Complex-Valued Independent Component Analysis of Natural Images

Valero Laparra, Michael U. Gutmann, Jesús Malo, Aapo Hyvärinen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Linear independent component analysis (ICA) learns simple cell receptive fields from natural images. Here, we show that linear complex-valued ICA learns complex cell properties from Fourier-transformed natural images, i.e. two Gabor-like filters with quadrature-phase relationship. Conventional methods for complex-valued ICA assume that the phases of the output signals have uniform distribution. We show here that for natural images the phase distributions are, however, often far from uniform. We thus relax the uniformity assumption and model also the phase of the sources in complex-valued ICA. Compared to the original complex ICA model, the new model provides a better fit to the data, and leads to Gabor filters of qualitatively different shape.
Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning -- ICANN 2011: 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part II
EditorsTimo Honkela, Wlodzislaw Duch, Mark Girolami, Samuel Kaski
Place of PublicationBerlin, Heidelberg
PublisherSpringer Berlin Heidelberg
Number of pages8
ISBN (Electronic)978-3-642-21738-8
ISBN (Print)978-3-642-21737-1
Publication statusPublished - 2011

Publication series

NameLecture Notes in Computer Science
Publisher Springer Berlin Heidelberg
ISSN (Print)0302-9743


Dive into the research topics of 'Complex-Valued Independent Component Analysis of Natural Images'. Together they form a unique fingerprint.

Cite this