Serial updating rule for blind separation derived from the method of scoring

Author

Yang, Howard Hua

Author_Institution

Dept. of Electr. & Comput. Eng., Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA

Volume

47

Issue

8

fYear

1999

fDate

8/1/1999 12:00:00 AM

Firstpage

2279

Lastpage

2285

Abstract

In the context of blind source separation, the method of scoring based on the inverse of the Fisher information matrix (FIM) becomes the serial updating learning rule with an equivariant property. This learning rule can be simplified to a low-complexity algorithm by using the asymptotic form of the FTM around the equilibrium. The simplified learning rule is still general enough to include some existing equivariant blind separation algorithms as its special cases

Keywords

adaptive signal processing; computational complexity; information theory; learning systems; matrix inversion; asymptotic FIM; blind source separation; equilibrium; equivariant blind separation algorithms; inverse Fisher information matrix; low-complexity algorithm; method of scoring; serial updating learning rule; Adaptive signal detection; Algorithm design and analysis; Blind source separation; Data models; Gradient methods; Maximum likelihood estimation; Signal analysis; Signal processing algorithms; Space technology; Tensile stress;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.774771

Filename

774771