Toward a robust 2D spatio-temporal self-organization

Abstract. Several models have been proposed for spatio-temporal selforganization, among which the TOM model by Wiemer [1] 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. 1 Spatio-temporal self-organization Fundamental property, in biological as well as artificial systems, is that of adaptive information representation. Self-Organizing Maps (SOM), proposed by Kohonen [2] in the framework of cortical modeling and extensively used for various tasks of information processing, underline how, from simple learning and connectivity rules within a map of neurons, a topological representation can emerge, where similar data activate close regions of the map. The resulting representation is interesting for several reasons: using short connections in the brain saves energy; the neighborhood property is r...

• Type: Conference
• Year: 2007
• Where: ESANN
• Authors: Thomas Girod, Laurent Bougrain, Frédéric Alexandre
• Keywords: ESANN 2007, Information Processing, Neural Networks, Self-organization Fundamental Property, Spatio-temporal Self-organization