论文信息 - A Hierarchical Learning Rule for Independent Component Analysis

A Hierarchical Learning Rule for Independent Component Analysis

In this paper, a two-layer neural network is presented that organizes itself to perform Independent Component Analysis (ICA). A hierarchical, nonlinear learning rule is proposed which allows to extract the unknown independent source signals out of a linear mixture. The convergence behaviour of the network is analyzed mathematically.

Bernd Freisleben | Claudia Hagen | C. Hagen | Bernd Freisleben

[1] Terence D. Sanger,et al. Optimal unsupervised learning in a single-layer linear feedforward neural network , 1989, Neural Networks.

[2] Christian Jutten,et al. Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[3] Esfandiar Sorouchyari,et al. Blind separation of sources, part III: Stability analysis , 1991, Signal Process..

[4] Gilles Burel,et al. Blind separation of sources: A nonlinear neural algorithm , 1992, Neural Networks.

[5] Pierre Comon,et al. Blind separation of sources, part II: Problems statement , 1991, Signal Process..

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

[7] Andrzej Cichocki,et al. A New Learning Algorithm for Blind Signal Separation , 1995, NIPS.

[8] D. L. Wallace. Asymptotic Approximations to Distributions , 1958 .

[9] J. Karhunen,et al. A bigradient optimization approach for robust PCA, MCA, and source separation , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[10] Nathalie Delfosse,et al. Adaptive blind separation of independent sources: A deflation approach , 1995, Signal Process..

[11] Erkki Oja,et al. A class of neural networks for independent component analysis , 1997, IEEE Trans. Neural Networks.