Proceedings of the IEEE

Issue 9 • Sep 1990

Filter Results

Displaying Results 1 - 7 of 7
  • 30 years of adaptive neural networks: perceptron, Madaline, and backpropagation

    Publication Year: 1990, Page(s):1415 - 1442
    Cited by:  Papers (1096)  |  Patents (30)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2440 KB)

    Fundamental developments in feedforward artificial neural networks from the past thirty years are reviewed. The history, origination, operating characteristics, and basic theory of several supervised neural-network training algorithms (including the perceptron rule, the least-mean-square algorithm, three Madaline rules, and the backpropagation technique) are described. The concept underlying these... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The self-organizing map

    Publication Year: 1990, Page(s):1464 - 1480
    Cited by:  Papers (3118)  |  Patents (63)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1556 KB)

    The self-organized map, an architecture suggested for artificial neural networks, is explained by presenting simulation experiments and practical applications. The self-organizing map has the property of effectively creating spatially organized internal representations of various features of input signals and their abstractions. One result of this is that the self-organization process can discover... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Complex temporal sequence learning based on short-term memory

    Publication Year: 1990, Page(s):1536 - 1543
    Cited by:  Papers (64)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (656 KB)

    An approach to storing of temporal sequences that deals with complex temporal sequences directly is presented. Short-term memory (STM) is modeled by units comprised of recurrent excitatory connections between two neurons. A dual-neuron model is proposed. By applying the Hebbian learning rule at each synapse and a normalization rule among all synaptic weights of a neuron, it is shown that a quantit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mathematical foundations of neurocomputing

    Publication Year: 1990, Page(s):1443 - 1463
    Cited by:  Papers (109)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1476 KB)

    An attempt is made to establish a mathematical theory that shows the intrinsic mechanisms, capabilities, and limitations of information processing by various architectures of neural networks. A method of statistically analyzing one-layer neural networks is given, covering the stability of associative mapping and mapping by totally random networks. A fundamental problem of statistical neurodynamics... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Networks for approximation and learning

    Publication Year: 1990, Page(s):1481 - 1497
    Cited by:  Papers (1671)  |  Patents (25)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1520 KB)

    The problem of the approximation of nonlinear mapping, (especially continuous mappings) is considered. Regularization theory and a theoretical framework for approximation (based on regularization techniques) that leads to a class of three-layer networks called regularization networks are discussed. Regularization networks are mathematically related to the radial basis functions, mainly used for st... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Synthetic neural modeling: the `Darwin' series of recognition automata

    Publication Year: 1990, Page(s):1498 - 1530
    Cited by:  Papers (58)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2716 KB)

    The authors describe how the theory of neuronal group selection (TNGS) can form the basis for an approach to computer modeling of the nervous system. Three examples of synthetic neural modeling are discussed. Darwin I was designed to examine the process of pattern recognition and some general factors relating to degeneracy and amplification in selective systems. Darwin II introduced recognition un... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network model for control of muscle force based on the size principle of motor unit

    Publication Year: 1990, Page(s):1531 - 1535
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (352 KB)

    A neural-network model consisting of a single motor cortex output cell, α motoneurons, Renshaw cells, and muscle units is proposed. Linear relations between motor cortex output and force output that were observed in monkeys and firing rate versus force relations in human skeletal muscles are explained by computer simulations. It is suggested that Renshaw recurrent inhibition has the effect o... View full abstract»

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

Aims & Scope

The most highly-cited general interest journal in electrical engineering and computer science, the Proceedings is the best way to stay informed on an exemplary range of topics.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
H. Joel Trussell
North Carolina State University