Online Bayes Point Machines

Simple item page
dc.contributor.authorHarrington, Edward
dc.contributor.authorHerbrich, Ralf
dc.contributor.authorKivinen, Jyrki
dc.contributor.authorPlatt, John C
dc.contributor.authorWilliamson, Robert
dc.coverage.spatialSeoul Korea
dc.date.accessioned2015-12-13T23:07:12Z
dc.date.available2015-12-13T23:07:12Z
dc.date.createdApril 30 2003
dc.date.issued2003
dc.date.updated2016-02-24T09:47:17Z
dc.description.abstractWe present a new and simple algorithm for learning large margin classifiers that works in a truly online manner. The algorithm generates a linear classifier by averaging the weights associated with several perceptron-like algorithms run in parallel in order to approximate the Bayes point. A random subsample of the incoming data stream is used to ensure diversity in the perceptron solutions. We experimentally study the algorithm's performance on online and batch learning settings. The online experiments showed that our algorithm produces a low prediction error on the training sequence and tracks the presence of concept drift. On the batch problems its performance is comparable to the maximum margin algorithm which explicitly maximises the margin.
dc.identifier.isbn3540047603
dc.identifier.urihttp://hdl.handle.net/1885/86101
dc.publisherSpringer
dc.relation.ispartofseriesPacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2003)
dc.sourceAdvances in Knowledge Discovery and Data Mining: Proceedings of 7th Pacific-Asia Conference, PAKDD 2003
dc.subjectKeywords: Batch learning settings; Bayes point machines; Linear classifiers; Training sequence; Algorithms; Approximation theory; Error analysis; Learning systems; Neural networks; Problem solving; Classification (of information)
dc.titleOnline Bayes Point Machines
dc.typeConference paper
local.bibliographicCitation.lastpage252
local.bibliographicCitation.startpage241
local.contributor.affiliationHarrington, Edward, College of Engineering and Computer Science, ANU
local.contributor.affiliationHerbrich, Ralf, Microsoft Research Ltd
local.contributor.affiliationKivinen, Jyrki, College of Engineering and Computer Science, ANU
local.contributor.affiliationPlatt, John C, Microsoft Research
local.contributor.affiliationWilliamson, Robert, College of Engineering and Computer Science, ANU
local.contributor.authoremailu9000163@anu.edu.au
local.contributor.authoruidHarrington, Edward, u3902855
local.contributor.authoruidKivinen, Jyrki, u4010726
local.contributor.authoruidWilliamson, Robert, u9000163
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.absfor080109 - Pattern Recognition and Data Mining
local.identifier.ariespublicationMigratedxPub14844
local.identifier.scopusID2-s2.0-7344268878
local.identifier.uidSubmittedByMigrated
local.type.statusPublished Version

Downloads

Collections

ANU Research Publications

DSpace software copyright © 2002-2024 LYRASIS