Learning Algorithms for Neural Networks

  • Eduard Aved’yan
Chapter

Abstract

The optimal value w for the memory of a multilayer neural network is determined by the minimisation of the performance index J(w) which characterises the proximity of the network outputs to the teacher’s instructions. Here w is a composite vector which consists of the memory vectors w (μ,ν) of the individual neurons.

This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    B. T. Polyak, Introduction to optimization. New York: Optimization Software, Inc, Publications Division, 1987.Google Scholar
  2. [2]
    Ya. Z. Tsypkin, Adaptation and learning in automatic systems. New York: Academic Press, 1971.Google Scholar
  3. [3]
    D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning internal representations by error propagation”, Parallel Distributed Processing, V.I, ch. 8, pp. 675–695, D. E. Rumelhart and J. L. McClelland, Eds., Cambridge, MA: MIT Press, 1986.Google Scholar
  4. [4]
    K. Narendra, and K. Parthasarathy, “Identification and control of dynamic systems using neural networks”, IEEE Trans, on NN, No. 1, pp. 4–27, 1990.Google Scholar
  5. [5]
    L. Fortuna, S. Geaziani, M. L. Presti, and G. Muscato, “Improving back-propagation learning using auxiliary neural networks”, Int. J. Contr., v.55, No. 4, pp. 793–807, 1992MATHCrossRefGoogle Scholar
  6. [6]
    Y. Hirose, K. Yamashita, and S. Hijiya, “Back-propagation algorithm which varies the number of hidden units”, Neural Networks, v.4, pp. 61–66. 1991CrossRefGoogle Scholar
  7. [7]
    Y. C. Lee, G. Doolen, H. H. Chen, G. Z. Sun, T. Maxwell, H. Y. Lee, and C. L. Giles, “Machine learning using a higher order correlation network”, Physica D, v. 22, pp. 276–306, 1986.MathSciNetGoogle Scholar
  8. [8]
    P. Peretto, J. J. Niez, “Long term memory storage capacity of multi-connected neural networks”, Biol. Cybern., v. 54, pp. 53–63, 1986.MATHCrossRefGoogle Scholar
  9. [9]
    E. D. Avedyan, M. L. Kovalenko, L. E. Tsitolovsky, and Y. Z. Tsypkin, Autonomous learning algorithms for neural networks “,Proceedings of the International Conference Mathematics, Computer, and Investments” pp. 2–11,15–19 Feb. 1993, Moscow, Garant, 1993.Google Scholar

Copyright information

© Springer-Verlag London Limited 1995

Authors and Affiliations

  • Eduard Aved’yan
    • 1
  1. 1.Institute of Control SciencesLaboratory 07Profsoyuznaja 65MoscowRussia

Personalised recommendations