File Download
Supplementary

Conference Paper: Supervised learning of the adaptive resonance theory system

TitleSupervised learning of the adaptive resonance theory system
Authors
Issue Date1994
PublisherIEEE.
Citation
Proceedings of the 1994 International Symposium on Artificial Neural Networks (ISANN '94), National Cheng Kung University, Tainan, Taiwan, 15-17 December 1994, p. 63-68 How to Cite?
AbstractA supervised learning ART model (SART) is proposed which is based on the structure of ARTMAP but is much simpler. The techniques of match tracking and complement coding have been implemented to ensure the correct selection of category and stability during the training and testing phases. Two simulations have been done in order to verify and evaluate the classification power of SART. The result of identification of poisonous mushroom by SART is compared with that by ARTMAP.
Persistent Identifierhttp://hdl.handle.net/10722/53616

 

DC FieldValueLanguage
dc.contributor.authorSo, YTen_HK
dc.contributor.authorChan, KPen_HK
dc.date.accessioned2009-04-03T07:24:44Z-
dc.date.available2009-04-03T07:24:44Z-
dc.date.issued1994en_HK
dc.identifier.citationProceedings of the 1994 International Symposium on Artificial Neural Networks (ISANN '94), National Cheng Kung University, Tainan, Taiwan, 15-17 December 1994, p. 63-68en_HK
dc.identifier.urihttp://hdl.handle.net/10722/53616-
dc.description.abstractA supervised learning ART model (SART) is proposed which is based on the structure of ARTMAP but is much simpler. The techniques of match tracking and complement coding have been implemented to ensure the correct selection of category and stability during the training and testing phases. Two simulations have been done in order to verify and evaluate the classification power of SART. The result of identification of poisonous mushroom by SART is compared with that by ARTMAP.en_HK
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.relation.ispartofProceedings of the 1994 International Symposium on Artificial Neural Networks (ISANN '94)-
dc.rights©1994 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.titleSupervised learning of the adaptive resonance theory systemen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailChan, KP: kpchan@cs.hku.hken_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.hkuros5538-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats