Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources
- 1 February 1999
- journal article
- Published by MIT Press in Neural Computation
- Vol. 11 (2) , 417-441
- https://doi.org/10.1162/089976699300016719
Abstract
An extension of the infomax algorithm of Bell and Sejnowski (1995) is presented that is able blindly to separate mixed signals with sub- and supergaussian source distributions. This was achieved by using a simple type of learning rule first derived by Girolami (1997) by choosing negentropy as a projection pursuit index. Parameterized probability distributions that have sub- and supergaussian regimes were used to derive a general learning rule that preserves the simple architecture proposed by Bell and Sejnowski (1995), is optimized using the natural gradient by Amari (1998), and uses the stability analysis of Cardoso and Laheld (1996) to switch between sub- and supergaussian regimes. We demonstrate that the extended infomax algorithm is able to separate 20 sources with a variety of source distributions easily. Applied to high-dimensional data from electroencephalographic recordings, it is effective at separating artifacts such as eye blinks and line noise from weaker electrical signals that arise from sources in the brain.Keywords
This publication has 23 references indexed in Scilit:
- An Alternative Perspective on Adaptive Independent Component Analysis AlgorithmsNeural Computation, 1998
- Blind signal separation: statistical principlesProceedings of the IEEE, 1998
- Natural Gradient Works Efficiently in LearningNeural Computation, 1998
- Stability Analysis of Learning Algorithms for Blind Source SeparationNeural Networks, 1997
- Blind source separation-semiparametric statistical approachIEEE Transactions on Signal Processing, 1997
- Infomax and maximum likelihood for blind source separationIEEE Signal Processing Letters, 1997
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Robust learning algorithmfor blind separation of signalsElectronics Letters, 1994
- Independent component analysis, A new concept?Signal Processing, 1994
- Dipole models of eye movements and blinksElectroencephalography and Clinical Neurophysiology, 1991