A Simple Reservoir Model of Working Memory with Real Values

Anthony Strock 1 Nicolas Rougier 1 Xavier Hinaut 1
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : The prefrontal cortex is known to be involved in many high-level cognitive functions, in particular, working memory. Here, we study to what extent a group of randomly connected units (namely an Echo State Network, ESN) can store and main-tain (as output) an arbitrary real value from a streamed input, i.e., can act as a sustained working memory unit. Furthermore, we explore to what extent such an architecture can take advantage of the stored value in order to produce non-linear computations. Comparison between different architectures (with and without feedback, with and without a working memory unit) shows that an explicit memory improves the performances.
Type de document :
Communication dans un congrès
2018 International Joint Conference on Neural Networks (IJCNN), Jul 2018, Rio de Janeiro, Brazil. 2018, 〈https://ieeexplore.ieee.org/document/8489262〉. 〈10.1109/IJCNN.2018.8489262〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01803594
Contributeur : Nicolas P. Rougier <>
Soumis le : vendredi 15 juin 2018 - 16:16:44
Dernière modification le : jeudi 7 février 2019 - 14:36:21
Document(s) archivé(s) le : lundi 17 septembre 2018 - 16:04:42

Fichiers

main.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Anthony Strock, Nicolas Rougier, Xavier Hinaut. A Simple Reservoir Model of Working Memory with Real Values. 2018 International Joint Conference on Neural Networks (IJCNN), Jul 2018, Rio de Janeiro, Brazil. 2018, 〈https://ieeexplore.ieee.org/document/8489262〉. 〈10.1109/IJCNN.2018.8489262〉. 〈hal-01803594〉

Partager

Métriques

Consultations de la notice

200

Téléchargements de fichiers

175