%. (1) Coherency functions were not governed by decreasing rate of reactivity in the range of 0.41x10-2dollar/s to 1.62x10-2dollar /s or by decreasing depth of the feed water temperature in the range of 3 deg C to 10 deg C or by a change of 10% or less in the three other causes. Change in coherency functions only depended on the type of cause. (2) The direct cause from the other four ones could be discriminated with 0.94+-0.01 of output level. A maximum of 0.06 output height was found among the other four causes. (3) Calculation load which is represented as products of learning times and numbers of the hidden units did not depend on the numbers

  19. A COMPREHENSIVE EVOLUTIONARY APPROACH FOR NEURAL NETWORK ENSEMBLES AUTOMATIC DESIGN

    OpenAIRE

    Bukhtoyarov, V.; Semenkin, E.

    2010-01-01

    A new comprehensive approach for neural network ensembles design is proposed. It consists of a method of neural networks automatic design and a method of automatic formation of an ensemble solution on the basis of separate neural networks solutions. It is demonstrated that the proposed approach is not less effective than a number of other approaches for neural network ensembles design.

  20. Wireless traffic steering for green cellular networks

    CERN Document Server

    Zhang, Shan; Zhou, Sheng; Niu, Zhisheng; Shen, Xuemin (Sherman)

    2016-01-01

    This book introduces wireless traffic steering as a paradigm to realize green communication in multi-tier heterogeneous cellular networks. By matching network resources and dynamic mobile traffic demand, traffic steering helps to reduce on-grid power consumption with on-demand services provided. This book reviews existing solutions from the perspectives of energy consumption reduction and renewable energy harvesting. Specifically, it explains how traffic steering can improve energy efficiency through intelligent traffic-resource matching. Several promising traffic steering approaches for dynamic network planning and renewable energy demand-supply balancing are discussed. This book presents an energy-aware traffic steering method for networks with energy harvesting, which optimizes the traffic allocated to each cell based on the renewable energy status. Renewable energy demand-supply balancing is a key factor in energy dynamics, aimed at enhancing renewable energy sustainability to reduce on-grid energy consum...

  1. Neural networks for NOx-emission

    International Nuclear Information System (INIS)

    The government wants to restrict nitrogen oxide emissions. However, continuous measurement of these emissions is expensive and maintenance-sensitive. A prediction model based on the use of neural networks might be a reliable and efficient alternative

  2. Neural Networks in Mobile Robot Motion

    Directory of Open Access Journals (Sweden)

    Danica Janglova

    2008-11-01

    Full Text Available This paper deals with a path planning and intelligent control of an autonomous robot which should move safely in partially structured environment. This environment may involve any number of obstacles of arbitrary shape and size; some of them are allowed to move. We describe our approach to solving the motion-planning problem in mobile robot control using neural networks-based technique. Our method of the construction of a collision-free path for moving robot among obstacles is based on two neural networks. The first neural network is used to determine the "free" space using ultrasound range finder data. The second neural network "finds" a safe direction for the next robot section of the path in the workspace while avoiding the nearest obstacles. Simulation examples of generated path with proposed techniques will be presented.

  3. Neural Network Based 3D Surface Reconstruction

    Directory of Open Access Journals (Sweden)

    Vincy Joseph

    2009-11-01

    Full Text Available This paper proposes a novel neural-network-based adaptive hybrid-reflectance three-dimensional (3-D surface reconstruction model. The neural network combines the diffuse and specular components into a hybrid model. The proposed model considers the characteristics of each point and the variant albedo to prevent the reconstructed surface from being distorted. The neural network inputs are the pixel values of the two-dimensional images to be reconstructed. The normal vectors of the surface can then be obtained from the output of the neural network after supervised learning, where the illuminant direction does not have to be known in advance. Finally, the obtained normal vectors can be applied to integration method when reconstructing 3-D objects. Facial images were used for training in the proposed approach

  4. TIME SERIES FORECASTING USING NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    BOGDAN OANCEA

    2013-05-01

    Full Text Available Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for predicting the exchange rate EUR/RON and USD/RON. We used data series with daily exchange rates starting from 2005 until 2013.

  5. Additive Feed Forward Control with Neural Networks

    DEFF Research Database (Denmark)

    Sørensen, O.

    1999-01-01

    This paper demonstrates a method to control a non-linear, multivariable, noisy process using trained neural networks. The basis for the method is a trained neural network controller acting as the inverse process model. A training method for obtaining such an inverse process model is applied....... A suitable 'shaped' (low-pass filtered) reference is used to overcome problems with excessive control action when using a controller acting as the inverse process model. The control concept is Additive Feed Forward Control, where the trained neural network controller, acting as the inverse process model......, is placed in a supplementary pure feed-forward path to an existing feedback controller. This concept benefits from the fact, that an existing, traditional designed, feedback controller can be retained without any modifications, and after training the connection of the neural network feed-forward controller...

  6. Mobile Node Localization in Cellular Networks

    Directory of Open Access Journals (Sweden)

    Yasir Malik

    2012-01-01

    Full Text Available Location information is the major component in location based applications. This information is used in different safety and service oriented applications to provide users with services according to their Geolocation. There are many approaches to locate mobile nodes in indoor and outdoor environments. In thispaper, we are interested in outdoor localization particularly in cellular networks of mobile nodes andpresented a localization method based on cell and user location information. Our localization method is based on hello message delay (sending and receiving time and coordinate information of Base Transceiver Station (BTSs. To validate our method across cellular network, we implemented and simulated our method in two scenarios i.e. maintaining database of base stations in centralize and distributed system. Simulation results show the effectiveness of our approach and its implementation applicability in telecommunication systems.

  7. WD40 proteins propel cellular networks.

    Science.gov (United States)

    Stirnimann, Christian U; Petsalaki, Evangelia; Russell, Robert B; Müller, Christoph W

    2010-10-01

    Recent findings indicate that WD40 domains play central roles in biological processes by acting as hubs in cellular networks; however, they have been studied less intensely than other common domains, such as the kinase, PDZ or SH3 domains. As suggested by various interactome studies, they are among the most promiscuous interactors. Structural studies suggest that this property stems from their ability, as scaffolds, to interact with diverse proteins, peptides or nucleic acids using multiple surfaces or modes of interaction. A general scaffolding role is supported by the fact that no WD40 domain has been found with intrinsic enzymatic activity despite often being part of large molecular machines. We discuss the WD40 domain distributions in protein networks and structures of WD40-containing assemblies to demonstrate their versatility in mediating critical cellular functions.

  8. Virtualized cognitive network architecture for 5G cellular networks

    KAUST Repository

    Elsawy, Hesham

    2015-07-17

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

  9. SAR ATR Based on Convolutional Neural Network

    OpenAIRE

    Tian Zhuangzhuang; Zhan Ronghui; Hu Jiemin; Zhang Jun

    2016-01-01

    This study presents a new method of Synthetic Aperture Radar (SAR) image target recognition based on a convolutional neural network. First, we introduce a class separability measure into the cost function to improve this network’s ability to distinguish between categories. Then, we extract SAR image features using the improved convolutional neural network and classify these features using a support vector machine. Experimental results using moving and stationary target acquisition and recogni...

  10. Applications of Pulse-Coupled Neural Networks

    CERN Document Server

    Ma, Yide; Wang, Zhaobin

    2011-01-01

    "Applications of Pulse-Coupled Neural Networks" explores the fields of image processing, including image filtering, image segmentation, image fusion, image coding, image retrieval, and biometric recognition, and the role of pulse-coupled neural networks in these fields. This book is intended for researchers and graduate students in artificial intelligence, pattern recognition, electronic engineering, and computer science. Prof. Yide Ma conducts research on intelligent information processing, biomedical image processing, and embedded system development at the School of Information Sci

  11. Neural networks, D0, and the SSC

    International Nuclear Information System (INIS)

    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

  12. An Introduction to Convolutional Neural Networks

    OpenAIRE

    O'Shea, Keiron; Nash, Ryan

    2015-01-01

    The field of machine learning has taken a dramatic twist in recent times, with the rise of the Artificial Neural Network (ANN). These biologically inspired computational models are able to far exceed the performance of previous forms of artificial intelligence in common machine learning tasks. One of the most impressive forms of ANN architecture is that of the Convolutional Neural Network (CNN). CNNs are primarily used to solve difficult image-driven pattern recognition tasks and with their p...

  13. Parameterizing Stellar Spectra Using Deep Neural Networks

    OpenAIRE

    Li, Xiangru; Pan, Ruyang

    2016-01-01

    This work investigates the spectrum parameterization problem using deep neural networks (DNNs). The proposed scheme consists of the following procedures: first, the configuration of a DNN is initialized using a series of autoencoder neural networks; second, the DNN is fine-tuned using a gradient descent scheme; third, stellar parameters ($T_{eff}$, log$~g$, and [Fe/H]) are estimated using the obtained DNN. This scheme was evaluated on both real spectra from SDSS/SEGUE and synthetic spectra ca...

  14. Hindcasting cyclonic waves using neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Rao, S.; Chakravarty, N.V.

    for computing extreme wave conditions or design wave statistics. As far as Indian seas are concerned recorded wave data are available for short periods for some places along the coasts. Estimation of wave parameters by numerical wave forecasting schemes.... Some applications of neural network (NN) in wave forecasting are carried out by Deo and Naidu (1999), and Prabaharan (2001). Londhe and Deo (2001) have worked on wave propagation using neural network. This paper describes about hindcasting of wave...

  15. Density functional and neural network analysis

    DEFF Research Database (Denmark)

    Jalkanen, K. J.; Suhai, S.; Bohr, Henrik

    1997-01-01

    dichroism (VCD) intensities. The large changes due to hydration on the structures, relative stability of conformers, and in the VA and VCD spectra observed experimentally are reproduced by the DFT calculations. Furthermore a neural network was constructed for reproducing the inverse scattering data (infer...... the structural coordinates from spectroscopic data) that the DFT method could produce. Finally the neural network performances are used to monitor a sensitivity or dependence analysis of the importance of secondary structures....

  16. Neural network segmentation of magnetic resonance images

    Science.gov (United States)

    Frederick, Blaise

    1990-07-01

    Neural networks are well adapted to the task of grouping input patterns into subsets which share some similarity. Moreover once trained they can generalize their classification rules to classify new data sets. Sets of pixel intensities from magnetic resonance (MR) images provide a natural input to a neural network by varying imaging parameters MR images can reflect various independent physical parameters of tissues in their pixel intensities. A neural net can then be trained to classify physically similar tissue types based on sets of pixel intensities resulting from different imaging studies on the same subject. A neural network classifier for image segmentation was implemented on a Sun 4/60 and was tested on the task of classifying tissues of canine head MR images. Four images of a transaxial slice with different imaging sequences were taken as input to the network (three spin-echo images and an inversion recovery image). The training set consisted of 691 representative samples of gray matter white matter cerebrospinal fluid bone and muscle preclassified by a neuroscientist. The network was trained using a fast backpropagation algorithm to derive the decision criteria to classify any location in the image by its pixel intensities and the image was subsequently segmented by the classifier. The classifier''s performance was evaluated as a function of network size number of network layers and length of training. A single layer neural network performed quite well at

  17. Deep Learning with Darwin: Evolutionary Synthesis of Deep Neural Networks

    OpenAIRE

    Shafiee, Mohammad Javad; Mishra, Akshaya; Wong, Alexander

    2016-01-01

    Taking inspiration from biological evolution, we explore the idea of "Can deep neural networks evolve naturally over successive generations into highly efficient deep neural networks?" by introducing the notion of synthesizing new highly efficient, yet powerful deep neural networks over successive generations via an evolutionary process from ancestor deep neural networks. The architectural traits of ancestor deep neural networks are encoded using synaptic probability models, which can be view...

  18. Hopfield neural network based on ant system

    Institute of Scientific and Technical Information of China (English)

    洪炳镕; 金飞虎; 郭琦

    2004-01-01

    Hopfield neural network is a single layer feedforward neural network. Hopfield network requires some control parameters to be carefully selected, else the network is apt to converge to local minimum. An ant system is a nature inspired meta heuristic algorithm. It has been applied to several combinatorial optimization problems such as Traveling Salesman Problem, Scheduling Problems, etc. This paper will show an ant system may be used in tuning the network control parameters by a group of cooperated ants. The major advantage of this network is to adjust the network parameters automatically, avoiding a blind search for the set of control parameters.This network was tested on two TSP problems, 5 cities and 10 cities. The results have shown an obvious improvement.

  19. Fastest learning in small world neural networks

    OpenAIRE

    Simard, D.; Nadeau, L; Kröger, H.

    2004-01-01

    We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition.

  20. Option Pricing Using Bayesian Neural Networks

    CERN Document Server

    Pires, Michael Maio

    2007-01-01

    Options have provided a field of much study because of the complexity involved in pricing them. The Black-Scholes equations were developed to price options but they are only valid for European styled options. There is added complexity when trying to price American styled options and this is why the use of neural networks has been proposed. Neural Networks are able to predict outcomes based on past data. The inputs to the networks here are stock volatility, strike price and time to maturity with the output of the network being the call option price. There are two techniques for Bayesian neural networks used. One is Automatic Relevance Determination (for Gaussian Approximation) and one is a Hybrid Monte Carlo method, both used with Multi-Layer Perceptrons.

  1. Application of Partially Connected Neural Network

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    This paper focuses mainly on application of Partially Connected Backpropagation Neural Network (PCBP) instead of typical Fully Connected Neural Network (FCBP). The initial neural network is fully connected, after training with sample data using cross-entropy as error function, a clustering method is employed to cluster weights between inputs to hidden layer and from hidden to output layer, and connections that are relatively unnecessary are deleted, thus the initial network becomes a PCBP network.Then PCBP can be used in prediction or data mining by training PCBP with data that comes from database. At the end of this paper, several experiments are conducted to illustrate the effects of PCBP using Iris data set.

  2. Lambda and the edge of chaos in recurrent neural networks.

    Science.gov (United States)

    Seifter, Jared; Reggia, James A

    2015-01-01

    The idea that there is an edge of chaos, a region in the space of dynamical systems having special meaning for complex living entities, has a long history in artificial life. The significance of this region was first emphasized in cellular automata models when a single simple measure, λCA, identified it as a transitional region between order and chaos. Here we introduce a parameter λNN that is inspired by λCA but is defined for recurrent neural networks. We show through a series of systematic computational experiments that λNN generally orders the dynamical behaviors of randomly connected/weighted recurrent neural networks in the same way that λCA does for cellular automata. By extending this ordering to larger values of λNN than has typically been done with λCA and cellular automata, we find that a second edge-of-chaos region exists on the opposite side of the chaotic region. These basic results are found to hold under different assumptions about network connectivity, but vary substantially in their details. The results show that the basic concept underlying the lambda parameter can usefully be extended to other types of complex dynamical systems than just cellular automata.

  3. Artificial astrocytes improve neural network performance.

    Directory of Open Access Journals (Sweden)

    Ana B Porto-Pazos

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

  4. Pattern Classification using Simplified Neural Networks

    CERN Document Server

    Kamruzzaman, S M

    2010-01-01

    In recent years, many neural network models have been proposed for pattern classification, function approximation and regression problems. This paper presents an approach for classifying patterns from simplified NNs. Although the predictive accuracy of ANNs is often higher than that of other methods or human experts, it is often said that ANNs are practically "black boxes", due to the complexity of the networks. In this paper, we have an attempted to open up these black boxes by reducing the complexity of the network. The factor makes this possible is the pruning algorithm. By eliminating redundant weights, redundant input and hidden units are identified and removed from the network. Using the pruning algorithm, we have been able to prune networks such that only a few input units, hidden units and connections left yield a simplified network. Experimental results on several benchmarks problems in neural networks show the effectiveness of the proposed approach with good generalization ability.

  5. Weight discretization paradigm for optical neural networks

    Science.gov (United States)

    Fiesler, Emile; Choudry, Amar; Caulfield, H. John

    1990-08-01

    Neural networks are a primary candidate architecture for optical computing. One of the major problems in using neural networks for optical computers is that the information holders: the interconnection strengths (or weights) are normally real valued (continuous), whereas optics (light) is only capable of representing a few distinguishable intensity levels (discrete). In this paper a weight discretization paradigm is presented for back(ward error) propagation neural networks which can work with a very limited number of discretization levels. The number of interconnections in a (fully connected) neural network grows quadratically with the number of neurons of the network. Optics can handle a large number of interconnections because of the fact that light beams do not interfere with each other. A vast amount of light beams can therefore be used per unit of area. However the number of different values one can represent in a light beam is very limited. A flexible, portable (machine independent) neural network software package which is capable of weight discretization, is presented. The development of the software and some experiments have been done on personal computers. The major part of the testing, which requires a lot of computation, has been done using a CRAY X-MP/24 super computer.

  6. Estimating Conditional Distributions by Neural Networks

    DEFF Research Database (Denmark)

    Kulczycki, P.; Schiøler, Henrik

    1998-01-01

    Neural Networks for estimating conditionaldistributions and their associated quantiles are investigated in this paper. A basic network structure is developed on the basis of kernel estimation theory, and consistency property is considered from a mild set of assumptions. A number of applications...

  7. Comparing artificial and biological dynamical neural networks

    Science.gov (United States)

    McAulay, Alastair D.

    2006-05-01

    Modern computers can be made more friendly and otherwise improved by making them behave more like humans. Perhaps we can learn how to do this from biology in which human brains evolved over a long period of time. Therefore, we first explain a commonly used biological neural network (BNN) model, the Wilson-Cowan neural oscillator, that has cross-coupled excitatory (positive) and inhibitory (negative) neurons. The two types of neurons are used for frequency modulation communication between neurons which provides immunity to electromagnetic interference. We then evolve, for the first time, an artificial neural network (ANN) to perform the same task. Two dynamical feed-forward artificial neural networks use cross-coupling feedback (like that in a flip-flop) to form an ANN nonlinear dynamic neural oscillator with the same equations as the Wilson-Cowan neural oscillator. Finally we show, through simulation, that the equations perform the basic neural threshold function, switching between stable zero output and a stable oscillation, that is a stable limit cycle. Optical implementation with an injected laser diode and future research are discussed.

  8. Design of Robust Neural Network Classifiers

    DEFF Research Database (Denmark)

    Larsen, Jan; Andersen, Lars Nonboe; Hintz-Madsen, Mads;

    1998-01-01

    This paper addresses a new framework for designing robust neural network classifiers. The network is optimized using the maximum a posteriori technique, i.e., the cost function is the sum of the log-likelihood and a regularization term (prior). In order to perform robust classification, we present...... a modified likelihood function which incorporates the potential risk of outliers in the data. This leads to the introduction of a new parameter, the outlier probability. Designing the neural classifier involves optimization of network weights as well as outlier probability and regularization parameters. We...

  9. Electronic device aspects of neural network memories

    Science.gov (United States)

    Lambe, J.; Moopenn, A.; Thakoor, A. P.

    1985-01-01

    The basic issues related to the electronic implementation of the neural network model (NNM) for content addressable memories are examined. A brief introduction to the principles of the NNM is followed by an analysis of the information storage of the neural network in the form of a binary connection matrix and the recall capability of such matrix memories based on a hardware simulation study. In addition, materials and device architecture issues involved in the future realization of such networks in VLSI-compatible ultrahigh-density memories are considered. A possible space application of such devices would be in the area of large-scale information storage without mechanical devices.

  10. GLOBAL ASYMPTOTIC STABILITY CONDITIONS OF DELAYED NEURAL NETWORKS

    Institute of Scientific and Technical Information of China (English)

    ZHOU Dong-ming; CAO Jin-de; ZHANG Li-ming

    2005-01-01

    Utilizing the Liapunov functional method and combining the inequality of matrices technique to analyze the existence of a unique equilibrium point and the global asymptotic stability for delayed cellular neural networks (DCNNs), a new sufficient criterion ensuring the global stability of DCNNs is obtained. Our criteria provide some parameters to appropriately compensate for the tradeoff between the matrix definite condition on feedback matrix and delayed feedback matrix. The criteria can easily be used to design and verify globally stable networks. Furthermore, the condition presented here is independent of the delay parameter and is less restrictive than that given in the references.

  11. Improving neural network performance on SIMD architectures

    Science.gov (United States)

    Limonova, Elena; Ilin, Dmitry; Nikolaev, Dmitry

    2015-12-01

    Neural network calculations for the image recognition problems can be very time consuming. In this paper we propose three methods of increasing neural network performance on SIMD architectures. The usage of SIMD extensions is a way to speed up neural network processing available for a number of modern CPUs. In our experiments, we use ARM NEON as SIMD architecture example. The first method deals with half float data type for matrix computations. The second method describes fixed-point data type for the same purpose. The third method considers vectorized activation functions implementation. For each method we set up a series of experiments for convolutional and fully connected networks designed for image recognition task.

  12. Neural-networks-based Modelling and a Fuzzy Neural Networks Controller of MCFC

    Institute of Scientific and Technical Information of China (English)

    2002-01-01

    Molten Carbonate Fuel Cells (MCFC) are produced with a highly efficient and clean power generation technology which will soon be widely utilized. The temperature characters of MCFC stack are briefly analyzed. A radial basis function (RBF) neural networks identification technology is applied to set up the temperature nonlinear model of MCFC stack, and the identification structure, algorithm and modeling training process are given in detail. A fuzzy controller of MCFC stack is designed. In order to improve its online control ability, a neural network trained by the I/O data of a fuzzy controller is designed. The neural networks can memorize and expand the inference rules of the fuzzy controller and substitute for the fuzzy controller to control MCFC stack online. A detailed design of the controller is given. The validity of MCFC stack modelling based on neural networks and the superior performance of the fuzzy neural networks controller are proved by Simulations.

