Presentation 1999/6/18
Semiparametric Approach to Blind Deconvolution
Liqing Zhang, Andrzej Cichocki, Jianting Cao, Shun-ichi Amari,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper we discuss the semiparametric statistical model for blind deconvolution. First the blind deconvolution problem is formulated in the framework of a semiparametric model, and a family of estimating functions is derived for blind deconvolution. To improve learning efficiency of online algorithm, an explicit form of the standardized estimating function is given. Superefficiency of off-line learning and online learning is proven in this framework. The theory of semiparametric models for blind deconvolution shows that both the batch learning and the natural gradient learning converge to the true solution if certain nonsingular conditions are satisfied, needless to estimate the nuisance parameters, the probalility density functions of source signals.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Semiparametric model / Estimating function / Superefficiency / Blind deconvolution / Natural gradient / Independent component analysis
Paper # NC99-25
Date of Issue

Conference Information
Committee NC
Conference Date 1999/6/18(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Semiparametric Approach to Blind Deconvolution
Sub Title (in English)
Keyword(1) Semiparametric model
Keyword(2) Estimating function
Keyword(3) Superefficiency
Keyword(4) Blind deconvolution
Keyword(5) Natural gradient
Keyword(6) Independent component analysis
1st Author's Name Liqing Zhang
1st Author's Affiliation Brain-style Information Processing Group, BSI The Institute of Physical and Chemical Research (RIKEN)()
2nd Author's Name Andrzej Cichocki
2nd Author's Affiliation Brain-style Information Processing Group, BSI The Institute of Physical and Chemical Research (RIKEN)
3rd Author's Name Jianting Cao
3rd Author's Affiliation Department of Electrical and Electronics Engineering, Sophia University:Brain-style Information Processing Group, BSI The Institute of Physical and Chemical Research (RIKEN)
4th Author's Name Shun-ichi Amari
4th Author's Affiliation Brain-style Information Processing Group, BSI The Institute of Physical and Chemical Research (RIKEN)
Date 1999/6/18
Paper # NC99-25
Volume (vol) vol.99
Number (no) 131
Page pp.pp.-
#Pages 8
Date of Issue