HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Spratling, M. W. Articles by Johnson, M. H. Search for Related Content PubMed PubMed Citation Articles by Spratling, M. W. Articles by Johnson, M. H.

Preintegration Lateral Inhibition Enhances Unsupervised Learning

m.spratling{at}bbk.ac.uk, Centre for Brain and Cognitive Development, Birkbeck College, London WC1E 7JL, U.K.

M. H. Johnson

mark.johnson{at}bbk.ac.uk, Centre for Brain and Cognitive Development, Birkbeck College, London WC1E 7JL, U.K.

A large and influential class of neural network architectures uses postintegration lateral inhibition as a mechanism for competition. We argue that these algorithms are computationally deficient in that they fail to generate, or learn, appropriate perceptual representations under certain circumstances. An alternative neural network architecture is presented here in which nodes compete for the right to receive inputs rather than for the right to generate outputs. This form of competition, implemented through preintegration lateral inhibition, does provide appropriate coding properties and can be used to learn such representations efficiently. Furthermore, this architecture is consistent with both neuroanatomical and neurophysiological data. We thus argue that preintegration lateral inhibition has computational advantages over conventional neural network architectures while remaining equally biologically plausible.

This article has been cited by other articles:

				K. Morita Possible Role of Dendritic Compartmentalization in the Spatial Working Memory Circuit J. Neurosci., July 23, 2008; 28(30): 7699 - 7724. [Abstract] [Full Text] [PDF]

				K. Morita, M. Okada, and K. Aihara Selectivity and Stability via Dendritic Nonlinearity. Neural Comput., July 1, 2007; 19(7): 1798 - 1853. [Abstract] [Full Text] [PDF]

				R. Kompass A generalized divergence measure for nonnegative matrix factorization. Neural Comput., March 1, 2007; 19(3): 780 - 791. [Abstract] [Full Text] [PDF]

				S. Fiori Nonlinear Complex-Valued Extensions of Hebbian Learning: An Essay Neural Comput., April 1, 2005; 17(4): 779 - 838. [Abstract] [Full Text] [PDF]

				D. Domijan Recurrent Network with Large Representational Capacity Neural Comput., September 1, 2004; 16(9): 1917 - 1942. [Abstract] [Full Text] [PDF]

				J. Lucke and C. von der Malsburg Rapid Processing and Unsupervised Learning in a Model of the Cortical Macrocolumn Neural Comput., March 1, 2004; 16(3): 501 - 533. [Abstract] [Full Text] [PDF]

				M. W. Spratling and M. H. Johnson A Feedback Model of Visual Attention J. Cogn. Neurosci., February 1, 2004; 16(2): 219 - 237. [Abstract] [Full Text] [PDF]