By Topic

IEEE Transactions on Neural Networks

Issue 5 • Date Sep 1993

Filter Results

Displaying Results 1 - 16 of 16
  • Symmetries and discriminability in feedforward network architectures

    Publication Year: 1993, Page(s):816 - 826
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1032 KB)

    This paper investigates the effects of introducing symmetries into feedforward neural networks in what are termed symmetry networks. This technique allows more efficient training for problems in which we require the output of a network to be invariant under a set of transformations of the input. The particular problem of graph recognition is considered. In this case the network is designed to deli... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Determining and improving the fault tolerance of multilayer perceptrons in a pattern-recognition application

    Publication Year: 1993, Page(s):788 - 793
    Cited by:  Papers (32)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (576 KB)

    We investigate empirically the performance under damage conditions of single- and multilayer perceptrons (MLP's), with various numbers of hidden units, in a representative pattern-recognition task. While some degree of graceful degradation was observed, the single-layer perceptron was considerably less fault tolerant than any of the multilayer perceptrons, including one with fewer adjustable weigh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Backpropagation uses prior information efficiently

    Publication Year: 1993, Page(s):794 - 802
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (612 KB)

    The ability of neural net classifiers to deal with a priori information is investigated. For this purpose, backpropagation classifiers are trained with data from known distributions with variable a priori probabilities, and their performance on separate test sets is evaluated. It is found that backpropagation employs a priori information in a slightly suboptimal fashion, but this does not have ser... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Anti-Hebbian learning in topologically constrained linear networks: a tutorial

    Publication Year: 1993, Page(s):748 - 761
    Cited by:  Papers (20)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1036 KB)

    Using standard results from the adaptive signal processing literature, we review the learning behavior of various constrained linear neural networks made up of anti-Hebbian synapses, where learning is driven by the criterion of minimizing the node information energy. We point out how simple learning rules of Hebbian type can provide fast self-organization, under rather wide connectivity constraint... View full abstract»

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

    Publication Year: 1993, Page(s):803 - 815
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1136 KB)

    This paper introduces techniques to train feedforward nets to automate ranking and classification tasks. The techniques are denoted mimic nets since the nets can always mimic self-consistent training data. The mimic nets are constructed not for any neurological analogy, but for computational ease and purposeful utility. Mimic nets are designed for problems requiring sensible extrapolation from noi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network design using Voronoi diagrams

    Publication Year: 1993, Page(s):778 - 787
    Cited by:  Papers (39)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (864 KB)

    A novel approach is proposed which determines the number of layers, the number of neurons in each layer, and their connection weights for a particular implementation of a neural network, with the multilayer feedforward topology, designed to classify patterns in the multidimensional feature space. The approach is based on construction of a Voronoi diagram over the set of points representing pattern... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Curvature-driven smoothing: a learning algorithm for feedforward networks

    Publication Year: 1993, Page(s):882 - 884
    Cited by:  Papers (15)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (240 KB)

    The performance of feedforward neural networks in real applications can often be improved significantly if use is made of a priori information. For interpolation problems this prior knowledge frequently includes smoothness requirements on the network mapping, and can be imposed by the addition to the error function of suitable regularization terms. The new error function, however, now depends on t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance analysis of the bidirectional associative memory and an improved model from the matched-filtering viewpoint

    Publication Year: 1993, Page(s):864 - 872
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (660 KB)

    This paper discusses the bidirectional associative memory (BAM) model from the matched-filtering viewpoint and offers it a new interpretation. Our attention is focused on the problem of stability and attractivity of equilibrium states. Several sufficient and/or necessary conditions are presented. To improve the BAM performance, an exponential function is used to enhance the correlations between th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal winner-take-all networks: a time-based mechanism for fast selection in neural networks

    Publication Year: 1993, Page(s):844 - 853
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (816 KB)

    Winner-take-all (WTA) networks frequently appear in neural network models. They are primarily used for decision making and selection. As an alternative to the conventional activation-based winner-take-all mechanisms (AWTA), we present a time-based temporal-winner-take-all mechanism with O(n) space complexity and roughly O(log n) time complexity. The mechanism exploits systematic and stochastic dif... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pruning algorithms-a survey

    Publication Year: 1993, Page(s):740 - 747
    Cited by:  Papers (333)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (676 KB)

    A rule of thumb for obtaining good generalization in systems trained by examples is that one should use the smallest system that will fit the data. Unfortunately, it usually is not obvious what size is best; a system that is too small will not be able to learn the data while one that is just big enough may learn very slowly and be very sensitive to initial conditions and learning parameters. This ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Single layer neural networks for linear system identification using gradient descent technique

    Publication Year: 1993, Page(s):884 - 888
    Cited by:  Papers (26)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (368 KB)

    Recently, some researchers have focused on the applications of neural networks for the system identification problems. In this letter we describe how to use the gradient descent (GD) technique with single layer neural networks to identify the parameters of a linear dynamical system whose states and derivatives of state are given. It is shown that the use of the GD technique for the purpose of syst... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Encoding method for bidirectional associative memory using projection on convex sets

    Publication Year: 1993, Page(s):879 - 881
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (232 KB)

    The traditional encoding method of bidirectional associative memory (BAM) suggested by Kosko (1988) is based on the correlation method with which the capacity is very small. The enhanced Householder encoding algorithm (EHCA) presented here is developed on the basis of the Householder encoding algorithm (HCA) and projection on convex sets (POCS). The capacity of BAM with HCA tends to the dimension ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Synthesis of a nonrecurrent associative memory model based on a nonlinear transformation in the spectral domain

    Publication Year: 1993, Page(s):873 - 878
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    A new nonrecurrent associative memory model is proposed. This model is composed of a nonlinear transformation in the spectral domain followed by the association. The Moore-Penrose pseudoinverse is employed to obtain the least squares optimal solution. Computer simulations are done to evaluate the performance of the model. The simulations use one-dimensional speech signals and two-dimensional head/... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks for routing of communication networks with unreliable components

    Publication Year: 1993, Page(s):854 - 863
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (680 KB)

    A new neural network model, Routron, which can handle dependent component failures of communication networks, is proposed. We prove that the proposed Routron has a stable solution. Moreover, useful upper and lower bounds for the design parameters are derived to help select them in implementations. Simulation results are included to illustrate the effectiveness of the algorithm View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ranging through Gabor logons-a consistent, hierarchical approach

    Publication Year: 1993, Page(s):827 - 843
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2028 KB)

    In this work, the correspondence problem in stereo vision is handled by matching two sets of dense feature vectors. Inspired by biological evidence, these feature vectors are generated by a correlation between a bank of Gabor sensors and the intensity image. The sensors consist of two-dimensional Gabor filters at various scales (spatial frequencies) and orientations, which bear close resemblance t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multipurpose neural processor for machine vision systems

    Publication Year: 1993, Page(s):762 - 777
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1476 KB)

    A multitask neural network is proposed as a plausible visual information processor for performing a variety of real-time operations associated with the early stages of vision. The computational role performed by the processor, named the positive-negative (PN) neural processor, emulates the spatiotemporal information processing capabilities of certain neural activity fields found along the human vi... 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