NATURAL GRADIENT LEARNING WITH A NONHOLONOMIC CONSTRAINT FOR BLIND DECONVOLUTION OF MULTIPLE CHANNELS

This paper addresses natural gradient learning algorithms with a nonholonomic constraint and their application to multichannel blind deconvolution First we incorporate a nonholonomic constraint into the natural gradient learn ing algorithm for multichannel blind deconvolution that has been developed by Amari Douglas Cichocki Yang and present a slightly modi ed algorithm which works e ciently for the case where we overestimate the number of sources or the number of sources is not known in advance Sec ond we also derive a natural gradient learning algorithm that can be used to train a linear feedback network with FIR synapses Again a nonholonomic constraint is incor porated It is applied to the blind equalization of single input multiple output SIMO channels and is compared with the spatio temporal anti Hebbian rule which is the extension of the anti Hebbian rule The algorithms are rigorously derived and their validity is con rmed by com puter simulations

[1]  James L. Massey,et al.  Inverses of Linear Sequential Circuits , 1968, IEEE Transactions on Computers.

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

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

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

[5]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[6]  Nathalie Delfosse,et al.  Adaptive blind separation of convolutive mixtures , 1996, Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers.

[7]  Eric Moulines,et al.  Subspace methods for the blind identification of multichannel FIR filters , 1995, IEEE Trans. Signal Process..

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

[9]  Roland Gautier,et al.  Blind separation of convolutive mixtures using second and fourth order moments , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[10]  P. Loubaton,et al.  Adaptive blind separation of convolutive mixtures , 1995, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

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

[12]  Andrzej Cichocki,et al.  Robust neural networks with on-line learning for blind identification and blind separation of sources , 1996 .

[13]  Jitendra K. Tugnait,et al.  Identification and deconvolution of multichannel linear non-Gaussian processes using higher order statistics and inverse filter criteria , 1997, IEEE Trans. Signal Process..

[14]  S.C. Douglas,et al.  Multichannel blind deconvolution and equalization using the natural gradient , 1997, First IEEE Signal Processing Workshop on Signal Processing Advances in Wireless Communications.

[15]  Andrzej Cichocki,et al.  On-line Adaptive Algorithms for Blind Equalization of Multi-Channel Systems , 1997, ICONIP.

[16]  S. Choi,et al.  An adaptive system for direct blind multi-channel equalization , 1997, First IEEE Signal Processing Workshop on Signal Processing Advances in Wireless Communications.

[17]  최승진.  Blind signal deconvolution by spatio-temporal decorrelation and demixing , 1997 .

[18]  Shun-ichi Amari,et al.  Blind equalization of SIMO channels via spatio-temporal anti-Hebbian learning rule , 1998, Neural Networks for Signal Processing VIII. Proceedings of the 1998 IEEE Signal Processing Society Workshop (Cat. No.98TH8378).

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

[20]  Hui Luo,et al.  Direct blind separation of independent non-Gaussian signals with dynamic channels , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[21]  A. J. Bell,et al.  A Unifying Information-Theoretic Framework for Independent Component Analysis , 2000 .

[22]  Seungjin Choi.  Linear Neural Networks with FIR Synapses for Blind Deconvolution and Equalization , 1999 .

[23]  Andrzej Cichocki,et al.  Nonholonomic Orthogonal Learning Algorithms for Blind Source Separation , 2000, Neural Computation.