Dynamic Formation of Self-Organizing Maps

Jérémy Fix 1
1 IMS - Equipe Information, Multimodalité et Signal
UMI2958 - Georgia Tech - CNRS [Metz], SUPELEC-Campus Metz
Abstract : In this paper, an original dynamical system derived from dynamic neural fields is studied in the context of the formation of topographic maps. This dynamical system overcomes limitations of the original Self-Organizing Map (SOM) model of Kohonen. Both competition and learning are driven by dynamical systems and performed continuously in time. The equations governing competition are shown to be able to reconsider dynamically their decision through a mechanism rendering the current decision unstable, which allows to avoid the use of a global reset signal.
Document type :
Conference papers
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-01060971
Contributor : Sébastien van Luchene <>
Submitted on : Thursday, September 4, 2014 - 4:47:43 PM
Last modification on : Thursday, October 24, 2019 - 3:52:04 PM

Identifiers

Collections

Citation

Jérémy Fix. Dynamic Formation of Self-Organizing Maps. 10th International Workshop, WSOM, Jul 2014, Mittweida, Germany. pp.25-34, ⟨10.1007/978-3-319-07695-9_2⟩. ⟨hal-01060971⟩

Share

Metrics

Record views

192