Generalized relevance learning vector quantization

DC FieldValueLanguage
dc.contributor.authorHammer, B
dc.contributor.authorVillmann, T
dc.date.accessioned2021-12-23T16:10:18Z-
dc.date.available2021-12-23T16:10:18Z-
dc.date.issued2002
dc.identifier.issn08936080
dc.identifier.urihttps://osnascholar.ub.uni-osnabrueck.de/handle/unios/9268-
dc.description.abstractWe propose a new scheme for enlarging generalized learning vector quantization (GLVQ) with weighting factors for the input dimensions. The factors allow an appropriate scaling of the input dimensions according to their relevance. They are adapted automatically during training according to the specific classification task whereby training can be interpreted as stochastic gradient descent on an appropriate error function. This method leads to a more powerful classifier and to an adaptive metric with little extra cost compared to standard GLVQ. Moreover, the size of the weighting factors indicates the relevance of the input dimensions. This proposes a scheme for automatically pruning irrelevant input dimensions. The algorithm is verified on artificial data sets and the iris data from the UCI repository. Afterwards, the method is compared to several well known algorithms which determine the intrinsic data dimension on real world satellite image data. (C) 2002 Elsevier Science Ltd. All rights reserved.
dc.language.isoen
dc.publisherPERGAMON-ELSEVIER SCIENCE LTD
dc.relation.ispartofNEURAL NETWORKS
dc.subjectadaptive metric
dc.subjectclustering
dc.subjectComputer Science
dc.subjectComputer Science, Artificial Intelligence
dc.subjectlearning vector quantization
dc.subjectNeurosciences
dc.subjectNeurosciences & Neurology
dc.subjectrelevance determination
dc.subjectSELECTION
dc.subjectSELF-ORGANIZING MAPS
dc.titleGeneralized relevance learning vector quantization
dc.typejournal article
dc.identifier.doi10.1016/S0893-6080(02)00079-5
dc.identifier.isiISI:000178756400011
dc.description.volume15
dc.description.issue8-9
dc.description.startpage1059
dc.description.endpage1068
dc.contributor.orcid0000-0002-0935-5591
dc.contributor.researcheridE-8624-2010
dc.identifier.eissn18792782
dc.publisher.placeTHE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND
dcterms.isPartOf.abbreviationNeural Netw.
Show simple item record

Google ScholarTM

Check

Altmetric