A Heteroassociative Learning Model Robust to Interference

Randa Kassab 1 Frédéric Alexandre 1, 2, 3
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : Neuronal models of associative memories are recurrent networks able to learn quickly patterns as stable states of the network. Their main acknowledged weakness is related to catastrophic interference when too many or too close examples are stored. Based on biological data we have recently proposed a model resistant to some kinds of interferences related to heteroassociative learning. In this paper we report numerical experiments that highlight this robustness and demonstrate very good performances of memorization. We also discuss convergence of interests for such an adaptive mechanism for biological modeling and information processing in the domain of machine learning.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01232017
Contributor : Frédéric Alexandre <>
Submitted on : Wednesday, November 25, 2015 - 10:26:11 PM
Last modification on : Friday, May 10, 2019 - 1:54:01 PM

File

NCTAuthor15.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01232017, version 2

Citation

Randa Kassab, Frédéric Alexandre. A Heteroassociative Learning Model Robust to Interference. International Joint Conference on Computational Intelligence, Nov 2015, Lisboa, Portugal. ⟨hal-01232017⟩

Share

Metrics

Record views

333

Files downloads

385