Header

UZH-Logo

Maintenance Infos

On the central limit theorem for the overlap in the Hopfield model


Gentz, B (1998). On the central limit theorem for the overlap in the Hopfield model. In: Bovier, A; Picco, P. Mathematical aspects of spin glasses and neural networks. Boston, MA: Birkhäuser, 115-149.

Abstract

We consider the Hopfield model with N neurons and an increasing number M=M(N) of randomly chosen patterns. Under the condition M 2 /N→0, we prove for every fixed choice of overlap parameters a central limit theorem as N→∞, which holds for almost all realizations of the random patterns. In the special case where the temperature is above the critical one and there is no external magnetic field, the condition M 3/2 logM≤N suffices. As in the case of a finite number of patterns, the central limit theorem requires a centering which depends on the random patterns. In addition, we describe the almost sure asymptotic behavior of the partition function under the condition M 3 /N→0.

Abstract

We consider the Hopfield model with N neurons and an increasing number M=M(N) of randomly chosen patterns. Under the condition M 2 /N→0, we prove for every fixed choice of overlap parameters a central limit theorem as N→∞, which holds for almost all realizations of the random patterns. In the special case where the temperature is above the critical one and there is no external magnetic field, the condition M 3/2 logM≤N suffices. As in the case of a finite number of patterns, the central limit theorem requires a centering which depends on the random patterns. In addition, we describe the almost sure asymptotic behavior of the partition function under the condition M 3 /N→0.

Statistics

Altmetrics

Additional indexing

Item Type:Book Section, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Mathematics
Dewey Decimal Classification:510 Mathematics
Uncontrolled Keywords:Hopfield model; central limit theorem; almost sure asymptotic behavior of the partition function
Language:English
Date:1998
Deposited On:29 Nov 2010 16:28
Last Modified:05 Apr 2016 13:26
Publisher:Birkhäuser
Series Name:Progress in Probability
Number:41
ISSN:1050-6977
ISBN:0-8176-3863-6
Related URLs:http://www.zentralblatt-math.org/zbmath/search/?q=an%3A0896.60012
http://www.springer.com/birkhauser/mathematics/book/978-0-8176-3863-4

Download

Full text not available from this repository.