Storing sequences in binary tournament-based neural networks - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Neural Networks and Learning Systems Année : 2016

Storing sequences in binary tournament-based neural networks

Résumé

An extension to a recently introduced architecture of clique-based neural networks is presented. This extension makes it possible to store sequences with high eff i ciency. To obtain this property, network connections are provided with orientation and with f l exible redundancy carried by both spatial and temporal redundancy, a mechanism of anticipation being introduced in the model. In addition to the sequence storage with high efficiency, this new scheme also offers biological plausibility. In order to achieve accurate sequence retrieval, a double layered structure combining hetero-association and auto-association is also proposed.

Dates et versions

hal-01308341 , version 1 (27-04-2016)

Identifiants

Citer

Xiaoran Jiang, Vincent Gripon, Claude Berrou, Michael Rabbat. Storing sequences in binary tournament-based neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27 (5), pp.913 - 925. ⟨10.1109/TNNLS.2015.2431319⟩. ⟨hal-01308341⟩
116 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More