@inproceedings{adf71e8d56fc48df9013c0daa9bc7edc,
title = "Complex-Valued Independent Component Analysis of Natural Images",
abstract = "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.",
author = "Valero Laparra and Gutmann, {Michael U.} and Jes{\'u}s Malo and Aapo Hyv{\"a}rinen",
year = "2011",
doi = "10.1007/978-3-642-21738-8_28",
language = "English",
isbn = "978-3-642-21737-1",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "213--220",
editor = "Timo Honkela and Wlodzislaw Duch and Mark Girolami and Samuel Kaski",
booktitle = "Artificial Neural Networks and Machine Learning -- ICANN 2011: 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part II",
address = "United Kingdom",
}