By Topic

IEEE Transactions on Neural Networks

Issue 4 • Date Jul 1994

Filter Results

Displaying Results 1 - 15 of 15
  • Weight shifting techniques for self-recovery neural networks

    Publication Year: 1994, Page(s):651 - 658
    Cited by:  Papers (15)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (600 KB)

    In this paper, a self-recovery technique of feedforward neural networks called weight shifting and its analytical models are proposed. The technique is applied to recover a network when some faulty links and/or neurons occur during the operation. If some input links of a specific neuron are detected faulty, their weights will be shifted to healthy links of the same neuron. On the other hand, if a ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network control of communications systems

    Publication Year: 1994, Page(s):639 - 650
    Cited by:  Papers (37)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1100 KB)

    Neural networks appear well suited to applications in the control of communications systems for two reasons: adaptivity and high speed. This paper describes application of neural networks to two problems, admission control and switch control, which exploit the adaptivity and speed property, respectively. The admission control problem is the selective admission of a set of calls from a number of in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Diffusion network architectures for implementation of Gibbs samplers with applications to assignment problems

    Publication Year: 1994, Page(s):622 - 638
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1208 KB)

    In this paper, analog circuit designs for implementations of Gibbs samplers are presented, which offer fully parallel computation. The Gibbs sampler for a discrete solution space (or Boltzmann machine) can be used to solve both deterministic and probabilistic assignment (association) problems. The primary drawback to the use of a Boltzmann machine for optimization is its computational complexity, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Second-order bounds on the domain of attraction and the rate of convergence of nonlinear dynamical systems and neural networks

    Publication Year: 1994, Page(s):551 - 560
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (732 KB)

    We present a method for analyzing the convergence properties of nonlinear dynamical systems yielding second-order bounds on the domain of attraction of an asymptotically stable equilibrium point and on the time of convergence in the estimated domain. We show that under certain conditions on the system, there exists an analytic solution to the corresponding optimization problem. The method is appli... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Novel heterostructure device for electronic pulse-mode neural circuits

    Publication Year: 1994, Page(s):663 - 665
    Cited by:  Papers (4)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB)

    A new approach to the hardware implementation of artificial, electronic pulse-mode neural circuits is proposed and demonstrated based on the use of a novel heterostructure device that exhibits an S-type current-voltage characteristic. The new device consists of a multi-period quantum well structure with heavily doped n+ GaAs quantum wells and undoped AlGaAs barriers between an n+ GaAs cathode and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • How delays affect neural dynamics and learning

    Publication Year: 1994, Page(s):612 - 621
    Cited by:  Papers (263)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (872 KB)

    We investigate the effects of delays on the dynamics and, in particular, on the oscillatory properties of simple neural network models. We extend previously known results regarding the effects of delays on stability and convergence properties. We treat in detail the case of ring networks for which we derive simple conditions for oscillating behavior and several formulas to predict the regions of b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using mutual information for selecting features in supervised neural net learning

    Publication Year: 1994, Page(s):537 - 550
    Cited by:  Papers (393)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1228 KB)

    This paper investigates the application of the mutual information criterion to evaluate a set of candidate features and to select an informative subset to be used as input data for a neural network classifier. Because the mutual information measures arbitrary dependencies between random variables, it is suitable for assessing the “information content” of features in complex classificat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems

    Publication Year: 1994, Page(s):594 - 603
    Cited by:  Papers (166)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (780 KB)

    This paper presents a means to approximate the dynamic and static equations of stochastic nonlinear systems and to estimate state variables based on radial basis function neural network (RBFNN). After a nonparametric approximate model of the system is constructed from a priori experiments or simulations, a suboptimal filter is designed based on the upper bound error in approximating the original u... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Acoustic-to-phonetic mapping using recurrent neural networks

    Publication Year: 1994, Page(s):659 - 662
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    This paper describes the application of artificial neural networks to acoustic-to-phonetic mapping. The experiments described are typical of problems in speech recognition in which the temporal nature of the input sequence is critical. The specific task considered is that of mapping formant contours to the corresponding CVC' syllable. We performed experiments on formant data extracted from the aco... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-creating and organizing neural networks

    Publication Year: 1994, Page(s):561 - 575
    Cited by:  Papers (39)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1268 KB)

    We have developed a self-creating and organizing unsupervised learning algorithm for artificial neural networks. In this study, we introduce SCONN and SCONN2 as two versions of self-creating and organizing neural network (SCONN) algorithms. SCONN creates an adaptive uniform vector quantizer (VQ), whereas SCONN2 creates an adaptive nonuniform VQ by neural-like architecture. SCONN's begin with only ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy logic and neural networks: clips from the field

    Publication Year: 1994, Page(s):666 - 667
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (232 KB)

    This is a review of a video consisting of clips from presentations made at the Second IEEE International Conference on Fuzzy Systems (1993) and the 1993 IEEE International Conference on Neural Networks. Each video clip describes significant achievements and current advances in the fields of fuzzy logic and neural networks contributed by researchers from around the world View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural network model of causality

    Publication Year: 1994, Page(s):604 - 611
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (696 KB)

    This paper proposes a model for commonsense causal reasoning, based on the basic idea of neural networks. After an analysis of the advantages and limitations of existing accounts of causality, a fuzzy logic based formalism FEL is proposed that takes into account the inexactness and the cumulative evidentiality of commonsense causal reasoning, overcoming the limitations of existing accounts. Analys... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptation of the relaxation method for learning in bidirectional associative memory

    Publication Year: 1994, Page(s):576 - 583
    Cited by:  Papers (56)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (696 KB)

    An iterative learning algorithm called PRLAB is described for the discrete bidirectional associative memory (BAM). Guaranteed recall of all training pairs is ensured by PRLAB. The proposed algorithm is significant in many ways. Unlike many existing iterative learning algorithms, PRLAB is not based on the gradient descent technique. It is a novel adaptation from the well-known relaxation method for... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information processing with fuzzy logic-Piero Bonissone

    Publication Year: 1994, Page(s):667 - 668
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (188 KB)

    This is a review of a video on the foundations of approximate reasoning systems. The outline found in the visual materials accompanying the video refers to the lecture as fuzzy information systems (approximate reasoning systems). Almost half of the tape is devoted to probabilistic systems, but the presentation tends to justify the need for fuzzy methods in information processing, and so the title ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning in linear systolic neural network engines: analysis and implementation

    Publication Year: 1994, Page(s):584 - 593
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (748 KB)

    Linear systolic processor arrays are a widely proposed digital architecture for neural networks. This paper reports the analysis of a range of training algorithms implemented on a linear systolic ring, with a view to (a) identifying low-level instruction requirements, (b) assessing different hardware structures for PE implementation and (c) evaluating the impact of different array controller desig... 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