dc.contributor.author | Thornton, John | |
dc.contributor.author | Srbic, Andrew | |
dc.contributor.author | Main, Linda | |
dc.contributor.author | Chitsaz, Mahsa | |
dc.contributor.editor | D. Wang and M. Reynolds | |
dc.date.accessioned | 2017-05-03T12:54:37Z | |
dc.date.available | 2017-05-03T12:54:37Z | |
dc.date.issued | 2011 | |
dc.date.modified | 2012-07-22T22:51:06Z | |
dc.identifier.issn | 03029743 | |
dc.identifier.doi | 10.1007/978-3-642-25832-9_27 | |
dc.identifier.uri | http://hdl.handle.net/10072/43965 | |
dc.description.abstract | It 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. | |
dc.description.peerreviewed | Yes | |
dc.description.publicationstatus | Yes | |
dc.format.extent | 154125 bytes | |
dc.format.mimetype | application/pdf | |
dc.language | English | |
dc.language.iso | eng | |
dc.publisher | Springer | |
dc.publisher.place | Germany | |
dc.relation.ispartofstudentpublication | N | |
dc.relation.ispartofpagefrom | 261 | |
dc.relation.ispartofpageto | 270 | |
dc.relation.ispartofjournal | Lecture Notes in Computer science | |
dc.relation.ispartofvolume | 7106 | |
dc.rights.retention | Y | |
dc.subject.fieldofresearch | Artificial Intelligence and Image Processing not elsewhere classified | |
dc.subject.fieldofresearchcode | 080199 | |
dc.title | Augmented Spatial Pooling | |
dc.type | Journal article | |
dc.type.description | C1 - Articles | |
dc.type.code | C - Journal Articles | |
gro.faculty | Griffith Sciences, School of Information and Communication Technology | |
gro.rights.copyright | © 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.com | |
gro.date.issued | 2011 | |
gro.hasfulltext | Full Text | |
gro.griffith.author | Thornton, John R. | |
gro.griffith.author | Main, Linda M. | |
gro.griffith.author | Srbic, Andrew | |
gro.griffith.author | Chitsaz, Mahsa | |