J. Phys. I France
Volume 3, Number 6, June 1993
Page(s) 1303 - 1328
DOI: 10.1051/jp1:1993101
J. Phys. I France 3 (1993) 1303-1328

Relevant parameters for a class of sequence-retrieving neural networks

O. Lefèvre1 and J.-P. Nadal2

1  II Universitá di Roma "Tor Vergata", Dipartimento di Fisica via Emanuele Carnevale, I-00173 Roma, Italy
2  Laboratoire de Physique Statistique, Ecole Normale Supérieure, 24 rue Lhomond, F-75231 Paris Cedex 05, France

(Received 21 November 1990, revised 21 December 1992, accepted 15 February 1993)

Reconsidering a recently introduced model of sequence-retrieving neural network, we introduce appropriate analogues of the well-known stabilities and show how these, together with two coupling parameters $\lambda$ and $\vartheta$, entirely control the dynamics in the case of strong dilution. The model is exactly solved and phase diagrams are drawn for two different choices of the synaptic matrices; they reveal a rich structure. We then briefly speculate as to the role of these parameters within a more general framework.

05.20 - 87.30

© Les Editions de Physique 1993