• DocumentCode
    1150208
  • Title

    Integer-weight neural nets

  • Author

    Khan, Affan Hasan ; Hines, E.L.

  • Author_Institution
    Dept. of Eng., Warwick Univ., Coventry
  • Volume
    30
  • Issue
    15
  • fYear
    1994
  • fDate
    7/21/1994 12:00:00 AM
  • Firstpage
    1237
  • Lastpage
    1238
  • Abstract
    Integer-weight neural nets (IWNN) are better suited for hardware implementation than their real-weight analogues. The authors present a learning procedure for generating multilayer IWNNs having all weights in the set {-3, -2, -1, 0, 1, 2, 3}. The performance of this procedure was evaluated on XOR, encoder/decoder and the MONK benchmark. The IWNNS were found to be as capable as their real-weight counterparts with regard to generalisation performance
  • Keywords
    learning (artificial intelligence); neural nets; MONK benchmark; integer-weight neural nets; learning procedure; multilayer type;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19940817
  • Filename
    311914