Skip to Main content Skip to Navigation
Conference papers

A new penalisation term for image retrieval in clique neural networks

Romain Huet 1 Nicolas Courty 1 Sébastien Lefèvre 1
1 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : 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.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01320024
Contributor : Sébastien Lefèvre <>
Submitted on : Wednesday, November 13, 2019 - 6:37:25 PM
Last modification on : Thursday, April 2, 2020 - 1:54:54 AM

File

esann2016.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01320024, version 1

Citation

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⟩

Share

Metrics

Record views

1030

Files downloads

21