Multilayer nonnegative matrix factorisation

被引：99

作者：

Cichocki, A. ^{[1
]}

Zdunek, R. ^{[1
]}

机构：

[1] RIKEN, BSI, Lab Adv Brain Signal Proc, Wako, Saitama 3510198, Japan

来源：

ELECTRONICS LETTERS | 2006年 / 42卷 / 16期

关键词：

D O I：

10.1049/el:20060983

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A multilayer approach to nonnegative matrix factorisation algorithms is proposed. It considerably improves their performance; especially if a problem is ill-conditioned, or data are badly scaled, and projected gradient algorithms are used. This is fully confirmed by extensive simulations with diverse types of data in application to blind source separation.

引用

页码：947 / 948

页数：2