• DocumentCode
    288577
  • Title

    Choosing among several parallel implementations of the backpropagation algorithm

  • Author

    Pétrowski, A.

  • Author_Institution
    Dept. Inf., Inst. Nat. des Telecommun., Evry, France
  • Volume
    3
  • fYear
    1994
  • fDate
    27 Jun-2 Jul 1994
  • Firstpage
    1981
  • Abstract
    Three parallel implementations of the backpropagation algorithm are studied. The performance for each of these implementations is estimated for three prototypes of neural architectures chosen in such a way that they are limit cases of a wide range of feedforward architectures. This study, based on performance analysis validated by experiments, follows two other papers already published
  • Keywords
    backpropagation; feedforward neural nets; neural net architecture; backpropagation algorithm; feedforward architectures; neural architectures; parallel implementations; Backpropagation algorithms; Computer networks; Feedforward systems; Iterative algorithms; Neural networks; Neurons; Parallel processing; Performance analysis; Pipelines; Prototypes;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
  • Conference_Location
    Orlando, FL
  • Print_ISBN
    0-7803-1901-X
  • Type

    conf

  • DOI
    10.1109/ICNN.1994.374465
  • Filename
    374465