Open Access
Translator Disclaimer
November 1998 On the storage capacity of Hopfield models with correlated patterns
Matthias Löwe
Ann. Appl. Probab. 8(4): 1216-1250 (November 1998). DOI: 10.1214/aoap/1028903378

Abstract

We analyze the storage capacity of the Hopfield model with correlated patterns $(\xi_i^{\nu})$. We treat both the case of semantically and spatially correlated patterns (i.e., the patterns are either correlated in $\nu$ but independent in i or vice versa). We show that the standard Hopfield model of neural networks with N neurons can store $N/(\gamma \log N)$ or $\alpha N$ correlated patterns (depending on which notion of storage is used), provided that the correlation comes from a homogeneous Markov chain. This answers the open question whether the standard Hopfield model can store any increasing number of correlated patterns at all in the affirmative. While our bound on the critical value for $\alpha$ decreases with large correlations, the critical $\gamma$ behaves differently for the different types of correlations.

Citation

Download Citation

Matthias Löwe. "On the storage capacity of Hopfield models with correlated patterns." Ann. Appl. Probab. 8 (4) 1216 - 1250, November 1998. https://doi.org/10.1214/aoap/1028903378

Information

Published: November 1998
First available in Project Euclid: 9 August 2002

zbMATH: 0941.60090
MathSciNet: MR1661188
Digital Object Identifier: 10.1214/aoap/1028903378

Subjects:
Primary: 82C32
Secondary: 60K35 , 82B44

Keywords: Hopfield model , large deviations , Markov chains , neural networks , storage capacity

Rights: Copyright © 1998 Institute of Mathematical Statistics

JOURNAL ARTICLE
35 PAGES


SHARE
Vol.8 • No. 4 • November 1998
Back to Top