论文信息 - Blind Source Separation by Adaptive Estimation of Score Function Difference

Blind Source Separation by Adaptive Estimation of Score Function Difference

In this paper, an adaptive algorithm for blind source separation in linear instantaneous mixtures is proposed, and it is shown to be the optimum version of the EASI algorithm. The algorithm is based on minimization of mutual information of outputs. This minimization is done using adaptive estimation of a recently proposed non-parametric “gradient” for mutual information.

[1] Christian Jutten,et al. Entropy Optimization - Application to Blind Source Separation , 1997, ICANN.

[2] Shun-ichi Amari,et al. Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[3] Dinh-Tuan Pham,et al. Mutual information approach to blind separation of stationary sources , 2002, IEEE Trans. Inf. Theory.

[4] Massoud Babaiezadeh Malmiri. On blind source separation in convolutive and nonlinear mixtures , 2002 .

[5] Christian Jutten,et al. Separating Convolutive Mixtures by Mutual Information Minimization , 2001, IWANN.

[6] Christian Jutten,et al. Differential of the mutual information , 2004, IEEE Signal Processing Letters.

[7] Wulfram Gerstner,et al. Artificial Neural Networks — ICANN'97 , 1997, Lecture Notes in Computer Science.

[8] Jean-François Cardoso,et al. Equivariant adaptive source separation , 1996, IEEE Trans. Signal Process..

[9] T. Ens,et al. Blind signal separation : statistical principles , 1998 .

[10] Pierre Comon,et al. Independent component analysis, A new concept? , 1994, Signal Process..

[11] Andrzej Cichocki,et al. Adaptive blind signal and image processing , 2002 .

[12] José Mira,et al. Bio-Inspired Applications of Connectionism , 2001, Lecture Notes in Computer Science.