Title :
Optimal convergence factor for the LMS/Newton algorithm
Author :
Diniz, Paulo S R ; Biscainho, Luiz W P
Author_Institution :
Federal Univ., Rio de Janeiro, Brazil
Abstract :
An efficient approach for the computation of the optimum convergence factor for the LMS (least mean square)/Newton algorithm applied to a transversal FIR structure is proposed. The approach leads to a variable step size algorithm that results in a dramatic reduction in convergence time. The algorithm is evaluated in systems identification applications
Keywords :
convergence of numerical methods; digital filters; filtering and prediction theory; identification; least squares approximations; signal processing; LMS/Newton algorithm; convergence time; optimum convergence factor; systems identification; transversal FIR structure; Adaptive filters; Autocorrelation; Convergence; Eigenvalues and eigenfunctions; Finite impulse response filter; IIR filters; Least squares approximation; Statistics; System identification; Transversal filters;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7803-0003-3
DOI :
10.1109/ICASSP.1991.150256
