• DocumentCode
    324563
  • Title

    Asymptotic approximation power for neural networks

  • Author

    Ferreira, Paulo J S G ; Pinho, Armando J.

  • Author_Institution
    Univ. of Aveiro, Portugal
  • Volume
    2
  • fYear
    1998
  • fDate
    4-9 May 1998
  • Firstpage
    1261
  • Abstract
    This paper studies the asymptotic approximation power of radial basis function neural networks in the sup norm. The methods used are constructive and based on discretization of approximate identities. The effect of the kernel on the approximation order is discussed
  • Keywords
    computational complexity; convergence of numerical methods; feedforward neural nets; function approximation; approximation order; asymptotic approximation power; computational complexity; convergence; discretization; function approximation; radial basis function neural networks; Approximation error; Approximation methods; Convergence; Fourier series; Interpolation; Joining processes; Kernel; Neural networks; Nonlinear filters; Radial basis function networks;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
  • Conference_Location
    Anchorage, AK
  • ISSN
    1098-7576
  • Print_ISBN
    0-7803-4859-1
  • Type

    conf

  • DOI
    10.1109/IJCNN.1998.685955
  • Filename
    685955