Learned parametric mixture based ica algorithm

Neurocomputing

Volumn 22, Issue 1-3, 1998, Pages 69-80

  Xu, Lei ^a   Chiu Cheung, Chi ^a   Amari, Shun Ichi ^b  

^a CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

^b RIKEN   (Japan)

Author keywords

Blind separation; Independent component analysis; Information theoretic; Learning; Maximum likelihood; Nonlinearity; Parametric density mixture

Indexed keywords

ADAPTIVE ALGORITHMS; CONTROL NONLINEARITIES; HEURISTIC METHODS; INFORMATION THEORY; LEARNING ALGORITHMS; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; SPURIOUS SIGNAL NOISE; STATISTICAL METHODS;

BLIND SOURCE SEPARATIONS; INDEPENDENT COMPONENT ANALYSIS; PARAMETRIC DENSITY MIXTURES;

NEURAL NETWORKS;

ALGORITHM; CALCULATION; MATHEMATICAL ANALYSIS; PRIORITY JOURNAL; REVIEW; STATISTICAL ANALYSIS; STATISTICS;

EID: 0345019851     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(98)00050-2     Document Type: Article

References (24)

1. S.-I. Amari, A. Cichocki, H. Yang, A new learning algorithm for blind separation of sources, in: D.S. Touretzky, M.C. Mozer, M.E. Hasselmo (Eds.), Advances in Neural Information Processing, 8, MIT Press, Cambridge, MA, 1996, pp. 757-763.
2. Bell A.J., Sejnowski T.J. An information-maximatization approach to blind separation and blind deconvolution. Neural Comput. 7:1995;1129-1159.
3. J.F. Cardoso, Informax and maximum likelihood for blind source separation, IEEE Signal Process. Lett. 4, 109-111.
4. Cardoso J.F., Laheld B. Equivalent adaptive source separation. IEEE Trans. Signal Process. 44:1996;3017-3030.
5. C.C. Cheung, Adaptive blind signal separation, Master Thesis, Department of Computer Science and Engineering, The Chinese University of Hong Kong, June 1997.
6. C.C. Cheung, L. Xu, Separation of two independent sources by the information-theoretic approach with cubic nonlinearity, Proc. IEEE Int. Conf. on Neural Networks (IEEE-INNS IJCNN97), 9-12 June 1997, Houston, TX, USA, vol. 4, pp. 2239-2244.
7. Cichocki et al., Independent component analysis for noisy data in: C. Fyfe (Ed.), Proc. Int. ICSC Workshop on Independence and Artificial neural networks (I&ANN'98), 9-10 February, Tenerife, Spain, ICSC Academic Press, 1998, pp. 52-58.
8. P. Comon, Independent component analysis - a new concept? Signal Process. 36 (1994) 287-314.
9. M.Gaeta, J.-L Lacounme, Source separation without a priori knowledge: the maximum likelihood solution, Proc. European Signal Process. Conf. EUSIPCO90 (1990) 621-624.
10. I. King, L. Xu, Adaptive contrast enhancement by entropy maximization with a 1-K-1 constrained network, Proc. 1995 Int. Conf. on Neural Information Process. (ICONIP95), 30 October-3 November 1995, Beijing, vol. II, pp. 703-706.
11. Nadal J.-P., Parga N. Nonlinear neurons in the low-noise limit. a factorial code maximizes information transfer Network. 5:1994;565-581.
12. E. Oja, ICA Learning rules: stationarity, stability, and sigmoids, in: C. Fyfe (Ed.), Proc. of Int. ICSC Workshop on Independence and Artificial Neural Networks (I&ANN'98), 9-10 Febraury, Tenerife, Spain, ICSC Academic Press, New York, 1998, pp. 97-103.
13. E. Oja, J. Karhunen, A. Hyvärinen, From neural principal components to neural independent components, Proc. Int. Conf. on Artificial Neural Networks ICANN'97, 8-10 October, Lausanne, Switzerland, 1997, pp. 519-528.
14. B.A. Pearlmutter, L.C. Parra, A context-sensitive generalization of ICA, in: Progress in Neural Information Processing: Proc. Int. Conf. on Neural Information Processing (ICONIP 96), Hong Kong, 24-27 September 1996, Springer, Singapore, 1996, pp. 1235-1239.
15. Pham D.T., Garat P., Jutten C. Separation of a mixture of independent sources through a maximum likelihood approach. Vandewalle J.et al. Singal Processing VI. Theories and Applications:1992;771-774 Elsevier, Amsterdam.
16. Xu L. Bayesian Ying-Yang System and Theory as A Unified Statistical Learning Approach: (I) Unsupervised and Semi-Unsupervised Learning, Invited paper. Amari S., Kassabov N. Brain-like Computing and Intelligent Information Systems. 1997;241-274 Springer, Berlin.
17. L. Xu, Bayesian Ying-Yang system and theory as a unified statistical learning approach (II): from unsupervised learning to supervised learning and temporal modeling and (III): models and algorithms for dependence reduction, data dimension reduction, ICA and supervised learning, in: K.W. Wong, I. King, D.Y. Yeung (Eds.), Theoretical Aspects of Neural Computation: A Multidisciplinary Perspective (TANC97), Springer, Berlin, 1997, pp. 25-60.
18. L. Xu, Bayesian Ying-Yang learning based ICA models, Neural Networks for Signal Processing VII: Proc. IEEE Signal Processing Society Workshop, 24-26 September 1997, Florida, pp. 476-485.
19. L. Xu, BYY dependence reduction theory and blind source separation, Proc. Intentional Joint Conf. on Neural Networks, 5-9 May 1998, Anchorage, Alaska, Vol. II, pp. 2495-2500.
20. L. Xu, S.-I. Amari, A general independent component analysis framework based on Bayesian-Kullback Ying-Yang Learning, in: Progress in Neural Information Processing: Proc. Int. Conf. on Neural Information Processing (ICONIP 96), Hong Kong, 24-27 September 1996, Springer, Singapore, 1996, pp. 1235-1239.
21. L. Xu, C.C. Cheung, J. Ruan, S.-I. Amari, Nonlinearity and separation capability: further justification for the ICA algorithm with a learned mixture of parametric densities, Invited special session on Blind Signal Separation, Proc. European Symp. on Artificial Neural Networks, Bruges, 16-18 April 1997, pp. 291-296.
22. L. Xu, C.C. Cheung, H.H. Yang, S.-I. Amari, Independent component analysis by the information-theoretic approach with mixture of density, Proc. IEEE Int. Conf. on Neural Networks (IEEE-INNS IJCNN97), 9-12 June, Houston, TX, USA, 1997, pp. 1821-1826.
23. L.Xu, H.H. Yang, S.-I. Amari, Signal source separation by mixtures accumulative distribution functions or mixture of bell-shape density distribution functions, Research Proposal, Presented at FRONTIER FORUM (speakers: D. Sherrington, S. Tanaka, L. Xu, J. F. Cardoso), organized by S. Amari, S. Tanaka, A. Cichocki, The Institute of Physical and Chemical Research (RIKEN), Japan, 10 April 1996.
24. Yang H.H., Amari S.-I. Adaptive online learning algorithms for blind separation. maximum entropy and minimum mutual information Neural Comput. 9:1997;1457-1482.