• DocumentCode
    1905338
  • Title

    Evolving neural network connectivity

  • Author

    McDonnell, John R. ; Waagen, Don

  • Author_Institution
    NCCOSC, San Diego, CA, USA
  • fYear
    1993
  • fDate
    1993
  • Firstpage
    863
  • Abstract
    The application of evolutionary programming, a stochastic search technique, for determining connectivity in feedforward neural networks is investigated. The method is capable of simultaneously evolving both the connection scheme and the network weights. The number of connections are incorporated into an objective function so that network parameter optimization is done with respect to network complexity as well as mean pattern error. Experimental results are shown for simple binary mapping problems
  • Keywords
    feedforward neural nets; stochastic programming; binary mapping problems; connection scheme; evolutionary programming; feedforward neural networks; mean pattern error; network complexity; network parameter optimization; network weights; neural network connectivity; objective function; stochastic search technique; Computational complexity; Computer architecture; Feedforward neural networks; Genetic algorithms; Genetic programming; Neural networks; Process design; Signal processing algorithms; Stochastic processes; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1993., IEEE International Conference on
  • Conference_Location
    San Francisco, CA
  • Print_ISBN
    0-7803-0999-5
  • Type

    conf

  • DOI
    10.1109/ICNN.1993.298671
  • Filename
    298671