• DocumentCode
    1575243
  • Title

    Capacity of cellular neural networks as associative memories

  • Author

    Lukianiuk, Andrzej

  • Author_Institution
    Inst. of Control & Ind. Electron., Warsaw Univ. of Technol., Poland
  • fYear
    1996
  • Firstpage
    37
  • Lastpage
    40
  • Abstract
    In the paper a cellular neural network (CNN) architecture as an associative memory is considered. The boundary for the maximum number of memory vectors is obtained. The result suggests that the maximum number of memory vectors arbitrarily chosen from a set of linearly independent vectors is not related to the size of CNN but depends only on radius of the neighborhood
  • Keywords
    cellular neural nets; content-addressable storage; neural net architecture; associative memories; cellular neural networks; linearly independent vectors; memory vectors; Associative memory; Cellular neural networks; Design methodology; Equations; Hopfield neural networks; Industrial electronics; Memory architecture; Network synthesis; Neural networks; Neurons;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Cellular Neural Networks and their Applications, 1996. CNNA-96. Proceedings., 1996 Fourth IEEE International Workshop on
  • Conference_Location
    Seville
  • Print_ISBN
    0-7803-3261-X
  • Type

    conf

  • DOI
    10.1109/CNNA.1996.566486
  • Filename
    566486