Relevant parameters for a class of sequence-retrieving neural networks - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal de Physique I Année : 1993

Relevant parameters for a class of sequence-retrieving neural networks

O. Lefèvre
  • Fonction : Auteur
J.-P. Nadal

Résumé

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 λ and ϑ, 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.


Domaines

Articles anciens
Fichier principal
Vignette du fichier
ajp-jp1v3p1303.pdf (1.48 Mo) Télécharger le fichier
Origine : Accord explicite pour ce dépôt

Dates et versions

jpa-00246798 , version 1 (04-02-2008)

Identifiants

Citer

O. Lefèvre, J.-P. Nadal. Relevant parameters for a class of sequence-retrieving neural networks. Journal de Physique I, 1993, 3 (6), pp.1303-1328. ⟨10.1051/jp1:1993101⟩. ⟨jpa-00246798⟩

Collections

AJP
57 Consultations
54 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More