Presentation 1998/3/20
A Variable Step (VS) Algorithm for Blind Source Separation (BSS)
Pun Man On, Yuzo HIRAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Most of the existing algorithms in the blind source separation are confronted with the learning step-size problems. In this paper, we propose to break down the demixing matrix into row vector space. From the row vector viewpoint, a variable step (VS) algorithm for the blind source separation problem has been proposed. Instead of using a constant step-size, the VS learning algorithm adaptively changes the learning step-size of each row vector according to the convergence behaviors of its corresponding row vector. Out simulation results showed that the new VS learning algorithm outperforms the conventional algorithms.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Blind Source Separation(BSS) / row vector space / step-size / convergence
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1998/3/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Variable Step (VS) Algorithm for Blind Source Separation (BSS)
Sub Title (in English)
Keyword(1) Blind Source Separation(BSS)
Keyword(2) row vector space
Keyword(3) step-size
Keyword(4) convergence
1st Author's Name Pun Man On
1st Author's Affiliation Master Program of Science and Engineering, University of Tsukuba()
2nd Author's Name Yuzo HIRAI
2nd Author's Affiliation Institute of Information Sciences and Electronics, University of Tsukuba
Date 1998/3/20
Paper #
Volume (vol) vol.97
Number (no) 624
Page pp.pp.-
#Pages 8
Date of Issue