A Modular Network Architecture Resolving Memory Interference through Inhibition

Randa Kassab 1 Frédéric Alexandre 1
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : In real learning paradigms like pavlovian conditioning, several modes of learning are associated, including generalization from cues and integration of specific cases in context. Associative memories have been shown to be interesting neuronal models to learn quickly specific cases but they are hardly used in realistic applications because of their limited storage capacities resulting in interferences when too many examples are considered. Inspired by biological considerations, we propose a modular model of associative memory including mechanisms to manipulate properly multimodal inputs and to detect and manage interferences. This paper reports experiments that demonstrate the good behavior of the model in a wide series of simulations and discusses its impact both in machine learning and in biological modeling.
Document type :
Book sections
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.inria.fr/hal-01251022
Contributor : Frédéric Alexandre <>
Submitted on : Tuesday, January 5, 2016 - 3:13:39 PM
Last modification on : Friday, May 10, 2019 - 1:54:01 PM
Long-term archiving on : Thursday, April 7, 2016 - 3:26:59 PM

File

ChapterKassabAlexandre.pdf
Files produced by the author(s)

Identifiers

Citation

Randa Kassab, Frédéric Alexandre. A Modular Network Architecture Resolving Memory Interference through Inhibition. Merelo, J.J. Computational Intelligence, 669, ⟨Springer⟩, pp.407-422, 2016, Studies in Computational Intelligence, ⟨10.1007/978-3-319-48506-5⟩. ⟨hal-01251022⟩

Share

Metrics

Record views

272

Files downloads

304