Skip to main content
Log in

Retrieval and chaos in extremely dilutedQ-Ising neural networks

  • Published:
Journal of Statistical Physics Aims and scope Submit manuscript

Abstract

Using a probabilistic approach, the deterministic and the stochastic parallel dynamics of aQ-Ising neural network are studied at finiteQ and in the limitQ→∞. Exact evolution equations are presented for the first time-step. These formulas constitute recursion relations for the parallel dynamics of the extremely diluted asymmetric versions of these networks. An explicit analysis of the retrieval properties is carried out in terms of the gain parameter, the loading capacity, and the temperature. The results for theQ→∞ network are compared with those for theQ=3 andQ=4 models. Possible chaotic microscopic behavior is studied using the time evolution of the distance between two network configurations. For arbitrary finiteQ the retrieval regime is always chaotic. In the limitQ→∞ the network exhibits a dynamical transition toward chaos.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. D. Bollé, B. Vinck, and V. A. Zagrebnov,J. Stat. Phys. 70:1099 (1993).

    Article  Google Scholar 

  2. H. Rieger, inStatistical Mechanics of Neural Networks, L. Garrido, ed. (Springer, Berlin, 1990), p. 33.

    Google Scholar 

  3. S. Mertens,J. Phys. A 24:337 (1991).

    MathSciNet  Google Scholar 

  4. D. Gandolfo, J. Ruiz, and V. A. Zagrebnov, On the parallel dynamics of the diluted clock neural network, Preprint Marseille CPT-92/P.2728.

  5. J. Jedrzejewski and A. Komoda,Europhys. Lett. 18:275 (1992).

    Google Scholar 

  6. E. Gardner,J. Phys. A 19:L1047 (1986).

    Google Scholar 

  7. C. Newman,Neural Networks 1:223 (1988).

    Article  Google Scholar 

  8. G. M. Zaslavsky, R. Z. Sagdeev, D. A. Usikov, and A. A. Chernikov,Weak Chaos and Quasi-regular Patterns (Cambridge University Press, Cambridge, 1991).

    Google Scholar 

  9. H. Sompolinsky, A. Crisanti, and H. J. Sommers,Phys. Rev. Lett. 61:259 (1988).

    Article  Google Scholar 

  10. B. Tirozzi and M. Tsodyks,Europhys. Lett. 14:727 (1991).

    Google Scholar 

  11. L. Molgedey, J. Schuchardt, and H. G. Schuster,Phys. Rev. Lett. 26:3717 (1992).

    Article  Google Scholar 

  12. M. Bauer and W. Martienssen,J. Phys. A 24:4557 (1991).

    Google Scholar 

  13. B. Derrida, E. Gardner, and A. Zippelius,Europhys. Lett. 4:167 (1987).

    Google Scholar 

  14. B. Derrida,J. Phys. A 20:L721 (1987).

    Google Scholar 

  15. B. Derrida and R. Meir,Phys. Rev. A 38:3116 (1988).

    Google Scholar 

  16. A. N. Shiryaev,Probability (Springer-Verlag, Berlin, 1991).

    Google Scholar 

  17. L. Wang and J. Ross,Phys. Rev. A 44:R2259 (1991).

    Article  MathSciNet  Google Scholar 

  18. H. Rieger,J. Phys. A 23:L1273 (1990).

    Google Scholar 

  19. R. Kree and A. Zippelius, inModels of Neural Networks, E. Domany, J. L. van Hemmen, and K. Schulten, eds. (Springer-Verlag, Berlin 1991), p. 193.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bollé, D., Shim, G.M., Vinck, B. et al. Retrieval and chaos in extremely dilutedQ-Ising neural networks. J Stat Phys 74, 565–582 (1994). https://doi.org/10.1007/BF02188571

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02188571

Key Words

Navigation