Recursive ICA

Honghao Shan, Lingyun Zhang, Garrison W. Cottrell

NeurIPS 2006 pp. 1273-1280

/neurips/2006/shan2006neurips-recursive/

Abstract

Independent Component Analysis (ICA) is a popular method for extracting independent features from visual data. However, as a fundamentally linear technique, there is always nonlinear residual redundancy that is not captured by ICA. Hence there have been many attempts to try to create a hierarchical version of ICA, but so far none of the approaches have a natural way to apply them more than once. Here we show that there is a relatively simple technique that transforms the absolute values of the outputs of a previous application of ICA into a normal distribution, to which ICA maybe applied again. This results in a recursive ICA algorithm that may be applied any number of times in order to extract higher order structure from previous layers.

PDF NeurIPS Semantic Scholar

Cite

Text

Shan et al. "Recursive ICA." Neural Information Processing Systems, 2006.

Markdown

[Shan et al. "Recursive ICA." Neural Information Processing Systems, 2006.](https://mlanthology.org/neurips/2006/shan2006neurips-recursive/)

BibTeX

@inproceedings{shan2006neurips-recursive,
  title     = {{Recursive ICA}},
  author    = {Shan, Honghao and Zhang, Lingyun and Cottrell, Garrison W.},
  booktitle = {Neural Information Processing Systems},
  year      = {2006},
  pages     = {1273-1280},
  url       = {https://mlanthology.org/neurips/2006/shan2006neurips-recursive/}
}