Collaborative adaptive learning using hybrid filters

D. Mandic; P. Vayanos; C. Boukis; B. Jelfs; S. L. Goh; T. Gautama; T. Rutkowski

doi:10.1109/ICASSP.2007.366831

Collaborative adaptive learning using hybrid filters

D. Mandic^*, P. Vayanos, C. Boukis, B. Jelfs, S. L. Goh, T. Gautama, T. Rutkowski

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

30 Citations (Scopus)

Abstract

A novel stable and robust algorithm for training of finite impulse response adaptive filters is proposed. This is achieved based on a convex combination of the Least Mean Square (LMS) and a recently proposed Generalised Normalised Gradient Descent (GNGD) algorithm. In this way, the desirable fast convergence and stability of GNGD is combined with the robustness and small steady state misadjustment of LMS. Simulations on linear and nonlinear signals in the prediction setting support the analysis.

Original language	English
Title of host publication	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Pages	III921-III924
DOIs	https://doi.org/10.1109/ICASSP.2007.366831
Publication status	Published - 2007
Externally published	Yes

Keywords

Adaptive
Collaborative SP
Distributed

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2007.366831

Cite this

@inproceedings{e155bd54965b4420b6120fcb769a64ee,

title = "Collaborative adaptive learning using hybrid filters",

abstract = "A novel stable and robust algorithm for training of finite impulse response adaptive filters is proposed. This is achieved based on a convex combination of the Least Mean Square (LMS) and a recently proposed Generalised Normalised Gradient Descent (GNGD) algorithm. In this way, the desirable fast convergence and stability of GNGD is combined with the robustness and small steady state misadjustment of LMS. Simulations on linear and nonlinear signals in the prediction setting support the analysis.",

keywords = "Adaptive, Collaborative SP, Distributed",

author = "D. Mandic and P. Vayanos and C. Boukis and B. Jelfs and Goh, {S. L.} and T. Gautama and T. Rutkowski",

year = "2007",

doi = "10.1109/ICASSP.2007.366831",

language = "English",

isbn = "1424407281",

pages = "III921--III924",

booktitle = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07",

}

TY - GEN

T1 - Collaborative adaptive learning using hybrid filters

AU - Mandic, D.

AU - Vayanos, P.

AU - Boukis, C.

AU - Jelfs, B.

AU - Goh, S. L.

AU - Gautama, T.

AU - Rutkowski, T.

PY - 2007

Y1 - 2007

N2 - A novel stable and robust algorithm for training of finite impulse response adaptive filters is proposed. This is achieved based on a convex combination of the Least Mean Square (LMS) and a recently proposed Generalised Normalised Gradient Descent (GNGD) algorithm. In this way, the desirable fast convergence and stability of GNGD is combined with the robustness and small steady state misadjustment of LMS. Simulations on linear and nonlinear signals in the prediction setting support the analysis.

AB - A novel stable and robust algorithm for training of finite impulse response adaptive filters is proposed. This is achieved based on a convex combination of the Least Mean Square (LMS) and a recently proposed Generalised Normalised Gradient Descent (GNGD) algorithm. In this way, the desirable fast convergence and stability of GNGD is combined with the robustness and small steady state misadjustment of LMS. Simulations on linear and nonlinear signals in the prediction setting support the analysis.

KW - Adaptive

KW - Collaborative SP

KW - Distributed

UR - http://www.scopus.com/inward/record.url?scp=34547498123&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2007.366831

DO - 10.1109/ICASSP.2007.366831

M3 - Conference contribution

AN - SCOPUS:34547498123

SN - 1424407281

SN - 9781424407286

SP - III921-III924

BT - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07

ER -

Collaborative adaptive learning using hybrid filters

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this