  13. Stability analysis of discrete-time BAM neural networks based on standard neural network models

    Institute of Scientific and Technical Information of China (English)

    ZHANG Sen-lin; LIU Mei-qin

    2005-01-01

    To facilitate stability analysis of discrete-time bidirectional associative memory (BAM) neural networks, they were converted into novel neural network models, termed standard neural network models (SNNMs), which interconnect linear dynamic systems and bounded static nonlinear operators. By combining a number of different Lyapunov functionals with S-procedure, some useful criteria of global asymptotic stability and global exponential stability of the equilibrium points of SNNMs were derived. These stability conditions were formulated as linear matrix inequalities (LMIs). So global stability of the discrete-time BAM neural networks could be analyzed by using the stability results of the SNNMs. Compared to the existing stability analysis methods, the proposed approach is easy to implement, less conservative, and is applicable to other recurrent neural networks.

  14. Empirical multiscale networks of cellular regulation.

    Directory of Open Access Journals (Sweden)

    Benjamin de Bivort

    2007-10-01

    Full Text Available Grouping genes by similarity of expression across multiple cellular conditions enables the identification of cellular modules. The known functions of genes enable the characterization of the aggregate biological functions of these modules. In this paper, we use a high-throughput approach to identify the effective mutual regulatory interactions between modules composed of mouse genes from the Alliance for Cell Signaling (AfCS murine B-lymphocyte database which tracks the response of approximately 15,000 genes following chemokine perturbation. This analysis reveals principles of cellular organization that we discuss along four conceptual axes. (1 Regulatory implications: the derived collection of influences between any two modules quantifies intuitive as well as unexpected regulatory interactions. (2 Behavior across scales: trends across global networks of varying resolution (composed of various numbers of modules reveal principles of assembly of high-level behaviors from smaller components. (3 Temporal behavior: tracking the mutual module influences over different time intervals provides features of regulation dynamics such as duration, persistence, and periodicity. (4 Gene Ontology correspondence: the association of modules to known biological roles of individual genes describes the organization of functions within coexpressed modules of various sizes. We present key specific results in each of these four areas, as well as derive general principles of cellular organization. At the coarsest scale, the entire transcriptional network contains five divisions: two divisions devoted to ATP production/biosynthesis and DNA replication that activate all other divisions, an "extracellular interaction" division that represses all other divisions, and two divisions (proliferation/differentiation and membrane infrastructure that activate and repress other divisions in specific ways consistent with cell cycle control.

  15. Applying neural networks in autonomous systems

    Science.gov (United States)

    Thornbrugh, Allison L.; Layne, J. D.; Wilson, James M., III

    1992-03-01

    Autonomous and teleautonomous operations have been defined in a variety of ways by different groups involved with remote robotic operations. For example, Conway describes architectures for producing intelligent actions in teleautonomous systems. Applying neural nets in such systems is similar to applying them in general. However, for autonomy, learning or learned behavior may become a significant system driver. Thus, artificial neural networks are being evaluated as components in fully autonomous and teleautonomous systems. Feed- forward networks may be trained to perform adaptive signal processing, pattern recognition, data fusion, and function approximation -- as in control subsystems. Certain components of particular autonomous systems become more amenable to implementation using a neural net due to a match between the net's attributes and desired attributes of the system component. Criteria have been developed for distinguishing such applications and then implementing them. The success of hardware implementation is a crucial part of this application evaluation process. Three basic applications of neural nets -- autoassociation, classification, and function approximation -- are used to exemplify this process and to highlight procedures that are followed during the requirements, design, and implementation phases. This paper assumes some familiarity with basic neural network terminology and concentrates upon the use of different neural network types while citing references that cover the underlying mathematics and related research.

  16. Cellular automata modelling of biomolecular networks dynamics.

    Science.gov (United States)

    Bonchev, D; Thomas, S; Apte, A; Kier, L B

    2010-01-01

    The modelling of biological systems dynamics is traditionally performed by ordinary differential equations (ODEs). When dealing with intracellular networks of genes, proteins and metabolites, however, this approach is hindered by network complexity and the lack of experimental kinetic parameters. This opened the field for other modelling techniques, such as cellular automata (CA) and agent-based modelling (ABM). This article reviews this emerging field of studies on network dynamics in molecular biology. The basics of the CA technique are discussed along with an extensive list of related software and websites. The application of CA to networks of biochemical reactions is exemplified in detail by the case studies of the mitogen-activated protein kinase (MAPK) signalling pathway, the FAS-ligand (FASL)-induced and Bcl-2-related apoptosis. The potential of the CA method to model basic pathways patterns, to identify ways to control pathway dynamics and to help in generating strategies to fight with cancer is demonstrated. The different line of CA applications presented includes the search for the best-performing network motifs, an analysis of importance for effective intracellular signalling and pathway cross-talk. PMID:20373215

  17. Dynamic pricing by hopfield neural network

    Institute of Scientific and Technical Information of China (English)

    Lusajo M Minga; FENG Yu-qiang(冯玉强); LI Yi-jun(李一军); LU Yang(路杨); Kimutai Kimeli

    2004-01-01

    The increase in the number of shopbots users in e-commerce has triggered flexibility of sellers in their pricing strategies. Sellers see the importance of automated price setting which provides efficient services to a large number of buyers who are using shopbots. This paper studies the characteristic of decreasing energy with time in a continuous model of a Hopfield neural network that is the decreasing of errors in the network with respect to time. The characteristic shows that it is possible to use Hopfield neural network to get the main factor of dynamic pricing; the least variable cost, from production function principles. The least variable cost is obtained by reducing or increasing the input combination factors, and then making the comparison of the network output with the desired output, where the difference between the network output and desired output will be decreasing in the same manner as in the Hopfield neural network energy. Hopfield neural network will simplify the rapid change of prices in e-commerce during transaction that depends on the demand quantity for demand sensitive model of pricing.

  18. Neutron spectrometry using artificial neural networks

    International Nuclear Information System (INIS)

    An artificial neural network has been designed to obtain neutron spectra from Bonner spheres spectrometer count rates. The neural network was trained using 129 neutron spectra. These include spectra from isotopic neutron sources; reference and operational spectra from accelerators and nuclear reactors, spectra based on mathematical functions as well as few energy groups and monoenergetic spectra. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. The re-binned spectra and the UTA4 response matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and their respective spectra were used as output during the neural network training. After training, the network was tested with the Bonner spheres count rates produced by folding a set of neutron spectra with the response matrix. This set contains data used during network training as well as data not used. Training and testing was carried out using the Matlab(R) program. To verify the network unfolding performance, the original and unfolded spectra were compared using the root mean square error. The use of artificial neural networks to unfold neutron spectra in neutron spectrometry is an alternative procedure that overcomes the drawbacks associated with this ill-conditioned problem

  19. Neutron spectrometry with artificial neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Rodriguez, J.M.; Mercado S, G.A. [Universidad Autonoma de Zacatecas, A.P. 336, 98000 Zacatecas (Mexico); Iniguez de la Torre Bayo, M.P. [Universidad de Valladolid, Valladolid (Spain); Barquero, R. [Hospital Universitario Rio Hortega, Valladolid (Spain); Arteaga A, T. [Envases de Zacatecas, S.A. de C.V., Zacatecas (Mexico)]. e-mail: rvega@cantera.reduaz.mx

    2005-07-01

    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 {chi}{sup 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)

  20. Using neural networks to describe tracer correlations

    Directory of Open Access Journals (Sweden)

    D. J. Lary

    2004-01-01

    Full Text Available Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and methane volume mixing ratio (v.m.r.. In this study a neural network using Quickprop learning and one hidden layer with eight nodes was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9995. Such an accurate representation of tracer-tracer correlations allows more use to be made of long-term datasets to constrain chemical models. Such as the dataset from the Halogen Occultation Experiment (HALOE which has continuously observed CH4  (but not N2O from 1991 till the present. The neural network Fortran code used is available for download.

  1. Fuzzy neural network with fast backpropagation learning

    Science.gov (United States)

    Wang, Zhiling; De Sario, Marco; Guerriero, Andrea; Mugnuolo, Raffaele

    1995-03-01

    Neural filters with multilayer backpropagation network have been proved to be able to define mostly all linear or non-linear filters. Because of the slowness of the networks' convergency, however, the applicable fields have been limited. In this paper, fuzzy logic is introduced to adjust learning rate and momentum parameter depending upon output errors and training times. This makes the convergency of the network greatly improved. Test curves are shown to prove the fast filters' performance.

  2. Neural network plasticity in the human brain

    OpenAIRE

    Rizk, Sviatlana

    2013-01-01

    The human brain is highly organized within networks. Functionally related neural-assemblies communicate by oscillating synchronously. Intrinsic brain activity contains information on healthy and damaged brain functioning. This thesis investigated the relationship between functional networks and behavior. Furthermore, we assessed functional network plasticity after brain damage and as a result of brain stimulation. In different groups of patients we observed reduced functional connectivity bet...

  3. Molding the Knowledge in Modular Neural Networks

    OpenAIRE

    Spaanenburg, L.; Achterop, S.; Slump, C. H.; Zwaag, van der, M.B.

    2002-01-01

    Problem description. The learning of monolithic neural networks becomes harder with growing network size. Likewise the knowledge obtained while learning becomes harder to extract. Such disadvantages are caused by a lack of internal structure, that by its presence would reduce the degrees of freedom in evolving to a training target. A suitable internal structure with respect to modular network construction as well as to nodal discrimination is required. Details on the grouping and selection of...

  4. Modular neural networks and reinforcement learning

    OpenAIRE

    Raicevic, Peter

    2004-01-01

    We investigate the effect of modular architecture in an artificial neural network for a reinforcement learning problem. Using the supervised backpropagation algorithm to solve a two-task problem, the network performance can be increased by using networks with modular structures. However, using a modular architecture to solve a two-task reinforcement learning problem will not increase the performance compared to a non-modular structure. We show that by combining a modular structure with a modu...

  5. Call Admission Control in Mobile Cellular Networks

    CERN Document Server

    Ghosh, Sanchita

    2013-01-01

    Call Admission Control (CAC) and Dynamic Channel Assignments (DCA) are important decision-making problems in mobile cellular communication systems. Current research in mobile communication considers them as two independent problems, although the former greatly depends on the resulting free channels obtained as the outcome of the latter. This book provides a solution to the CAC problem, considering DCA as an integral part of decision-making for call admission. Further, current technical resources ignore movement issues of mobile stations and fluctuation in network load (incoming calls) in the control strategy used for call admission. In addition, the present techniques on call admission offers solution globally for the entire network, instead of considering the cells independently.      CAC here has been formulated by two alternative approaches. The first approach aimed at handling the uncertainty in the CAC problem by employing fuzzy comparators.  The second approach is concerned with formulation of CAC ...

  6. Environment Aware Location Estimation in Cellular Networks

    Directory of Open Access Journals (Sweden)

    Tuna Tugcu

    2008-03-01

    Full Text Available We propose a novel mobile positioning algorithm for cellular networks based on the estimation of the radio propagation environment. Since radio propagation characteristics vary in different environments, knowing the environment of the mobile user is essential for accurate Received Signal Strength- (RSS- based location estimation. The key feature of our method is its capability to estimate the environment of the mobile user using machine learning techniques and to utilize this information for enhancing RSS-based distance calculations. The proposed algorithm, namely, EARBALE, has been evaluated using field measurements collected from a GSM network in diverse geographic locations. Our approach turns out to be significantly beneficial, enhancing estimation accuracy, and thereby enabling high-performance mobile positioning in a practical and cost-effective manner. Additionally, it is computationally light-wei

  7. Network Traffic Prediction based on Particle Swarm BP Neural Network

    OpenAIRE

    Yan Zhu; Guanghua Zhang; Jing Qiu

    2013-01-01

    The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Particle swarm optimization is an evolutionary computation technology based on swarm intelligence which can not guarantee global convergence. Artificial Bee Colony algorithm is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony algorithm and part...

  8. Estimates on compressed neural networks regression.

    Science.gov (United States)

    Zhang, Yongquan; Li, Youmei; Sun, Jianyong; Ji, Jiabing

    2015-03-01

    When the neural element number n of neural networks is larger than the sample size m, the overfitting problem arises since there are more parameters than actual data (more variable than constraints). In order to overcome the overfitting problem, we propose to reduce the number of neural elements by using compressed projection A which does not need to satisfy the condition of Restricted Isometric Property (RIP). By applying probability inequalities and approximation properties of the feedforward neural networks (FNNs), we prove that solving the FNNs regression learning algorithm in the compressed domain instead of the original domain reduces the sample error at the price of an increased (but controlled) approximation error, where the covering number theory is used to estimate the excess error, and an upper bound of the excess error is given.

  9. Parameter estimation using compensatory neural networks

    Indian Academy of Sciences (India)

    M Sinha; P K Kalra; K Kumar

    2000-04-01

    Proposed here is a new neuron model, a basis for Compensatory Neural Network Architecture (CNNA), which not only reduces the total number of interconnections among neurons but also reduces the total computing time for training. The suggested model has properties of the basic neuron model as well as the higher neuron model (multiplicative aggregation function). It can adapt to standard neuron and higher order neuron, as well as a combination of the two. This approach is found to estimate the orbit with accuracy significantly better than Kalman Filter (KF) and Feedforward Multilayer Neural Network (FMNN) (also simply referred to as Artificial Neural Network, ANN) with lambda-gamma learning. The typical simulation runs also bring out the superiority of the proposed scheme over Kalman filter from the standpoint of computation time and the amount of data needed for the desired degree of estimated accuracy for the specific problem of orbit determination.

  10. Reconstruction of neutron spectra through neural networks

    International Nuclear Information System (INIS)

    A neural network has been used to reconstruct the neutron spectra starting from the counting rates of the detectors of the Bonner sphere spectrophotometric system. A group of 56 neutron spectra was selected to calculate the counting rates that would produce in a Bonner sphere system, with these data and the spectra it was trained the neural network. To prove the performance of the net, 12 spectra were used, 6 were taken of the group used for the training, 3 were obtained of mathematical functions and those other 3 correspond to real spectra. When comparing the original spectra of those reconstructed by the net we find that our net has a poor performance when reconstructing monoenergetic spectra, this attributes it to those characteristic of the spectra used for the training of the neural network, however for the other groups of spectra the results of the net are appropriate with the prospective ones. (Author)

  11. Hair Loss Diagnosis Using Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Ahmad Esfandiari

    2012-09-01

    Full Text Available Hair is an appendage of the skin that plays an important role in the beauty of people's face. Daily averages of 50 to 80 hairs are shed naturally. Various factors are effective in hair loss. In this paper using the eight influence attributes of gender, age, genetic factors, surgery, pregnancy, Zinc deficiency, iron deficiency, anemia and the use of cosmetics, the amount of hair loss is predicted. This work has been performed using artificial neural networks. 60 percent of the collected data was used for train, 20 percent for validation and the remaining 20 percent is used for testing the neural networks. For this, various training algorithms has been used. The result of the implementation of these algorithms has been compared. It seems that neural networks can be successful to predict hair loss.

  12. Recurrent Neural Network for Computing Outer Inverse.

    Science.gov (United States)

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

    2016-05-01

    Two linear recurrent neural networks for generating outer inverses with prescribed range and null space are defined. Each of the proposed recurrent neural networks is based on the matrix-valued differential equation, a generalization of dynamic equations proposed earlier for the nonsingular matrix inversion, the Moore-Penrose inversion, as well as the Drazin inversion, under the condition of zero initial state. The application of the first approach is conditioned by the properties of the spectrum of a certain matrix; the second approach eliminates this drawback, though at the cost of increasing the number of matrix operations. The cases corresponding to the most common generalized inverses are defined. The conditions that ensure stability of the proposed neural network are presented. Illustrative examples present the results of numerical simulations.

  13. Prediction of metal corrosion by neural networks

    Directory of Open Access Journals (Sweden)

    Z. Jančíková

    2013-07-01

    Full Text Available The contribution deals with the use of artificial neural networks for prediction of steel atmospheric corrosion. Atmospheric corrosion of metal materials exposed under atmospheric conditions depends on various factors such as local temperature, relative humidity, amount of precipitation, pH of rainfall, concentration of main pollutants and exposition time. As these factors are very complex, exact relation for mathematical description of atmospheric corrosion of various metals are not known so far. Classical analytical and mathematical functions are of limited use to describe this type of strongly non-linear system depending on various meteorological-chemical factors and interaction between them and on material parameters. Nowadays there is certain chance to predict a corrosion loss of materials by artificial neural networks. Neural networks are used primarily in real systems, which are characterized by high nonlinearity, considerable complexity and great difficulty of their formal mathematical description.

  14. Assessing Landslide Hazard Using Artificial Neural Network

    DEFF Research Database (Denmark)

    Farrokhzad, Farzad; Choobbasti, Asskar Janalizadeh; Barari, Amin;

    2011-01-01

    neural network has been developed for use in the stability evaluation of slopes under various geological conditions and engineering requirements. The Artificial neural network model of this research uses slope characteristics as input and leads to the output in form of the probability of failure...... and factor of safety. It can be stated that the trained neural networks are capable of predicting the stability of slopes and safety factor of landslide hazard in study area with an acceptable level of confidence. Landslide hazard analysis and mapping can provide useful information for catastrophic loss...... failure" which is main concentration of the current research and "liquefaction failure". Shear failures along shear planes occur when the shear stress along the sliding surfaces exceed the effective shear strength. These slides have been referred to as landslide. An expert system based on artificial...

  15. Classification of radar clutter using neural networks.

    Science.gov (United States)

    Haykin, S; Deng, C

    1991-01-01

    A classifier that incorporates both preprocessing and postprocessing procedures as well as a multilayer feedforward network (based on the back-propagation algorithm) in its design to distinguish between several major classes of radar returns including weather, birds, and aircraft is described. The classifier achieves an average classification accuracy of 89% on generalization for data collected during a single scan of the radar antenna. The procedures of feature selection for neural network training, the classifier design considerations, the learning algorithm development, the implementation, and the experimental results of the neural clutter classifier, which is simulated on a Warp systolic computer, are discussed. A comparative evaluation of the multilayer neural network with a traditional Bayes classifier is presented.

  16. Network Traffic Prediction based on Particle Swarm BP Neural Network

    Directory of Open Access Journals (Sweden)

    Yan Zhu

    2013-11-01

    Full Text Available The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Particle swarm optimization is an evolutionary computation technology based on swarm intelligence which can not guarantee global convergence. Artificial Bee Colony algorithm is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony algorithm and particle swarm optimization algorithm is proposed to optimize the weight and threshold value of BP neural network. After network traffic prediction experiment, we can conclude that optimized BP network traffic prediction based on PSO-ABC has high prediction accuracy and has stable prediction performance.

  17. Accident scenario diagnostics with neural networks

    International Nuclear Information System (INIS)

    Nuclear power plants are very complex systems. The diagnoses of transients or accident conditions is very difficult because a large amount of information, which is often noisy, or intermittent, or even incomplete, need to be processed in real time. To demonstrate their potential application to nuclear power plants, neural networks axe used to monitor the accident scenarios simulated by the training simulator of TVA's Watts Bar Nuclear Power Plant. A self-organization network is used to compress original data to reduce the total number of training patterns. Different accident scenarios are closely related to different key parameters which distinguish one accident scenario from another. Therefore, the accident scenarios can be monitored by a set of small size neural networks, called modular networks, each one of which monitors only one assigned accident scenario, to obtain fast training and recall. Sensitivity analysis is applied to select proper input variables for modular networks

  18. Neural networks and particle physics

    CERN Document Server

    Peterson, Carsten

    1993-01-01

    1. Introduction : Structure of the Central Nervous System Generics2. Feed-forward networks, Perceptions, Function approximators3. Self-organisation, Feature Maps4. Feed-back Networks, The Hopfield model, Optimization problems, Feed-back, Networks, Deformable templates, Graph bisection

  19. Optimal control learning with artificial neural networks

    International Nuclear Information System (INIS)

    This paper shows neural networks capabilities in optimal control applications of non linear dynamic systems. Our method is issued of a classical method concerning the direct research of the optimal control using gradient techniques. We show that neural approach and backpropagation paradigm are able to solve efficiently equations relative to necessary conditions for an optimizing solution. We have taken into account the known capabilities of multi layered networks in approximation functions. And for dynamic systems, we have generalized the indirect learning of inverse model adaptive architecture that is capable to define an optimal control in relation to a temporal criterion. (orig.)

  20. 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.

  1. SAR ATR Based on Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Tian Zhuangzhuang

    2016-06-01

    Full Text Available This study presents a new method of Synthetic Aperture Radar (SAR image target recognition based on a convolutional neural network. First, we introduce a class separability measure into the cost function to improve this network’s ability to distinguish between categories. Then, we extract SAR image features using the improved convolutional neural network and classify these features using a support vector machine. Experimental results using moving and stationary target acquisition and recognition SAR datasets prove the validity of this method.

  2. Contractor Prequalification Based on Neural Networks

    Institute of Scientific and Technical Information of China (English)

    ZHANG Jin-long; YANG Lan-rong

    2002-01-01

    Contractor Prequalification involves the screening of contractors by a project owner, according to a given set of criteria, in order to determine their competence to perform the work if awarded the construction contract. This paper introduces the capabilities of neural networks in solving problems related to contractor prequalification. The neural network systems for contractor prequalification has an input vector of 8 components and an output vector of 1 component. The output vector represents whether a contractor is qualified or not qualified to submit a bid on a project.

  3. Neural network approach to radiologic lesion detection

    International Nuclear Information System (INIS)

    An area of artificial intelligence that has gained recent attention is the neural network approach to pattern recognition. The authors explore the use of neural networks in radiologic lesion detection with what is known in the literature as the novelty filter. This filter uses a linear model; images of normal patterns become training vectors and are stored as columns of a matrix. An image of an abnormal pattern is introduced and the abnormality or novelty is extracted. A VAX 750 was used to encode the novelty filter, and two experiments have been examined

  4. Ferroelectric Memory Capacitors For Neural Networks

    Science.gov (United States)

    Thakoor, Sarita; Moopenn, Alexander W.; Stadler, Henry L.

