Vincent Gripon's Homepage

Research and Teaching Blog

Réseaux de Clusters de Neurones Restreints

R. Danilo, V. Gripon, P. Coussy and L. Conde-Canencia, "Réseaux de Clusters de Neurones Restreints," in Proceedings of the GRETSI conference, 2015.

Associative memories are capable of retrieving a message previously stored when an incomplete version of this message is presented. A model of associative memory based on binary neurons and binary connections, named Clustered Neural Network, has been recently introduce. The performance of this model drops when the stored message distribution is non-uniform. The goal of this paper, is to propose a new model of associative memory inspired by Clustered Neural Network and Restricted Boltzmann Machine, in order to decrease the vulnerability to non-uniform distribution.In addition, a fully parallel hardware design of the model. The proposed implementation multiplies the number of stored messages by a factor of 3 with an increase of complexity of 40%.

Download manuscript.

Bibtex
@inproceedings{DanGriCouCon2015,
  author = {Robin Danilo and Vincent Gripon and
Philippe Coussy and Laura Conde-Canencia},
  title = {Réseaux de Clusters de Neurones
Restreints},
  booktitle = {Proceedings of the GRETSI conference},
  year = {2015},
}




You are the 504760th visitor

Vincent Gripon's Homepage