Title :
Sign-sign LMS convergence with independent stochastic inputs
Author :
Dasgupta, Soura ; Johnson, Richard C., Jr. ; Baksho, Maylar A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Iowa Univ., Iowa City, IA, USA
fDate :
1/1/1990 12:00:00 AM
Abstract :
The sign-sign adaptive least-mean-square (LMS) identifier filter is a computationally efficient variant of the LMS identifier filter. It involves the introduction of signum functions in the traditional LMS update term. Consideration is given to global convergence of parameter estimates offered by this algorithm, to a ball with radius proportional to the algorithm step size for white input sequences, specially from Gaussian and uniform distributions
Keywords :
adaptive filters; convergence of numerical methods; filtering and prediction theory; least squares approximations; parameter estimation; stochastic processes; Gaussian distribution; LMS identifier filter; adaptive least mean square filter; algorithm step size; global convergence; independent stochastic inputs; parameter estimation; sign-sign identifier; uniform distributions; white input sequences; Adaptive filters; Convergence; Filtering algorithms; Image reconstruction; Least squares approximation; Parameter estimation; Pattern recognition; Robustness; Signal processing algorithms; Stochastic processes;
Journal_Title :
Information Theory, IEEE Transactions on
