Critical vector learning for text categorisation

UTSePress Research/Manakin Repository

Search UTSePress Research

Advanced Search


My Account

Show simple item record Zhang, Lei en_US Zhang, Debbie en_US Simoff, Simeon en_US
dc.contributor.editor Simoff, S; Williams, G; Galloway, J; Volyshkina, I. en_US 2010-05-18T06:48:12Z 2010-05-18T06:48:12Z 2005 en_US
dc.identifier 2005002856 en_US
dc.identifier.citation Zhang Lei, Zhang Debbie, and Simoff Simeon 2005, 'Critical vector learning for text categorisation', UTS Press, Sydney, Aust, pp. 27-36. en_US
dc.identifier.issn 1-86365-716-9 en_US
dc.identifier.other E1 en_US
dc.description.abstract This paper proposes a new text categorisation method based on the critical vector learning algorithm. By implementing a Bayesian treatment of a generalised linear model of identical function form to the support vector machine, the proposed approach requires signi?cantly fewer support vectors. This leads to much reduced computational com- plexity of the prediction process, which is critical in online applications. en_US
dc.publisher UTS Press en_US
dc.relation.isbasedon en_US
dc.title Critical vector learning for text categorisation en_US
dc.parent Proceedings 4th Australasion Data Mining Conference AusDM05 en_US
dc.journal.volume en_US
dc.journal.number en_US
dc.publocation Sydney, Aust en_US
dc.identifier.startpage 27 en_US
dc.identifier.endpage 36 en_US FEIT.School of Systems, Management and Leadership en_US
dc.conference en_US
dc.conference Verified OK en_US
dc.conference.location Sydney, Aust en_US
dc.for 080100 en_US
dc.personcode 10356057 en_US
dc.personcode 020492 en_US
dc.personcode 000716 en_US
dc.percentage 100 en_US Artificial Intelligence and Image Processing en_US
dc.classification.type FOR-08 en_US
dc.custom Australian Data Mining Conference en_US 20051205 en_US
dc.location.activity Sydney, Aust en_US
dc.description.keywords vector learning, support vector mechanisms, text mining en_US
dc.staffid 000716 en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record