Stability conditions of Hopfield ring networks with discontinuous piecewise-affine activation functions - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Stability conditions of Hopfield ring networks with discontinuous piecewise-affine activation functions

Résumé

Ring networks, a particular form of Hopfield neural networks, can be used in computational neurosciences in order to model the activity of place cells or head-direction cells. The behaviour of these models is highly dependent on their recurrent synaptic connectivity matrix and on individual neurons' activation function, which must be chosen appropriately to obtain physiologically meaningful conclusions. In this article, we propose some simpler ways to tune this synaptic connectivity matrix compared to existing literature so as to achieve stability in a ring attractor network with a piece-wise affine activation functions, and we link these results to the possible stable states the network can converge to.
Fichier principal
Vignette du fichier
CDC_Conference_Paper_VF_.pdf (613.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01645410 , version 1 (23-11-2017)

Identifiants

  • HAL Id : hal-01645410 , version 1

Citer

Amélie Aussel, Laure Buhry, Radu Ranta. Stability conditions of Hopfield ring networks with discontinuous piecewise-affine activation functions. 56th IEEE Conference on Decision and Control, CDC 2017, Dec 2017, Melbourne, Australia. ⟨hal-01645410⟩
264 Consultations
444 Téléchargements

Partager

Gmail Facebook X LinkedIn More