A global optimization method for continuous time adaptive recursive filters

Authors
Edmonson, W Palacios, JC Lai, CA Latchman, H
Citation
W. Edmonson et al., A global optimization method for continuous time adaptive recursive filters, IEEE SIG PL, 6(8), 1999, pp. 199-201
Citations number
3
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
IEEE SIGNAL PROCESSING LETTERS
ISSN journal
10709908 → ACNP
Volume
6
Issue
8
Year of publication
1999
Pages
199 - 201
Database
ISI
SICI code
1070-9908(199908)6:8<199:AGOMFC>2.0.ZU;2-A
Abstract
A major drawback of recursive adaptive filters based on gradient methods is that convergence to global minimum is not always achieved. This is due to a nonconvex mean square error (MSE) performance surface. This letter develo ps a continuous-time least mean square algorithm that converges to the glob al minimum with probability one.