A SOM-based classifier with enhanced structure learning

Pateritsas, C; Pertselakis, M; Stafylopatis, A

dc.contributor.author	Pateritsas, C	en
dc.contributor.author	Pertselakis, M	en
dc.contributor.author	Stafylopatis, A	en
dc.date.accessioned	2014-03-01T02:42:25Z
dc.date.available	2014-03-01T02:42:25Z
dc.date.issued	2004	en
dc.identifier.issn	1062922X	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30999
dc.subject	Classification	en
dc.subject	Feature evaluation	en
dc.subject	Neuro-fuzzy	en
dc.subject	Self-organized map	en
dc.subject	Structure-learning	en
dc.subject.other	Classification	en
dc.subject.other	Feature evaluation	en
dc.subject.other	Neuro-fuzzy	en
dc.subject.other	Self-Organized Maps (SOM)	en
dc.subject.other	Structure-learning	en
dc.subject.other	Classifiers	en
dc.subject.other	Data acquisition	en
dc.subject.other	Database systems	en
dc.subject.other	Neural networks	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Problem solving	en
dc.subject.other	Resource allocation	en
dc.subject.other	Learning systems	en
dc.title	A SOM-based classifier with enhanced structure learning	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICSMC.2004.1401296	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICSMC.2004.1401296	en
heal.publicationDate	2004	en
heal.abstract	This paper introduces an innovative synergistic model that aims to improve the efficiency of a neuro-fiizzy classifier, providing the means of on-line adaptation and fast learning. It combines the advantages of a self-organized map (SOM) network, as well as the benefits of a structure allocation fuzzy neural network. The system initializes its parameters using the clustering result on the SOM structure, while a novel approach of evaluating the input features leads to a more efficient way of handling the on-line learning rate of the training process. Experimental results on benchmark classification problems showed that this robust combination can also tackle tasks of great dimensionality in a successful manner. © 2004 IEEE.	en
heal.journalName	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics	en
dc.identifier.doi	10.1109/ICSMC.2004.1401296	en
dc.identifier.volume	5	en
dc.identifier.spage	4832	en
dc.identifier.epage	4837	en