    1991-01-01

    Thin-film ferroelectric capacitors proposed as nonvolatile analog memory devices. Intended primarily for use as synaptic connections in electronic neural networks. Connection strengths (synaptic weights) stored as nonlinear remanent polarizations of ferroelectric films. Ferroelectric memory and interrogation capacitors combined into memory devices in vertical or lateral configurations. Photoconductive layer modulated by light provides variable resistance to alter bias signal applied to memory capacitor. Features include nondestructive readout, simplicity, and resistance to ionizing radiation. Interrogated without destroying stored analog data. Also amenable to very-large-scale integration. Allows use of ac coupling, eliminating errors caused by dc offsets in amplifier circuits of neural networks.

  5. Spectral classification using convolutional neural networks

    CERN Document Server

    Hála, Pavel

    2014-01-01

    There is a great need for accurate and autonomous spectral classification methods in astrophysics. This thesis is about training a convolutional neural network (ConvNet) to recognize an object class (quasar, star or galaxy) from one-dimension spectra only. Author developed several scripts and C programs for datasets preparation, preprocessing and postprocessing of the data. EBLearn library (developed by Pierre Sermanet and Yann LeCun) was used to create ConvNets. Application on dataset of more than 60000 spectra yielded success rate of nearly 95%. This thesis conclusively proved great potential of convolutional neural networks and deep learning methods in astrophysics.

  6. 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.

  7. Neural networks advances and applications 2

    CERN Document Server

    Gelenbe, E

    1992-01-01

    The present volume is a natural follow-up to Neural Networks: Advances and Applications which appeared one year previously. As the title indicates, it combines the presentation of recent methodological results concerning computational models and results inspired by neural networks, and of well-documented applications which illustrate the use of such models in the solution of difficult problems. The volume is balanced with respect to these two orientations: it contains six papers concerning methodological developments and five papers concerning applications and examples illustrating the theoret

  8. Speech Recognition Method Based on Multilayer Chaotic Neural Network

    Institute of Scientific and Technical Information of China (English)

    REN Xiaolin; HU Guangrui

    2001-01-01

    In this paper,speech recognitionusing neural networks is investigated.Especially,chaotic dynamics is introduced to neurons,and a mul-tilayer chaotic neural network (MLCNN) architectureis built.A learning algorithm is also derived to trainthe weights of the network.We apply the MLCNNto speech recognition and compare the performanceof the network with those of recurrent neural net-work (RNN) and time-delay neural network (TDNN).Experimental results show that the MLCNN methodoutperforms the other neural networks methods withrespect to average recognition rate.

  9. Autonomous robot behavior based on neural networks

    Science.gov (United States)

    Grolinger, Katarina; Jerbic, Bojan; Vranjes, Bozo

    1997-04-01

    The purpose of autonomous robot is to solve various tasks while adapting its behavior to the variable environment, expecting it is able to navigate much like a human would, including handling uncertain and unexpected obstacles. To achieve this the robot has to be able to find solution to unknown situations, to learn experienced knowledge, that means action procedure together with corresponding knowledge on the work space structure, and to recognize working environment. The planning of the intelligent robot behavior presented in this paper implements the reinforcement learning based on strategic and random attempts for finding solution and neural network approach for memorizing and recognizing work space structure (structural assignment problem). Some of the well known neural networks based on unsupervised learning are considered with regard to the structural assignment problem. The adaptive fuzzy shadowed neural network is developed. It has the additional shadowed hidden layer, specific learning rule and initialization phase. The developed neural network combines advantages of networks based on the Adaptive Resonance Theory and using shadowed hidden layer provides ability to recognize lightly translated or rotated obstacles in any direction.

  10. Optimal flux patterns in cellular metabolic networks

    Energy Technology Data Exchange (ETDEWEB)

    Almaas, E

    2007-01-20

    The availability of whole-cell level metabolic networks of high quality has made it possible to develop a predictive understanding of bacterial metabolism. Using the optimization framework of flux balance analysis, I investigate metabolic response and activity patterns to variations in the availability of nutrient and chemical factors such as oxygen and ammonia by simulating 30,000 random cellular environments. The distribution of reaction fluxes is heavy-tailed for the bacteria H. pylori and E. coli, and the eukaryote S. cerevisiae. While the majority of flux balance investigations have relied on implementations of the simplex method, it is necessary to use interior-point optimization algorithms to adequately characterize the full range of activity patterns on metabolic networks. The interior-point activity pattern is bimodal for E. coli and S. cerevisiae, suggesting that most metabolic reaction are either in frequent use or are rarely active. The trimodal activity pattern of H. pylori indicates that a group of its metabolic reactions (20%) are active in approximately half of the simulated environments. Constructing the high-flux backbone of the network for every environment, there is a clear trend that the more frequently a reaction is active, the more likely it is a part of the backbone. Finally, I briefly discuss the predicted activity patterns of the central-carbon metabolic pathways for the sample of random environments.

  11. Neutron spectrum unfolding using neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E. [Universidad Autonoma de Zacatecas, A.P. 336, 98000 Zacatecas (Mexico)]. E-mail: rvega@cantera.reduaz.mx

    2004-07-01

    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 a large set of neutron spectra compiled by the International Atomic Energy Agency. These include spectra from iso- topic neutron sources, reference and operational neutron spectra obtained from accelerators and nuclear reactors. 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 and UTA4 matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and correspondent spectrum was used as output during neural network training. The network has 7 input nodes, 56 neurons as hidden layer and 31 neurons in the output layer. After training the network was tested with the Bonner spheres count rates produced by twelve neutron spectra. The network allows unfolding the neutron spectrum from count rates measured with Bonner spheres. Good results are obtained when testing count rates belong to neutron spectra used during training, acceptable results are obtained for count rates obtained from actual neutron fields; however the network fails when count rates belong to monoenergetic neutron sources. (Author)

  12. Stability prediction of berm breakwater using neural network

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Rao, S.; Manjunath, Y.R.

    In the present study, an artificial neural network method has been applied to predict the stability of berm breakwaters. Four neural network models are constructed based on the parameters which influence the stability of breakwater. Training...

  13. Wave transmission prediction of multilayer floating breakwater using neural network

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Patil, S.G.; Hegde, A.V.

    In the present study, an artificial neural network method has been applied for wave transmission prediction of multilayer floating breakwater. Two neural network models are constructed based on the parameters which influence the wave transmission...

  14. Parameter Identification by Bayes Decision and Neural Networks

    DEFF Research Database (Denmark)

    Kulczycki, P.; Schiøler, Henrik

    1994-01-01

    The problem of parameter identification by Bayes point estimation using neural networks is investigated.......The problem of parameter identification by Bayes point estimation using neural networks is investigated....

  15. Simulated Annealing for Location Area Planning in Cellular networks

    OpenAIRE

    Prajapati, N. B.; R. R. Agravat; Hasan, M I

    2010-01-01

    LA planning in cellular network is useful for minimizing location management cost in GSM network. In fact, size of LA can be optimized to create a balance between the LA update rate and expected paging rate within LA. To get optimal result for LA planning in cellular network simulated annealing algorithm is used. Simulated annealing give optimal results in acceptable run-time.

  16. A Wireless Communications Laboratory on Cellular Network Planning

    Science.gov (United States)

    Dawy, Z.; Husseini, A.; Yaacoub, E.; Al-Kanj, L.

    2010-01-01

    The field of radio network planning and optimization (RNPO) is central for wireless cellular network design, deployment, and enhancement. Wireless cellular operators invest huge sums of capital on deploying, launching, and maintaining their networks in order to ensure competitive performance and high user satisfaction. This work presents a lab…

  17. Simulated Annealing for Location Area Planning in Cellular networks

    Directory of Open Access Journals (Sweden)

    N. B. Prajapati

    2010-03-01

    Full Text Available LA planning in cellular network is useful for minimizing location management cost in GSM network. Infact, size of LA can be optimized to create a balance between the LA update rate and expected pagingrate within LA. To get optimal result for LA planning in cellular network simulated annealing algorithmis used. Simulated annealing give optimal results in acceptable run-time.

  18. Sparse neural networks with large learning diversity

    CERN Document Server

    Gripon, Vincent

    2011-01-01

    Coded recurrent neural networks with three levels of sparsity are introduced. The first level is related to the size of messages, much smaller than the number of available neurons. The second one is provided by a particular coding rule, acting as a local constraint in the neural activity. The third one is a characteristic of the low final connection density of the network after the learning phase. Though the proposed network is very simple since it is based on binary neurons and binary connections, it is able to learn a large number of messages and recall them, even in presence of strong erasures. The performance of the network is assessed as a classifier and as an associative memory.

  19. Neural Networks for Wordform Recognition

    OpenAIRE

    Eineborg, Martin; Gambäck, Björn

    1994-01-01

    The paper outlines a method for automatic lexical acquisition using three-layered back-propagation networks. Several experiments have been carried out where the performance of different network architectures have been compared to each other on two tasks: overall part-of-speech (noun, adjective or verb) classification and classification by a set of 13 possible output categories. The best results for the simple task were obtained by networks consisting of 204-212 input neurons...

  20. Performance Comparison of Neural Networks for HRTFs Approximation

    Institute of Scientific and Technical Information of China (English)

    2000-01-01

    In order to approach to head-related transfer functions (HRTFs), this paper employs and compares three kinds of one-input neural network models, namely, multi-layer perceptron (MLP) networks, radial basis function (RBF) networks and wavelet neural networks (WNN) so as to select the best network model for further HRTFs approximation. Experimental results demonstrate that wavelet neural networks are more efficient and useful.

  1. Dynamic Object Identification with SOM-based neural networks

    Directory of Open Access Journals (Sweden)

    Aleksey Averkin

    2014-03-01

    Full Text Available In this article a number of neural networks based on self-organizing maps, that can be successfully used for dynamic object identification, is described. Unique SOM-based modular neural networks with vector quantized associative memory and recurrent self-organizing maps as modules are presented. The structured algorithms of learning and operation of such SOM-based neural networks are described in details, also some experimental results and comparison with some other neural networks are given.

  2. Simplified Neural Network Design for Hand Written Digit Recognition

    OpenAIRE

    Muhammad Zubair Asghar; Hussain Ahmad; Shakeel Ahmad; Sheikh Muhammad Saqib; Bashir Ahmad; Muhammad Junaid Asghar

    2011-01-01

    Neural Network is abstraction of the central nervous system and works as parallel processing system. Optimization, image processing, Diagnosis and many other applications are made very simple through neural networks, which are difficult and time consuming when conventional methods are used for their implementation. Neural Network is the simplified version of human brain. Like human brain, neural networks also exhibit efficient performance on perceptive tasks like recognition of visual images ...

  3. Remote Sensing Image Segmentation with Probabilistic Neural Networks

    Institute of Scientific and Technical Information of China (English)

    LIU Gang

    2005-01-01

    This paper focuses on the image segmentation with probabilistic neural networks (PNNs). Back propagation neural networks (BpNNs) and multi perceptron neural networks (MLPs) are also considered in this study. Especially, this paper investigates the implementation of PNNs in image segmentation and optimal processing of image segmentation with a PNN. The comparison between image segmentations with PNNs and with other neural networks is given. The experimental results show that PNNs can be successfully applied to image segmentation for good results.

  4. Neural network method for solving elastoplastic finite element problems

    Institute of Scientific and Technical Information of China (English)

    2006-01-01

    A basic optimization principle of Artificial Neural Network-the Lagrange Programming Neural Network (LPNN) model for solving elastoplastic finite element problems is presented. The nonlinear problems of mechanics are represented as a neural network based optimization problem by adopting the nonlinear function as nerve cell transfer function. Finally, two simple elastoplastic problems are numerically simulated. LPNN optimization results for elastoplastic problem are found to be comparable to traditional Hopfield neural network optimization model.

  5. Optimizing neural network models: motivation and case studies

    OpenAIRE

    Harp, S A; T. Samad

    2012-01-01

    Practical successes have been achieved  with neural network models in a variety of domains, including energy-related industry. The large, complex design space presented by neural networks is only minimally explored in current practice. The satisfactory results that nevertheless have been obtained testify that neural networks are a robust modeling technology; at the same time, however, the lack of a systematic design approach implies that the best neural network models generally  rem...

  6. Applications of Neural Networks in Spinning Prediction

    Institute of Scientific and Technical Information of China (English)

    程文红; 陆凯

    2003-01-01

    The neural network spinning prediction model (BP and RBF Networks) trained by data from the mill can predict yarn qualities and spinning performance. The input parameters of the model are as follows: yarn count, diameter, hauteur, bundle strength, spinning draft, spinning speed, traveler number and twist.And the output parameters are: yarn evenness, thin places, tenacity and elongation, ends-down.Predicting results match the testing data well.

  7. Multilingual Text Detection with Nonlinear Neural Network

    OpenAIRE

    Lin Li; Shengsheng Yu; Luo Zhong; Xiaozhen Li

    2015-01-01

    Multilingual text detection in natural scenes is still a challenging task in computer vision. In this paper, we apply an unsupervised learning algorithm to learn language-independent stroke feature and combine unsupervised stroke feature learning and automatically multilayer feature extraction to improve the representational power of text feature. We also develop a novel nonlinear network based on traditional Convolutional Neural Network that is able to detect multilingual text regions in th...

  8. Weighted Learning for Feedforward Neural Networks

    Institute of Scientific and Technical Information of China (English)

    Rong-Fang Xu; Thao-Tsen Chen; Shie-Jue Lee

    2014-01-01

    ⎯In this paper, we propose two weighted learning methods for the construction of single hidden layer feedforward neural networks. Both methods incorporate weighted least squares. Our idea is to allow the training instances nearer to the query to offer bigger contributions to the estimated output. By minimizing the weighted mean square error function, optimal networks can be obtained. The results of a number of experiments demonstrate the effectiveness of our proposed methods.

  9. Local learning algorithm for optical neural networks

    OpenAIRE

    QIAO, YONG; Psaltis, Demetri

    1992-01-01

    An anti-Hebbian local learning algorithm for two-layer optical neural networks is introduced. With this learning rule, the weight update for a certain connection depends only on the input and output of that connection and a global, scalar error signal. Therefore the backpropagation of error signals through the network, as required by the commonly used back error propagation algorithm, is avoided. It still guarantees, however, that the synaptic weights are updated in the error descent directio...

  10. Auto-associative nanoelectronic neural network

    Energy Technology Data Exchange (ETDEWEB)

    Nogueira, C. P. S. M.; Guimarães, J. G. [Departamento de Engenharia Elétrica - Laboratório de Dispositivos e Circuito Integrado, Universidade de Brasília, CP 4386, CEP 70904-970 Brasília DF (Brazil)

    2014-05-15

    In this paper, an auto-associative neural network using single-electron tunneling (SET) devices is proposed and simulated at low temperature. The nanoelectronic auto-associative network is able to converge to a stable state, previously stored during training. The recognition of the pattern involves decreasing the energy of the input state until it achieves a point of local minimum energy, which corresponds to one of the stored patterns.

  11. Designing Deep Learning Neural Networks using Caffe

    OpenAIRE

    Kishore, Anurag; Jindal, Stuti; Singh, Sanjay

    2015-01-01

    This tutorial investigates various tools for designing Deep Learning Neural Networks (DLNN). Our exploration of many tools has revealed that Caffe is the fastest and most appropriate tool for designing DLNNs. We have given step by step procedure for installing and configuring Caffe and its dependencies for designing DLNN.

  12. Chaotic behavior of a layered neural network

    Energy Technology Data Exchange (ETDEWEB)

    Derrida, B.; Meir, R.

    1988-09-15

    We consider the evolution of configurations in a layered feed-forward neural network. Exact expressions for the evolution of the distance between two configurations are obtained in the thermodynamic limit. Our results show that the distance between two arbitrarily close configurations always increases, implying chaotic behavior, even in the phase of good retrieval.

  13. A Modified Algorithm for Feedforward Neural Networks

    Institute of Scientific and Technical Information of China (English)

    夏战国; 管红杰; 李政伟; 孟斌

    2002-01-01

    As a most popular learning algorithm for the feedforward neural networks, the classic BP algorithm has its many shortages. To overcome some of the shortages, a modified learning algorithm is proposed in the article. And the simulation result illustrate the modified algorithm is more effective and practicable.

  14. Nonlinear Time Series Analysis via Neural Networks

    Science.gov (United States)

    Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin

    This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.

  15. Neural Network Output Optimization Using Interval Analysis

    NARCIS (Netherlands)

    De Weerdt, E.; Chu, Q.P.; Mulder, J.A.

    2009-01-01

    The problem of output optimization within a specified input space of neural networks (NNs) with fixed weights is discussed in this paper. The problem is (highly) nonlinear when nonlinear activation functions are used. This global optimization problem is encountered in the reinforcement learning (RL)

  16. NEURAL NETWORK APPROACH FOR EYE DETECTION

    Directory of Open Access Journals (Sweden)

    Vijayalaxmi

    2012-05-01

    Full Text Available Driving support systems, such as car navigation systems are becoming common and they support driver in several aspects. Non-intrusive method of detecting Fatigue and drowsiness based on eye-blink count and eye directed instruction controlhelps the driver to prevent from collision caused by drowsy driving. Eye detection and tracking under various conditions such as illumination, background, face alignment and facial expression makes the problem complex.Neural Network based algorithm is proposed in this paper to detect the eyes efficiently. In the proposed algorithm, first the neural Network is trained to reject the non-eye regionbased on images with features of eyes and the images with features of non-eye using Gabor filter and Support Vector Machines to reduce the dimension and classify efficiently. In the algorithm, first the face is segmented using L*a*btransform color space, then eyes are detected using HSV and Neural Network approach. The algorithm is tested on nearly 100 images of different persons under different conditions and the results are satisfactory with success rate of 98%.The Neural Network is trained with 50 non-eye images and 50 eye images with different angles using Gabor filter. This paper is a part of research work on “Development of Non-Intrusive system for realtime Monitoring and Prediction of Driver Fatigue and drowsiness” project sponsored by Department of Science & Technology, Govt. of India, New Delhi at Vignan Institute of Technology and Sciences, Vignan Hills, Hyderabad.

  17. Applying Artificial Neural Networks for Face Recognition

    Directory of Open Access Journals (Sweden)

    Thai Hoang Le

    2011-01-01

    Full Text Available This paper introduces some novel models for all steps of a face recognition system. In the step of face detection, we propose a hybrid model combining AdaBoost and Artificial Neural Network (ABANN to solve the process efficiently. In the next step, labeled faces detected by ABANN will be aligned by Active Shape Model and Multi Layer Perceptron. In this alignment step, we propose a new 2D local texture model based on Multi Layer Perceptron. The classifier of the model significantly improves the accuracy and the robustness of local searching on faces with expression variation and ambiguous contours. In the feature extraction step, we describe a methodology for improving the efficiency by the association of two methods: geometric feature based method and Independent Component Analysis method. In the face matching step, we apply a model combining many Neural Networks for matching geometric features of human face. The model links many Neural Networks together, so we call it Multi Artificial Neural Network. MIT + CMU database is used for evaluating our proposed methods for face detection and alignment. Finally, the experimental results of all steps on CallTech database show the feasibility of our proposed model.

  18. Empirical generalization assessment of neural network models

    DEFF Research Database (Denmark)

    Larsen, Jan; Hansen, Lars Kai

    1995-01-01

    This paper addresses the assessment of generalization performance of neural network models by use of empirical techniques. We suggest to use the cross-validation scheme combined with a resampling technique to obtain an estimate of the generalization performance distribution of a specific model...

  19. 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.

  20. Localizing Tortoise Nests by Neural Networks.

    Science.gov (United States)

    Barbuti, Roberto; Chessa, Stefano; Micheli, Alessio; Pucci, Rita

    2016-01-01

    The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating). Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS) which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN). We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours), the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition. PMID:26985660

  1. 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...

  2. 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...

  3. Towards semen quality assessment using neural networks

    DEFF Research Database (Denmark)

    Linneberg, Christian; Salamon, P.; Svarer, C.;

    1994-01-01

    The paper presents the methodology and results from a neural net based classification of human sperm head morphology. The methodology uses a preprocessing scheme in which invariant Fourier descriptors are lumped into “energy” bands. The resulting networks are pruned using optimal brain damage. Pe...

  4. 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)

  5. Brain tumor grading based on Neural Networks and Convolutional Neural Networks.

    Science.gov (United States)

    Yuehao Pan; Weimin Huang; Zhiping Lin; Wanzheng Zhu; Jiayin Zhou; Wong, Jocelyn; Zhongxiang Ding

    2015-08-01

    This paper studies brain tumor grading using multiphase MRI images and compares the results with various configurations of deep learning structure and baseline Neural Networks. The MRI images are used directly into the learning machine, with some combination operations between multiphase MRIs. Compared to other researches, which involve additional effort to design and choose feature sets, the approach used in this paper leverages the learning capability of deep learning machine. We present the grading performance on the testing data measured by the sensitivity and specificity. The results show a maximum improvement of 18% on grading performance of Convolutional Neural Networks based on sensitivity and specificity compared to Neural Networks. We also visualize the kernels trained in different layers and display some self-learned features obtained from Convolutional Neural Networks. PMID:26736358

  6. Brain tumor grading based on Neural Networks and Convolutional Neural Networks.

    Science.gov (United States)

    Yuehao Pan; Weimin Huang; Zhiping Lin; Wanzheng Zhu; Jiayin Zhou; Wong, Jocelyn; Zhongxiang Ding

    2015-08-01

    This paper studies brain tumor grading using multiphase MRI images and compares the results with various configurations of deep learning structure and baseline Neural Networks. The MRI images are used directly into the learning machine, with some combination operations between multiphase MRIs. Compared to other researches, which involve additional effort to design and choose feature sets, the approach used in this paper leverages the learning capability of deep learning machine. We present the grading performance on the testing data measured by the sensitivity and specificity. The results show a maximum improvement of 18% on grading performance of Convolutional Neural Networks based on sensitivity and specificity compared to Neural Networks. We also visualize the kernels trained in different layers and display some self-learned features obtained from Convolutional Neural Networks.

  7. SOLVING INVERSE KINEMATICS OF REDUNDANT MANIPULATOR BASED ON NEURAL NETWORK

    Institute of Scientific and Technical Information of China (English)

    2003-01-01

    For the redundant manipulators, neural network is used to tackle the velocity inverse kinematics of robot manipulators. The neural networks utilized are multi-layered perceptions with a back-propagation training algorithm. The weight table is used to save the weights solving the inverse kinematics based on the different optimization performance criteria. Simulations verify the effectiveness of using neural network.

