Title :
On the optimum step size for the adaptive sign and LMS algorithms
Author :
Chen, Rong-Yih ; Wang, Chin-Liang
Author_Institution :
Inst. of Electr. Eng., Nat. Tsing Hua Univ., Taiwan
fDate :
6/1/1990 12:00:00 AM
Abstract :
A derivation is presented of the optimum step size to yield the most rapid convergence under a desired mean-square error (MSE) for adaptive finite impulse response digital filters equipped with the sign algorithm or the least-mean-square (LMS) algorithm. For white input data, the optimum step size is a simple closed-form function of the number of filter taps, the input signal variance, the initial MSE, and the desired MSE. This characteristic makes it easily designed in many practical applications. Computer simulations are employed to show the correctness and effectiveness of the derived results
Keywords :
adaptive filters; circuit CAD; digital filters; digital simulation; least squares approximations; LMS algorithms; adaptive finite impulse response digital filters; adaptive sign; computer simulation; filter taps; least mean square algorithm; mean-square error; optimum step size; white input data; Adaptive filters; Application software; Computer simulation; Convergence; Digital filters; Echo cancellers; Filtering algorithms; Finite impulse response filter; Information filtering; Least squares approximation;
Journal_Title :
Circuits and Systems, IEEE Transactions on
