What does the landscape of a Hopfield associative memory look like?

  • Akira Imada
  • Keijiro Araki
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1447)


We apply evolutionary computations to the Hopfield's neural network model of associative memory. In the model, some of the appropriate configurations of synaptic weights give the network a function of associative memory. One of our goals is to obtain the distribution of these configurations in the synaptic weight space. In other words, our aim is to learn a geometry of a fitness landscape defined on the space. For the purpose, we use evolutionary walks to explore the fitness landscape in this paper.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Amit, D. J. (1989) Modeling Brain Function: The World of Attractor Neural Networks. Cambridge University Press.Google Scholar
  2. Bray, A., and M. Moore (1980) Metastable States in Spin Glasses. Journal of Physics C: Solid State Physics 13, ppL469–L476.Google Scholar
  3. Fogel, D. B. (1995) Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. IEEE Press.Google Scholar
  4. Fogel, L. J., A. J. Owens, and M. J. Walsh (1966) Artificial Intelligence through Simulated Evolution. Wiley.Google Scholar
  5. Fontana, W., and P. Schuster (1987) A Computer Model of Evolutionary Optimization. Biophysical Chemistry 26, pp123–147.Google Scholar
  6. Gardner, E. (1988) The Phase Space of Interactions in Neural Network Models. Journal of Physics 21A, pp257–270.Google Scholar
  7. Hebb, D. O. (1949) The Organization of Behavior. Wiley.Google Scholar
  8. Hopfield, J. J. (1982) Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proceedings of the National Academy of Sciences, USA 79, pp 2554–2558.Google Scholar
  9. Imada, A., and K. Araki (1997a), Random Perturbations to Hebbian Synapses of Associative Memory using a Genetic Algorithm. J. Mira, R. Moreno-Díaz, and J. Cabestany (Eds.) Proceedings of International Work-Conference on Artificial and Natural Neural Networks. Springer Verlag, Lecture Notes in Computer Science No. 1240, pp398–407.Google Scholar
  10. Imada, A., and K. Araki (1997b) Evolution of Hopfield Model of Associative Memory by the Breeder Genetic Algorithm. T. Bäck (Ed.) Proceedings of the 7th International Conference on Genetic Algorithms, Morgan Kaufmann, pp784–791.Google Scholar
  11. Kauffman, S. A., and S. Levin (1987) Towards a General Theory of Adaptive Walks on Rugged Landscapes. Journal of Theoretical Biology 128, pp11–45.Google Scholar
  12. Kauffman, S. A. (1993) The origin of Order: Self-organization and Selection in Evolution. Oxford University Press.Google Scholar
  13. Komlós, J., and R. Paturi (1988) Convergence Results in an Associative Memory Model. Neural Networks 1, pp239–250.Google Scholar
  14. Macken, C., P. Hagan, and A. Perelson (1991) Evolutionary Walks on Rugged Landscapes. SIAM Journal of Applied Mathematics 51, pp799–827.Google Scholar
  15. Maynard Smith, J. (1970) Natural Selection and the Concept of a Protein Space. Nature 225. pp563–564.Google Scholar
  16. Weinberger, E. D. (1990) Correlated and Uncorrelated Fitness Landscapes and How to Tell the Difference. Biological Cybernetics 63, pp325–336.Google Scholar
  17. Wright, S. (1932) The Roles of Mutation, Inbreeding, Crossbreeding and Selection in Evolution. Proceedings of the 6th International Congress of Genetics, pp356–366.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Akira Imada
    • 1
  • Keijiro Araki
    • 2
  1. 1.Graduate School of Information ScienceNara Institute of Science and TechnologyNaraJapan
  2. 2.Department of Computer Science and Computer EngineeringGraduate School of Information Science and Electrical Engineering Kyusyu UniversityFukuokaJapan

Personalised recommendations