  8. Hidden Neural Networks: A Framework for HMM/NN Hybrids

    DEFF Research Database (Denmark)

    Riis, Søren Kamaric; Krogh, Anders Stærmose

    1997-01-01

    This paper presents a general framework for hybrids of hidden Markov models (HMM) and neural networks (NN). In the new framework called hidden neural networks (HNN) the usual HMM probability parameters are replaced by neural network outputs. To ensure a probabilistic interpretation the HNN...

  9. Self-Organizing Multilayered Neural Networks of Optimal Complexity

    OpenAIRE

    Schetinin, V.

    2005-01-01

    The principles of self-organizing the neural networks of optimal complexity is considered under the unrepresentative learning set. The method of self-organizing the multi-layered neural networks is offered and used to train the logical neural networks which were applied to the medical diagnostics.

  10. A brief review of feed-forward neural networks

    OpenAIRE

    SAZLI, Murat Hüsnü

    2006-01-01

    Artificial neural networks, or shortly neural networks, find applications in a very wide spectrum. In this paper, following a brief presentation of the basic aspects of feed-forward neural networks, their mostly used learning/training algorithm, the so-called back-propagation algorithm, have been described.

  11. Extracting Knowledge from Supervised Neural Networks in Image Procsssing

    NARCIS (Netherlands)

    Zwaag, van der Berend Jan; Slump, Kees; Spaanenburg, Lambert; Jain, R.; Abraham, A.; Faucher, C.; Zwaag, van der B.J.

    2003-01-01

    Despite their success-story, artificial 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 as a my

  12. Analysis of Neural Networks in Terms of Domain Functions

    NARCIS (Netherlands)

    Zwaag, van der Berend Jan; Slump, Cees; Spaanenburg, Lambert

    2002-01-01

    Despite their success-story, artificial 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 as a my

  13. Recognition of Continuous Digits by Quantum Neural Networks

    Institute of Scientific and Technical Information of China (English)

    2003-01-01

    This paper describes a new kind of neural network-Quantum Neural Network (QNN) and its application to recognition of continuous digits. QNN combines the advantages of neural modeling and fuzzy theoretic principles. Experiment results show that more than 15 percent error reduction is achieved on a speaker-independent continuous digits recognition task compared with BP networks.

  14. A Direct Feedback Control Based on Fuzzy Recurrent Neural Network

    Institute of Scientific and Technical Information of China (English)

    李明; 马小平

    2002-01-01

    A direct feedback control system based on fuzzy-recurrent neural network is proposed, and a method of training weights of fuzzy-recurrent neural network was designed by applying modified contract mapping genetic algorithm. Computer simul ation results indicate that fuzzy-recurrent neural network controller has perfect dynamic and static performances .

  15. Combining neural networks for protein secondary structure prediction

    DEFF Research Database (Denmark)

    Riis, Søren Kamaric

    1995-01-01

    In this paper structured neural networks are applied to the problem of predicting the secondary structure of proteins. A hierarchical approach is used where specialized neural networks are designed for each structural class and then combined using another neural network. The submodels are designed...

  16. A Fuzzy Neural Network for Fault Pattern Recognition

    Institute of Scientific and Technical Information of China (English)

    2001-01-01

    This paper combines fuzzy set theory with AR T neural network, and demonstrates some important properties of the fuzzy ART neural network algorithm. The results from application on a ball bearing diagnosis indicate that a fuzzy ART neural network has an effect of fast stable recognition for fuzzy patterns.

  17. A novel method combining cellular neural networks and the coupled nonlinear oscillators' paradigm involving a related bifurcation analysis for robust image contrast enhancement in dynamically changing difficult visual environments

    International Nuclear Information System (INIS)

    It is well known that a machine vision-based analysis of a dynamic scene, for example in the context of advanced driver assistance systems (ADAS), does require real-time processing capabilities. Therefore, the system used must be capable of performing both robust and ultrafast analyses. Machine vision in ADAS must fulfil the above requirements when dealing with a dynamically changing visual context (i.e. driving in darkness or in a foggy environment, etc). Among the various challenges related to the analysis of a dynamic scene, this paper focuses on contrast enhancement, which is a well-known basic operation to improve the visual quality of an image (dynamic or static) suffering from poor illumination. The key objective is to develop a systematic and fundamental concept for image contrast enhancement that should be robust despite a dynamic environment and that should fulfil the real-time constraints by ensuring an ultrafast analysis. It is demonstrated that the new approach developed in this paper is capable of fulfilling the expected requirements. The proposed approach combines the good features of the 'coupled oscillators'-based signal processing paradigm with the good features of the 'cellular neural network (CNN)'-based one. The first paradigm in this combination is the 'master system' and consists of a set of coupled nonlinear ordinary differential equations (ODEs) that are (a) the so-called 'van der Pol oscillator' and (b) the so-called 'Duffing oscillator'. It is then implemented or realized on top of a 'slave system' platform consisting of a CNN-processors platform. An offline bifurcation analysis is used to find out, a priori, the windows of parameter settings in which the coupled oscillator system exhibits the best and most appropriate behaviours of interest for an optimal resulting image processing quality. In the frame of the extensive bifurcation analysis carried out, analytical formulae have been derived, which are capable of determining the various

  18. Stability analysis of Markovian jumping stochastic Cohen—Grossberg neural networks with discrete and distributed time varying delays

    Science.gov (United States)

    M. Syed, Ali

    2014-06-01

    In this paper, the global asymptotic stability problem of Markovian jumping stochastic Cohen—Grossberg neural networks with discrete and distributed time-varying delays (MJSCGNNs) is considered. A novel LMI-based stability criterion is obtained by constructing a new Lyapunov functional to guarantee the asymptotic stability of MJSCGNNs. Our results can be easily verified and they are also less restrictive than previously known criteria and can be applied to Cohen—Grossberg neural networks, recurrent neural networks, and cellular neural networks. Finally, the proposed stability conditions are demonstrated with numerical examples.

  19. Hopfield Neural Network Approach to Clustering in Mobile Radio Networks

    Institute of Scientific and Technical Information of China (English)

    JiangYan; LiChengshu

    1995-01-01

    In this paper ,the Hopfield neural network(NN) algorithm is developed for selecting gateways in cluster linkage.The linked cluster(LC) architecture is assumed to achieve distributed network control in multihop radio networks throrgh the local controllers,called clusterheads and the nodes connecting these clusterheads are defined to be gateways.In Hopfield NN models ,the most critical issue being the determination of connection weights,we use the approach of Lagrange multipliers(LM) for its dynamic nature.

  20. From Designing A Single Neural Network to Designing Neural Network Ensembles

    Institute of Scientific and Technical Information of China (English)

    Liu Yong; Zou Xiu-fer

    2003-01-01

    This paper introduces supervised learning model,and surveys related research work. The paper is organised as follows. A supervised learning model is firstly described. The bias variance trade-off is then discussed for the supervised learning model. Based on the bias variance trade-off, both the single neural network approaches and the neural network en semble approaches are overviewed, and problems with the existing approaches are indicated. Finally, the paper concludes with specifying potential future research directions.

  1. A Fuzzy Quantum Neural Network and Its Application in Pattern Recognition

    Institute of Scientific and Technical Information of China (English)

    MIAOFuyou; XIONGYan; CHENHuanhuan; WANGXingfu

    2005-01-01

    This paper proposes a fuzzy quantum neural network model combining quantum neural network and fuzzy logic, which applies the fuzzy logic to design the collapse rules of the quantum neural network, and solves the character recognition problem. Theoretical analysis and experimental results show that fuzzy quantum neural network improves recognizing veracity than the traditional neural network and quantum neural network.

  2. Color control of printers by neural networks

    Science.gov (United States)

    Tominaga, Shoji

    1998-07-01

    A method is proposed for solving the mapping problem from the 3D color space to the 4D CMYK space of printer ink signals by means of a neural network. The CIE-L*a*b* color system is used as the device-independent color space. The color reproduction problem is considered as the problem of controlling an unknown static system with four inputs and three outputs. A controller determines the CMYK signals necessary to produce the desired L*a*b* values with a given printer. Our solution method for this control problem is based on a two-phase procedure which eliminates the need for UCR and GCR. The first phase determines a neural network as a model of the given printer, and the second phase determines the combined neural network system by combining the printer model and the controller in such a way that it represents an identity mapping in the L*a*b* color space. Then the network of the controller part realizes the mapping from the L*a*b* space to the CMYK space. Practical algorithms are presented in the form of multilayer feedforward networks. The feasibility of the proposed method is shown in experiments using a dye sublimation printer and an ink jet printer.

  3. 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.

  4. a Heterosynaptic Learning Rule for Neural Networks

    Science.gov (United States)

    Emmert-Streib, Frank

    In this article we introduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.

  5. Fuzzy logic and neural network technologies

    Science.gov (United States)

    Villarreal, James A.; Lea, Robert N.; Savely, Robert T.

    1992-01-01

    Applications of fuzzy logic technologies in NASA projects are reviewed to examine their advantages in the development of neural networks for aerospace and commercial expert systems and control. Examples of fuzzy-logic applications include a 6-DOF spacecraft controller, collision-avoidance systems, and reinforcement-learning techniques. The commercial applications examined include a fuzzy autofocusing system, an air conditioning system, and an automobile transmission application. The practical use of fuzzy logic is set in the theoretical context of artificial neural systems (ANSs) to give the background for an overview of ANS research programs at NASA. The research and application programs include the Network Execution and Training Simulator and faster training algorithms such as the Difference Optimized Training Scheme. The networks are well suited for pattern-recognition applications such as predicting sunspots, controlling posture maintenance, and conducting adaptive diagnoses.

  6. Computationally Efficient Neural Network Intrusion Security Awareness

    Energy Technology Data Exchange (ETDEWEB)

    Todd Vollmer; Milos Manic

    2009-08-01

    An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.

  7. The Stellar parametrization using Artificial Neural Network

    CERN Document Server

    Giridhar, Sunetra; Kunder, Andrea; Muneer, S; Kumar, G Selva

    2012-01-01

    An update on recent methods for automated stellar parametrization is given. We present preliminary results of the ongoing program for rapid parametrization of field stars using medium resolution spectra obtained using Vainu Bappu Telescope at VBO, Kavalur, India. We have used Artificial Neural Network for estimating temperature, gravity, metallicity and absolute magnitude of the field stars. The network for each parameter is trained independently using a large number of calibrating stars. The trained network is used for estimating atmospheric parameters of unexplored field stars.

  8. Reconstruction of periodic signals using neural networks

    Directory of Open Access Journals (Sweden)

    José Danilo Rairán Antolines

    2014-01-01

    Full Text Available In this paper, we reconstruct a periodic signal by using two neural networks. The first network is trained to approximate the period of a signal, and the second network estimates the corresponding coefficients of the signal's Fourier expansion. The reconstruction strategy consists in minimizing the mean-square error via backpro-pagation algorithms over a single neuron with a sine transfer function. Additionally, this paper presents mathematical proof about the quality of the approximation as well as a first modification of the algorithm, which requires less data to reach the same estimation; thus making the algorithm suitable for real-time implementations.

  9. Distribution network planning algorithm based on Hopfield neural network

    Institute of Scientific and Technical Information of China (English)

    GAO Wei-xin; LUO Xian-jue

    2005-01-01

    This paper presents a new algorithm based on Hopfield neural network to find the optimal solution for an electric distribution network. This algorithm transforms the distribution power network-planning problem into a directed graph-planning problem. The Hopfield neural network is designed to decide the in-degree of each node and is in combined application with an energy function. The new algorithm doesn't need to code city streets and normalize data, so the program is easier to be realized. A case study applying the method to a district of 29 street proved that an optimal solution for the planning of such a power system could be obtained by only 26 iterations. The energy function and algorithm developed in this work have the following advantages over many existing algorithms for electric distribution network planning: fast convergence and unnecessary to code all possible lines.

  10. The importance of artificial neural networks in biomedicine

    Energy Technology Data Exchange (ETDEWEB)

    Burke, H.B. [New York Medical College, Valhalla, NY (United States)

    1995-12-31

    The future explanatory power in biomedicine will be at the molecular-genetic level of analysis (rather than the epidemiologic-demographic or anatomic-cellular levels). This is the level of complex systems. Complex systems are characterized by nonlinearity and complex interactions. It is difficult for traditional statistical methods to capture complex systems because traditional methods attempt to find the model that best fits the statistician`s understanding of the phenomenon; complex systems are difficult to understand and therefore difficult to fit with a simple model. Artificial neural networks are nonparametric regression models. They can capture any phenomena, to any degree of accuracy (depending on the adequacy of the data and the power of the predictors), without prior knowledge of the phenomena. Further, artificial neural networks can be represented, not only as formulae, but also as graphical models. Graphical models can increase analytic power and flexibility. Artificial neural networks are a powerful method for capturing complex phenomena, but their use requires a paradigm shift, from exploratory analysis of the data to exploratory analysis of the model.

  11. Inference and contradictory analysis for binary neural networks

    Institute of Scientific and Technical Information of China (English)

    郭宝龙; 郭雷

    1996-01-01

    A weak-inference theory and a contradictory analysis for binary neural networks (BNNs).are presented.The analysis indicates that the essential reason why a neural network is changing its slates is the existence of superior contradiction inside the network,and that the process by which a neural network seeks a solution corresponds to eliminating the superior contradiction.Different from general constraint satisfaction networks,the solutions found by BNNs may contain inferior contradiction but not superior contradiction.

  12. Connectivity-driven Attachment in Mobile Cellular Ad Hoc Networks

    OpenAIRE

    Boite, Julien; Leguay, Jérémie

    2014-01-01

    International audience Cellular wireless technologies (e.g. LTE) can be used to build cellular ad hoc networks. In this new class of ad hoc networks, nodes are equipped with two radio interfaces: one being a terminal, the other one being an access point. In this context, attachment decisions based on traditional criteria (e.g. signal quality) may lead to network partitions or suboptimal path lengths, thus making access point selection critical to ensure efficient network connectivity. This...

  13. 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

  14. Cancer classification based on gene expression using neural networks.

    Science.gov (United States)

    Hu, H P; Niu, Z J; Bai, Y P; Tan, X H

    2015-12-21

    Based on gene expression, we have classified 53 colon cancer patients with UICC II into two groups: relapse and no relapse. Samples were taken from each patient, and gene information was extracted. Of the 53 samples examined, 500 genes were considered proper through analyses by S-Kohonen, BP, and SVM neural networks. Classification accuracy obtained by S-Kohonen neural network reaches 91%, which was more accurate than classification by BP and SVM neural networks. The results show that S-Kohonen neural network is more plausible for classification and has a certain feasibility and validity as compared with BP and SVM neural networks.

  15. Membership generation using multilayer neural network

    Science.gov (United States)

    Kim, Jaeseok

    1992-01-01

    There has been intensive research in neural network applications to pattern recognition problems. Particularly, the back-propagation network has attracted many researchers because of its outstanding performance in pattern recognition applications. In this section, we describe a new method to generate membership functions from training data using a multilayer neural network. The basic idea behind the approach is as follows. The output values of a sigmoid activation function of a neuron bear remarkable resemblance to membership values. Therefore, we can regard the sigmoid activation values as the membership values in fuzzy set theory. Thus, in order to generate class membership values, we first train a suitable multilayer network using a training algorithm such as the back-propagation algorithm. After the training procedure converges, the resulting network can be treated as a membership generation network, where the inputs are feature values and the outputs are membership values in the different classes. This method allows fairly complex membership functions to be generated because the network is highly nonlinear in general. Also, it is to be noted that the membership functions are generated from a classification point of view. For pattern recognition applications, this is highly desirable, although the membership values may not be indicative of the degree of typicality of a feature value in a particular class.

  16. Phase Diagram of Spiking Neural Networks

    Directory of Open Access Journals (Sweden)

    Hamed eSeyed-Allaei

    2015-03-01

    Full Text Available In computer simulations of spiking neural networks, often it is assumed that every two neurons of the network are connected by a probablilty of 2%, 20% of neurons are inhibitory and 80% are excitatory. These common values are based on experiments, observations. but here, I take a different perspective, inspired by evolution. I simulate many networks, each with a different set of parameters, and then I try to figure out what makes the common values desirable by nature. Networks which are configured according to the common values, have the best dynamic range in response to an impulse and their dynamic range is more robust in respect to synaptic weights. In fact, evolution has favored networks of best dynamic range. I present a phase diagram that shows the dynamic ranges of different networks of different parameteres. This phase diagram gives an insight into the space of parameters -- excitatory to inhibitory ratio, sparseness of connections and synaptic weights. It may serve as a guideline to decide about the values of parameters in a simulation of spiking neural network.

  17. Clustering in mobile ad hoc network based on neural network

    Institute of Scientific and Technical Information of China (English)

    CHEN Ai-bin; CAI Zi-xing; HU De-wen

    2006-01-01

    An on-demand distributed clustering algorithm based on neural network was proposed. The system parameters and the combined weight for each node were computed, and cluster-heads were chosen using the weighted clustering algorithm, then a training set was created and a neural network was trained. In this algorithm, several system parameters were taken into account, such as the ideal node-degree, the transmission power, the mobility and the battery power of the nodes. The algorithm can be used directly to test whether a node is a cluster-head or not. Moreover, the clusters recreation can be speeded up.

  18. Computational capabilities of recurrent NARX neural networks.

    Science.gov (United States)

    Siegelmann, H T; Horne, B G; Giles, C L

    1997-01-01

    Recently, fully connected recurrent neural networks have been proven to be computationally rich-at least as powerful as Turing machines. This work focuses on another network which is popular in control applications and has been found to be very effective at learning a variety of problems. These networks are based upon Nonlinear AutoRegressive models with eXogenous Inputs (NARX models), and are therefore called NARX networks. As opposed to other recurrent networks, NARX networks have a limited feedback which comes only from the output neuron rather than from hidden states. They are formalized by y(t)=Psi(u(t-n(u)), ..., u(t-1), u(t), y(t-n(y)), ..., y(t-1)) where u(t) and y(t) represent input and output of the network at time t, n(u) and n(y) are the input and output order, and the function Psi is the mapping performed by a Multilayer Perceptron. We constructively prove that the NARX networks with a finite number of parameters are computationally as strong as fully connected recurrent networks and thus Turing machines. We conclude that in theory one can use the NARX models, rather than conventional recurrent networks without any computational loss even though their feedback is limited. Furthermore, these results raise the issue of what amount of feedback or recurrence is necessary for any network to be Turing equivalent and what restrictions on feedback limit computational power. PMID:18255858

  19. Mechanical stress in abdominal aortic aneurysms using artificial neural networks

    OpenAIRE

    Soudah Prieto, Eduardo; Rodriguez, Jose; López González, Roberto

    2015-01-01

    Combination of numerical modeling and artificial intelligence (AI) in bioengineering processes are a promising pathway for the further development of bioengineering sciences. The objective of this work is to use Artificial Neural Networks (ANN) to reduce the long computational times needed in the analysis of shear stress in the Abdominal Aortic Aneurysm (AAA) by finite element methods (FEM). For that purpose two different neural networks are created. The first neural network (Mesh Neural Netw...

  20. The EEG signal prediction bz using neural network

    OpenAIRE

    Babušiak, B.; Mohylová, J.

    2008-01-01

    The neural network is computational model based on the features abstraction of biological neural systems. The neural networks have many ways of usage in technical field. They have been applied successfully to speech recognition, image analysis and adaptive control, in order to construct software agents or autonomous robots. In this paper is described usage of neural networks for ECG signal prediction. The ECG signal prediction can be used for automated detection of irregular heart...

  1. The EEG Signal Prediction by Using Neural Network

    OpenAIRE

    Branko Babusiak; Jitka Mohylova

    2008-01-01

    The neural network is computational model based on the features abstraction of biological neural systems. The neural networks have many ways of usage in technical field. They have been applied successfully to speech recognition, image analysis and adaptive control, in order to construct software agents or autonomous robots. In this paper is described usage of neural networks for ECG signal prediction. The ECG signal prediction can be used for  automated detection of irregular heartbeat – extr...

  2. Evolving Chart Pattern Sensitive Neural Network Based Forex Trading Agents

    CERN Document Server

    Sher, Gene I

    2011-01-01

    Though machine learning has been applied to the foreign exchange market for quiet some time now, and neural networks have been shown to yield good results, in modern approaches neural network systems are optimized through the traditional methods, and their input signals are vectors containing prices and other indicator elements. The aim of this paper is twofold, the presentation and testing of the application of topology and weight evolving artificial neural network (TWEANN) systems to automated currency trading, and the use of chart images as input to a geometrical regularity aware indirectly encoded neural network systems. This paper presents the benchmark results of neural network based automated currency trading systems evolved using TWEANNs, and compares the generalization capabilities of these direct encoded neural networks which use the standard price vector inputs, and the indirect (substrate) encoded neural networks which use chart images as input. The TWEANN algorithm used to evolve these currency t...

  3. A Projection Neural Network for Constrained Quadratic Minimax Optimization.

    Science.gov (United States)

    Liu, Qingshan; Wang, Jun

    2015-11-01

    This paper presents a projection neural network described by a dynamic system for solving constrained quadratic minimax programming problems. Sufficient conditions based on a linear matrix inequality are provided for global convergence of the proposed neural network. Compared with some of the existing neural networks for quadratic minimax optimization, the proposed neural network in this paper is capable of solving more general constrained quadratic minimax optimization problems, and the designed neural network does not include any parameter. Moreover, the neural network has lower model complexities, the number of state variables of which is equal to that of the dimension of the optimization problems. The simulation results on numerical examples are discussed to demonstrate the effectiveness and characteristics of the proposed neural network.

