• DocumentCode
    285352
  • Title

    A new class of neural networks based on approximate identities for approximation and learning

  • Author

    Turchetti, Claudio ; Conti, M.

  • Author_Institution
    Dipartimento di Elettronica, Ancona Univ., Italy
  • Volume
    1
  • fYear
    1992
  • fDate
    10-13 May 1992
  • Firstpage
    359
  • Abstract
    Learning a given input-output mapping can be regarded as a problem of approximating a multivariate function. A theoretical framework for approximation, based on sequences of functions named approximate identities, is developed. It is proved that such sequences are able to approximate a generally continuous function with a given error. This leads to a new class of three-layer networks that can efficiently be implemented in analog MOS VLSI
  • Keywords
    MOS integrated circuits; VLSI; analogue processing circuits; feedforward neural nets; learning (artificial intelligence); analog MOS VLSI; approximate identities; generally continuous function; input-output mapping; learning; multivariate function; neural networks; three-layer networks; Analog circuits; Approximation methods; Convolution; Linear approximation; Multidimensional systems; Neural networks; Very large scale integration;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on
  • Conference_Location
    San Diego, CA
  • Print_ISBN
    0-7803-0593-0
  • Type

    conf

  • DOI
    10.1109/ISCAS.1992.229939
  • Filename
    229939