Abstract
We prove the almost sure convergence of the free energy and of the overlap order parameters in aq-state version of the Hopfield neural network model. We compute explicitly these limits for all temperatures different from some critical value. The number of stored patterns is allowed to grow with the size of the systemN like (α/lnq) lnN. We study the limiting behavior of the extremal states of the model that are the measures induced on the Gibbs measures by the overlap parameters.
Similar content being viewed by others
References
D. J. Amit,Modeling Brain Function, The World of Attractor Neural Networks (Cambridge University Press, Cambridge, 1989).
D. J. Amit, H. Gutfreund, and H. Sompolinsky, Spins-glass models of neural networks,Phys. Rev. A 32:1007 (1985); Storing infinite number of patterns in a spins-glass model of neural network,Phys. Rev. A 55:1530 (1985).
D. Bolle, P. Dupont, and J. van Mourik, Stability properties of Potts neural networks with biased patterns and low loading,J. Phys. A: Math. Gen. 24:1065 (1991).
H. Cramer, On a new limit theorem on the theory of probability, inColloquium on the Theory of Probability (Herman, Paris, 1937).
Y. S. Chow and H. Teicher,Probability Theory (Springer-Verlag, Berlin, 1978).
R. S. Ellis,Entropy, Large Deviations, and Statistical Mechanics (Springer-Verlag, Berlin, 1985).
R. S. Ellis and C. M. Newman, The statistics of the Curie-Weiss Models,J. Stat. Phys. 19:149 (1978).
P. A. Ferrari, S. Martinez, and P. Picco, A lower bound for the memory capacity in the Potts-Hopfield model, Preprint (1991).
D. Grensing and K. Kühn, Random-site spin-glass models,J. Phys. A 19:L1153 (1986).
E. Golez and S. Martinez, Neural and automata networks: A dynamical approach, inColloquium on Mathematics and Its Applications (Kluwer, 1990).
I. Kanter, Potts-glass model of neural networks,Phys. Rev. A 37:2739 (1988).
H. Koch and J. Piasko, Some rigorous results on the Hopfield neural network model,J. Stat. Phys. 55:903 (1989).
H. Kesten and R. H. Schonmann, Behaviour in large dimensions of the Potts and Heisenberg model,Rev. Math. Phys. 2:147 (1990).
M. Mezard, G. Parisi, and M. A. Virasoro,Spin-Glass and Beyond (World Scientific, Singapore, 1988).
C. M. Newman, Memory capacity in neural network models: Rigorous lower bounds,Neural Networks 1 (1988).
S. R. S. Varadhan,Large Deviations and Applications (Society for Industrial and Applied Mathematics, Philadelphia, Pensylvania, 1984).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Gayrard, V. Thermodynamic limit of theq-state Potts-Hopfield model with infinitely many patterns. J Stat Phys 68, 977–1011 (1992). https://doi.org/10.1007/BF01048882
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01048882