This site uses cookies. By continuing to use this site you agree to our use of cookies. To find out more, see our Privacy and Cookies policy.

An Exactly Solvable Asymmetric Neural Network Model

, and

Published under licence by IOP Publishing Ltd
, , Citation B. Derrida et al 1987 EPL 4 167 DOI 10.1209/0295-5075/4/2/007

0295-5075/4/2/167

Abstract

We consider a diluted and nonsymmetric version of the Little-Hopfield model which can be solved exactly. We obtain the analytic expression of the evolution of one configuration having a finite overlap on one stored pattern. We show that even when the system remembers, two different configurations which remain close to the same pattern never become identical. Lastly, we show that when two stored patterns are correlated, there exists a regime for which the system remembers these patterns without being able to distinguish them.

Export citation and abstract BibTeX RIS