Novel on-line adaptive learning algorithms for blind deconvolution using the natural gradient approach

被引：0

作者：

Amari, S ^{[1
]}

Douglas, SC ^{[1
]}

Cichocki, A ^{[1
]}

Yang, HH ^{[1
]}

机构：

[1] RIKEN, FRP, Brain Inform Proc Grp, Wako, Saitama 35101, Japan

来源：

(SYSID'97): SYSTEM IDENTIFICATION, VOLS 1-3 | 1998年

关键词：

adaptive algorithms; blind deconvolution; blind equalization; maximum entropy; multichannel systems; natural gradient; on-line learning;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Blind deconvolution is an important task for numerous applications in control, signal processing, and communications. In this paper, the efficient natural gradient [Amari et.al. (1996)] or relative gradient [Cardoso and Laheld (1996)] is extended to derive a set of on-line adaptive algorithms for single channel and combined multichannel linear blind source separation and time-domain deconvolution/equalization of additive, convolved signal mixtures. The single-channel algorithms are based on Bussgang blind error criteria, and the multichannel algorithm is based on a modified maximum entropy formulation. Both algorithms possess the so-called "equivariance property" [Cardoso and Laheld (1996)] such that their convergence properties are independent of the mixing characteristics of the unknown channel. Simulations indicate the abilities of the proposed algorithms to perform single-channel or simultaneous multichannel signal deconvolution and source separation.

引用

页码：1007 / 1012

页数：6

共 50 条

[11] On-line adaptive principal component extraction algorithms using iteration approach
Sun, Jian
Chai, Yi
Guo, Maoyun
Li, H. F.
[J]. SIGNAL PROCESSING, 2012, 92 (04) : 1044 - 1068
[12] Blind deconvolution by using phase spectral constraints and natural gradient
Uchino, Eiji
Suetake, Noriaki
Sakano, Morihiko
[J]. IEICE ELECTRONICS EXPRESS, 2005, 2 (09): : 316 - 320
[13] Adaptive and self-confident on-line learning algorithms
Auer, P
Cesa-Bianchi, N
Gentile, C
[J]. JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 2002, 64 (01) : 48 - 75
[14] Natural gradient blind deconvolution and equalization using causal FIR filters
Douglas, SC
Sawada, HO
Makino, S
[J]. CONFERENCE RECORD OF THE THIRTY-SEVENTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1 AND 2, 2003, : 197 - 201
[15] On-line adaptive algorithms for blind equalization of multi-channel systems
Cichocki, A
Cao, JT
Sabala, I
[J]. PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 649 - 652
[16] Adaptive natural gradient learning algorithms for various stochastic models
Park, H
Amari, SI
Fukumizu, K
[J]. NEURAL NETWORKS, 2000, 13 (07) : 755 - 764
[17] Adaptive Natural Gradient Learning Algorithms for Unnormalized Statistical Models
Karakida, Ryo
Okada, Masato
Amari, Shun-ichi
[J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT I, 2016, 9886 : 427 - 434
[18] On-line gradient learning algorithms for k-nearest neighbor classifiers
Bermejo, S
Cabestany, J
[J]. FOUNDATIONS AND TOOLS FOR NEURAL MODELING, PROCEEDINGS, VOL I, 1999, 1606 : 546 - 555
[19] Signal-flow-graph derivation of on-line gradient learning algorithms
Campolucci, P
Marchegiani, A
Uncini, A
Piazza, F
[J]. 1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 1884 - 1889
[20] Non-blind image deconvolution using natural image gradient prior
Tao, Shuyin
Dong, Wende
Feng, Huajun
Xu, Zhihai
Li, Qi
[J]. OPTIK, 2013, 124 (24): : 6599 - 6605

← 1 2 3 4 5 →