Abstract
The variation of the convergence timeτ, as a function of the storage capacityα is studied numerically for systems ranging in size fromN=1000 toN=16,000 neurons.τ is found to increase likeτ∼exp[−A(αc−α)] as one nears the critical storage capacityα c =0.142=0.002.
This is a preview of subscription content, log in via an institution to check access.
References
I. Kanter,Phys. Rev. A 40:2611 (1989).
G. A. Kohring,J. Phys. A 23:2237 (1990).
K. Binder and A. P. Young,Rev. Mod. Phys. 58:801 (1986).
I. A. Campbell, J. M. Flesseles, R. Julien, and R. Botet,Phys. Rev. B 37:3825 (1988); M. Ghosh and B. K. Chakrabarti,Phys. Rev. B, in press.
D. Amit, H. Gutfreund, and H. Sompolinsky,Ann. Phys. 173:30 (1987); A. Crisanti, D.J. Amit, and H. Gutfreund,Eur. Phys. Lett. 2:337 (1986).
G. A. Kohring,J. Stat. Phys. 59:1077 (1990).
J. Komlós and R. Paturi,Neural Networks 1:239 (1988).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ghosh, M., Sen, A.K., Chakrabarti, B.K. et al. Slowing down of retrieval in the hopfield model. J Stat Phys 61, 501–504 (1990). https://doi.org/10.1007/BF01013978
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01013978