• DocumentCode
    881523
  • Title

    Improvement of bidirectional associative memories by using correlation significance

  • Author

    Wang, Wen-June

  • Volume
    29
  • Issue
    8
  • fYear
    1993
  • fDate
    4/15/1993 12:00:00 AM
  • Firstpage
    688
  • Lastpage
    690
  • Abstract
    A correlation significance technique is introduced, which uses the significances between the training associations and between the neurons of the different fields, such that the storage capacity of Kosko (1988) bidirectional associative memories (BAMs) is improved. Based on the gradient descent method, an error function is constructed such that the maximal number of stored nations which are successfully recalled can be obtained. Finally computer simulations demonstrate that the proposed method has much better storage capacity than the existing methods.
  • Keywords
    content-addressable storage; correlation methods; learning (artificial intelligence); neural nets; bidirectional associative memories; computer simulations; correlation significance; error function; gradient descent method; neurons; storage capacity; training associations;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19930461
  • Filename
    209953