  4. Convolutional Neural Network Based dem Super Resolution

    Science.gov (United States)

    Chen, Zixuan; Wang, Xuewen; Xu, Zekai; Hou, Wenguang

    2016-06-01

    DEM super resolution is proposed in our previous publication to improve the resolution for a DEM on basis of some learning examples. Meanwhile, the nonlocal algorithm is introduced to deal with it and lots of experiments show that the strategy is feasible. In our publication, the learning examples are defined as the partial original DEM and their related high measurements due to this way can avoid the incompatibility between the data to be processed and the learning examples. To further extent the applications of this new strategy, the learning examples should be diverse and easy to obtain. Yet, it may cause the problem of incompatibility and unrobustness. To overcome it, we intend to investigate a convolutional neural network based method. The input of the convolutional neural network is a low resolution DEM and the output is expected to be its high resolution one. A three layers model will be adopted. The first layer is used to detect some features from the input, the second integrates the detected features to some compressed ones and the final step transforms the compressed features as a new DEM. According to this designed structure, some learning DEMs will be taken to train it. Specifically, the designed network will be optimized by minimizing the error of the output and its expected high resolution DEM. In practical applications, a testing DEM will be input to the convolutional neural network and a super resolution will be obtained. Many experiments show that the CNN based method can obtain better reconstructions than many classic interpolation methods.

  5. Character Recognition Using Genetically Trained Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

    Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.

    1998-10-01

    Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the

  6. Analytical Modeling of Uplink Cellular Networks

    CERN Document Server

    Novlan, Thomas D; Andrews, Jeffrey G

    2012-01-01

    Cellular uplink analysis has typically been undertaken by either a simple approach that lumps all interference into a single deterministic or random parameter in a Wyner-type model, or via complex system level simulations that often do not provide insight into why various trends are observed. This paper proposes a novel middle way that is both accurate and also results in easy-to-evaluate integral expressions based on the Laplace transform of the interference. We assume mobiles and base stations are randomly placed in the network with each mobile pairing up to its closest base station. The model requires two important changes compared to related recent work on the downlink. First, dependence is introduced between the user and base station point processes to make sure each base station serves a single mobile in the given resource block. Second, per-mobile power control is included, which further couples the locations of the mobiles and their receiving base stations. Nevertheless, we succeed in deriving the cov...

  7. Classification of Epileptic EEG Signals using Time-Delay Neural Networks and Probabilistic Neural Networks

    Directory of Open Access Journals (Sweden)

    Ateke Goshvarpour

    2013-05-01

    Full Text Available The aim of this paper is to investigate the performance of time delay neural networks (TDNNs and the probabilistic neural networks (PNNs trained with nonlinear features (Lyapunov exponents and Entropy on electroencephalogram signals (EEG in a specific pathological state. For this purpose, two types of EEG signals (normal and partial epilepsy are analyzed. To evaluate the performance of the classifiers, mean square error (MSE and elapsed time of each classifier are examined. The results show that TDNN with 12 neurons in hidden layer result in a lower MSE with the training time of about 19.69 second. According to the results, when the sigma values are lower than 0.56, the best performance in the proposed probabilistic neural network structure is achieved. The results of present study show that applying the nonlinear features to train these networks can serve as useful tool in classifying of the EEG signals.

  8. Neural network correction of astrometric chromaticity

    CERN Document Server

    Gai, M

    2005-01-01

    In this paper we deal with the problem of chromaticity, i.e. apparent position variation of stellar images with their spectral distribution, using neural networks to analyse and process astronomical images. The goal is to remove this relevant source of systematic error in the data reduction of high precision astrometric experiments, like Gaia. This task can be accomplished thanks to the capability of neural networks to solve a nonlinear approximation problem, i.e. to construct an hypersurface that approximates a given set of scattered data couples. Images are encoded associating each of them with conveniently chosen moments, evaluated along the y axis. The technique proposed, in the current framework, reduces the initial chromaticity of few milliarcseconds to values of few microarcseconds.

  9. Automatic breast density classification using neural network

    Science.gov (United States)

    Arefan, D.; Talebpour, A.; Ahmadinejhad, N.; Kamali Asl, A.

    2015-12-01

    According to studies, the risk of breast cancer directly associated with breast density. Many researches are done on automatic diagnosis of breast density using mammography. In the current study, artifacts of mammograms are removed by using image processing techniques and by using the method presented in this study, including the diagnosis of points of the pectoral muscle edges and estimating them using regression techniques, pectoral muscle is detected with high accuracy in mammography and breast tissue is fully automatically extracted. In order to classify mammography images into three categories: Fatty, Glandular, Dense, a feature based on difference of gray-levels of hard tissue and soft tissue in mammograms has been used addition to the statistical features and a neural network classifier with a hidden layer. Image database used in this research is the mini-MIAS database and the maximum accuracy of system in classifying images has been reported 97.66% with 8 hidden layers in neural network.

  10. Web Page Categorization Using Artificial Neural Networks

    CERN Document Server

    Kamruzzaman, S M

    2010-01-01

    Web page categorization is one of the challenging tasks in the world of ever increasing web technologies. There are many ways of categorization of web pages based on different approach and features. This paper proposes a new dimension in the way of categorization of web pages using artificial neural network (ANN) through extracting the features automatically. Here eight major categories of web pages have been selected for categorization; these are business & economy, education, government, entertainment, sports, news & media, job search, and science. The whole process of the proposed system is done in three successive stages. In the first stage, the features are automatically extracted through analyzing the source of the web pages. The second stage includes fixing the input values of the neural network; all the values remain between 0 and 1. The variations in those values affect the output. Finally the third stage determines the class of a certain web page out of eight predefined classes. This stage i...

  11. Artificial Neural Network for Displacement Vectors Determination

    Directory of Open Access Journals (Sweden)

    P. Bohmann

    1997-09-01

    Full Text Available An artificial neural network (NN for displacement vectors (DV determination is presented in this paper. DV are computed in areas which are essential for image analysis and computer vision, in areas where are edges, lines, corners etc. These special features are found by edges operators with the following filtration. The filtration is performed by a threshold function. The next step is DV computation by 2D Hamming artificial neural network. A method of DV computation is based on the full search block matching algorithms. The pre-processing (edges finding is the reason why the correlation function is very simple, the process of DV determination needs less computation and the structure of the NN is simpler.

  12. Automatic breast density classification using neural network

    International Nuclear Information System (INIS)

    According to studies, the risk of breast cancer directly associated with breast density. Many researches are done on automatic diagnosis of breast density using mammography. In the current study, artifacts of mammograms are removed by using image processing techniques and by using the method presented in this study, including the diagnosis of points of the pectoral muscle edges and estimating them using regression techniques, pectoral muscle is detected with high accuracy in mammography and breast tissue is fully automatically extracted. In order to classify mammography images into three categories: Fatty, Glandular, Dense, a feature based on difference of gray-levels of hard tissue and soft tissue in mammograms has been used addition to the statistical features and a neural network classifier with a hidden layer. Image database used in this research is the mini-MIAS database and the maximum accuracy of system in classifying images has been reported 97.66% with 8 hidden layers in neural network

  13. Multi-Dimensional Recurrent Neural Networks

    CERN Document Server

    Graves, Alex; Schmidhuber, Juergen

    2007-01-01

    Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to input warping, and the ability to access contextual information, are also desirable in multidimensional domains. However, there has so far been no direct way of applying RNNs to data with more than one spatio-temporal dimension. This paper introduces multi-dimensional recurrent neural networks (MDRNNs), thereby extending the potential applicability of RNNs to vision, video processing, medical imaging and many other areas, while avoiding the scaling problems that have plagued other multi-dimensional models. Experimental results are provided for two image segmentation tasks.

  14. Face Recognition using Eigenfaces and Neural Networks

    Directory of Open Access Journals (Sweden)

    Mohamed Rizon

    2006-01-01

    Full Text Available In this study, we develop a computational model to identify the face of an unknown person’s by applying eigenfaces. The eigenfaces has been applied to extract the basic face of the human face images. The eigenfaces is then projecting onto human faces to identify unique features vectors. This significant features vector can be used to identify an unknown face by using the backpropagation neural network that utilized euclidean distance for classification and recognition. The ORL database for this investigation consists of 40 people with various 400 face images had been used for the learning. The eigenfaces including implemented Jacobi’s method for eigenvalues and eigenvectors has been performed. The classification and recognition using backpropagation neural network showed impressive positive result to classify face images.

  15. Supervised Sequence Labelling with Recurrent Neural Networks

    CERN Document Server

    Graves, Alex

    2012-01-01

    Supervised sequence labelling is a vital area of machine learning, encompassing tasks such as speech, handwriting and gesture recognition, protein secondary structure prediction and part-of-speech tagging. Recurrent neural networks are powerful sequence learning tools—robust to input noise and distortion, able to exploit long-range contextual information—that would seem ideally suited to such problems. However their role in large-scale sequence labelling systems has so far been auxiliary.    The goal of this book is a complete framework for classifying and transcribing sequential data with recurrent neural networks only. Three main innovations are introduced in order to realise this goal. Firstly, the connectionist temporal classification output layer allows the framework to be trained with unsegmented target sequences, such as phoneme-level speech transcriptions; this is in contrast to previous connectionist approaches, which were dependent on error-prone prior segmentation. Secondly, multidimensional...

  16. Neural network prediction of solar cycle 24

    Institute of Scientific and Technical Information of China (English)

    A. Ajabshirizadeh; N. Masoumzadeh Jouzdani; Shahram Abbassi

    2011-01-01

    The ability to predict the future behavior of solar activity has become extremely import due to its effect on the environment near the Earth. Predictions of both the amplitude and timing of the next solar cycle will assist in estimating the various consequences of space weather. The level of solar activity is usually expressed by international sunspot number (Rz). Several prediction techniques have been applied and have achieved varying degrees of success in the domain of solar activity prediction.We predict a solar index (Rz) in solar cycle 24 by using a neural network method. The neural network technique is used to analyze the time series of solar activity. According to our predictions of yearly sunspot number, the maximum of cycle 24 will occur in the year 2013 and will have an annual mean sunspot number of 65. Finally, we discuss our results in order to compare them with other suggested predictions.

  17. Learning in Neural Networks: VLSI Implementation Strategies

    Science.gov (United States)

    Duong, Tuan Anh

    1995-01-01

    Fully-parallel hardware neural network implementations may be applied to high-speed recognition, classification, and mapping tasks in areas such as vision, or can be used as low-cost self-contained units for tasks such as error detection in mechanical systems (e.g. autos). Learning is required not only to satisfy application requirements, but also to overcome hardware-imposed limitations such as reduced dynamic range of connections.

  18. Improving Recurrent Neural Networks For Sequence Labelling

    OpenAIRE

    Dinarelli, Marco; Tellier, Isabelle

    2016-01-01

    In this paper we study different types of Recurrent Neural Networks (RNN) for sequence labeling tasks. We propose two new variants of RNNs integrating improvements for sequence labeling, and we compare them to the more traditional Elman and Jordan RNNs. We compare all models, either traditional or new, on four distinct tasks of sequence labeling: two on Spoken Language Understanding (ATIS and MEDIA); and two of POS tagging for the French Treebank (FTB) and the Penn Treebank (PTB) corpora. The...

  19. Deep convolutional neural networks for pedestrian detection

    OpenAIRE

    Tomè, Denis; Monti, Federico; Baroffio, Luca; Bondi, Luca; Tagliasacchi, Marco; Tubaro, Stefano

    2015-01-01

    Pedestrian detection is a popular research topic due to its paramount importance for a number of applications, especially in the fields of automotive, surveillance and robotics. Despite the significant improvements, pedestrian detection is still an open challenge that calls for more and more accurate algorithms. In the last few years, deep learning and in particular convolutional neural networks emerged as the state of the art in terms of accuracy for a number of computer vision tasks such as...

  20. Diagnosing process faults using neural network models

    Energy Technology Data Exchange (ETDEWEB)

    Buescher, K.L.; Jones, R.D.; Messina, M.J.

    1993-11-01

    In order to be of use for realistic problems, a fault diagnosis method should have the following three features. First, it should apply to nonlinear processes. Second, it should not rely on extensive amounts of data regarding previous faults. Lastly, it should detect faults promptly. The authors present such a scheme for static (i.e., non-dynamic) systems. It involves using a neural network to create an associative memory whose fixed points represent the normal behavior of the system.

  1. Differential Recurrent Neural Networks for Action Recognition

    OpenAIRE

    Veeriah, Vivek; Zhuang, Naifan; Qi, Guo-Jun

    2015-01-01

    The long short-term memory (LSTM) neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from long input sequences. It has the potential to model any sequential time-series data, where the current hidden state has to be considered in the context of the past hidden states. This property makes LSTM an ideal choice to learn the complex dynamics of various actions. Unfortunately, the conventional LSTMs do not co...

  2. Neural network with dynamically adaptable neurons

    Science.gov (United States)

    Tawel, Raoul (Inventor)

    1994-01-01

    This invention is an adaptive neuron for use in neural network processors. The adaptive neuron participates in the supervised learning phase of operation on a co-equal basis with the synapse matrix elements by adaptively changing its gain in a similar manner to the change of weights in the synapse IO elements. In this manner, training time is decreased by as much as three orders of magnitude.

  3. Pedestrian Detection Using Convolutional Neural Networks

    OpenAIRE

    Molin, David

    2015-01-01

    Pedestrian detection is an important field with applications in active safety systems for cars as well as autonomous driving. Since autonomous driving and active safety are becoming technically feasible now the interest for these applications has dramatically increased.The aim of this thesis is to investigate convolutional neural networks (CNN) for pedestrian detection. The reason for this is that CNN have recently beensuccessfully applied to several different computer vision problems. The ma...

  4. Analysis of SSR Using Artificial Neural Networks

    OpenAIRE

    Nagabhushana, BS; Chandrasekharaiah, HS

    1996-01-01

    Artificial neural networks (ANNs) are being advantageously applied to power system analysis problems. They possess the ability to establish complicated input-output mappings through a learning process, without any explicit programming. In this paper, an ANN based method for subsynchronous resonance (SSR) analysis is presented. The designed ANN outputs a measure of the possibility of the occurrence of SSR and is fully trained to accommodate the variations of power system parameters over the en...

  5. Practical introduction to artificial neural networks

    OpenAIRE

    Bougrain, Laurent

    2004-01-01

    What are they ? What for are they ? How to use them ? This article wants to answer these three fundamental questions about artificial neural networks that every engineer interested by this machine learning technique asks to oneself. We present the most useful architectures. We explain how to train them using a supervised or an unsupervised learning depending on the task we want to do : regression, discrimination or clustering. What kind of data can one use and how to prepare them ? Finally, w...

  6. Context dependent learning in neural networks

    OpenAIRE

    Spreeuwers, L.J.; Zwaag, van der, Berend Jan; Heijden, van der, M.

    1995-01-01

    In this paper an extension to the standard error backpropagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to be trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent informa...

  7. Deep Learning in Neural Networks: An Overview

    OpenAIRE

    Schmidhuber, Juergen

    2014-01-01

    In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpr...

  8. Neural Networks with Complex and Quaternion Inputs

    OpenAIRE

    Rishiyur, Adityan

    2006-01-01

    This article investigates Kak neural networks, which can be instantaneously trained, for complex and quaternion inputs. The performance of the basic algorithm has been analyzed and shown how it provides a plausible model of human perception and understanding of images. The motivation for studying quaternion inputs is their use in representing spatial rotations that find applications in computer graphics, robotics, global navigation, computer vision and the spatial orientation of instruments. ...

  9. Adaptive Filtering Using Recurrent Neural Networks

    Science.gov (United States)

    Parlos, Alexander G.; Menon, Sunil K.; Atiya, Amir F.

    2005-01-01

    A method for adaptive (or, optionally, nonadaptive) filtering has been developed for estimating the states of complex process systems (e.g., chemical plants, factories, or manufacturing processes at some level of abstraction) from time series of measurements of system inputs and outputs. The method is based partly on the fundamental principles of the Kalman filter and partly on the use of recurrent neural networks. The standard Kalman filter involves an assumption of linearity of the mathematical model used to describe a process system. The extended Kalman filter accommodates a nonlinear process model but still requires linearization about the state estimate. Both the standard and extended Kalman filters involve the often unrealistic assumption that process and measurement noise are zero-mean, Gaussian, and white. In contrast, the present method does not involve any assumptions of linearity of process models or of the nature of process noise; on the contrary, few (if any) assumptions are made about process models, noise models, or the parameters of such models. In this regard, the method can be characterized as one of nonlinear, nonparametric filtering. The method exploits the unique ability of neural networks to approximate nonlinear functions. In a given case, the process model is limited mainly by limitations of the approximation ability of the neural networks chosen for that case. Moreover, despite the lack of assumptions regarding process noise, the method yields minimum- variance filters. In that they do not require statistical models of noise, the neural- network-based state filters of this method are comparable to conventional nonlinear least-squares estimators.

  10. Turing Computation with Recurrent Artificial Neural Networks

    OpenAIRE

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

    2015-01-01

    We improve the results by Siegelmann & Sontag (1995) by providing a novel and parsimonious constructive mapping between Turing Machines and Recurrent Artificial Neural Networks, based on recent developments of Nonlinear Dynamical Automata. The architecture of the resulting R-ANNs is simple and elegant, stemming from its transparent relation with the underlying NDAs. These characteristics yield promise for developments in machine learning methods and symbolic computation with continuous time d...

  11. Web Page Categorization Using Artificial Neural Networks

    OpenAIRE

    S. M. Kamruzzaman

    2010-01-01

    Web page categorization is one of the challenging tasks in the world of ever increasing web technologies. There are many ways of categorization of web pages based on different approach and features. This paper proposes a new dimension in the way of categorization of web pages using artificial neural network (ANN) through extracting the features automatically. Here eight major categories of web pages have been selected for categorization; these are business & economy, education, government, en...

  12. Artificial Neural Networks in Stellar Astronomy

    Directory of Open Access Journals (Sweden)

    R. K. Gulati

    2001-01-01

    Full Text Available Next generation of optical spectroscopic surveys, such as the Sloan Digital Sky Survey and the 2 degree field survey, will provide large stellar databases. New tools will be required to extract useful information from these. We show the applications of artificial neural networks to stellar databases. In another application of this method, we predict spectral and luminosity classes from the catalog of spectral indices. We assess the importance of such methods for stellar populations studies.

  13. Prediction of metal corrosion by neural networks

    OpenAIRE

    Jančíková, Zora; Zimný, Ondřej; Koštial, Pavol

    2013-01-01

    The contribution deals with the use of artifi cial neural networks for prediction of steel atmospheric corrosion. Atmospheric corrosion of metal materials exposed under atmospheric conditions depends on various factors such as local temperature, relative humidity, amount of precipitation, pH of rainfall, concentration of main pollutants and exposition time. As these factors are very complex, exact relation for mathematical description of atmospheric corrosion of various metals are...

  14. Prediction of metal corrosion by neural networks

    OpenAIRE

    Jančíková, Z.; Zimný, O.; Koštial, P.

    2013-01-01

    The contribution deals with the use of artificial neural networks for prediction of steel atmospheric corrosion. Atmospheric corrosion of metal materials exposed under atmospheric conditions depends on various factors such as local temperature, relative humidity, amount of precipitation, pH of rainfall, concentration of main pollutants and exposition time. As these factors are very complex, exact relation for mathematical description of atmospheric corrosion of various metals are not known so...

  15. POWER SCALABLE IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORKS

    OpenAIRE

    Modi, Sankalp; Wilson, Peter; Brown, Andrew

    2005-01-01

    As the use of Artificial Neural Network(ANN) in mobile embedded devices gets more pervasive, power consumption of ANN hardware is becoming a major limiting factor. Although considerable research efforts are now directed towards low-power implementations of ANN, the issue of dynamic power scalability of the implemented design has been largely overlooked. In this paper, we discuss the motivation and basic principles for implementing power scaling in ANN Hardware. With the help of a simple examp...

  16. Neural Networks in Chemical Reaction Dynamics

    CERN Document Server

    Raff, Lionel; Hagan, Martin

    2011-01-01

    This monograph presents recent advances in neural network (NN) approaches and applications to chemical reaction dynamics. Topics covered include: (i) the development of ab initio potential-energy surfaces (PES) for complex multichannel systems using modified novelty sampling and feedforward NNs; (ii) methods for sampling the configuration space of critical importance, such as trajectory and novelty sampling methods and gradient fitting methods; (iii) parametrization of interatomic potential functions using a genetic algorithm accelerated with a NN; (iv) parametrization of analytic interatomic

  17. Neural network error correction for solving coupled ordinary differential equations

    Science.gov (United States)

    Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

    1992-01-01

    A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

  18. A Bionic Neural Network for Fish-Robot Locomotion

    Institute of Scientific and Technical Information of China (English)

    Dai-bing Zhang; De-wen Hu; Lin-cheng Shen; Hai-bin Xie

    2006-01-01

    A bionic neural network for fish-robot locomotion is presented. The bionic neural network inspired from fish neural network consists of one high level controller and one chain of central pattern generators (CPGs). Each CPG contains a nonlinear neural Zhang oscillator which shows properties similar to sine-cosine model. Simulation results show that the bionic neural network presents a good performance in controlling the fish-robot to execute various motions such as startup,stop,forward swimming,backward swimming,turn right and turn left.

  19. Segmentation of magnetic resonance images using an artificial neural network.

    OpenAIRE

    Piraino, D. W.; Amartur, S. C.; Richmond, B. J.; Schils, J. P.; Thome, J. M.; Weber, P. B.

    1991-01-01

    Signal intensities from intermediate and T2 weighted spin echo images of the brain were used as inputs into an artificial neural network (ANN). The signal intensities were used to train the network to recognize anatomically-important segments. The ANN was a self-organizing map (SOM) neural network which develops a continuous topographical map of the signal intensities within the two images. The neural network segmented images demonstrated good correlation with white matter, gray matter, and c...

  20. Comparison of Training Methods for Deep Neural Networks

    OpenAIRE

    Glauner, Patrick O.

    2015-01-01

    This report describes the difficulties of training neural networks and in particular deep neural networks. It then provides a literature review of training methods for deep neural networks, with a focus on pre-training. It focuses on Deep Belief Networks composed of Restricted Boltzmann Machines and Stacked Autoencoders and provides an outreach on further and alternative approaches. It also includes related practical recommendations from the literature on training them. In the second part, in...

