A simple and efficient way to store many messages using neural cliques - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

A simple and efficient way to store many messages using neural cliques

Résumé

Associative memories are devices that are able to learn messages and to retrieve them in presence of errors or erasures. Their mecanics is similar to the one of error decoders. However, the role of correlation is opposed in the two devices, used as the essence of the retrieval process in the first one and avoided in the second one. Original codes are introduced in this paper to allow the effective combination of the two domains. The main idea is to associate with each message to learn a clique in a binary neural network. The obtained performance is dramatically better than the one corresponding to the state of the art, for instance Hopfield Neural Networks. Moreover, the model proposed is biologically plausible: it uses binary sparse connections between clusters of neurons provided with only two operations: sum and selection of maximum.
Fichier non déposé

Dates et versions

hal-01056522 , version 1 (20-08-2014)

Identifiants

  • HAL Id : hal-01056522 , version 1

Citer

Vincent Gripon, Claude Berrou. A simple and efficient way to store many messages using neural cliques. CCMB 2011: IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, May 2011, Paris, France. ⟨hal-01056522⟩
101 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More