• DocumentCode
    2985531
  • Title

    Optical neural network for engineering design

  • Author

    McAulay, Alastair D.

  • Author_Institution
    Dept. of Comput. Sci., Wright State Univ., Dayton, OH, USA
  • fYear
    1988
  • fDate
    23-27 May 1988
  • Firstpage
    1302
  • Abstract
    An optical neural-network architecture is proposed that captures engineering design expertise and makes it available to designers. The network and its use as an associative memory are described. A novel fast learning algorithm is shown to be orders-of-magnitude faster than backpropagation. Reasons are presented for the feasibility of an optical implementation that uses novel optical devices. A structural example illustrates how engineering design expertise is captured and recovered from the network
  • Keywords
    CAD; design engineering; expert systems; neural nets; associative memory; engineering design; fast learning algorithm; optical devices; optical neural-network architecture; Associative memory; Backpropagation algorithms; Design engineering; Expert systems; Humans; Neural networks; Optical computing; Optical design; Optical devices; Optical fiber networks;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Aerospace and Electronics Conference, 1988. NAECON 1988., Proceedings of the IEEE 1988 National
  • Conference_Location
    Dayton, OH
  • Type

    conf

  • DOI
    10.1109/NAECON.1988.195173
  • Filename
    195173