Advertisement

Parallel Methods of Training for Multilayer Neural Network

  • ElMostafa Daoudi⋆
  • ElMiloud Jaâra
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1685)

Abstract

In this paper, we present two parallel techniques of training for multilayer neural network. One technique is based on the duplication of the network but the other one is based on the distribution of the multilayer network onto processors. We only have implemented the first parallel technique under PVM, but the parallel implementations for the second one are in progress.

Keywords

Intermediate Layer Parallel Implementation Communication Time Parallel Method Parallel Technique 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    H. Nait Charif, “A Fault Tolerant Learning Algorithm for Feedforward Neural Networks” Conférence FTPD 1996, Hawaï.Google Scholar
  2. [2]
    H. Paugam-moisy, “FrRé;seaux de Neurones Artificiels: Parallélisme, Apprentissage et Modélisation” Habilitation à Diriger des Recherches, Ecole Normale Supérieure de Lyon, 6 Janvier 1997.Google Scholar
  3. [3]
    H. Paugam-moisy et A. Pétrowski, “Parallel Neural Computation Based on Algebraic Partitioning” InI. Pitas, editor, Parallel Algorithms for Digital Image Processing, Computer Vision and Neural Networks p. 259–304. John Wiley, 1993.Google Scholar
  4. [4]
    S. Wang, “Réseaux Multicouches de Neurones Artificiels”, Thèse de Doctorat, Institut National Polytechnique de Grenoble, 26 Septembre 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • ElMostafa Daoudi⋆
    • 1
  • ElMiloud Jaâra
    • 1
  1. 1.Faculté des Sciences Département de Mathématiques et d’InformatiqueUniversité Mohammed 1erOujdaMOROCCO

Personalised recommendations