• DocumentCode
    303366
  • Title

    A sensitivity analysis algorithm for pruning feedforward neural networks

  • Author

    Engelbrech, AP ; Cloete, I.

  • Author_Institution
    Dept. of Comput. Sci., South Africa Univ., Pretoria, South Africa
  • Volume
    2
  • fYear
    1996
  • fDate
    3-6 Jun 1996
  • Firstpage
    1274
  • Abstract
    A pruning algorithm, based on sensitivity analysis, is presented in this paper. We show that the sensitivity analysis technique efficiently prunes both input and hidden layers. Results of the application of the pruning algorithm to various N-bit parity problems agree with well-known published results
  • Keywords
    feedforward neural nets; learning (artificial intelligence); sensitivity analysis; feedforward neural networks; hidden layers; input layers; learning pattern; parity problems; pruning algorithm; sensitivity analysis; Africa; Computer networks; Computer science; Equations; Feedforward neural networks; Mathematical model; Neural networks; Sensitivity analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1996., IEEE International Conference on
  • Conference_Location
    Washington, DC
  • Print_ISBN
    0-7803-3210-5
  • Type

    conf

  • DOI
    10.1109/ICNN.1996.549081
  • Filename
    549081
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=303366