Cogprints

An Extension of Slow Feature Analysis for Nonlinear Blind Source Separation

Sprekeler, Dr. Henning and Zito, Tiziano and Wiskott, Dr. Laurenz (2010) An Extension of Slow Feature Analysis for Nonlinear Blind Source Separation. [Preprint]

This is the latest version of this eprint.

Full text available as:

[img]
Preview
PDF - Submitted Version
903Kb

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 reliability of more than $90$\%. 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.

Item Type:Preprint
Keywords:slow feature analysis, nonlinear blind source separation, independent component analysis
Subjects:Computer Science > Machine Learning
ID Code:7056
Deposited By:Sprekeler, Henning
Deposited On:18 Oct 2010 12:03
Last Modified:11 Mar 2011 08:57

Available Versions of this Item

  • An Extension of Slow Feature Analysis for Nonlinear Blind Source Separation. (deposited 18 Oct 2010 12:03) [Currently Displayed]

Metadata

Repository Staff Only: item control page