  1. Deep learning in neural networks: an overview.

    Science.gov (United States)

    Schmidhuber, Jürgen

    2015-01-01

    In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

  2. Multilingual Text Detection with Nonlinear Neural Network

    Directory of Open Access Journals (Sweden)

    Lin Li

    2015-01-01

    Full Text Available Multilingual text detection in natural scenes is still a challenging task in computer vision. In this paper, we apply an unsupervised learning algorithm to learn language-independent stroke feature and combine unsupervised stroke feature learning and automatically multilayer feature extraction to improve the representational power of text feature. We also develop a novel nonlinear network based on traditional Convolutional Neural Network that is able to detect multilingual text regions in the images. The proposed method is evaluated on standard benchmarks and multilingual dataset and demonstrates improvement over the previous work.

  3. Deep learning in neural networks: an overview.

    Science.gov (United States)

    Schmidhuber, Jürgen

    2015-01-01

    In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks. PMID:25462637

  4. Neural network method for characterizing video cameras

    Science.gov (United States)

    Zhou, Shuangquan; Zhao, Dazun

    1998-08-01

    This paper presents a neural network method for characterizing color video camera. A multilayer feedforward network with the error back-propagation learning rule for training, is used as a nonlinear transformer to model a camera, which realizes a mapping from the CIELAB color space to RGB color space. With SONY video camera, D65 illuminant, Pritchard Spectroradiometer, 410 JIS color charts as training data and 36 charts as testing data, results show that the mean error of training data is 2.9 and that of testing data is 4.0 in a 2563 RGB space.

  5. Neural Network Approach for Eye Detection

    CERN Document Server

    Vijayalaxmi,; Sreehari, S

    2012-01-01

    Driving support systems, such as car navigation systems are becoming common and they support driver in several aspects. Non-intrusive method of detecting Fatigue and drowsiness based on eye-blink count and eye directed instruction controlhelps the driver to prevent from collision caused by drowsy driving. Eye detection and tracking under various conditions such as illumination, background, face alignment and facial expression makes the problem complex.Neural Network based algorithm is proposed in this paper to detect the eyes efficiently. In the proposed algorithm, first the neural Network is trained to reject the non-eye regionbased on images with features of eyes and the images with features of non-eye using Gabor filter and Support Vector Machines to reduce the dimension and classify efficiently. In the algorithm, first the face is segmented using L*a*btransform color space, then eyes are detected using HSV and Neural Network approach. The algorithm is tested on nearly 100 images of different persons under...

  6. File access prediction using neural networks.

    Science.gov (United States)

    Patra, Prashanta Kumar; Sahu, Muktikanta; Mohapatra, Subasish; Samantray, Ronak Kumar

    2010-06-01

    One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors.

  7. Artificial Neural Network Model for Predicting Compressive

    Directory of Open Access Journals (Sweden)

    Salim T. Yousif

    2013-05-01

    Full Text Available   Compressive strength of concrete is a commonly used criterion in evaluating concrete. Although testing of the compressive strength of concrete specimens is done routinely, it is performed on the 28th day after concrete placement. Therefore, strength estimation of concrete at early time is highly desirable. This study presents the effort in applying neural network-based system identification techniques to predict the compressive strength of concrete based on concrete mix proportions, maximum aggregate size (MAS, and slump of fresh concrete. Back-propagation neural networks model is successively developed, trained, and tested using actual data sets of concrete mix proportions gathered from literature.    The test of the model by un-used data within the range of input parameters shows that the maximum absolute error for model is about 20% and 88% of the output results has absolute errors less than 10%. The parametric study shows that water/cement ratio (w/c is the most significant factor  affecting the output of the model.     The results showed that neural networks has strong potential as a feasible tool for predicting compressive strength of concrete.

  8. Artificial neural network applications in ionospheric studies

    Directory of Open Access Journals (Sweden)

    L. R. Cander

    1998-06-01

    Full Text Available The ionosphere of Earth exhibits considerable spatial changes and has large temporal variability of various timescales related to the mechanisms of creation, decay and transport of space ionospheric plasma. Many techniques for modelling electron density profiles through entire ionosphere have been developed in order to solve the "age-old problem" of ionospheric physics which has not yet been fully solved. A new way to address this problem is by applying artificial intelligence methodologies to current large amounts of solar-terrestrial and ionospheric data. It is the aim of this paper to show by the most recent examples that modern development of numerical models for ionospheric monthly median long-term prediction and daily hourly short-term forecasting may proceed successfully applying the artificial neural networks. The performance of these techniques is illustrated with different artificial neural networks developed to model and predict the temporal and spatial variations of ionospheric critical frequency, f0F2 and Total Electron Content (TEC. Comparisons between results obtained by the proposed approaches and measured f0F2 and TEC data provide prospects for future applications of the artificial neural networks in ionospheric studies.

  9. Clustering-based selective neural network ensemble

    Institute of Scientific and Technical Information of China (English)

    FU Qiang; HU Shang-xu; ZHAO Sheng-ying

    2005-01-01

    An effective ensemble should consist of a set of networks that are both accurate and diverse. We propose a novel clustering-based selective algorithm for constructing neural network ensemble, where clustering technology is used to classify trained networks according to similarity and optimally select the most accurate individual network from each cluster to make up the ensemble. Empirical studies on regression of four typical datasets showed that this approach yields significantly smaller en semble achieving better performance than other traditional ones such as Bagging and Boosting. The bias variance decomposition of the predictive error shows that the success of the proposed approach may lie in its properly tuning the bias/variance trade-offto reduce the prediction error (the sum of bias2 and variance).

  10. A new approach to artificial neural networks.

    Science.gov (United States)

    Baptista Filho, B D; Cabral, E L; Soares, A J

    1998-01-01

    A novel approach to artificial neural networks is presented. The philosophy of this approach is based on two aspects: the design of task-specific networks, and a new neuron model with multiple synapses. The synapses' connective strengths are modified through selective and cumulative processes conducted by axo-axonic connections from a feedforward circuit. This new concept was applied to the position control of a planar two-link manipulator exhibiting excellent results on learning capability and generalization when compared with a conventional feedforward network. In the present paper, the example shows only a network developed from a neuronal reflexive circuit with some useful artifices, nevertheless without the intention of covering all possibilities devised.

  11. Microscopic instability in recurrent neural networks

    Science.gov (United States)

    Yamanaka, Yuzuru; Amari, Shun-ichi; Shinomoto, Shigeru

    2015-03-01

    In a manner similar to the molecular chaos that underlies the stable thermodynamics of gases, a neuronal system may exhibit microscopic instability in individual neuronal dynamics while a macroscopic order of the entire population possibly remains stable. In this study, we analyze the microscopic stability of a network of neurons whose macroscopic activity obeys stable dynamics, expressing either monostable, bistable, or periodic state. We reveal that the network exhibits a variety of dynamical states for microscopic instability residing in a given stable macroscopic dynamics. The presence of a variety of dynamical states in such a simple random network implies more abundant microscopic fluctuations in real neural networks which consist of more complex and hierarchically structured interactions.

  12. Fuzzy Neural Network Based Traffic Prediction and Congestion Control in High-Speed Networks

    Institute of Scientific and Technical Information of China (English)

    费翔; 何小燕; 罗军舟; 吴介一; 顾冠群

    2000-01-01

    Congestion control is one of the key problems in high-speed networks, such as ATM. In this paper, a kind of traffic prediction and preventive congestion control scheme is proposed using neural network approach. Traditional predictor using BP neural network has suffered from long convergence time and dissatisfying error. Fuzzy neural network developed in this paper can solve these problems satisfactorily. Simulations show the comparison among no-feedback control scheme,reactive control scheme and neural network based control scheme.

  13. PSO optimized Feed Forward Neural Network for offline Signature Classification

    Directory of Open Access Journals (Sweden)

    Pratik R. Hajare

    2015-07-01

    Full Text Available The paper is based on feed forward neural network (FFNN optimization by particle swarm intelligence (PSI used to provide initial weights and biases to train neural network. Once the weights and biases are found using Particle swarm optimization (PSO with neural network used as training algorithm for specified epoch, the same are used to train the neural network for training and classification of benchmark problems. Further the approach is tested for offline signature classifications. A comparison is made between normal FFNN with random weights and biases and FFNN with particle swarm optimized weights and biases. Firstly, the performance is tested on two benchmark databases for neural network, The Breast Cancer Database and the Diabetic Database. Result shows that neural network performs better with initial weights and biases obtained by Particle Swarm optimization. The network converges faster with PSO obtained initial weights and biases for FFNN and classification accuracy is increased.

  14. 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....

  15. Optimizing Cellular Networks Enabled with Renewal Energy via Strategic Learning.

    Directory of Open Access Journals (Sweden)

    Insoo Sohn

    Full Text Available An important issue in the cellular industry is the rising energy cost and carbon footprint due to the rapid expansion of the cellular infrastructure. Greening cellular networks has thus attracted attention. Among the promising green cellular network techniques, the renewable energy-powered cellular network has drawn increasing attention as a critical element towards reducing carbon emissions due to massive energy consumption in the base stations deployed in cellular networks. Game theory is a branch of mathematics that is used to evaluate and optimize systems with multiple players with conflicting objectives and has been successfully used to solve various problems in cellular networks. In this paper, we model the green energy utilization and power consumption optimization problem of a green cellular network as a pilot power selection strategic game and propose a novel distributed algorithm based on a strategic learning method. The simulation results indicate that the proposed algorithm achieves correlated equilibrium of the pilot power selection game, resulting in optimum green energy utilization and power consumption reduction.

  16. Optimizing Cellular Networks Enabled with Renewal Energy via Strategic Learning.

    Science.gov (United States)

    Sohn, Insoo; Liu, Huaping; Ansari, Nirwan

    2015-01-01

    An important issue in the cellular industry is the rising energy cost and carbon footprint due to the rapid expansion of the cellular infrastructure. Greening cellular networks has thus attracted attention. Among the promising green cellular network techniques, the renewable energy-powered cellular network has drawn increasing attention as a critical element towards reducing carbon emissions due to massive energy consumption in the base stations deployed in cellular networks. Game theory is a branch of mathematics that is used to evaluate and optimize systems with multiple players with conflicting objectives and has been successfully used to solve various problems in cellular networks. In this paper, we model the green energy utilization and power consumption optimization problem of a green cellular network as a pilot power selection strategic game and propose a novel distributed algorithm based on a strategic learning method. The simulation results indicate that the proposed algorithm achieves correlated equilibrium of the pilot power selection game, resulting in optimum green energy utilization and power consumption reduction. PMID:26167934

  17. Intensity Coding in Two-Dimensional Excitable Neural Networks

    CERN Document Server

    Copelli, Mauro

    2016-01-01

    In the light of recent experimental findings that gap junctions are essential for low level intensity detection in the sensory periphery, the Greenberg-Hastings cellular automaton is employed to model the response of a two-dimensional sensory network to external stimuli. We show that excitable elements (sensory neurons) that have a small dynamical range are shown to give rise to a collective large dynamical range. Therefore the network transfer (gain) function (which is Hill or Stevens law-like) is an emergent property generated from a pool of small dynamical range cells, providing a basis for a "neural psychophysics". The growth of the dynamical range with the system size is approximately logarithmic, suggesting a functional role for electrical coupling. For a fixed number of neurons, the dynamical range displays a maximum as a function of the refractory period, which suggests experimental tests for the model. A biological application to ephaptic interactions in olfactory nerve fascicles is proposed.

  18. Phase Synchronization in Small World Chaotic Neural Networks

    Institute of Scientific and Technical Information of China (English)

    WANG Qing-Yun; LU Qi-Shao

    2005-01-01

    @@ To understand collective motion of realneural networks very well, we investigate collective phase synchronization of small world chaotic Hindmarsh-Rose (HR) neural networks. By numerical simulations, we conclude that small world chaotic HR neural networks can achieve collective phase synchronization. Furthermore, it is shown that phase synchronization of small world chaotic HR neural networks is dependent on the coupling strength,the connection topology (which is determined by the probability p), as well as the coupling number. These phenomena are important to guide us to understand the synchronization of real neural networks.

  19. Detection of Wildfires with Artificial Neural Networks

    Science.gov (United States)

    Umphlett, B.; Leeman, J.; Morrissey, M. L.

    2011-12-01

    Currently fire detection for the National Oceanic and Atmospheric Administration (NOAA) using satellite data is accomplished with algorithms and error checking human analysts. Artificial neural networks (ANNs) have been shown to be more accurate than algorithms or statistical methods for applications dealing with multiple datasets of complex observed data in the natural sciences. ANNs also deal well with multiple data sources that are not all equally reliable or equally informative to the problem. An ANN was tested to evaluate its accuracy in detecting wildfires utilizing polar orbiter numerical data from the Advanced Very High Resolution Radiometer (AVHRR). Datasets containing locations of known fires were gathered from the NOAA's polar orbiting satellites via the Comprehensive Large Array-data Stewardship System (CLASS). The data was then calibrated and navigation corrected using the Environment for Visualizing Images (ENVI). Fires were located with the aid of shapefiles generated via ArcGIS. Afterwards, several smaller ten pixel by ten pixel datasets were created for each fire (using the ENVI corrected data). Several datasets were created for each fire in order to vary fire position and avoid training the ANN to look only at fires in the center of an image. Datasets containing no fires were also created. A basic pattern recognition neural network was established with the MATLAB neural network toolbox. The datasets were then randomly separated into categories used to train, validate, and test the ANN. To prevent over fitting of the data, the mean squared error (MSE) of the network was monitored and training was stopped when the MSE began to rise. Networks were tested using each channel of the AVHRR data independently, channels 3a and 3b combined, and all six channels. The number of hidden neurons for each input set was also varied between 5-350 in steps of 5 neurons. Each configuration was run 10 times, totaling about 4,200 individual network evaluations. Thirty

  20. Neural Network Model of Memory Retrieval.

    Science.gov (United States)

    Recanatesi, Stefano; Katkov, Mikhail; Romani, Sandro; Tsodyks, Misha

    2015-01-01

    Human memory can store large amount of information. Nevertheless, recalling is often a challenging task. In a classical free recall paradigm, where participants are asked to repeat a briefly presented list of words, people make mistakes for lists as short as 5 words. We present a model for memory retrieval based on a Hopfield neural network where transition between items are determined by similarities in their long-term memory representations. Meanfield analysis of the model reveals stable states of the network corresponding (1) to single memory representations and (2) intersection between memory representations. We show that oscillating feedback inhibition in the presence of noise induces transitions between these states triggering the retrieval of different memories. The network dynamics qualitatively predicts the distribution of time intervals required to recall new memory items observed in experiments. It shows that items having larger number of neurons in their representation are statistically easier to recall and reveals possible bottlenecks in our ability of retrieving memories. Overall, we propose a neural network model of information retrieval broadly compatible with experimental observations and is consistent with our recent graphical model (Romani et al., 2013). PMID:26732491

  1. Neural Network Model of memory retrieval

    Directory of Open Access Journals (Sweden)

    Stefano eRecanatesi

    2015-12-01

    Full Text Available Human memory can store large amount of information. Nevertheless, recalling is often achallenging task. In a classical free recall paradigm, where participants are asked to repeat abriefly presented list of words, people make mistakes for lists as short as 5 words. We present amodel for memory retrieval based on a Hopfield neural network where transition between itemsare determined by similarities in their long-term memory representations. Meanfield analysis ofthe model reveals stable states of the network corresponding (1 to single memory representationsand (2 intersection between memory representations. We show that oscillating feedback inhibitionin the presence of noise induces transitions between these states triggering the retrieval ofdifferent memories. The network dynamics qualitatively predicts the distribution of time intervalsrequired to recall new memory items observed in experiments. It shows that items having largernumber of neurons in their representation are statistically easier to recall and reveals possiblebottlenecks in our ability of retrieving memories. Overall, we propose a neural network model ofinformation retrieval broadly compatible with experimental observations and is consistent with ourrecent graphical model (Romani et al., 2013.

  2. Absolute stability of nonlinear systems with time delays and applications to neural networks

    Directory of Open Access Journals (Sweden)

    Xinzhi Liu

    2001-01-01

    Full Text Available In this paper, absolute stability of nonlinear systems with time delays is investigated. Sufficient conditions on absolute stability are derived by using the comparison principle and differential inequalities. These conditions are simple and easy to check. In addition, exponential stability conditions for some special cases of nonlinear delay systems are discussed. Applications of those results to cellular neural networks are presented.

  3. Stability of discrete Hopfield neural networks with delay

    Institute of Scientific and Technical Information of China (English)

    Ma Runnian; Lei Sheping; Liu Naigong

    2005-01-01

    Discrete Hopfield neural network with delay is an extension of discrete Hopfield neural network. As it is well known, the stability of neural networks is not only the most basic and important problem but also foundation of the network's applications. The stability of discrete Hopfield neural networks with delay is mainly investigated by using Lyapunov function. The sufficient conditions for the networks with delay converging towards a limit cycle of length 4 are obtained. Also, some sufficient criteria are given to ensure the networks having neither a stable state nor a limit cycle with length 2. The obtained results here generalize the previous results on stability of discrete Hopfield neural network with delay and without delay.

  4. Facial expression recognition using constructive neural networks

    Science.gov (United States)

    Ma, Liying; Khorasani, Khashayar

    2001-08-01

    The computer-based recognition of facial expressions has been an active area of research for quite a long time. The ultimate goal is to realize intelligent and transparent communications between human beings and machines. The neural network (NN) based recognition methods have been found to be particularly promising, since NN is capable of implementing mapping from the feature space of face images to the facial expression space. However, finding a proper network size has always been a frustrating and time consuming experience for NN developers. In this paper, we propose to use the constructive one-hidden-layer feed forward neural networks (OHL-FNNs) to overcome this problem. The constructive OHL-FNN will obtain in a systematic way a proper network size which is required by the complexity of the problem being considered. Furthermore, the computational cost involved in network training can be considerably reduced when compared to standard back- propagation (BP) based FNNs. In our proposed technique, the 2-dimensional discrete cosine transform (2-D DCT) is applied over the entire difference face image for extracting relevant features for recognition purpose. The lower- frequency 2-D DCT coefficients obtained are then used to train a constructive OHL-FNN. An input-side pruning technique previously proposed by the authors is also incorporated into the constructive OHL-FNN. An input-side pruning technique previously proposed by the authors is also incorporated into the constructive learning process to reduce the network size without sacrificing the performance of the resulting network. The proposed technique is applied to a database consisting of images of 60 men, each having the resulting network. The proposed technique is applied to a database consisting of images of 60 men, each having 5 facial expression images (neutral, smile, anger, sadness, and surprise). Images of 40 men are used for network training, and the remaining images are used for generalization and

  5. Neural network learning dynamics in a path integral framework

    OpenAIRE

    Balakrishnan, J.

    2003-01-01

    A path-integral formalism is proposed for studying the dynamical evolution in time of patterns in an artificial neural network in the presence of noise. An effective cost function is constructed which determines the unique global minimum of the neural network system. The perturbative method discussed also provides a way for determining the storage capacity of the network.

  6. Dynamic artificial neural networks with affective systems.

    Science.gov (United States)

    Schuman, Catherine D; Birdwell, J Douglas

    2013-01-01

    Artificial neural networks (ANNs) are processors that are trained to perform particular tasks. We couple a computational ANN with a simulated affective system in order to explore the interaction between the two. In particular, we design a simple affective system that adjusts the threshold values in the neurons of our ANN. The aim of this paper is to demonstrate that this simple affective system can control the firing rate of the ensemble of neurons in the ANN, as well as to explore the coupling between the affective system and the processes of long term potentiation (LTP) and long term depression (LTD), and the effect of the parameters of the affective system on its performance. We apply our networks with affective systems to a simple pole balancing example and briefly discuss the effect of affective systems on network performance.

  7. Applying neural networks to ultrasonographic texture recognition

    Science.gov (United States)

    Gallant, Jean-Francois; Meunier, Jean; Stampfler, Robert; Cloutier, Jocelyn

    1993-09-01

    A neural network was trained to classify ultrasound image samples of normal, adenomatous (benign tumor) and carcinomatous (malignant tumor) thyroid gland tissue. The samples themselves, as well as their Fourier spectrum, miscellaneous cooccurrence matrices and 'generalized' cooccurrence matrices, were successively submitted to the network, to determine if it could be trained to identify discriminating features of the texture of the image, and if not, which feature extractor would give the best results. Results indicate that the network could indeed extract some distinctive features from the textures, since it could accomplish a partial classification when trained with the samples themselves. But a significant improvement both in learning speed and performance was observed when it was trained with the generalized cooccurrence matrices of the samples.

  8. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks

    Science.gov (United States)

    Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli

    2016-01-01

    In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423

  9. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.

    Science.gov (United States)

    Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli

    2016-01-01

    In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423

  10. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.

    Science.gov (United States)

    Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli

    2016-01-01

    In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.

  11. An introduction to neural network methods for differential equations

    CERN Document Server

    Yadav, Neha; Kumar, Manoj

    2015-01-01

    This book introduces a variety of neural network methods for solving differential equations arising in science and engineering. The emphasis is placed on a deep understanding of the neural network techniques, which has been presented in a mostly heuristic and intuitive manner. This approach will enable the reader to understand the working, efficiency and shortcomings of each neural network technique for solving differential equations. The objective of this book is to provide the reader with a sound understanding of the foundations of neural networks, and a comprehensive introduction to neural network methods for solving differential equations together with recent developments in the techniques and their applications. The book comprises four major sections. Section I consists of a brief overview of differential equations and the relevant physical problems arising in science and engineering. Section II illustrates the history of neural networks starting from their beginnings in the 1940s through to the renewed...

