Stability analysis of an unsupervised competitive neural network

Anke Meyer-Baese, Vera Thümmler, Fabian Theis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Unsupervised competitive neural networks (UCNN) are an established technique in pattern recognition for feature extraction and cluster analysis. A novel model of an unsupervised competitive neural network implementing a multi-time scale dynamics is proposed in this paper. The global asymptotic stability of the equilibrium points of this continuous-time recurrent system whose weights are adapted based on a competitive learning law is mathematically analyzed. The proposed neural network and the derived results are compared with those obtained from other multi-time scale architectures.

Original languageEnglish
Title of host publicationInternational Joint Conference on Neural Networks 2006, IJCNN '06
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1025-1028
Number of pages4
ISBN (Print)0780394909, 9780780394902
DOIs
StatePublished - 2006
Externally publishedYes
EventInternational Joint Conference on Neural Networks 2006, IJCNN '06 - Vancouver, BC, Canada
Duration: 16 Jul 200621 Jul 2006

Publication series

NameIEEE International Conference on Neural Networks - Conference Proceedings
ISSN (Print)1098-7576

Conference

ConferenceInternational Joint Conference on Neural Networks 2006, IJCNN '06
Country/TerritoryCanada
CityVancouver, BC
Period16/07/0621/07/06

Fingerprint

Dive into the research topics of 'Stability analysis of an unsupervised competitive neural network'. Together they form a unique fingerprint.

Cite this