creators_name: Berkes, Pietro
creators_name: Wiskott, Laurenz
editors_name: Dorronsoro, José R.
type: confpaper
datestamp: 2003-01-09
lastmod: 2011-03-11 08:55:08
metadata_visibility: show
title: Applying Slow Feature Analysis to Image Sequences Yields a Rich Repertoire of Complex Cell Properties
ispublished: pub
subjects: neuro-mod
subjects: comp-neuro-sci
subjects: comp-sci-mach-vis
subjects: bio-theory
full_text_status: public
keywords: Complex cells, slow feature analysis, temporal slowness, model , spatio-temporal, receptive fields
abstract: We apply Slow Feature Analysis (SFA) to image sequences generated from natural images using a range of spatial transformations. An analysis of the resulting receptive fields shows that they have a rich spectrum of invariances and share many properties with complex and hypercomplex cells of the primary visual cortex. Furthermore, the dependence of the solutions on the statistics of the transformations is investigated.

date: 2002
date_type: published
publisher: Springer Verlag
pagerange: 81-86
refereed: TRUE
citation:   Berkes, Pietro and Wiskott, Laurenz  (2002) Applying Slow Feature Analysis to Image Sequences Yields a Rich Repertoire of Complex Cell Properties.  [Conference Paper]     
document_url: http://cogprints.org/2706/1/I0220.ps