Dimension Reduction Based on Orthogonality - A Decorrelation Method in ICA

Kun Zhang, Lai-Wan ChanICANN 2003 · OpenReview

Abstract

In independent component analysis problems, when we use a one-unit objective function to iteratively estimate several independent components, the uncorrelatedness between the independent components prevents them from converging to the same optimum. A simple and popular way of achieving decorrelation between recovered independent components is a deflation scheme based on a Gram-Schmidt-like decorrelation
BibTeX
@inproceedings{zhang2003dimension,
  author = {Kun Zhang and Lai-Wan Chan},
  title = {{Dimension Reduction Based on Orthogonality - A Decorrelation Method in ICA}},
  booktitle = {ICANN},
  year = {2003},
  url = {https://openreview.net/forum?id=S8DXQD2ADE},
}

Loading related content...

Figure