• DocumentCode
    978864
  • Title

    Time difference simultaneous perturbation method

  • Author

    Maeda, Yuji

  • Author_Institution
    Dept. of Electr. Eng., Kansai Univ., Osaka
  • Volume
    32
  • Issue
    11
  • fYear
    1996
  • fDate
    5/23/1996 12:00:00 AM
  • Firstpage
    1016
  • Lastpage
    1018
  • Abstract
    The authors propose a heuristic recursive algorithm to find the minimum point of a function without using the gradient of the function. This algorithm is based on the time difference and simultaneous perturbation method. However, it does not need an additional measurement of the function to update the estimated point
  • Keywords
    approximation theory; neural nets; perturbation theory; recursion method; stochastic systems; heuristic recursive algorithm; minimum point; neural nets; stochastic approximation; time difference simultaneous perturbation method;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19960637
  • Filename
    503090
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=978864