Stability analysis of learning algorithms for blind source separation

Neural Networks

Volumn 10, Issue 8, 1997, Pages 1345-1351

  Amari, Shun Ichi ^a   Chen, Tian Ping ^a   Cichocki, Andrzej ^a  

^a RIKEN   (Japan)

Author keywords

Blind source separation; Efficiency of learning; Independent component analysis (ICA); Natural gradient; Stability of learning

Indexed keywords

ADAPTIVE ALGORITHMS; ADAPTIVE FILTERING; STATISTICAL METHODS;

BLIND SOURCE SEPARATION; INDEPENDENT COMPONENT ANALYSIS (ICA);

LEARNING ALGORITHMS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; LEARNING; PRIORITY JOURNAL; SIGNAL PROCESSING; STOCHASTIC MODEL;

EID: 0031277419     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(97)00039-7     Document Type: Article

References (23)

1. Amari S. A theory of adaptive pattern classifiers. IEEE Transaction on Electronic Computers. EC-16:1967;299-307.
2. Amari, S. (1985) Differential-geometrical methods in statistics, Springer lectures notes in statistics. Heidelberg: Springer.
3. Amari, S. (1997). Natural gradient works efficiently in learning. Neural Computation, (in print).
4. Amari, S., Cichocki A., & Yang, H. H. (1995). Recurrent neural networks for blind separation of sources. Proceedings of International Symposium on Nonlinear Theory and its Applications (pp. 37-42). Las Vegas: NOLTA-95.
5. Amari, S., Cichocki, A., & Yang, H. H. (1996). A new learning algorithm for blind signal separation. In D. S. Touretzky, C. Michakel, M. C. Mozer & M. E. Hasselmo (Eds.), Advances in Neural Information Processing Systems (pp. 757-763). Cambridge, MA: MIT Press.
6. Amari, S., & Cardoso, J. F. (1997). Blind source separation - semi-parametric statistical approach. IEEE Trans. on Signal Processing, (in print).
7. Amari S., Kawanabe M. Information geometry of estimating functions in semiparametric statistical models. Bernoulli. 2(3):1997;29-54.
8. Bell A. J., Sejnowski T. J. An information-maximization approach to blind separation and blind deconvolution. Neural Computation. 7:1995;1129-1159.
9. Bickel, P. J., Klaassen, C. A. J., Ritov, Y., & Wellner, J. A. (1993). Efficient and adaptive estimation for semiparametric models. Baltimore: Johns Hopkins University Press.
10. Cardoso J. F., Laheld B. Equivariant adaptive source separation. IEEE Transaction on Signal Processing. 44:1996;3017-3030.
11. Common P. Independent component analysis, a new concept? Signal Processing. 36:1994;287-314.
12. Chen, T., & Chen, R. (1994). Blind extraction of stochastic and deterministic signals by neural network approach. Proceedings of 28th Asilomar Conference on Signals, Systems and Computer (pp. 892-896). Pacific Grove, CA: IEEE Computer Society.
13. Cichocki A., Unbehauen R., Rummert E. Robust learning algorithm for blind separation of signals. Electronics Letters. 30:1994;1386-1387.
14. Cichocki, A., Unbehauen, R., Moszczyński, L., & Rummert, E. (1994b). A new on-line adaptive learning algorithm for blind separation of source signals. Proceedings of International Symposium of Artificial Neural Networks (pp. 406-411). Taiwan: ISANN-94.
15. Cichocki, A., Amari, S., Adachi, M., & Kasprzak, W. (1996). Self-adaptive neural networks for blind separation of sources. Proceedings of International Symposium on Circuits and Systems (pp.157-161). Atlanta, GA: ISCAS-96.
16. Deville Y. A unified stability analysis of the Herault-Jutten source separation neural network. Signal Processing. 51:1996;229-233.
17. Fort J. C. Stabilite de l'algorithme de separation de sources de Jutten at Herault. Traitement du Signal. 8:1991;35-42.
18. Godambe, V. P. (Ed.) (1991). Estimating functions. New York: Oxford University Press.
19. Herault, J., & Jutten, C. (1986). Space or time adaptive signal processing by neural network models. In J. S. Denker (Ed.), Neural networks for computing (pp. 206-211). New York: American Institute of Physics.
20. Macchi, O., & Moreau E. (submitted). Self-adaptive source separation Part I: convergence analysis of a direct linear network controlled by Herault-Jutten algorithm. IEEE Transactions on Signal Processing.
21. Murray, M. K., & Rice, J. W. (1993). Differential geometry and statistics. New York: Chapman & Hall.
22. Oja, E., & Karhunen, J. (1995). Signal separation by nonlinear Hebbian learning. In M. Palaniswami et al. (Eds.), Computational intelligence - a dynamic system perspective (pp. 83-97). New York: IEEE.
23. Sorouchyari E. Blind separation of sources, part III: stability analysis. Signal Processing. 24:1991;21-30.