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. 1087-1093 (2002-08-27) (bibtex)

An improved cumulant based method for independent component analysis.

Tobias Blaschke and Laurenz Wiskott


Abstract: An improved method for independent component analysis based on the diagonalization of cumulant tensors is proposed. It is based on Comon's algorithm [Comon, 1994] but it takes third- and fourth-order cumulant tensors into account simultaneously. The underlying contrast function is also mathematically much simpler and has a more intuitive interpretation. It is therefore easier to optimize and approximate. A comparison with Comon's algorithm, JADE [Cardoso, 1993] and FastICA [Hyvärinen, 1999] on different data sets demonstrates its performance.


Relevant Project:


September 26, 2002, Laurenz Wiskott, http://www.neuroinformatik.ruhr-uni-bochum.de/PEOPLE/wiskott/