  12. Modeling of Magneto-Rheological Damper with Neural Network

    Institute of Scientific and Technical Information of China (English)

    2006-01-01

    With the revival of magnetorheological technology research in the 1980's, its application in vehicles is increasingly focused on vibration suppression. Based on the importance of magnetorheological damper modeling, nonparametric modeling with neural network, which is a promising development in semi-active online control of vehicles with MR suspension, has been carried out in this study. A two layer neural network with 7 neurons in a hidden layer and 3 inputs and 1 output was established to simulate the behavior of MR damper at different excitation currents. In the neural network modeling, the damping force is a function of displacement, velocity and the applied current. A MR damper for vehicles is fabricated and tested by MTS; the data acquired are utilized for neural network training and validation. The application and validation show that the predicted forces of the neural network match well with the forces tested with a small variance, which demonstrates the effectiveness and precision of neural network modeling.

  13. Flow of Information in Feed-Forward Deep Neural Networks

    OpenAIRE

    Khadivi, Pejman; Tandon, Ravi; Ramakrishnan, Naren

    2016-01-01

    Feed-forward deep neural networks have been used extensively in various machine learning applications. Developing a precise understanding of the underling behavior of neural networks is crucial for their efficient deployment. In this paper, we use an information theoretic approach to study the flow of information in a neural network and to determine how entropy of information changes between consecutive layers. Moreover, using the Information Bottleneck principle, we develop a constrained opt...

  14. Proceedings of intelligent engineering systems through artificial neural networks

    International Nuclear Information System (INIS)

    This book contains the edited versions of the technical presentation of ANNIE '91, the first international meeting on Artificial Neural Networks in Engineering. The conference covered the theory of Artificial Neural Networks and its contributions in the engineering domain and attracted researchers from twelve countries. The papers in this edited book are grouped into four categories: Artificial Neural Network Architectures; Pattern Recognition; Adaptive Control, Diagnosis and Process Monitoring; and Neuro-Engineering Systems

  15. Pixel-wise Segmentation of Street with Neural Networks

    OpenAIRE

    Bittel, Sebastian; Kaiser, Vitali; Teichmann, Marvin; Thoma, Martin

    2015-01-01

    Pixel-wise street segmentation of photographs taken from a drivers perspective is important for self-driving cars and can also support other object recognition tasks. A framework called SST was developed to examine the accuracy and execution time of different neural networks. The best neural network achieved an $F_1$-score of 89.5% with a simple feedforward neural network which trained to solve a regression task.

  16. Neural Networks in Economic Modelling: An Empirical Study.

    OpenAIRE

    Verkooijen, W.J.H.

    1996-01-01

    Abstract: 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 statistical technique that implements a model-free regression strategy. Model-free regression seems particularly useful in situations where economic theory cannot provide sensible model spec...

  17. Pattern recognition of state variables by neural networks

    International Nuclear Information System (INIS)

    An artificial intelligence system based on artificial neural networks can be used to classify predefined events and emergency procedures. These systems are being used in different areas. In the nuclear reactors safety, the goal is the classification of events whose data can be processed and recognized by neural networks. In this works we present a preliminary simple system, using neural networks in the recognition of patterns the recognition of variables which define a situation. (author)

  18. Computational Neural Networks: A New Paradigm for Spatial Analysis

    OpenAIRE

    Fischer, M.M.

    1996-01-01

    In this paper a systematic introduction to computational neural network models is given in order to help spatial analysts learn about this exciting new field. The power of computational neural networks viz-à-viz conventional modelling is illustrated for an application field with noisy data of limited record length: spatial interaction modelling of telecommunication data in Austria. The computational appeal of neural networks for solving some fundamental spatial analysis problems is summarized...

  19. Neural Networks Applied to Thermal Damage Classification in Grinding Process

    OpenAIRE

    Spadotto, Marcelo M.; Aguiar, Paulo Roberto de; Sousa, Carlos C. P.; Bianchi, Eduardo C.

    2008-01-01

    The utilization of neural network of type multi-layer perceptron using the back-propagation algorithm guaranteed very good results. Tests carried out in order to optimize the learning capacity of neural networks were of utmost importance in the training phase, where the optimum values for the number of neurons of the hidden layer, learning rate and momentum for each structure were determined. Once the architecture of the neural network was established with those optimum values, the mean squar...

  20. Analysis of Heart Diseases Dataset using Neural Network Approach

    CERN Document Server

    Rani, K Usha

    2011-01-01

    One of the important techniques of Data mining is Classification. Many real world problems in various fields such as business, science, industry and medicine can be solved by using classification approach. Neural Networks have emerged as an important tool for classification. The advantages of Neural Networks helps for efficient classification of given data. In this study a Heart diseases dataset is analyzed using Neural Network approach. To increase the efficiency of the classification process parallel approach is also adopted in the training phase.

  1. Sensor Temperature Compensation Technique Simulation Based on BP Neural Network

    OpenAIRE

    Xiangwu Wei

    2013-01-01

    Innovatively, neural network function programming in the BPNN (BP neural network) tool boxes from MATLAB are applied, and data processing is done about CYJ-101 pressure sensor, and the problem of the sensor temperature compensation is solved. The paper has made the pressure sensors major sensors and temperature sensor assistant sensors, input the voltage signal from the two sensors into the established BP neural network model, and done the simulation under the NN Toolbox environment of MATLAB...

  2. Neural Networks for Modeling and Control of Particle Accelerators

    CERN Document Server

    Edelen, A L; Chase, B E; Edstrom, D; Milton, S V; Stabile, P

    2016-01-01

    We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.

  3. A Neural Network-Based Interval Pattern Matcher

    Directory of Open Access Journals (Sweden)

    Jing Lu

    2015-07-01

    Full Text Available One of the most important roles in the machine learning area is to classify, and neural networks are very important classifiers. However, traditional neural networks cannot identify intervals, let alone classify them. To improve their identification ability, we propose a neural network-based interval matcher in our paper. After summarizing the theoretical construction of the model, we take a simple and a practical weather forecasting experiment, which show that the recognizer accuracy reaches 100% and that is promising.

  4. One pass learning for generalized classifier neural network.

    Science.gov (United States)

    Ozyildirim, Buse Melis; Avci, Mutlu

    2016-01-01

    Generalized classifier neural network introduced as a kind of radial basis function neural network, uses gradient descent based optimized smoothing parameter value to provide efficient classification. However, optimization consumes quite a long time and may cause a drawback. In this work, one pass learning for generalized classifier neural network is proposed to overcome this disadvantage. Proposed method utilizes standard deviation of each class to calculate corresponding smoothing parameter. Since different datasets may have different standard deviations and data distributions, proposed method tries to handle these differences by defining two functions for smoothing parameter calculation. Thresholding is applied to determine which function will be used. One of these functions is defined for datasets having different range of values. It provides balanced smoothing parameters for these datasets through logarithmic function and changing the operation range to lower boundary. On the other hand, the other function calculates smoothing parameter value for classes having standard deviation smaller than the threshold value. Proposed method is tested on 14 datasets and performance of one pass learning generalized classifier neural network is compared with that of probabilistic neural network, radial basis function neural network, extreme learning machines, and standard and logarithmic learning generalized classifier neural network in MATLAB environment. One pass learning generalized classifier neural network provides more than a thousand times faster classification than standard and logarithmic generalized classifier neural network. Due to its classification accuracy and speed, one pass generalized classifier neural network can be considered as an efficient alternative to probabilistic neural network. Test results show that proposed method overcomes computational drawback of generalized classifier neural network and may increase the classification performance.

  5. A walk in the statistical mechanical formulation of neural networks

    OpenAIRE

    Agliari, Elena; Barra, Adriano; Galluzzi, Andrea; Tantari, Daniele; Tavani, Flavia

    2014-01-01

    Neural networks are nowadays both powerful operational tools (e.g., for pattern recognition, data mining, error correction codes) and complex theoretical models on the focus of scientific investigation. As for the research branch, neural networks are handled and studied by psychologists, neurobiologists, engineers, mathematicians and theoretical physicists. In particular, in theoretical physics, the key instrument for the quantitative analysis of neural networks is statistical mechanics. From...

  6. Discrete Orthogonal Transforms and Neural Networks for Image Interpolation

    Directory of Open Access Journals (Sweden)

    J. Polec

    1999-09-01

    Full Text Available In this contribution we present transform and neural network approaches to the interpolation of images. From transform point of view, the principles from [1] are modified for 1st and 2nd order interpolation. We present several new interpolation discrete orthogonal transforms. From neural network point of view, we present interpolation possibilities of multilayer perceptrons. We use various configurations of neural networks for 1st and 2nd order interpolation. The results are compared by means of tables.

  7. Dissipativity Analysis of Neural Networks with Time-varying Delays

    Institute of Scientific and Technical Information of China (English)

    Yan Sun; Bao-Tong Cui

    2008-01-01

    A new definition of dissipativity for neural networks is presented in this paper. By constructing proper Lyapunov func- tionals and using some analytic techniques, sufficient conditions are given to ensure the dissipativity of neural networks with or without time-varying parametric uncertainties and the integro-differential neural networks in terms of linear matrix inequalities. Numerical examples are given to illustrate the effectiveness of the obtained results.

  8. ANOMALY NETWORK INTRUSION DETECTION SYSTEM BASED ON DISTRIBUTED TIME-DELAY NEURAL NETWORK (DTDNN)

    OpenAIRE

    LAHEEB MOHAMMAD IBRAHIM

    2010-01-01

    In this research, a hierarchical off-line anomaly network intrusion detection system based on Distributed Time-Delay Artificial Neural Network is introduced. This research aims to solve a hierarchical multi class problem in which the type of attack (DoS, U2R, R2L and Probe attack) detected by dynamic neural network. The results indicate that dynamic neural nets (Distributed Time-Delay Artificial Neural Network) can achieve a high detection rate, where the overall accuracy classification rate ...

  9. 一类具有时滞的模糊反应扩散神经网络的自适应同步研究%Adaptive Synchronization for a Class of Fuzzy Cellular Neural Networks with Time Delays and Reaction Diffusion Terms

    Institute of Scientific and Technical Information of China (English)

    秦丽华; 刘艳; 樊小琳

    2012-01-01

    The adaptive synchronization of delayed fuzzy cellular neural networks with reaction diffusion terms has been considered. Under two different kinds of boundary conditions, based on the LaSalle invariant principle of functional differential equations and the adaptive feedback control technique, some sufficient conditions for adaptive synchronization of a system are obtained.%研究了一类具有时滞的模糊反应扩散神经网络的自适应同步,在两种不同的边界条件下,利用泛函微分方稃的LaSalle不峦原王单以及反馈榨制的方法.得到了系缔同步的充分条件.

  10. Neural network approach for differential diagnosis of interstitial lung diseases

    Science.gov (United States)

    Asada, Naoki; Doi, Kunio; MacMahon, Heber; Montner, Steven M.; Giger, Maryellen L.; Abe, Chihiro; Wu, Chris Y.

    1990-07-01

    A neural network approach was applied for the differential diagnosis of interstitial lung diseases. The neural network was designed for distinguishing between 9 types of interstitial lung diseases based on 20 items of clinical and radiographic information. A database for training and testing the neural network was created with 10 hypothetical cases for each of the 9 diseases. The performance of the neural network was evaluated by ROC analysis. The optimal parameters for the current neural network were determined by selecting those yielding the highest ROC curves. In this case the neural network consisted of one hidden layer including 6 units and was trained with 200 learning iterations. When the decision performances of the neural network chest radiologists and senior radiology residents were compared the neural network indicated high performance comparable to that of chest radiologists and superior to that of senior radiology residents. Our preliminary results suggested strongly that the neural network approach had potential utility in the computer-aided differential diagnosis of interstitial lung diseases. 1_

  11. A hardware implementation of neural network with modified HANNIBAL architecture

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Bum youb; Chung, Duck Jin [Inha University, Inchon (Korea, Republic of)

    1996-03-01

    A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). 14 refs., 10 figs., 3 tabs.

  12. Neural network models: Insights and prescriptions from practical applications

    Energy Technology Data Exchange (ETDEWEB)

    Samad, T. [Honeywell Technology Center, Minneapolis, MN (United States)

    1995-12-31

    Neural networks are no longer just a research topic; numerous applications are now testament to their practical utility. In the course of developing these applications, researchers and practitioners have been faced with a variety of issues. This paper briefly discusses several of these, noting in particular the rich connections between neural networks and other, more conventional technologies. A more comprehensive version of this paper is under preparation that will include illustrations on real examples. Neural networks are being applied in several different ways. Our focus here is on neural networks as modeling technology. However, much of the discussion is also relevant to other types of applications such as classification, control, and optimization.

  13. Neural network for solving convex quadratic bilevel programming problems.

    Science.gov (United States)

    He, Xing; Li, Chuandong; Huang, Tingwen; Li, Chaojie

    2014-03-01

    In this paper, using the idea of successive approximation, we propose a neural network to solve convex quadratic bilevel programming problems (CQBPPs), which is modeled by a nonautonomous differential inclusion. Different from the existing neural network for CQBPP, the model has the least number of state variables and simple structure. Based on the theory of nonsmooth analysis, differential inclusions and Lyapunov-like method, the limit equilibrium points sequence of the proposed neural networks can approximately converge to an optimal solution of CQBPP under certain conditions. Finally, simulation results on two numerical examples and the portfolio selection problem show the effectiveness and performance of the proposed neural network.

  14. 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.

  15. Term Structure of Interest Rates Based on Artificial Neural Network

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    In light of the nonlinear approaching capability of artificial neural networks ( ANN), the term structure of interest rates is predicted using The generalized regression neural network (GRNN) and back propagation (BP) neural networks models. The prediction performance is measured with US interest rate data. Then, RBF and BP models are compared with Vasicek's model and Cox-Ingersoll-Ross (CIR) model. The comparison reveals that neural network models outperform Vasicek's model and CIR model,which are more precise and closer to the real market situation.

  16. Digital Watermarking Algorithm Based on Wavelet Transform and Neural Network

    Institute of Scientific and Technical Information of China (English)

    WANG Zhenfei; ZHAI Guangqun; WANG Nengchao

    2006-01-01

    An effective blind digital watermarking algorithm based on neural networks in the wavelet domain is presented. Firstly, the host image is decomposed through wavelet transform. The significant coefficients of wavelet are selected according to the human visual system (HVS) characteristics. Watermark bits are added to them. And then effectively cooperates neural networks to learn the characteristics of the embedded watermark related to them. Because of the learning and adaptive capabilities of neural networks, the trained neural networks almost exactly recover the watermark from the watermarked image. Experimental results and comparisons with other techniques prove the effectiveness of the new algorithm.

  17. Neural Network Inverse Adaptive Controller Based on Davidon Least Square

    Institute of Scientific and Technical Information of China (English)

    2000-01-01

    General neural network inverse adaptive controller haa two flaws: the first is the slow convergence speed; the second is the invalidation to the non-minimum phase system.These defects limit the scope in which the neural network inverse adaptive controller is used.We employ Davidon least squares in training the multi-layer feedforward neural network used in approximating the inverse model of plant to expedite the convergence,and then through constructing the pseudo-plant,a neural network inverse adaptive controller is put forward which is still effective to the nonlinear non-minimum phase system.The simulation results show the validity of this scheme.

  18. Robustness of the ATLAS pixel clustering neural network algorithm

    CERN Document Server

    AUTHOR|(INSPIRE)INSPIRE-00407780; The ATLAS collaboration

    2016-01-01

    Proton-proton collisions at the energy frontier puts strong constraints on track reconstruction algorithms. In the ATLAS track reconstruction algorithm, an artificial neural network is utilised to identify and split clusters of neighbouring read-out elements in the ATLAS pixel detector created by multiple charged particles. The robustness of the neural network algorithm is presented, probing its sensitivity to uncertainties in the detector conditions. The robustness is studied by evaluating the stability of the algorithm's performance under a range of variations in the inputs to the neural networks. Within reasonable variation magnitudes, the neural networks prove to be robust to most variation types.

  19. NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER

    Institute of Scientific and Technical Information of China (English)

    Qin Zheng; Liu Yu; Wang Yu

    2006-01-01

    Objective To reduce the execution time of neural network training. Methods Parallel particle swarm optimization algorithm based on master-slave model is proposed to train radial basis function neural networks, which is implemented on a cluster using MPI libraries for inter-process communication. Results High speed-up factor is achieved and execution time is reduced greatly. On the other hand, the resulting neural network has good classification accuracy not only on training sets but also on test sets. Conclusion Since the fitness evaluation is intensive, parallel particle swarm optimization shows great advantages to speed up neural network training.

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

    Directory of Open Access Journals (Sweden)

    Yanbo Huang

    2009-08-01

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

  1. 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.

  2. Uncovering the footprints of malicious traffic in cellular data networks

    OpenAIRE

    Raghuramu, A; Zang, H.; Chuah, CN

    2015-01-01

    © Springer International Publishing Switzerland 2015. In this paper, we present a comprehensive characterization of malicious traffic generated by mobile devices using Deep Packet Inspection (DPI) records and security event logs from a large US based cellular provider network. Our analysis reveals that 0.17% of mobile devices in the cellular network are affected by security threats. This proportion, while small, is orders of magnitude higher than the last reported (in 2013) infection rate of ...

  3. Convolution neural networks for ship type recognition

    Science.gov (United States)

    Rainey, Katie; Reeder, John D.; Corelli, Alexander G.

    2016-05-01

    Algorithms to automatically recognize ship type from satellite imagery are desired for numerous maritime applications. This task is difficult, and example imagery accurately labeled with ship type is hard to obtain. Convolutional neural networks (CNNs) have shown promise in image recognition settings, but many of these applications rely on the availability of thousands of example images for training. This work attempts to under- stand for which types of ship recognition tasks CNNs might be well suited. We report the results of baseline experiments applying a CNN to several ship type classification tasks, and discuss many of the considerations that must be made in approaching this problem.

  4. An Intelligent technical analysis using neural network

    Directory of Open Access Journals (Sweden)

    Reza Raei

    2011-07-01

    Full Text Available Technical analysis has been one of the most popular methods for stock market predictions for the past few decades. There have been enormous technical analysis methods to study the behavior of stock market for different kinds of trading markets such as currency, commodity or stock. In this paper, we propose two different methods based on volume adjusted moving average and ease of movement for stock trading. These methods are used with and without generalized regression neural network methods and the results are compared with each other. The preliminary results on historical stock price of 20 firms indicate that there is no meaningful difference between various proposed models of this paper.

  5. Artificial Neural Network applied to lightning flashes

    Science.gov (United States)

    Gin, R. B.; Guedes, D.; Bianchi, R.

    2013-05-01

    The development of video cameras enabled cientists to study lightning discharges comportment with more precision. The main goal of this project is to create a system able to detect images of lightning discharges stored in videos and classify them using an Artificial Neural Network (ANN)using C Language and OpenCV libraries. The developed system, can be split in two different modules: detection module and classification module. The detection module uses OpenCV`s computer vision libraries and image processing techniques to detect if there are significant differences between frames in a sequence, indicating that something, still not classified, occurred. Whenever there is a significant difference between two consecutive frames, two main algorithms are used to analyze the frame image: brightness and shape algorithms. These algorithms detect both shape and brightness of the event, removing irrelevant events like birds, as well as detecting the relevant events exact position, allowing the system to track it over time. The classification module uses a neural network to classify the relevant events as horizontal or vertical lightning, save the event`s images and calculates his number of discharges. The Neural Network was implemented using the backpropagation algorithm, and was trained with 42 training images , containing 57 lightning events (one image can have more than one lightning). TheANN was tested with one to five hidden layers, with up to 50 neurons each. The best configuration achieved a success rate of 95%, with one layer containing 20 neurons (33 test images with 42 events were used in this phase). This configuration was implemented in the developed system to analyze 20 video files, containing 63 lightning discharges previously manually detected. Results showed that all the lightning discharges were detected, many irrelevant events were unconsidered, and the event's number of discharges was correctly computed. The neural network used in this project achieved a

  6. Transient Stability Assessment using Artificial Neural Networks

    OpenAIRE

    Krishna, S; Padiyar, KR

    2000-01-01

    Online transient stability assessment (TSA) of a power system is not yet feasible due to the intensive computation involved. Artificial neural networks (ANN) have been proposed as one of the approaches to this problem because of their ability to quickly map nonlinear relationships between the input data and the output. In this paper a review of the previously published papers on TSA using ANN is presented. The paper also reports the results of the application of ANN to the problem of TSA of a...

  7. Evaluating Neural Network Predictors by Bootstrapping

    OpenAIRE

    Blake LeBaron; Andreas S. Weigend

    1994-01-01

    We present a new method, inspired by the bootstrap, whose goal it is to determine the quality and reliability of a neural network predictor. Our method leads to more robust forecasting along with a large amount of statistical information on forecast performance that we exploit. We exhibit the method in the context of multi-variate time series prediction on financial data from the New York Stock Exchange. It turns out that the variation due to different resamplings (i.e., splits between traini...

  8. Email Spam Filter using Bayesian Neural Networks

    Directory of Open Access Journals (Sweden)

    Nibedita Chakraborty

    2012-03-01

    Full Text Available Nowadays, e-mail is widely becoming one of the fastest and most economical forms of communication but they are prone to be misused. One such misuse is the posting of unsolicited, unwanted e-mails known as spam or junk e-mails. This paper presents and discusses an implementation of a spam filtering system. The idea is to use a neural network which will be trained to recognize different forms of often used words in spam mails. The Bayesian ANN is trained with finite sample sizes to approximate the ideal observer. This strategy can provide improved filtering of Spam than existing Static Spam filters.

  9. Robotic velocity generation using neural network

    Institute of Scientific and Technical Information of China (English)

    2001-01-01

    The fast-paced nature of robotic soccer necessitates real-time sensing coupled with quick decision making and behaving. The robot must have high response-rate, exact motion ability, and must robust enough to confront interfere during drastic match. But during the match, we find that the robot usually do not act exactly as the commands from host computer. In this paper, we analyze the reason and present a method that uses BP neural network to output robotic velocity directly instead of conventional path-plan strategy, to reduce the error between actual motion and ideal plan.

