Improvement in stability and convergence speed on normalized LMS algorithm

Author

Fukumoto, Masahiro ; Kubota, Majime ; Tsujii, Shigeo

Author_Institution

Dept. of Electr. & Electron. Eng., Tokyo Inst. of Technol., Japan

Volume

2

fYear

1995

fDate

30 Apr-3 May 1995

Firstpage

1243

Abstract

The normalized LMS algorithm is widely used because of its simplicity. However, this algorithm behaves unstably when all elements of an input vector is very small. This property is caused by the division in the procedure of the normalized LMS algorithm. One of the modifications on this problem is taken that coefficients of the adaptive filter are not updated when a norm of an input vector is smaller than a threshold. This paper shows effects of interrupting adaptive filter´s coefficients update by the threshold derived from the error analysis. Also, it presents the guarantee value and the stochastic fastest convergence step gain

Keywords

adaptive filters; convergence of numerical methods; least mean squares methods; numerical stability; adaptive filter; coefficient update; convergence speed; error analysis; guarantee value; input vector; normalized LMS algorithm; stability; stochastic step gain; Adaptive filters; Convergence; Echo cancellers; Error analysis; Information systems; Large scale integration; Least squares approximation; Stability; Stochastic resonance; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1995. ISCAS '95., 1995 IEEE International Symposium on

Conference_Location

Seattle, WA

Print_ISBN

0-7803-2570-2

Type

conf

DOI

10.1109/ISCAS.1995.520370

Filename

520370