Neural blind separation of complex sources by extended Hebbian learning (EGHA)

Author

Fiori, Simone ; Piazza, Francesco

Author_Institution

Dipt. di Elettronica e Autom., Ancona Univ., Italy

Volume

5

fYear

1999

fDate

1999

Firstpage

339

Abstract

The aim of this paper is to present a nonlinear extension to Sanger´s generalized Hebbian learning rule for complex-valued data neural processing. A possible choice of the involved nonlinearity is discussed recalling the Sudjianto-Hassoun interpretation of the nonlinear Hebbian learning. Extension of this interpretation to the complex case leads to a nonlinearity called Rayleigh function, which allows for separation of mixed independent complex-valued source signals

Keywords

Hebbian learning; adaptive signal detection; neural nets; principal component analysis; signal sources; Rayleigh function; Sanger´s generalized Hebbian learning rule; Sudjianto-Hassoun interpretation; complex sources; complex-valued data neural processing; extended Hebbian learning; mixed independent complex-valued source signals; neural blind separation; nonlinear extension; Blind source separation; Equations; Hebbian theory; Lagrangian functions; Neural networks; Neurons; Principal component analysis; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-5471-0

Type

conf

DOI

10.1109/ISCAS.1999.777578

Filename

777578