FastICA - Wikipedia, the free encyclopedia

http://en.wikipedia.org/wiki/FastICA

FastICA
From Wikipedia, the free encyclopedia

FastICA is an efficient and popular algorithm for independent component analysis invented by Aapo Hyvrinen at Helsinki University of Technology. The algorithm is based on a fixed-point iteration scheme maximizing non-Gaussianity as a measure of statistical independence. It can also be derived as an approximative Newton iteration.

Contents
1 Algorithm 1.1 Preprocess the data 1.1.1 Centering the data 1.1.2 Whitening the data 1.2 Single component extraction 1.3 Multiple component extraction 2 See also 3 References 4 External links

Algorithm
Preprocess the data
Before the FastICA algorithm can be applied, the input vector data Centering the data The input data is centered by computing the mean of each component of has the effect of making each component have zero mean. Thus: and subtracting that mean. This should be centered and whitened.

Whitening the data Whitening the data involves linearly transforming the data so that the new components are uncorrelated and have variance one. If is the whitened data, then the covariance matrix of the whitened data is the identity matrix:

This can be done using eigenvalue decomposition of the covariance matrix of the data: where is the matrix of eigenvectors and is the diagonal matrix of eigenvalues. Once eigenvalue decomposition is done, the whitened data is:

1 of 3

8/25/2013 5:53 PM

FastICA - Wikipedia, the free encyclopedia

http://en.wikipedia.org/wiki/FastICA

Single component extraction

The iterative algorithm finds the direction for the weight vector maximizing the non-Gaussianity of the projection for the data . The function is the derivative of a nonquadratic nonlinearity function . Hyvrinen states that good equations for (shown with their derivatives and second derivatives ) are:

The first equation is a good general-purpose equation, while the second is highly robust. 1. Randomize the initial weight vector 2. Let vectors of matrix 3. Let 4. If not converged, go back to 2

, where

means averaging over all column-

Multiple component extraction

The single unit iterative algorithm only estimates one of the independent components, to estimate more the algorithm must repeated, and the projection vectors decorated. Although Hyvrinen provides several ways of decorating results the simplest multiple unit algorithm follows. indicates a column vector of 1's with dimension M. Algorithm FastICA Input: Number of desired components Input: Matrix, where each column represents an N-dimensional sample, where Output: Un-mixing matrix where each row projects X onto into independent component. Output: Independent components matrix, with M columns representing a sample with C dimensions.
for p in 1 to C: Random vector of length N while changes

2 of 3

8/25/2013 5:53 PM

FastICA - Wikipedia, the free encyclopedia

http://en.wikipedia.org/wiki/FastICA

Output:

Output:

See also
Unsupervised learning Machine learning The IT++ library features a FastICA implementation in C++

References
Hyvrinen, A; Oja, E (2000). Independent Component Analysis: Algorithms and Applications (http://www.cs.helsinki.fi/u/ahyvarin/papers/NN00new.pdf). Neural Networks, 13(4-5),411-430. Hyvrinen, A (1999). Fast and Robust Fixed-Point Algorithms for Independent Component Analysis (http://www.cs.helsinki.fi/u/ahyvarin/papers/TNN99new.pdf). IEEE Transactions on Neural Networks, 10(3),626-634.

External links
FastICA package for Matlab or Octave (http://www.cis.hut.fi/projects/ica/fastica/) fastICA package (http://cran.r-project.org/web/packages/fastICA/index.html) in R programming language FastICA in Java (http://sourceforge.net/projects/fastica) on SourceForge FastICA in Java (http://yale.sourceforge.net/rapidminer-4.2/javadoc/com/rapidminer/operator/features /transformation/FastICA.html) in RapidMiner. Retrieved from "http://en.wikipedia.org/w/index.php?title=FastICA&oldid=567140953" Categories: Multivariate statistics Computational statistics Machine learning algorithms Statistics stubs This page was last modified on 4 August 2013 at 18:11. Text is available under the Creative Commons Attribution-ShareAlike License; additional terms may apply. By using this site, you agree to the Terms of Use and Privacy Policy. Wikipedia is a registered trademark of the Wikimedia Foundation, Inc., a non-profit organization.

3 of 3

8/25/2013 5:53 PM