• DocumentCode
    947333
  • Title

    Optimal gradient descent learning for bidirectional associative memories

  • Author

    Perfetti, Renzo

  • Author_Institution
    Istituto di Elettronica, Perugia Univ., Italy
  • Volume
    29
  • Issue
    17
  • fYear
    1993
  • Firstpage
    1556
  • Lastpage
    1557
  • Abstract
    A learning algorithm for bidirectional associative memories (BAMs) is presented, which results in a greatly enhanced storage capacity. The design strategy is formulated as a convex optimisation problem, and then solved by a steepest-descent approach. The proposed method guarantees the storage of all the training pairs as stable states of the BAM. Computer simulation results are presented to demonstrate the performance of the proposed algorithm.<>
  • Keywords
    content-addressable storage; learning (artificial intelligence); memory architecture; neural nets; optimisation; bidirectional associative memories; convex optimisation problem; design strategy; learning algorithm; stable states; steepest-descent approach; storage capacity; training pairs;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19931037
  • Filename
    234322