By Topic

IEEE Transactions on Neural Networks

Issue 3 • Date May 2005

Filter Results

Displaying Results 1 - 25 of 33
  • Table of contents

    Publication Year: 2005, Page(s):c1 - c4
    Request permission for commercial reuse | PDF file iconPDF (41 KB)
    Freely Available from IEEE
  • IEEE Transactions on Neural Networks publication information

    Publication Year: 2005, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (35 KB)
    Freely Available from IEEE
  • Neural network learning algorithms for tracking minor subspace in high-dimensional data stream

    Publication Year: 2005, Page(s):513 - 521
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (359 KB) | HTML iconHTML

    A novel random-gradient-based algorithm is developed for online tracking the minor component (MC) associated with the smallest eigenvalue of the autocorrelation matrix of the input vector sequence. The five available learning algorithms for tracking one MC are extended to those for tracking multiple MCs or the minor subspace (MS). In order to overcome the dynamical divergence properties of some av... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • From projection pursuit and CART to adaptive discriminant analysis?

    Publication Year: 2005, Page(s):522 - 532
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (369 KB) | HTML iconHTML

    While many efforts have been put into the development of nonlinear approximation theory and its applications to signal and image compression, encoding and denoising, there seems to be very few theoretical developments of adaptive discriminant representations in the area of feature extraction, selection and signal classification. In this paper, we try to advocate the idea that such developments and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deterministic convergence of an online gradient method for BP neural networks

    Publication Year: 2005, Page(s):533 - 540
    Cited by:  Papers (60)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB) | HTML iconHTML

    Online gradient methods are widely used for training feedforward neural networks. We prove in this paper a convergence theorem for an online gradient method with variable step size for backward propagation (BP) neural networks with a hidden layer. Unlike most of the convergence results that are of probabilistic and nonmonotone nature, the convergence result that we establish here has a determinist... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient training algorithms for a class of shunting inhibitory convolutional neural networks

    Publication Year: 2005, Page(s):541 - 556
    Cited by:  Papers (28)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (800 KB) | HTML iconHTML

    This article presents some efficient training algorithms, based on first-order, second-order, and conjugate gradient optimization methods, for a class of convolutional neural networks (CoNNs), known as shunting inhibitory convolution neural networks. Furthermore, a new hybrid method is proposed, which is derived from the principles of Quickprop, Rprop, SuperSAB, and least squares (LS). Experimenta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enhanced FMAM based on empirical kernel map

    Publication Year: 2005, Page(s):557 - 564
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (541 KB) | HTML iconHTML

    The existing morphological auto-associative memory models based on the morphological operations, typically including morphological auto-associative memories (auto-MAM) proposed by Ritter et al. and our fuzzy morphological auto-associative memories (auto-FMAM), have many attractive advantages such as unlimited storage capacity, one-shot recall speed and good noise-tolerance to single erosive or dil... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Chaotic neurodynamics for autonomous agents

    Publication Year: 2005, Page(s):565 - 579
    Cited by:  Papers (34)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1034 KB) | HTML iconHTML

    Mesoscopic level neurodynamics study the collective dynamical behavior of neural populations. Such models are becoming increasingly important in understanding large-scale brain processes. Brains exhibit aperiodic oscillations with a much more rich dynamical behavior than fixed-point and limit-cycle approximation allow. Here we present a discretized model inspired by Freeman's K-set mesoscopic leve... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Global asymptotic stability analysis of bidirectional associative memory neural networks with time delays

    Publication Year: 2005, Page(s):580 - 586
    Cited by:  Papers (103)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (233 KB) | HTML iconHTML

    This paper presents a sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point for bidirectional associative memory (BAM) neural networks with distributed time delays. The results impose constraint conditions on the network parameters of neural system independently of the delay parameter, and they are applicable to all continuous nonmonotonic neur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mutation-based genetic neural network

    Publication Year: 2005, Page(s):587 - 600
    Cited by:  Papers (73)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (614 KB) | HTML iconHTML

