TY  - GEN
ID  - cogprints2706
UR  - http://cogprints.org/2706/
A1  - Berkes, Pietro
A1  - Wiskott, Laurenz
Y1  - 2002///
N2  - 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.

PB  - Springer Verlag
KW  - Complex cells
KW  -  slow feature analysis
KW  -  temporal slowness
KW  -  model 
KW  -  spatio-temporal
KW  -  receptive fields
TI  - Applying Slow Feature Analysis to Image Sequences Yields a Rich Repertoire of Complex Cell Properties
SP  - 81
AV  - public
EP  - 86
ER  -

<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>