Title :
Conjugate gradient techniques for adaptive filtering
Author :
Boray, G.K. ; Srinath, M.D.
Author_Institution :
Bell Northern Res., Richardson, TX, USA
Abstract :
The technique of conjugate gradients is applied to the adaptive filtering problem. The method provides convergence comparable to that of RLS (recursive-least-squares) schemes and has a computational requirement that is intermediate between the LMS (least-mean-square) and the RLS methods. It does not suffer from any known stability problems.<>
Keywords :
adaptive filters; convergence of numerical methods; filtering and prediction theory; adaptive filtering; conjugate gradients; convergence; stability; Adaptive filters; Approximation methods; Gradient methods; Iterative methods; Symmetric matrices; Vectors;
Conference_Titel :
Circuits and Systems, 1989., IEEE International Symposium on
Conference_Location :
Portland, OR, USA
DOI :
10.1109/ISCAS.1989.100705
