• DocumentCode
    488635
  • Title

    Design of Multi-Layer Neural Networks for Accurate Identification of Nonlinear Mappings

  • Author

    Teixeira, Edilberto ; Loparo, Kenneth ; Gomide, Fernando A.C.

  • Author_Institution
    Case W. R. University, Systems Engineering Department, Cleveland, Ohio; University of Uberlandia, Brazil; Graduate Program of UNICAMP/FEE/DCA.
  • fYear
    1991
  • fDate
    26-28 June 1991
  • Firstpage
    14
  • Lastpage
    15
  • Abstract
    Guidelines for the design of multi-layer neural networks for the identification of nonlinear mappings are considered in this work. Since nonlinear mappings can be approximated by a one hidden layer neural network, an approach to determine the sufficient number of hidden layer nodes to achieve a global minima of the identification error function is considered.
  • Keywords
    Discrete Fourier transforms; Frequency; Function approximation; Guidelines; Multi-layer neural network; Neural networks; Sampling methods; Spectral analysis; Systems engineering and theory; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    American Control Conference, 1991
  • Conference_Location
    Boston, MA, USA
  • Print_ISBN
    0-87942-565-2
  • Type

    conf

  • Filename
    4791311
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=488635