Advertisement

The Baldwin Effect on the Evolution of Associative Memory

  • A. Imada
  • K. Araki
Conference paper

Abstract

We apply genetic algorithms to the Hopfield model of associative memory. Previously, we reported that a genetic algorithm evolves a network with random synaptic weights to store eventually a set of random patterns. In this paper, we show how the Baldwin effect on the evolution enhances the storage capacity.

Keywords

Genetic Algorithm Weight Matrix Random Matrix Associative Memory Random Pattern 
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]
    D.J. Amit, H. Gutfreund, and H. Sompolinsky. Statistical mechanics of neural networks near saturation. Annals of Physics, 173:30–67, 1987.CrossRefGoogle Scholar
  2. [2]
    B.J. Baldwin. A new factor in evolution. The American Naturalist, 30:441–451, 536–553, 1886.CrossRefGoogle Scholar
  3. [3]
    F. Gruau and D. Whitley. Adding learning to the cellular development of neural networks: Evolution and the baldwin effect. Evolutionary Computation, 1(3):213–233, 1993.CrossRefGoogle Scholar
  4. [4]
    D.O. Hebb. The Organization of Behavior. John Wiley, Chichester, 1949.Google Scholar
  5. [5]
    G.E. Hinton and S.J. Nowlan. How learning guides evolution. Complex Systems, 1:495–502, 1987.MATHGoogle Scholar
  6. [6]
    J.J. Hopfield. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, 79:2554–2558, 1982.MathSciNetGoogle Scholar
  7. [7]
    A. Imada and K. Araki. Genetic algorithm enlarges the capacity of associative memory. In Proceedings of 6th International Conference on Genetic Algorithms, pages 413–420, 1995.Google Scholar
  8. [8]
    A. Imada and K. Araki. Mutually connected neural network can learn some patterns by means of ga. In Proceedings of the World Congress on Neural Networks, volume 1, pages 803–806, 1995.Google Scholar
  9. [9]
    A. Imada and K. Araki. Lamarckian evolution of associative memory. In Proceedings of IEEE International Conference on Evolutionary Computation, pages 676–680, 1996.Google Scholar
  10. [10]
    D. Parisi and S. Nolfi. How Learning can Influence Evolution within a Non-Lamarckian Framework. Santa Fe Institute Series. Addison-Wesley, 1995.Google Scholar
  11. [11]
    D. Whitley, V.S. Gordon, and K. Mathias. Lamarckian evolution, the baldwin effect and function optimization. In Proceedings of the 3rd Conference on Parallel Problem Solving from Nature, pages 6–15, 1994.Google Scholar

Copyright information

© Springer-Verlag Wien 1998

Authors and Affiliations

  • A. Imada
    • 1
  • K. Araki
    • 2
  1. 1.Graduate School of Information ScienceNara Institute of Science and TechnologyIkoma, NaraJapan
  2. 2.Graduate School of Information Science and Electrical EngineeringKyusyu UniversityFukuoka 816Japan

Personalised recommendations