Toward a robust 2D spatio-temporal self-organization

Thomas Girod (1) , Laurent Bougrain (1) , Frédéric Alexandre (1)

1 CORTEX - Neuromimetic intelligence

Several models have been proposed for spatio-temporal self-organization, among which the TOM model by Wiemer is particularly promising. In this paper, we propose to adapt and extend this model to 2D maps to make it more generic and biologically plausible and more adapted to realistic applications, illustrated here by an application to speech analysis.

Mots clés: neural networks; self-organization; spatio-temporal

Domaines: Réseau de neurones [cs.NE]

Thomas Girod, Laurent Bougrain, Frédéric Alexandre. Toward a robust 2D spatio-temporal self-organization. 15th European Symposium on Artificial Neural Networks - ESANN'2007, Apr 2007, Bruges, Belgium. ⟨inria-00164462⟩