• DocumentCode
    2435814
  • Title

    The causes for premature saturation with backpropagation training

  • Author

    Vitela, Javier E. ; Reifman, Jaques

  • Author_Institution
    Inst. de Ciencias Nucl., Univ. Nacional Autonoma de Mexico, Mexico City, Mexico
  • Volume
    3
  • fYear
    1994
  • fDate
    27 Jun-2 Jul 1994
  • Firstpage
    1449
  • Abstract
    The mechanism that causes the output nodes of feedforward multilayer networks mapped with sigmoid functions to prematurely saturate during backpropagation training is described. The necessary conditions for the occurrence of this undesirable phenomenon are also presented. Simulation results demonstrate the adequacy of the presented necessary conditions
  • Keywords
    backpropagation; feedforward neural nets; multilayer perceptrons; backpropagation training; feedforward multilayer networks; necessary conditions; output nodes; premature saturation; sigmoid functions; Algorithm design and analysis; Backpropagation algorithms; Convergence; Inductors; Iterative algorithms; Joining processes; Laboratories; Nonhomogeneous media;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
  • Conference_Location
    Orlando, FL
  • Print_ISBN
    0-7803-1901-X
  • Type

    conf

  • DOI
    10.1109/ICNN.1994.374499
  • Filename
    374499