• DocumentCode
    3266978
  • Title

    Evolutionary strategy for learning multiple-valued logic functions

  • Author

    Ngom, Alioune ; Simovici, D.A.

  • Author_Institution
    Comput. Sci. Dept., Windsor Univ., Ont., Canada
  • fYear
    2004
  • fDate
    19-22 May 2004
  • Firstpage
    154
  • Lastpage
    160
  • Abstract
    We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V⊆Kn is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into a certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.
  • Keywords
    evolutionary computation; feedforward neural nets; multilayer perceptrons; multivalued logic; evolutionary strategy; hidden units; inter-parallel hyperplane strips; minimal multilayer feedforward neural networks; multiple-valued logic function learning; multiple-valued multiple-threshold perceptrons; partitioning method; Computer science; Information technology; Logic functions; Mathematics; Multi-layer neural network; Network synthesis; Neural networks; Neurons; Poles and towers; Strips;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multiple-Valued Logic, 2004. Proceedings. 34th International Symposium on
  • ISSN
    0195-623X
  • Print_ISBN
    0-7695-2130-4
  • Type

    conf

  • DOI
    10.1109/ISMVL.2004.1319935
  • Filename
    1319935
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3266978