Optimizing the performance of polynomial adaptive filters: making quadratic filters converge like linear filters

Author

Therrien, Charles W. ; Jenkins, W. Kenneth ; Li, Xiaohui

Author_Institution

Dept. of Electr. & Comput. Eng., Naval Postgraduate Sch., Monterey, CA, USA

Volume

47

Issue

4

fYear

1999

fDate

4/1/1999 12:00:00 AM

Firstpage

1169

Lastpage

1171

Abstract

The correlation properties of the input vector determine the rate of convergence of the LMS algorithm for Volterra adaptive filters and are optimal when the nonlinear input terms are uncorrelated. This correspondence presents new results on the correlation properties for second-order Volterra filters and shows that when the input signal is whitened, the nonlinear terms automatically become uncorrelated

Keywords

adaptive filters; adaptive signal processing; convergence of numerical methods; correlation methods; least mean squares methods; nonlinear filters; polynomials; LMS algorithm; Volterra adaptive filters; convergence rate; correlation properties; input vector; linear filters; nonlinear filter; nonlinear terms; performance optimisation; polynomial adaptive filters; quadratic filters; second-order Volterra filters; uncorrelated nonlinear input terms; whitened input signal; Adaptive filters; Convergence; Kernel; Least squares approximation; Nonlinear equations; Nonlinear filters; Polynomials; Vectors;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.752619

Filename

752619