Advertisement

An Experimental Assessment of the Performance of Several Associative Memory Models

  • S. P. Turvey
  • S. P. Hunt
  • N. Davey
  • R. J. Frank
Conference paper

Abstract

The performance characteristics of four different associative memory models are examined. The models differ in the training algorithm employed, although all four employ algorithms that are iterative, and use local information. They are classified using the method of Abbott [1], their attractor performance is examined, and the time taken to train them is measured.

Keywords

Local Field Training Time Training Algorithm Training Pattern Attractor Performance 
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]
    L.F. Abbott, “Learning in Neural Network Memories” Network: Comp. Neural Sys. vol.1, pp. 105–122, 1990MathSciNetCrossRefGoogle Scholar
  2. [2]
    DJ. Amit, Modelling brainfunction: the world of attractor neural networks. Cambridge, UK: Cambridge University Press, 1989CrossRefGoogle Scholar
  3. [3]
    S.Diederich and M.Opper, “Learning of Correlated Patterns in Spin-Glass Networks by Local Learning Rules” Physical Review Letters vol.58, pp.949–952, 1987MathSciNetCrossRefGoogle Scholar
  4. [4]
    N. Davey R.G. Adams S.P. Hunt, “High performance associative memory models and symmetriC connections”, Proceedings of ISA 2000, to be published December 2000Google Scholar
  5. [5]
    W. Krauth M. Mezard, “Learning algorithms with optimal stability for neural networks” J. Phys. vol.A20, pp.L745–L752, 1987MathSciNetGoogle Scholar
  6. [6]
    M.G. Blatt E. G. Vergini (1991). “Neural Networks: A Local Learning Prescription for Arbitrary Correlated Patterns”, Physical Review Letters, vol.66, pp.1793–1797CrossRefGoogle Scholar
  7. [7]
    L. Personnaz I. Guyon G. Dreyfus, “Collective Computational Properties of Neural Networks: New Learning Mechanisms” Physical Review A vol.34, pp.4217–4228, 1986MathSciNetCrossRefGoogle Scholar
  8. [8]
    E. Gardner, “The space of interactions in neural network models” Journal of Physics vol.A21, pp.257–270, 1988Google Scholar
  9. [9]
    I. Kanter H. Sompolinsky, “Associative Recall of Memory without Errors”, Physical Review A vol.35,pp.380–392, 1987CrossRefGoogle Scholar
  10. [10]
    N. Davey S.P. Hunt, “The Capacity and Attractor Basins of Associative Memory Models”, Proceedings ofIWANN99,1999Google Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • S. P. Turvey
  • S. P. Hunt
  • N. Davey
  • R. J. Frank
    • 1
  1. 1.Department of Computer ScienceUniversity of HertfordshireHatfield, HertsUK

Personalised recommendations