Independent Component Analysis
Razvan Cristescu
CMI

Abstract: This is a talk on Independent Component Analysis (ICA), a
recently developped signal processing technique where the goal is to
find the data representation in which the transformed components are
statistically as independent as possible. I will outline an
information theoretic approach to ICA, the link with PCA, and the
derivation of a fast separation algorithm. I will conclude with
examples of applications. 

Reference: A. Hyvarinen and E. Oja. Independent Component Analysis:
Algorithms and Applications. Neural Networks, 13(4-5):411-430, 2000.