Recurrent Neural Networks For Blind Separation of Sources

In this paper, fully connected recurrent neural networks are investigated for blind separation of sources. For these networks, a new class of unsupervised on-line learning algorithms are proposed. These algorithms are the generalization of the Hebbian/anti-Hebbian rule. They are not only biologically plausible but also theoretically sound. An important property of these algorithms is that the performance of the networks is independent of the mixing matrix and the scaling factor of the input sources. This property is veri ed by analyses and simulations.

[1]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[2]  P. Foldiak,et al.  Adaptive network for optimal linear feature extraction , 1989, International 1989 Joint Conference on Neural Networks.

[3]  Peter Földiák,et al.  Adaptation and decorrelation in the cortex , 1989 .

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

[5]  J J Hopfield,et al.  Olfactory computation and object perception. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

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

[8]  J. Hopfield,et al.  Decomposition of a mixture of signals in a model of the olfactory bulb. , 1994, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Kiyotoshi Matsuoka,et al.  A neural net for blind separation of nonstationary signals , 1995, Neural Networks.

[10]  Tzyy-Ping Jung,et al.  Independent Component Analysis of Electroencephalographic Data , 1995, NIPS.

[11]  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.

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

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