• DocumentCode
    349602
  • Title

    A chaos memory model

  • Author

    Nakagawa, Masahiro

  • Author_Institution
    Fac. of Eng., Nagaoka Univ. of Technol., Niigata, Japan
  • Volume
    1
  • fYear
    1999
  • fDate
    1999
  • Firstpage
    408
  • Abstract
    In this paper we explore that a chaos neural network (CNN) model with a sinusoidal activation function may realise ~10-20 times larger memory capacity than CNN with conventionally proposed sigmoidal activation function proposed by K. Aihara et al (1990). In fact the complete association is found to be promoted up to ~100% loading rate even though a relevant noise is involved in an input vector
  • Keywords
    chaos; neural nets; chaos memory model; chaos neural network model; sigmoidal activation function; sinusoidal activation function; Associative memory; Autocorrelation; Cellular neural networks; Chaos; Computer aided manufacturing; Joining processes; Neural networks; Neurons; Optimal control; Traveling salesman problems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
  • Conference_Location
    Tokyo
  • ISSN
    1062-922X
  • Print_ISBN
    0-7803-5731-0
  • Type

    conf

  • DOI
    10.1109/ICSMC.1999.814126
  • Filename
    814126
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=349602