Augmented Spatial Pooling

File Size Format
76363_1.pdf 150Kb Adobe PDF View
Title Augmented Spatial Pooling
Author Thornton, John Richard; Srbic, Andrew; Main, Linda; Chitsaz, Mahsa
Journal Name Lecture Notes in Computer Science
Editor D. Wang and M. Reynolds
Year Published 2011
Place of publication Germany
Publisher Springer
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.
Peer Reviewed Yes
Published Yes
Alternative URI
Copyright Statement 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
Volume 7106
Page from 261
Page to 270
ISSN 0302-9743
Date Accessioned 2012-02-20
Language en_US
Research Centre Institute for Integrated and Intelligent Systems
Faculty Faculty of Science, Environment, Engineering and Technology
Subject Artificial Intelligence and Image Processing
Publication Type Journal Articles (Refereed Article)
Publication Type Code c1

Show simple item record

Griffith University copyright notice