Cogprints

Applying Slow Feature Analysis to Image Sequences Yields a Rich Repertoire of Complex Cell Properties

Berkes, Pietro and Wiskott, Laurenz (2002) Applying Slow Feature Analysis to Image Sequences Yields a Rich Repertoire of Complex Cell Properties. [Conference Paper]

Full text available as:

[img]
Preview
Postscript
315Kb

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.

Item Type:Conference Paper
Keywords:Complex cells, slow feature analysis, temporal slowness, model , spatio-temporal, receptive fields
Subjects:Neuroscience > Neural Modelling
Neuroscience > Computational Neuroscience
Computer Science > Machine Vision
Biology > Theoretical Biology
ID Code:2706
Deposited By: Berkes, Pietro
Deposited On:09 Jan 2003
Last Modified:11 Mar 2011 08:55

Metadata

Repository Staff Only: item control page