• DocumentCode
    344706
  • Title

    Overfitting: a fuzzy neural net solution

  • Author

    Feuring, Thomas ; Buckley, James J. ; Hayashi, Yoichi

  • Author_Institution
    Dept. of Electr. Eng. & Comput. Sci., Siegen Univ., Germany
  • Volume
    1
  • fYear
    1999
  • fDate
    22-25 Aug. 1999
  • Firstpage
    61
  • Abstract
    Given most continuous h:[a,b]/spl rarr/R and /spl epsiv/>0, we show how to obtain a neural net which will approximate h, to within /spl epsiv/, uniformly over [a,b]. To construct this neural net, we first train a fuzzy neural net on a finite training set, and the needed neural net is the defuzzified trained fuzzy neural net.
  • Keywords
    function approximation; fuzzy neural nets; fuzzy set theory; generalisation (artificial intelligence); learning (artificial intelligence); function approximation; fuzzy neural networks; fuzzy set theory; generalisation; learning; overfitting; Computer science; Fuzzy neural networks; Fuzzy sets; Mathematics; Neural networks; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Fuzzy Systems Conference Proceedings, 1999. FUZZ-IEEE '99. 1999 IEEE International
  • Conference_Location
    Seoul, South Korea
  • ISSN
    1098-7584
  • Print_ISBN
    0-7803-5406-0
  • Type

    conf

  • DOI
    10.1109/FUZZY.1999.793207
  • Filename
    793207
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=344706