  10. Colored Noise Prediction Based on Neural Network

    Institute of Scientific and Technical Information of China (English)

    Gao Fei; Zhang Xiaohui

    2003-01-01

    A method for predicting colored noise by introducing prediction of nonhnear time series is presented By adopting three kinds of neural networks prediction models, the colored noise prediction is studied through changing the filter bandwidth for stochastic noise and the sampling rate for colored noise The results show that colored noise can be predicted The prediction error decreases with the increasing of the sampling rate or the narrowing of the filter bandwidth. If the parameters are selected properly, the prediction precision can meet the requirement of engineering implementation. The results offer a new reference way for increasing the ability for detecting weak signal in signal processing system

  11. Supervised Learning in Multilayer Spiking Neural Networks

    CERN Document Server

    Sporea, Ioana

    2012-01-01

    The current article introduces a supervised learning algorithm for multilayer spiking neural networks. The algorithm presented here overcomes some limitations of existing learning algorithms as it can be applied to neurons firing multiple spikes and it can in principle be applied to any linearisable neuron model. The algorithm is applied successfully to various benchmarks, such as the XOR problem and the Iris data set, as well as complex classifications problems. The simulations also show the flexibility of this supervised learning algorithm which permits different encodings of the spike timing patterns, including precise spike trains encoding.

  12. 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.

  13. Predicate calculus for an architecture of multiple neural networks

    Science.gov (United States)

    Consoli, Robert H.

    1990-08-01

    Future projects with neural networks will require multiple individual network components. Current efforts along these lines are ad hoc. This paper relates the neural network to a classical device and derives a multi-part architecture from that model. Further it provides a Predicate Calculus variant for describing the location and nature of the trainings and suggests Resolution Refutation as a method for determining the performance of the system as well as the location of needed trainings for specific proofs. 2. THE NEURAL NETWORK AND A CLASSICAL DEVICE Recently investigators have been making reports about architectures of multiple neural networksL234. These efforts are appearing at an early stage in neural network investigations they are characterized by architectures suggested directly by the problem space. Touretzky and Hinton suggest an architecture for processing logical statements1 the design of this architecture arises from the syntax of a restricted class of logical expressions and exhibits syntactic limitations. In similar fashion a multiple neural netword arises out of a control problem2 from the sequence learning problem3 and from the domain of machine learning. 4 But a general theory of multiple neural devices is missing. More general attempts to relate single or multiple neural networks to classical computing devices are not common although an attempt is made to relate single neural devices to a Turing machines and Sun et a!. develop a multiple neural architecture that performs pattern classification.

  14. Sonar discrimination of cylinders from different angles using neural networks neural networks

    DEFF Research Database (Denmark)

    Andersen, Lars Nonboe; Au, Whiwlow; Larsen, Jan;

    1999-01-01

    This paper describes an underwater object discrimination system applied to recognize cylinders of various compositions from different angles. The system is based on a new combination of simulated dolphin clicks, simulated auditory filters and artificial neural networks. The model demonstrates its...

  15. Wavelet Neural Network Based Traffic Prediction for Next Generation Network

    Institute of Scientific and Technical Information of China (English)

    Zhao Qigang; Li Qunzhan; He Zhengyou

    2005-01-01

    By using netflow traffic collecting technology, some traffic data for analysis are collected from a next generation network (NGN) operator. To build a wavelet basis neural network (NN), the Sigmoid function is replaced with the wavelet in NN. Then the wavelet multiresolution analysis method is used to decompose the traffic signal, and the decomposed component sequences are employed to train the NN. By using the methods, an NGN traffic prediction model is built to predict one day's traffic. The experimental results show that the traffic prediction method of wavelet NN is more accurate than that without using wavelet in the NGN traffic forecasting.

  16. Neural Network Model Based Cluster Head Selection for Power Control

    Directory of Open Access Journals (Sweden)

    Krishan Kumar

    2011-01-01

    Full Text Available Mobile ad-hoc network has challenge of the limited power to prolong the lifetime of the network, because power is a valuable resource in mobile ad-hoc network. The status of power consumption should be continuously monitored after network deployment. In this paper, we propose coverage aware neural network based power control routing with the objective of maximizing the network lifetime. Cluster head selection is proposed using adaptive learning in neural networks followed by coverage. The simulation results show that the proposed scheme can be used in wide area of applications in mobile ad-hoc network.

  17. Programmable synaptic chip for electronic neural networks

    Science.gov (United States)

    Moopenn, A.; Langenbacher, H.; Thakoor, A. P.; Khanna, S. K.

    1988-01-01

    A binary synaptic matrix chip has been developed for electronic neural networks. The matrix chip contains a programmable 32X32 array of 'long channel' NMOSFET binary connection elements implemented in a 3-micron bulk CMOS process. Since the neurons are kept off-chip, the synaptic chip serves as a 'cascadable' building block for a multi-chip synaptic network as large as 512X512 in size. As an alternative to the programmable NMOSFET (long channel) connection elements, tailored thin film resistors are deposited, in series with FET switches, on some CMOS test chips, to obtain the weak synaptic connections. Although deposition and patterning of the resistors require additional processing steps, they promise substantial savings in silicon area. The performance of synaptic chip in a 32-neuron breadboard system in an associative memory test application is discussed.

  18. A hybrid neural network model for consciousness

    Institute of Scientific and Technical Information of China (English)

    蔺杰; 金小刚; 杨建刚

    2004-01-01

    A new framework for consciousness is introduced based upon traditional artificial neural network models. This framework reflects explicit connections between two parts of the brain: one global working memory and distributed modular cerebral networks relating to specific brain functions. Accordingly this framework is composed of three layers,physical mnemonic layer and abstract thinking layer,which cooperate together through a recognition layer to accomplish information storage and cognition using algorithms of how these interactions contribute to consciousness:(1)the reception process whereby cerebral subsystems group distributed signals into coherent object patterns;(2)the partial recognition process whereby patterns from particular subsystems are compared or stored as knowledge; and(3)the resonant learning process whereby global workspace stably adjusts its structure to adapt to patterns' changes. Using this framework,various sorts of human actions can be explained,leading to a general approach for analyzing brain functions.

  19. A Convolutional Neural Network Neutrino Event Classifier

    CERN Document Server

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

    2016-01-01

    Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

  20. A convolutional neural network neutrino event classifier

    Science.gov (United States)

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

    2016-09-01

    Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

  1. Software failures prediction using RBF neural network

    Directory of Open Access Journals (Sweden)

    Vitaliy S. Yakovyna

    2015-06-01

    Full Text Available One of the prospective techniques for software reliability prediction are those based on nonparametric models, in particular on artificial neural networks. In this paper the study of influence of number of input neurons of network based on radial basis function on the efficiency of software failures prediction presented in the form of time series is carried out. Software faults time series are constructed using Chromium and Chromium-OS open source software systems testing data with proposed further processing as a normalized values of the number of software failures in equal intervals, followed by transfer to man-days. It is demonstrated that the closest prediction can be achieved using Inverse Multiquadric activation function with 10…20 input layer neurons and 30 hidden neurons.

  2. A hybrid neural network model for consciousness

    Institute of Scientific and Technical Information of China (English)

    蔺杰; 金小刚; 杨建刚

    2004-01-01

    A new framework for consciousness is introduced based upon traditional artificial neural network models. This framework reflects explicit connections between two parts of the brain: one global working memory and distributed modular cerebral networks relating to specific brain functions. Accordingly this framework is composed of three layers, physical mnemonic layer and abstract thinking layer, which cooperate together through a recognition layer to accomplish information storage and cognition using algorithms of how these interactions contribute to consciousness: (l) the reception process whereby cerebral subsystems group distributed signals into coherent object patterns; (2) the partial recognition process whereby patterns from particular subsystems are compared or stored as knowledge; and (3) the resonant learning process whereby global workspace stably adjusts its structure to adapt to patterns' changes. Using this framework, various sorts of human actions can be explained, leading to a general approach for analyzing brain functions.

  3. Edge detection of range images using genetic neural networks

    Institute of Scientific and Technical Information of China (English)

    FAN Jian-ying; DU Ying; ZHOU Yang; WANG Yang

    2009-01-01

    Due to the complexity and asymmetrical illumination, the images of object are difficult to be effectively segmented by some routine method. In this paper, a kind of edge detection method based on image features and genetic algorithms neural network for range images was proposed. Fully considering the essential difference between an edge point and a noise point, some characteristic parameters were extracted from range maps as the input nodes of the network in the algorithm. Firstly, a genetic neural network was designed and implemented. The neural network is trained by genetic algorithm, and then genetic neural network algorithm is combined with the virtue of global optimization of genetic algorithm and the virtue of parallel computation of neural network, so that this algorithm is of good global property. The experimental results show that this method can get much faster and more accurate detection results than the classical differential algorithm, and has better anti-noise performance.

  4. Chinese word sense disambiguation based on neural networks

    Institute of Scientific and Technical Information of China (English)

    LIU Ting; LU Zhi-mao; LANG Jun; LI Sheng

    2005-01-01

    The input of a network is the key problem for Chinese word sense disambiguation utilizing the neural network. This paper presents an input model of the neural network that calculates the mutual information between contextual words and the ambiguous word by using statistical methodology and taking the contextual words of a certain number beside the ambiguous word according to ( - M, + N). The experiment adopts triple-layer BP Neural Network model and proves how the size of a training set and the value of M and N affect the performance of the Neural Network Model. The experimental objects are six pseudowords owning three word-senses constructed according to certain principles. The tested accuracy of our approach on a closed-corpus reaches 90. 31% ,and 89. 62% on an open-corpus. The experiment proves that the Neural Network Model has a good performance on Word Sense Disambiguation.

  5. A survey on RBF Neural Network for Intrusion Detection System

    Directory of Open Access Journals (Sweden)

    Henali Sheth

    2014-12-01

    Full Text Available Network security is a hot burning issue nowadays. With the help of technology advancement intruders or hackers are adopting new methods to create different attacks in order to harm network security. Intrusion detection system (IDS is a kind of security software which inspects all incoming and outgoing network traffic and it will generate alerts if any attack or unusual behavior is found in a network. Various approaches are used for IDS such as data mining, neural network, genetic and statistical approach. Among this Neural Network is more suitable approach for IDS. This paper describes RBF neural network approach for Intrusion detection system. RBF is a feed forward and supervise technique of neural network.RBF approach has good classification ability but its performance depends on its parameters. Based on survey we find that RBF approach has some short comings. In order to overcome this we need to do proper optimization of RBF parameters.

  6. USING A NEURAL NETWORK TO PREDICT ELECTRICITY GENERATION

    Science.gov (United States)

    The paper discusses using a neural network to predict electricity generation. uch predictions are important in developing forecasts of air pollutant release and in evaluating the effectiveness of alternative policies which may reduce pollution. eural network model (NUMOD) that pr...

  7. Layered learning of soccer robot based on artificial neural network

    Institute of Scientific and Technical Information of China (English)

    2001-01-01

    Discusses the application of artificial neural network for MIROSOT, introduces a layered model of BP network of soccer robot for learning basic behavior and cooperative behavior, and concludes from experimental results that the model is effective.

  8. Combining Neural Networks for Skin Detection

    CERN Document Server

    Doukim, Chelsia Amy; Chekima, Ali; Omatu, Sigeru

    2011-01-01

    Two types of combining strategies were evaluated namely combining skin features and combining skin classifiers. Several combining rules were applied where the outputs of the skin classifiers are combined using binary operators such as the AND and the OR operators, "Voting", "Sum of Weights" and a new neural network. Three chrominance components from the YCbCr colour space that gave the highest correct detection on their single feature MLP were selected as the combining parameters. A major issue in designing a MLP neural network is to determine the optimal number of hidden units given a set of training patterns. Therefore, a "coarse to fine search" method to find the number of neurons in the hidden layer is proposed. The strategy of combining Cb/Cr and Cr features improved the correct detection by 3.01% compared to the best single feature MLP given by Cb-Cr. The strategy of combining the outputs of three skin classifiers using the "Sum of Weights" rule further improved the correct detection by 4.38% compared t...

  9. Neural network analysis for hazardous waste characterization

    Energy Technology Data Exchange (ETDEWEB)

    Misra, M.; Pratt, L.Y.; Farris, C. [Colorado School of Mines, Golden, CO (United States)] [and others

    1995-12-31

    This paper is a summary of our work in developing a system for interpreting electromagnetic (EM) and magnetic sensor information from the dig face characterization experimental cell at INEL to determine the depth and nature of buried objects. This project contained three primary components: (1) development and evaluation of several geophysical interpolation schemes for correcting missing or noisy data, (2) development and evaluation of several wavelet compression schemes for removing redundancies from the data, and (3) construction of two neural networks that used the results of steps (1) and (2) to determine the depth and nature of buried objects. This work is a proof-of-concept study that demonstrates the feasibility of this approach. The resulting system was able to determine the nature of buried objects correctly 87% of the time and was able to locate a buried object to within an average error of 0.8 feet. These statistics were gathered based on a large test set and so can be considered reliable. Considering the limited nature of this study, these results strongly indicate the feasibility of this approach, and the importance of appropriate preprocessing of neural network input data.

  10. Artificial neural networks in neutron dosimetry

    International Nuclear Information System (INIS)

    An artificial neural network (ANN) has been designed to obtain neutron doses using only the count rates of a Bonner spheres spectrometer (BSS). Ambient, personal and effective neutron doses were included. One hundred and eighty-one neutron spectra were utilised 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 the BSS and the doses. Count rates were used as input and the respective doses were used as output during neural network training. Training and testing were carried out in the MATLABR environment. The impact of uncertainties in BSS count rates upon the dose quantities calculated with the ANN was investigated by modifying by ±5% the BSS count rates used in the training set. The use of ANNs in neutron dosimetry is an alternative procedure that overcomes the drawbacks associated with this ill-conditioned problem. (authors)

  11. Boundary Depth Information Using Hopfield Neural Network

    Science.gov (United States)

    Xu, Sheng; Wang, Ruisheng

    2016-06-01

    Depth information is widely used for representation, reconstruction and modeling of 3D scene. Generally two kinds of methods can obtain the depth information. One is to use the distance cues from the depth camera, but the results heavily depend on the device, and the accuracy is degraded greatly when the distance from the object is increased. The other one uses the binocular cues from the matching to obtain the depth information. It is more and more mature and convenient to collect the depth information of different scenes by stereo matching methods. In the objective function, the data term is to ensure that the difference between the matched pixels is small, and the smoothness term is to smooth the neighbors with different disparities. Nonetheless, the smoothness term blurs the boundary depth information of the object which becomes the bottleneck of the stereo matching. This paper proposes a novel energy function for the boundary to keep the discontinuities and uses the Hopfield neural network to solve the optimization. We first extract the region of interest areas which are the boundary pixels in original images. Then, we develop the boundary energy function to calculate the matching cost. At last, we solve the optimization globally by the Hopfield neural network. The Middlebury stereo benchmark is used to test the proposed method, and results show that our boundary depth information is more accurate than other state-of-the-art methods and can be used to optimize the results of other stereo matching methods.

  12. Parameterizing Stellar Spectra Using Deep Neural Networks

    CERN Document Server

    Li, Xiangru

    2016-01-01

    This work investigates the spectrum parameterization problem using deep neural networks (DNNs). The proposed scheme consists of the following procedures: first, the configuration of a DNN is initialized using a series of autoencoder neural networks; second, the DNN is fine-tuned using a gradient descent scheme; third, stellar parameters ($T_{eff}$, log$~g$, and [Fe/H]) are estimated using the obtained DNN. This scheme was evaluated on both real spectra from SDSS/SEGUE and synthetic spectra calculated from Kurucz's new opacity distribution function models. Test consistencies between our estimates and those provided by the spectroscopic parameter pipeline of SDSS show that the mean absolute errors (MAEs) are 0.0048, 0.1477, and 0.1129 dex for log$~T_{eff}$, log$~g$, and [Fe/H] (64.85 K for $T_{eff}$), respectively. For the synthetic spectra, the MAE test accuracies are 0.0011, 0.0182, and 0.0112 dex for log$~T_{eff}$, log$~g$, and [Fe/H] (14.90 K for $T_{eff}$), respectively.

  13. Damage identification with probabilistic neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Klenke, S.E.; Paez, T.L.

    1995-12-01

    This paper investigates the use of artificial neural networks (ANNs) to identify damage in mechanical systems. Two probabilistic neural networks (PNNs) are developed and used to judge whether or not damage has occurred in a specific mechanical system, based on experimental measurements. The first PNN is a classical type that casts Bayesian decision analysis into an ANN framework, it uses exemplars measured from the undamaged and damaged system to establish whether system response measurements of unknown origin come from the former class (undamaged) or the latter class (damaged). The second PNN establishes the character of the undamaged system in terms of a kernel density estimator of measures of system response; when presented with system response measures of unknown origin, it makes a probabilistic judgment whether or not the data come from the undamaged population. The physical system used to carry out the experiments is an aerospace system component, and the environment used to excite the system is a stationary random vibration. The results of damage identification experiments are presented along with conclusions rating the effectiveness of the approaches.

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

    International Nuclear Information System (INIS)

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

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

    Energy Technology Data Exchange (ETDEWEB)

    Ortiz R, J. M. [Escuela Politecnica Superior, Departamento de Electrotecnia y Electronica, Avda. Menendez Pidal s/n, Cordoba (Spain); Martinez B, M. R.; Vega C, H. R. [Universidad Autonoma de Zacatecas, Unidad Academica de Estudios Nucleares, Calle Cipres No. 10, Fracc. La Penuela, 98068 Zacatecas (Mexico); Gallego D, E.; Lorente F, A. [Universidad Politecnica de Madrid, Departamento de Ingenieria Nuclear, ETSI Industriales, C. Jose Gutierrez Abascal 2, 28006 Madrid (Spain); Mendez V, R.; Los Arcos M, J. M.; Guerrero A, J. E., E-mail: morvymm@yahoo.com.m [CIEMAT, Laboratorio de Metrologia de Radiaciones Ionizantes, Avda. Complutense 22, 28040 Madrid (Spain)

    2011-02-15

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

  16. Impact of Mutation Weights on Training Backpropagation Neural Networks

    Directory of Open Access Journals (Sweden)

    Lamia Abed Noor Muhammed

    2014-07-01

    Full Text Available Neural network is a computational approach, which based on the simulation of biology neural network. This approach is conducted by several parameters; learning rate, initialized weights, network architecture, and so on. However, this paper would be focused on one of these parameters that is weights. The aim is to shed lights on the mutation weights through training network and its effects on the results. The experiment was done using backpropagation neural network with one hidden layer. The results reveal the role of mutation in escape from the local minima and making the change

  17. Adaptive training of feedforward neural networks by Kalman filtering

    Energy Technology Data Exchange (ETDEWEB)

    Ciftcioglu, Oe. [Istanbul Technical Univ. (Turkey). Dept. of Electrical Engineering; Tuerkcan, E. [Netherlands Energy Research Foundation (ECN), Petten (Netherlands)

    1995-02-01

    Adaptive training of feedforward neural networks by Kalman filtering is described. Adaptive training is particularly important in estimation by neural network in real-time environmental where the trained network is used for system estimation while the network is further trained by means of the information provided by the experienced/exercised ongoing operation. As result of this, neural network adapts itself to a changing environment to perform its mission without recourse to re-training. The performance of the training method is demonstrated by means of actual process signals from a nuclear power plant. (orig.).

  18. Improved Local Weather Forecasts Using Artificial Neural Networks

    DEFF Research Database (Denmark)

    Wollsen, Morten Gill; Jørgensen, Bo Nørregaard

    2015-01-01

    using an artificial neural network. The neural network used is a NARX network, which is known to model non-linear systems well. The predictions are compared to both a design reference year as well as commercial weather forecasts based upon numerical modelling. The results presented in this paper show...... that the network outperforms the commercial forecast for lower step aheads (network’s performance is in the range of the commercial forecast. However, the neural network approach is fast, fairly precise and allows for further expansion with higher resolution....

  19. Learning and coding in biological neural networks

    Science.gov (United States)

    Fiete, Ila Rani

    How can large groups of neurons that locally modify their activities learn to collectively perform a desired task? Do studies of learning in small networks tell us anything about learning in the fantastically large collection of neurons that make up a vertebrate brain? What factors do neurons optimize by encoding sensory inputs or motor commands in the way they do? In this thesis I present a collection of four theoretical works: each of the projects was motivated by specific constraints and complexities of biological neural networks, as revealed by experimental studies; together, they aim to partially address some of the central questions of neuroscience posed above. We first study the role of sparse neural activity, as seen in the coding of sequential commands in a premotor area responsible for birdsong. We show that the sparse coding of temporal sequences in the songbird brain can, in a network where the feedforward plastic weights must translate the sparse sequential code into a time-varying muscle code, facilitate learning by minimizing synaptic interference. Next, we propose a biologically plausible synaptic plasticity rule that can perform goal-directed learning in recurrent networks of voltage-based spiking neurons that interact through conductances. Learning is based on the correlation of noisy local activity with a global reward signal; we prove that this rule performs stochastic gradient ascent on the reward. Thus, if the reward signal quantifies network performance on some desired task, the plasticity rule provably drives goal-directed learning in the network. To assess the convergence properties of the learning rule, we compare it with a known example of learning in the brain. Song-learning in finches is a clear example of a learned behavior, with detailed available neurophysiological data. With our learning rule, we train an anatomically accurate model birdsong network that drives a sound source to mimic an actual zebrafinch song. Simulation and

  20. Automated Modeling of Microwave Structures by Enhanced Neural Networks

    Directory of Open Access Journals (Sweden)

    Z. Raida

    2006-12-01

    Full Text Available The paper describes the methodology of the automated creation of neural models of microwave structures. During the creation process, artificial neural networks are trained using the combination of the particle swarm optimization and the quasi-Newton method to avoid critical training problems of the conventional neural nets. In the paper, neural networks are used to approximate the behavior of a planar microwave filter (moment method, Zeland IE3D. In order to evaluate the efficiency of neural modeling, global optimizations are performed using numerical models and neural ones. Both approaches are compared from the viewpoint of CPU-time demands and the accuracy. Considering conclusions, methodological recommendations for including neural networks to the microwave design are formulated.