    Evolving gradient-learning artificial neural networks (ANNs) using an evolutionary algorithm (EA) is a popular approach to address the local optima and design problems of ANN. The typical approach is to combine the strength of backpropagation (BP) in weight learning and EA's capability of searching the architecture space. However, the BP's "gradient descent" approach requires a highly computer-int... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Auditory learning: a developmental method

    Publication Year: 2005, Page(s):601 - 616
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1233 KB) | HTML iconHTML

    Motivated by the human autonomous development process from infancy to adulthood, we have built a robot that develops its cognitive and behavioral skills through real-time interactions with the environment. We call such a robot a developmental robot. In this paper, we present the theory and the architecture to implement a developmental robot and discuss the related techniques that address an array ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A performance analysis of two approximate adaptive designs

    Publication Year: 2005, Page(s):617 - 624
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (320 KB) | HTML iconHTML

    The performance of function approximator based adaptive control designs may scale badly with approximator dimension. For a simple system class, both projection based designs and multiresolution approximation based designs have been shown to have good scaling properties with respect to to linear quadratic (LQ) costs. Here we show that by considering a cost functional with penalties on the control r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive neural control for a class of nonlinearly parametric time-delay systems

    Publication Year: 2005, Page(s):625 - 635
    Cited by:  Papers (127)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB) | HTML iconHTML

    In this paper, an adaptive neural controller for a class of time-delay nonlinear systems with unknown nonlinearities is proposed. Based on a wavelet neural network (WNN) online approximation model, a state feedback adaptive controller is obtained by constructing a novel integral-type Lyapunov-Krasovskii functional, which also efficiently overcomes the controller singularity problem. It is shown th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Missile guidance law design using adaptive cerebellar model articulation controller

    Publication Year: 2005, Page(s):636 - 644
    Cited by:  Papers (44)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (666 KB) | HTML iconHTML

    An adaptive cerebellar model articulation controller (CMAC) is proposed for command to line-of-sight (CLOS) missile guidance law design. In this design, the three-dimensional (3-D) CLOS guidance problem is formulated as a tracking problem of a time-varying nonlinear system. The adaptive CMAC control system is comprised of a CMAC and a compensation controller. The CMAC control is used to imitate a ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Survey of clustering algorithms

    Publication Year: 2005, Page(s):645 - 678
    Cited by:  Papers (1423)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1528 KB) | HTML iconHTML

    Data analysis plays an indispensable role for understanding various phenomena. Cluster analysis, primitive exploration with little or no prior knowledge, consists of research developed across a wide variety of communities. The diversity, on one hand, equips us with many tools. On the other hand, the profusion of options causes confusion. We survey clustering algorithms for data sets appearing in s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High-speed face recognition based on discrete cosine transform and RBF neural networks

    Publication Year: 2005, Page(s):679 - 691
    Cited by:  Papers (134)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1948 KB) | HTML iconHTML

    In this paper, an efficient method for high-speed face recognition based on the discrete cosine transform (DCT), the Fisher's linear discriminant (FLD) and radial basis function (RBF) neural networks is presented. First, the dimensionality of the original face image is reduced by using the DCT and the large area illumination variations are alleviated by discarding the first few low-frequency DCT c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image shadow removal using pulse coupled neural network

    Publication Year: 2005, Page(s):692 - 698
    Cited by:  Papers (64)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (564 KB) | HTML iconHTML

    This paper introduces an approach for image shadow removal by using pulse coupled neural network (PCNN), based on the phenomena of synchronous pulse bursts in the animal visual cortexes. Two shadow-removing criteria are proposed. These two criteria decide how to choose the optimal parameter (the linking strength β). The computer simulation results of shadow removal based on PCNN show that if ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decision feedback recurrent neural equalization with fast convergence rate

    Publication Year: 2005, Page(s):699 - 708
    Cited by:  Papers (28)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1003 KB) | HTML iconHTML

