A new penalisation term for image retrieval in clique neural networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

A new penalisation term for image retrieval in clique neural networks

Résumé

Neural networks that are able to retrieve store and retrieve information constitue an old but still active area of research. Among the different existing architectures, recurrent networks that combine as-sociative memory with error correcting properties based on cliques have recently shown good performances on storing arbitrary random messages. However, they fail in scaling up to large dimensions data such as images, mostly because the distribution of activated neurons is not uniform in the network. We propose in this paper a new penalization term that alleviates this problem, and shows its efficiency on partially erased images reconstruction problem.
Fichier principal
Vignette du fichier
esann2016.pdf (406.98 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01320024 , version 1 (13-11-2019)

Identifiants

  • HAL Id : hal-01320024 , version 1

Citer

Romain Huet, Nicolas Courty, Sébastien Lefèvre. A new penalisation term for image retrieval in clique neural networks. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 2016, Bruges, Belgium. ⟨hal-01320024⟩
236 Consultations
120 Téléchargements

Partager

Gmail Facebook X LinkedIn More