| Numéro |
J. Phys. I France
Volume 3, Numéro 6, June 1993
|
|
|---|---|---|
| Page(s) | 1303 - 1328 | |
| DOI | https://doi.org/10.1051/jp1:1993101 | |
DOI: 10.1051/jp1:1993101
J. Phys. I France 3 (1993) 1303-1328
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
05.20 - 87.30
© Les Editions de Physique 1993
J. Phys. I France 3 (1993) 1303-1328
Relevant parameters for a class of sequence-retrieving neural networks
O. Lefèvre1 and J.-P. Nadal21 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)
Abstract
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
and
, 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