Advertisement

ICANN ’94 pp 443-446 | Cite as

An Efficient Method of Pattern Storage in the Hopfield Net

  • S. Coombes
  • J. G. Taylor
Conference paper

Abstract

We discuss a new a method of endowing the Hopfield net with the properties of an associative memory. A set of N patterns (biased or unbiased) may be stored in a Hopfield network of N spins with a set of connections called inverse-Hebb couplings. Furthermore, an algorithm exists called the quadratic Oja algorithm which can enhance the basin of attraction of a subset of these stored patterns. Simulations show that the combination of the quadratic Oja algorithm with initial conditions given by the inverse-Hebb rule leads to a successful alternative to the traditional Gardner algorithm. Lastly, we introduce the hardware capable of a fast implementation of the inverse-Hebb rule.

Keywords

Associative Memory Energy Landscape Matrix Inversion Fast Implementation Hopfield Network 
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]
    Hopfield, J., J. (1982). Neural Networks and Physical Systems with Emergent Collective Computational Abilities, Proc. Natl. Acad. Sci. USA, Vol. 79, 2554–2558.CrossRefMathSciNetGoogle Scholar
  2. [2]
    Gardner, E.(1988). The Space ofInteractions in Neural Network Models. J. Phys. A, 21, 257–270.CrossRefMathSciNetGoogle Scholar
  3. [3]
    Coombes, S., & Taylor, J., G. (1993). Using Generalised Principal Component Analysis to Achieve Associative Memory in a Hopfield Net, Network, To Appear.Google Scholar
  4. [4]
    Coombes, S., & Taylor, J., G. (1993). The Inverse-Hebb Rule, KCL Preprint.Google Scholar
  5. [5]
    Kohring, G. A. (1990). Neural Networks with Many-Neuron Interactions, Le Journal de Physique, 51, 145–155.CrossRefGoogle Scholar
  6. [6]
    Jang, J., Lee, S., & Shin, S. (1988). An Optimisation Network for Matrix Inversion, Neural Information Processing Systems, Ed. D. Z. Anderson, New York, 397–401.Google Scholar
  7. [7]
    Toulouse, G., Dehaene, S., & Changeux, J. (1986). Spin Glass Model of Learning by Selection, Proc. Natl. Acad. Sci. USA. Vol. 83, 1695–1698.CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1994

Authors and Affiliations

  • S. Coombes
    • 1
  • J. G. Taylor
    • 1
  1. 1.Centre for Neural NetworksKings CollegeLondonUK

Personalised recommendations