Skip to main content
Log in

Macroscopic Lyapunov functions for separable stochastic neural networks with detailed balance

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

Abstract

We derive macroscopic Lyapunov functions for large, long-range, Ising-spin neural networks with separable symmetric interactions, which evolve in time according to local field alignment. We generalize existing constructions, which correspond todeterministic (zero-temperature) evolution and to specific choices of the interaction structure, to the case ofstochastic evolution and arbitrary separable interaction matrices, for both parallel and sequential spin updating. We find a direct relation between the form of the Lyapunov functions (which describe dynamical processes) and the saddle-point integration that results from performing equilibrium statistical mechanical studies of the present type of model.

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. J. Amit,Modelling Brain Function (Cambridge University Press, Cambridge, 1989).

    Google Scholar 

  2. B. Müller and J. Reinhardt,Neural Networks—An Introduction (Springer-Verlag, Berlin, 1991).

    Google Scholar 

  3. J. Hertz, A. Krogh, and R. G. Palmer,Introduction to the Theory of Neural Computation (Addison-Wesley, Redwood City, California, 1991).

    Google Scholar 

  4. L. G. Abbott,Network 1:105 (1990).

    Google Scholar 

  5. D. Sherrington, inMathematical Approaches to Neural Networks, J. G. Taylor, ed. (North-Holland, Amsterdam, 1993), Chapter 8, p. 261.

    Google Scholar 

  6. J. L. van Hemmen and R. Kühn, inModels of Neural Networks, E. Domany, J. L. van Hemmen, and K. Schulten, eds. (Springer-Verlag, Berlin, 1991) Chapter 1.

    Google Scholar 

  7. A. C. C. Coolen and D. Sherrington, inMathematical Approaches to Neural Networks, J. G. Taylor, ed. (North-Holland, Amsterdam, 1993), Chapter 9, p. 293.

    Google Scholar 

  8. A. C. C. Coolen and T. W. Ruijgrok,Phys. Rev. A 38:4253 (1988).

    Google Scholar 

  9. U. Riedel, R. Kühn, and J. L. van Hemmen,Phys. Rev. A 38:1105 (1988).

    Google Scholar 

  10. O. Bernier,Europhys. Lett. 16531 (1991).

    Google Scholar 

  11. N. G. van Kampen,Stochastic Processes in Physics and Chemistry (North-Holland, Amsterdam, 1981).

    Google Scholar 

  12. J. J. Hopfield,Proc. Nat. Acad. Sci. USA 79:2554 (1982).

    Google Scholar 

  13. P. Peretto,Biol. Cybernet. 50:51 (1984).

    Google Scholar 

  14. D. Bollé, P. Dupont, and B. Vinck,J. Phys. A 25:2859 (1992).

    Google Scholar 

  15. A. V. M. Herz, Z. Li, and J. L. van Hemmen,Phys. Rev. Lett. 66:1370 (1991).

    Google Scholar 

  16. D. J. Amit, H. Gutfreund, and H. Sompolinsky,Phys. Rev. A 32:1007 (1985).

    Google Scholar 

  17. A. C. C. Coolen and D. Sherrington,Phys. Rev. Lett. 71:3886 (1993).

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Laughton, S.N., Coolen, A.C.C. Macroscopic Lyapunov functions for separable stochastic neural networks with detailed balance. J Stat Phys 80, 375–387 (1995). https://doi.org/10.1007/BF02178364

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02178364

Key Words

Navigation