• DocumentCode
    1526566
  • Title

    Efficient two-dimensional systolic array architecture for multilayer neural network

  • Author

    Amin, Hayder ; Curtis, K.M. ; Hayes-Gill, B.R.

  • Author_Institution
    Dept. of Electr. & Electron. Eng., Nottingham Univ.
  • Volume
    33
  • Issue
    24
  • fYear
    1997
  • fDate
    11/20/1997 12:00:00 AM
  • Firstpage
    2055
  • Lastpage
    2056
  • Abstract
    An efficient two-dimensional systolic array architecture for a multilayer perceptron neural network is presented. This structure can perform the weighted sum calculation in only N cycles, for an N×N network. A new technique is introduced to eliminate the problem of long connecting lines in the proposed systolic structure
  • Keywords
    multilayer perceptrons; neural net architecture; systolic arrays; efficiency; multilayer perceptron neural network; two-dimensional systolic array architecture; weighted sum calculation;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19971407
  • Filename
    648467
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1526566