A deflationary super-exponential method for solving independent component analysis with additive Gaussian noise

被引：0

作者：

Kawamoto, M

Ito, M

Ohata, M

Inouye, Y

机构：

[1] Shimane Univ, Dept Elect & Control Syst Engn, Matsue, Shimane 6908504, Japan

[2] Nagoya Univ, Nagoya, Aichi, Japan

来源：

BRAIN-INSPIRED IT I | 2004年 / 1269卷

关键词：

independent component analysis (ICA); super-exponential method; deflationary approach; Gaussian noise;

D O I：

10.1016/j.ics.2004.05.162

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a new method for solving independent component analysis (ICA) with additive Gaussian noise. One of the properties of our proposed method is to use only higher-order cumulants of observations. (C) 2004 Elsevier B.V. All rights reserved.

引用

页码：157 / 160

页数：4

共 4 条

[1] Super-exponential algorithms for multichannel blind deconvolution [J].