Natural gradient learning for spatio-temporal decorrelation: Recurrent network

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

Volumn E83-A, Issue 12, 2000, Pages 2715-2722

  Choi, Seungjin ^a,b   Amari, Shunichi ^a   Cichocki, Andrzej ^a  

^a Chungbuk National University   (South Korea)

^b RIKEN BRAIN SCIENCE INSTITUTE   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CORRELATION THEORY; LEARNING SYSTEMS; RECURRENT NEURAL NETWORKS;

HEBBIAN LEARNING; SPATIO-TEMPORAL DECORRELATION;

DIGITAL SIGNAL PROCESSING;

EID: 0034506767     PISSN: 09168508     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (19)

1. E. Oja, "Neural networks, principal component analysis, and subspnces," International J. Neural Systems, vol.1, pp.61-68, 1989.
2. K.I. Diamantaras and S.Y. Kung, Principal Component Neural Networks: Theory and Applications, John Wiley fc Sons, 199G.
3. P. Földiak, "Adaptive network for optimal linear feature extraction," Proc. Int. Joint Conf. Neural Networks, pp.401405, 1989.
4. L.B. Almeida and P.M. Suva, "Adaptive decorrelation," Artificial Neural Networks, pp.l49-15G, 1992.
5. S.C. Douglas and A. Cichocki, "Neural networks for blind decorrelation of signals," IEEE Trans. Signal Processing, vol.45, no. 11, pp.2829-2842, 1997.
6. F. Palmier!, J. Zhu, and C. Chang, "Anti-Hebbian learning in topologically constrained linear networks: A tutorial," IEEE Trans. Neural Networks, vol.5, no.4, pp.7487G1, Sept. 1993.
7. S. Amari, "Natural gradient works efficiently in learning," Neural Computation, vol.10, no.2, pp.251-27G, 1998.
8. S. Choi, "Adaptive blind equalization for multi-channel transmission via temporal decorrelation," J. Electrical Engineering fc Information Science, vol.4, no.l, pp.130-136, Feb. 1999.
9. S. Choi, II. Luo, and R. Liu, "An adaptive system for direct multi-channel blind equalization," Proc. SPAWC, pp.85-88, Paris, France, 1997.
10. S. Choi, A. Cichocki, and S. Amari, "Blind equalization of SIMO channels via spatio-temporal anti-Hebbian learning rule," in Neural Networks for Signal Processing VIII, eds. T. Constantinides, S.Y. Kung, M. Niranjan, and E. Wilson, pp.93-102, 1998.
11. S. Choi, "Linear neural networks with FIR synapses for blind deconvolution and equalization," J. Electrical Engineering &: Information Science, vol.4, no.2, pp.224-231, April 1999.
12. S. Aniari, S.C. Douglas, A. Cichocki, and H.H. Yang, "Multichannel blind dcconvolution and equalization using the natural gradient," Proc. SPAWC, pp.101-104, Paris, France, 1997.
13. S. Choi, S. Amari, and A. Cichocki, "Natural gradient learning algorithms for dccorrelation," Proc. ICONIP, vol.1, pp.645-648, Dunedin, New Zealand, 1997.
14. J.-F. Cardoso and B.H. Laheld, "Equivariant adaptive source separation," IEEE Trans. Signal Processing, vol.44, no.12, pp.3017-3030, Dec. 199G.
15. S. Van Gervcn and D. Van Compernolle, "Signal separation by symmetric adaptive decorrelation: Stability, convergence, and uniqueness," IEEE Trans. Signal Processing, vol.43, no.7, pp.1602-1612, 1995.
16. S. Choi and A. Cichocki, "An unsupcrvised hybrid network for blind separation of independent non-gaussian source signals in multipath environment," J. Communications & Networks, vol.1, no.l, pp.19-25, 1999.
17. S. Choi, S. Amari, A. Cichocki, and R. Liu, "Natural gradient learning with a nonholonomic constraint for blind deconvolution of multiple channels," Proc. ICA'99, pp.371376, Aussois, France, 1999.
18. L. Tong, G. Xu, and T. Kailath, "A new approach to blind identification and equalization of multipath channel," Proc. Asilomar Conference, pp.340-349, 1991.
19. E. Moulines, P. Duhamel, J.F. Cardoso, and S. Mayrargue, "Subspace methods for the blind identification of multipath channel FIR filters," IEEE Trans. Signal Processing, vol.43, pp.516-525, 1995.