Proc. Int'l Conf. on Artificial Neural Networks, ICANN'02, Madrid, August 27-30, ed. José R. Dorronsoro, in series Lecture Notes in Computer Science, publ. Springer-Verlag, pp. 81-86 (2002-08-27) (bibtex, paper.pdf, results.shtml)
Applying slow feature analysis to image sequences yields a rich
repertoire of complex cell properties.
Pietro Berkes and Laurenz Wiskott
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.
Relevant Project:
September 26, 2002, Laurenz Wiskott, http://www.neuroinformatik.ruhr-uni-bochum.de/PEOPLE/wiskott/