| HAL : jpa-00246798, version 1 |
| DOI : 10.1051/jp1:1993101 |
| Fiche détaillée | Récupérer au format |
|
|
| Journal de Physique I 3, 6 (1993) 1303-1328 |
|
|
|
|
| Relevant parameters for a class of sequence-retrieving neural networks |
|
|
| O. LefèvreJ.-P. Nadal |
|
|
| (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 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. |
|
|
|
|
| Domaine | : | Physique/Articles anciens |
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|
|
| jpa-00246798, version 1 | |
| http://hal.archives-ouvertes.fr/jpa-00246798/fr/ | |
| oai:hal.archives-ouvertes.fr:jpa-00246798_v1 | |
| Contributeur : Archives Journal de Physique | |
| Soumis le : Vendredi 1 Janvier 1993, 08:00:00 | |
| Dernière modification le : Vendredi 1 Janvier 1993, 08:00:00 | |