论文信息 - Fast Algorithms for Bayesian Independent Component Analysis

Fast Algorithms for Bayesian Independent Component Analysis

Fast algorithms for linear blind source separation are developed. The fast convergence is rst derived from low-noise approximation of the EM-algorithm given in 2], to which a modiication is made that leads as a special case to the FastICA algorithm 5]. The modii-cation is given a general interpretation and is applied to Bayesian blind source separation of noisy signals.

H. Lappalainen

[1] Aapo Hyvärinen,et al. Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces , 2000, Neural Computation.

[2] Harri Valpola. Nonlinear independent component analysis using ensemble learning: Theory , 2000 .

[3] Juha Karhunen,et al. Nonlinear Independent Component Analysis Using Ensemble Learning: Experiments and Discussion , 2000 .

[4] Hagai Attias,et al. Independent Factor Analysis , 1999, Neural Computation.

[5] Jean-Francois Cardoso,et al. Approximate likelihood for noisy mixtures , 1999 .

[6] Harri Lappalainen,et al. Ensemble learning for independent component analysis , 1999 .

[7] Jean-François Cardoso,et al. Multidimensional independent component analysis , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[8] Erkki Oja,et al. Independent Component Analysis for Identification of Artifacts in Magnetoencephalographic Recordings , 1997, NIPS.

[9] Eric Moulines,et al. Maximum likelihood for blind separation and deconvolution of noisy signals using mixture models , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.