Adaptive differential decorrelation: A natural gradient algorithm
SCIE
SCOPUS
- Title
- Adaptive differential decorrelation: A natural gradient algorithm
- Authors
- Choi, SJ
- Date Issued
- 2002-01
- Publisher
- SPRINGER-VERLAG BERLIN
- Abstract
- In this paper, I introduce a concept of differential decorrelation which finds a linear mapping that minimizes the concurrent change of variables. Motivated by the differential anti-Hebbian rule [1], I develop a natural gradient algorithm for differential decorrelation and present its local stability analysis. The algorithm is successfully applied to the task of nonstationary source separation.
- Keywords
- LEARNING ALGORITHMS; SOURCE SEPARATION; NONSTATIONARY
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/18649
- DOI
- 10.1007/3-540-46084-5_189
- ISSN
- 0302-9743
- Article Type
- Article
- Citation
- LECTURE NOTES IN COMPUTER SCIENCE, vol. 2415, page. 1168 - 1173, 2002-01
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.