An Extension of Slow Feature Analysis for Nonlinear Blind Source Separation
Abstract
We present and test an extension of slow feature analysis as a novel approach to nonlinear blind source separation. The algorithm relies on temporal correlations and iteratively reconstructs a set of statistically independent sources from arbitrary nonlinear instantaneous mixtures. Simulations show that it is able to invert a complicated nonlinear mixture of two audio signals with a high reliability. The algorithm is based on a mathematical analysis of slow feature analysis for the case of input data that are generated from statistically independent sources.
Cite
Text
Sprekeler et al. "An Extension of Slow Feature Analysis for Nonlinear Blind Source Separation." Journal of Machine Learning Research, 2014.Markdown
[Sprekeler et al. "An Extension of Slow Feature Analysis for Nonlinear Blind Source Separation." Journal of Machine Learning Research, 2014.](https://mlanthology.org/jmlr/2014/sprekeler2014jmlr-extension/)BibTeX
@article{sprekeler2014jmlr-extension,
title = {{An Extension of Slow Feature Analysis for Nonlinear Blind Source Separation}},
author = {Sprekeler, Henning and Zito, Tiziano and Wiskott, Laurenz},
journal = {Journal of Machine Learning Research},
year = {2014},
pages = {921-947},
volume = {15},
url = {https://mlanthology.org/jmlr/2014/sprekeler2014jmlr-extension/}
}