Advertisement

Independent Component Analysis

  • Te-Won Lee
Chapter

Abstract

The goal of blind source separation (BSS) is to recover independent sources given only sensor observations that are linear mixtures of independent source signals. The term blind indicates that both the source signals and the way the signals were mixed are unknown. Independent Component Analysis (ICA) is a method for solving the blind source separation problem. It is a way to find a linear coordinate system (the unmixing system) such that the resulting signals are as statistically independent from each other as possible. In contrast to correlation-based transformations such as Principal Component Analysis (PCA), ICA not only decorrelates the signals (2nd-order statistics) but also reduces higher-order statistical dependencies.

Keywords

Mutual Information Independent Component Analysis Learning Rule Independent Component Analysis Blind Source Separation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

  1. 1.
    as detailed in section 4 of Bell and Sejnowski (1995)Google Scholar
  2. 2.
    see eqs. 40 and 41 in their paper.Google Scholar
  3. 3.
    Symmetric bimodal densities considered in this paper are sub-Gaussian, however this is not always the case.Google Scholar
  4. 4.
    The presented estimation theory is related to the semiparametrical statistical approach by Amari and Cardoso (1997) and the stability analysis of adaptive blind source separation (Amari et al., 1997a)Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1998

Authors and Affiliations

  • Te-Won Lee
    • 1
  1. 1.Computational Neurobiology LaboratoryThe Salk InstituteLa JollaUSA

Personalised recommendations