Show simple item record

dc.contributor.convenorAuckland University of Technologyen_AU
dc.contributor.authorThornton, Johnen_US
dc.contributor.authorFaichney, Jolonen_US
dc.contributor.authorBlumenstein, Michaelen_US
dc.contributor.authorHine, Trevoren_US
dc.contributor.editorWayne Wobcke, Mengjie Zhangen_US
dc.date.accessioned2017-05-03T12:54:34Z
dc.date.available2017-05-03T12:54:34Z
dc.date.issued2008en_US
dc.date.modified2010-08-30T07:04:24Z
dc.identifier.refuriwww.ai08.orgen_AU
dc.identifier.doi10.1007/978-3-540-89378-3_57en_AU
dc.identifier.urihttp://hdl.handle.net/10072/23558
dc.description.abstractIn recent years, there has been a cross-fertilization of ideas between computational neuroscience models of the operation of the neo-cortex and artificial intelligence models of machine learning. Much of this work has focussed on the mammalian visual cortex, treating it as a hierarchically-structured pattern recognition machine that exploits statistical regularities in retinal input. It has further been proposed that the neocortex represents sensory information probabilistically, using some form of Bayesian inference to disambiguate noisy data. In the current paper, we focus on a particular model of the neocortex developed by Hawkins, known as hierarchical temporal memory (HTM). Our aim is to evaluate an important and recently implemented aspect of this model, namely its ability to represent temporal sequences of input within a hierarchically structured vector quantization algorithm. We test this temporal pooling feature of HTM on a benchmark of cursive hand-writing recognition problems and compare it to a current state-of-the-art support vector machine implementation. We also examine whether two pre-processing techniques can enhance the temporal pooling algorithm's performance. Our results show that a relatively simple temporal pooling approach can produce recognition rates that approach the current state-of-the-art without the need for extensive tuning of parameters. We also show that temporal pooling performance is surprisingly unaffected by the use of preprocessing techniques.en_US
dc.description.peerreviewedYesen_US
dc.description.publicationstatusYesen_AU
dc.format.extent30058 bytes
dc.format.extent171371 bytes
dc.format.mimetypetext/plain
dc.format.mimetypeapplication/pdf
dc.languageEnglishen_US
dc.language.isoen_AU
dc.publisherSpringeren_US
dc.publisher.placeHeidelberg, Germanyen_US
dc.relation.ispartofstudentpublicationNen_AU
dc.relation.ispartofconferencename21st Australasian Joint Conference on Artificial Intelligenceen_US
dc.relation.ispartofconferencetitleLecture Notes in Artificial Intelligenceen_US
dc.relation.ispartofdatefrom2008-12-03en_US
dc.relation.ispartofdateto2008-12-05en_US
dc.relation.ispartoflocationAuckland, New Zealanden_US
dc.rights.retentionYen_AU
dc.subject.fieldofresearchPattern Recognition and Data Miningen_US
dc.subject.fieldofresearchcode080109en_US
dc.titleCharacter Recognition using Hierarchical Vector Quantization and Temporal Poolingen_US
dc.typeConference outputen_US
dc.type.descriptionE1 - Conference Publications (HERDC)en_US
dc.type.codeE - Conference Publicationsen_US
gro.facultyGriffith Sciences, School of Information and Communication Technologyen_US
gro.rights.copyrightCopyright 2008 Springer. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher. The original publication is available at www.springerlink.comen_AU
gro.date.issued2008
gro.hasfulltextFull Text


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record