• DocumentCode
    1212628
  • Title

    Dynamics of fully complex-valued neural networks

  • Author

    Hirose, Akira

  • Author_Institution
    Tokyo Univ., Japan
  • Volume
    28
  • Issue
    16
  • fYear
    1992
  • fDate
    7/30/1992 12:00:00 AM
  • Firstpage
    1492
  • Lastpage
    1494
  • Abstract
    A novel neural network that processes input vectors and attractors fully in complex space using complex weights is proposed. Real and imaginary data are treated consistently with an equivalent significance in nondegenerate complex space. This network can be applied for ill-posed problems concerning realistic physical fields and continuous motion controls. The dynamics are presented and demonstrated.
  • Keywords
    content-addressable storage; dynamics; neural nets; Hopfield associative memory; attractor processing; complex weights; continuous motion controls; dynamics; fully complex-valued neural networks; ill-posed problems; input vector processing; nondegenerate complex space; physical field reconstruction;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19920948
  • Filename
    153204