Local Stability Analysis Of Flexible Independent Component Analysis Algorithm (original) (raw)

Abstract

This paper addresses local stability analysis for the exible independent component analysis (ICA) algorithm 6] where the generalized Gaussian density m o d e l w as employed for blind separation of mixtures of sub-and super-Gaussian sources. In the exible ICA algorithm, the shape of nonlinear function in the learning algorithm varies depending on the Gaussian exponent which is properly selected according to the kurtosis of estimated source. In the framework of the natural gradient in Stiefel manifold, the exible ICA algorithm is revisited and some new results about its local stability analysis are presented.

Loading...

Loading Preview

Sorry, preview is currently unavailable. You can download the paper by clicking the button above.

References (12)

  1. REFERENCES
  2. S. Amari. Natural gradient for over-and under- complete bases in ICA. Neural Computation, 11(8):1875{1883, Nov. 1999.
  3. S. Amari, T. P. Chen, and A. Cichocki. Stability anal- ysis of learning algorithms for blind source separation. Neural Networks, 10(8):1345{1351, 1997.
  4. A. Bell and T. Sejnowski. An information maximisa- tion approach to blind separation and blind deconvo- lution. Neural Computation, 7:1129{1159, 1995.
  5. J. -F. Cardoso. On the stability of source separation algorithms. In IEEE Workshop on Neural Networks for Signal Processing, pages 13{22, Cambridge, UK, 1998.
  6. J. -F. Cardoso and B. H. Laheld. Equivariant adap- tive source separation. IEEE Trans. Signal Processing, 44(12):3017{3030, Dec. 1996.
  7. S. Choi, A. Cichocki, and S. Amari. Flexible inde- pendent component analysis. In T. Constantinides, S. Y. Kung, M. Niranjan, and E. Wilson, editors, Neu- ral Networks for Signal Processing VIII, pages 83{92, 1998.
  8. A. Cichocki, I. Sabala, S. Choi, B. Orsier, and R. Szupiluk. Self-adaptive independent component analysis for sub-Gaussian and super-Gaussian mix- tures with unknown number of source signals. In In- ternational Symposium on Nonlinear Theory and Ap- plications, pages 731{734, 1997.
  9. P. Comon. Independent component analysis, a new concept? Signal Processing, 36(3):287{314, 1994.
  10. S. C. Douglas, A. Cichocki, and S. Amari. Multichan- nel blind separation and deconvolution of sources with arbitrary distributions. In J. Principe, L. Gile, N. Mor- gan, and E. Wilson, editors, Neural Networks for Sig- nal Processing VII, pages 436{445, 1997.
  11. M. Girolami. An alternative perspective on adaptive independent component analysis algorithms. Neural Computation, 10(8):2103{2114, Nov. 1998.
  12. T. W. Lee, M. Girolami, and T. Sejnowski. Indepen- dent component analysis using an extended infomax algorithm for mixed sub-Gaussian and super-Gaussian sources. Neural Computation, 11(2):609{633, 1999.