    Real-time recurrent learning (RTRL), commonly employed for training a fully connected recurrent neural network (RNN), has a drawback of slow convergence rate. In the light of this deficiency, a decision feedback recurrent neural equalizer (DFRNE) using the RTRL requires long training sequences to achieve good performance. In this paper, extended Kalman filter (EKF) algorithms based on the RTRL for... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Blind equalization using a predictive radial basis function neural network

    Publication Year: 2005, Page(s):709 - 720
    Cited by:  Papers (23)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1288 KB) | HTML iconHTML

    In this paper, we propose a novel blind equalization approach based on radial basis function (RBF) neural networks. By exploiting the short-term predictability of the system input, a RBF neural net is used to predict the inverse filter output. It is shown here that when the prediction error of the RBF neural net is minimized, the coefficients of the inverse system are identical to those of the unk... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Zeroing polynomials using modified constrained neural network approach

    Publication Year: 2005, Page(s):721 - 732
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1012 KB) | HTML iconHTML

    This paper proposes new modified constrained learning neural root finders (NRFs) of polynomial constructed by backpropagation network (BPN). The technique is based on the relationships between the roots and the coefficients of polynomial as well as between the root moments and the coefficients of the polynomial. We investigated different resulting constrained learning algorithms (CLAs) based on th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An analysis of neural models for walking control

    Publication Year: 2005, Page(s):733 - 742
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (377 KB) | HTML iconHTML

    A large space of different neural models exists from simple mathematical abstractions to detailed biophysical representations with strongly differing levels of complexity and biological relevance. Previous comparisons between models have looked at biological realism or mathematical tractability rather than expressive power. This paper, however, investigates whether more sophisticated models are be... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Landmine detection and classification with complex-valued hybrid neural network using scattering parameters dataset

    Publication Year: 2005, Page(s):743 - 753
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (929 KB) | HTML iconHTML

    Neural networks have been applied to landmine detection from data generated by different kinds of sensors. Real-valued neural networks have been used for detecting landmines from scattering parameters measured by ground penetrating radar (GPR) after disregarding phase information. This paper presents results using complex-valued neural networks, capable of phase-sensitive detection followed by cla... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A MOSFET-based model of a class 2 nerve membrane

    Publication Year: 2005, Page(s):754 - 773
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1042 KB) | HTML iconHTML

    We have constructed a nerve membrane using MOSFET circuitry, which can be a basic element of an FET-based neural system. Its mechanism of action potentials generation is designed to reproduce that of the Hodgkin-Huxley equations. The responses to singlet, doublet, repetitive pulse, and sustained stimuli are analyzed to show that it exhibits similar properties to the Hodgkin-Huxley equations; namel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rigorous proof of termination of SMO algorithm for support vector Machines

    Publication Year: 2005, Page(s):774 - 776
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (165 KB) | HTML iconHTML

    Sequential minimal optimization (SMO) algorithm is one of the simplest decomposition methods for learning of support vector machines (SVMs). Keerthi and Gilbert have recently studied the convergence property of SMO algorithm and given a proof that SMO algorithm always stops within a finite number of iterations. In this letter, we point out the incompleteness of their proof and give a more rigorous... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comments on "The multisynapse neural network and its application to fuzzy Clustering"

    Publication Year: 2005, Page(s):777 - 778
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (106 KB) | HTML iconHTML

    In the above-mentioned paper, Wei and Fahn proposed a neural architecture, the multisynapse neural network, to solve constrained optimization problems including high-order, logarithmic, and sinusoidal forms, etc. As one of its main applications, a fuzzy bidirectional associative clustering network (FBACN) was proposed for fuzzy-partition clustering according to the objective-functional method. The... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IEEE Transactions on Neural Networks is devoted to the science and technology of neural networks, which disclose significant technical knowledge, exploratory developments, and applications of neural networks from biology to software to hardware.

 

This Transactions ceased production in 2011. The current retitled publication is IEEE Transactions on Neural Networks and Learning Systems.

Full Aims & Scope