Show simple item record

dc.contributor.authorThornton, Johnen_US
dc.contributor.authorSrbic, Andrewen_US
dc.contributor.authorMain, Lindaen_US
dc.contributor.authorChitsaz, Mahsaen_US
dc.contributor.editorD. Wang and M. Reynoldsen_US
dc.date.accessioned2017-04-24T09:59:09Z
dc.date.available2017-04-24T09:59:09Z
dc.date.issued2011en_US
dc.date.modified2012-07-22T22:51:06Z
dc.identifier.issn03029743en_US
dc.identifier.doi10.1007/978-3-642-25832-9_27en_US
dc.identifier.urihttp://hdl.handle.net/10072/43965
dc.description.abstractIt is a widely held view in contemporary computational neuroscience that the brain responds to sensory input by producing sparse distributed representations. In this paper we investigate a brain-inspired spatial pooling algorithm that produces such sparse distributed representations by modelling the formation of proximal dendrites associated with neocortical minicolumns. In this approach, distributed representations are formed out of a competitive process of inter-column inhibition and subsequent learning. Specifically, we evaluate the performance of a recently proposed binary spatial pooling algorithm on a well-known benchmark of greyscale natural images. Our main contribution is to augment the algorithm to handle greyscale images, and to produce better quality encodings of binary images. We also show that the augmented algorithm produces superior population and lifetime kurtosis measures in comparison to a number of other well-known coding schemes.en_US
dc.description.peerreviewedYesen_US
dc.description.publicationstatusYesen_US
dc.format.extent154125 bytes
dc.format.mimetypeapplication/pdf
dc.languageEnglishen_US
dc.language.isoen_US
dc.publisherSpringeren_US
dc.publisher.placeGermanyen_US
dc.relation.ispartofstudentpublicationNen_US
dc.relation.ispartofpagefrom261en_US
dc.relation.ispartofpageto270en_US
dc.relation.ispartofjournalLecture Notes in Computer scienceen_US
dc.relation.ispartofvolume7106en_US
dc.rights.retentionYen_US
dc.subject.fieldofresearchArtificial Intelligence and Image Processing not elsewhere classifieden_US
dc.subject.fieldofresearchcode080199en_US
dc.titleAugmented Spatial Poolingen_US
dc.typeJournal articleen_US
dc.type.descriptionC1 - Peer Reviewed (HERDC)en_US
dc.type.codeC - Journal Articlesen_US
gro.facultyGriffith Sciences, School of Information and Communication Technologyen_US
gro.rights.copyrightCopyright 2011 Springer Berlin / Heidelberg. 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_US
gro.date.issued2011
gro.hasfulltextFull Text


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record