By Topic

IEEE Transactions on Neural Networks

Issue 4 • Jul 1991

Filter Results

Displaying Results 1 - 10 of 10
  • The convergence of Hamming memory networks

    Publication Year: 1991, Page(s):449 - 457
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB)

    The convergence properties of Hamming memory networks are studied. It is shown how to construct the network so that it probably converges to an appropriate result, and a tight bound is given on the convergence time. The bound on the convergence time is largest when several stored vectors are at the minimum distance from the input vector. For random binary vectors, the probability for such situatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Code vector density in topographic mappings: Scalar case

    Publication Year: 1991, Page(s):427 - 436
    Cited by:  Papers (31)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (704 KB)

    The author derives some new results that build on his earlier work (1989) of combining vector quantization (VQ) theory and topographic mapping (TM) theory. A VQ model (with a noisy transmission medium) is used to model the processes that occur in TMs, which leads to the standard TM training algorithm, albeit with a slight modification to the encoding process. To emphasize this difference, the mode... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayes statistical behavior and valid generalization of pattern classifying neural networks

    Publication Year: 1991, Page(s):471 - 475
    Cited by:  Papers (39)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    It is demonstrated both theoretically and experimentally that, under appropriate assumptions, a neural network pattern classifier implemented with a supervised learning algorithm generates the empirical Bayes rule that is optimal against the empirical distribution of the training sample. It is also shown that, for a sufficiently large sample size, asymptotic equivalence of the network-generated ru... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning vector quantization for the probabilistic neural network

    Publication Year: 1991, Page(s):458 - 461
    Cited by:  Papers (98)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (352 KB)

    A modified version of the PNN (probabilistic neural network) learning phase which allows a considerable simplification of network structure by including a vector quantization of learning data is proposed. It can be useful if large training sets are available. The procedure has been successfully tested in two synthetic data experiments. The proposed network has been shown to improve the classificat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exact associative neural memory dynamics utilizing Boolean matrices

    Publication Year: 1991, Page(s):437 - 448
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (920 KB)

    The exact dynamics of shallow loaded associative neural memories are generated and characterized. The Boolean matrix analysis approach is employed for the efficient generation of all possible state transition trajectories for parallel updated binary-state dynamic associative memories (DAMs). General expressions for the size of the basin of attraction of fundamental and oscillatory memories and the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A nonlinear regulator design in the presence of system uncertainties using multilayered neural network

    Publication Year: 1991, Page(s):410 - 417
    Cited by:  Papers (79)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB)

    The authors present a novel nonlinear regulator design method that integrates linear optimal control techniques and nonlinear neural network learning methods. Multilayered neural networks are used to add nonlinear effects to the linear optimal regulator (LOR). The regulator can compensate for nonlinear system uncertainties that are not considered in the LOR design and can tolerate a wider range of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A real-time experiment using a 50-neuron CMOS analog silicon chip with on-chip digital learning

    Publication Year: 1991, Page(s):461 - 464
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (284 KB)

    The authors present initial results of a pattern/character recognition and association experiment using a newly fabricated 50-neuron CMOS analog silicon chip with digital on-chip learning. Attention is given to the circuit architecture, the VLSI chips, and the interface circuitry View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Energy function analysis of dynamic programming neural networks

    Publication Year: 1991, Page(s):418 - 426
    Cited by:  Papers (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (624 KB)

    All analytical examination of the energy function associated with a dynamic programming neural network is presented. The analysis is carried out in two steps. First, the locations and numbers of the minimum states for different components of the energy function are investigated in the extreme cases. A clearer insight into the energy function can be gained through the minimum states of different co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic programming approach to optimal weight selection in multilayer neural networks

    Publication Year: 1991, Page(s):465 - 467
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (220 KB)

    A novel algorithm for weight adjustments in a multilayer neural network is derived using the principles of dynamic programming. The algorithm computes the optimal values for weights on a layer-by-layer basis starting from the output layer of the network. The advantage of this algorithm is that it provides an error function for every hidden layer expressed entirely in terms of the weights and outpu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A simple method to derive bounds on the size and to train multilayer neural networks

    Publication Year: 1991, Page(s):467 - 471
    Cited by:  Papers (105)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (436 KB)

    A new derivation is presented for the bounds on the size of a multilayer neural network to exactly implement an arbitrary training set; namely the training set can be implemented with zero error with two layers and with the number of the hidden-layer neurons equal to #1⩾ p-1. The derivation does not require the separation of the input space by particular hyperplanes, as in previous de... 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