Huffman Coding for Storing Non-uniformly Distributed Messages in Networks of Neural Cliques - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Huffman Coding for Storing Non-uniformly Distributed Messages in Networks of Neural Cliques

Résumé

Associative memories are data structures that allow retrieval of previously stored messages given part of their content. They thus behave similarly to human brain's memory that is capable for instance of retrieving the end of a song given its beginning. Among different families of associative memories, sparse ones are known to provide the best efficiency (ratio of the number of bits stored to that of bits used). Nevertheless, it is well known that non-uniformity of the stored messages can lead to dramatic decrease in performance. Recently, a new family of sparse associative memories achieving almost-optimal efficiency has been proposed. Their structure induces a direct mapping between input messages and stored patterns. In this work, we show the impact of non-uniformity on the performance of this recent model and we exploit the structure of the model to introduce several strategies to allow for efficient storage of non-uniform messages. We analyse and discuss the methods introduced and we envision future work in this context.
Fichier non déposé

Dates et versions

hal-01058337 , version 1 (26-08-2014)

Identifiants

  • HAL Id : hal-01058337 , version 1

Citer

Bartosz Boguslawski, Vincent Gripon, Fabrice Seguin, Frédéric Heitzmann. Huffman Coding for Storing Non-uniformly Distributed Messages in Networks of Neural Cliques. AAAI 2014 : the 28th Conference on Artificial Intelligence, Jul 2014, Québec, Canada. pp.262-268. ⟨hal-01058337⟩
81 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More