A study of retrieval algorithms of sparse messages in networks of neural cliques - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

A study of retrieval algorithms of sparse messages in networks of neural cliques

Résumé

Associative memories are data structures addressed using part of the content rather than an index. They offer good fault reliability and biological plausibility. Among different families of associative memories, sparse ones are known to offer the best efficiency (ratio of the amount of bits stored to that of bits used by the network itself). Their retrieval process performance has been shown to benefit from the use of iterations. We introduce several families of algorithms to enhance the performance of the retrieval process inrecently proposed sparse associative memories based on binary neural networks. We show that these algorithms provide better performance than existing techniques and discuss their biological plausibility. We also analyze the required number of iterations and derive corresponding curves.

Domaines

Neurosciences

Dates et versions

hal-01058303 , version 1 (26-08-2014)

Licence

Paternité

Identifiants

Citer

Ala Aboudib, Vincent Gripon, Xiaoran Jiang. A study of retrieval algorithms of sparse messages in networks of neural cliques. COGNITIVE 2014: 6th International Conference on Advanced Cognitive Technologies and Applications, May 2014, Venise, Italy. pp.140-146. ⟨hal-01058303⟩
590 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More