paper available: model of complex cells in V1



From: Laurenz Wiskott (l.wiskott@biologie.hu-berlin.de)
Date: Fri Feb 21 2003 - 14:57:34 CET


                       SLOW FEATURE ANALYSIS YIELDS
               A RICH REPERTOIRE OF COMPLEX-CELL PROPERTIES

                   by Pietro Berkes and Laurenz Wiskott

Abstract:
In this study, we investigate temporal slowness as a learning principle for
receptive fields using slow feature analysis, a new algorithm to determine
functions that extract slowly varying signals from the input data. We find
that the learned functions trained on image sequences develop many
properties found also experimentally in complex cells of primary visual
cortex, such as direction selectivity, non-orthogonal inhibition,
end-inhibition and side-inhibition. Our results demonstrate that a single
unsupervised learning principle can account for such a rich repertoire of
receptive field properties.

Available from:
http://cogprints.ecs.soton.ac.uk/archive/00002785/

Reference:
Berkes, P. and Wiskott, L. (2003).
Slow feature analysis yields a rich repertoire of complex-cell properties.
Cognitive Sciences EPrint Archive (CogPrint) 2785,
http://cogprints.ecs.soton.ac.uk/archive/00002785/,
(<add date of your document download here>).

Additional Information:
http://itb.biologie.hu-berlin.de/~wiskott/Projects/SFA-ReceptiveFields.html

-- 
Dr. Laurenz Wiskott, Institute for Theoretical Biology, Berlin
http://itb.biologie.hu-berlin.de/~wiskott/
l.wiskott@biologie.hu-berlin.de



 
Home   Login   Meetings   Courses   Belgium   Maillist   Credits
  Servers   Links   Archive

Please send comments and suggestions to Mike Wijnants.

 
Page last updated on Friday, 21-Feb-2003 15:09:19 CET © BBF 1998 all rights reserved