Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
A UNIFYING VIEW OF ERROR NONLINEARITIES IN LMS Ta.req Y. Al-Na.ffouri Azzedine Zerguine Ma.a.mar Bettayeb
 

Summary: A UNIFYING VIEW OF ERROR NONLINEARITIES IN LMS
ADAPTATION
Ta.req Y. Al-Na.ffouri Azzedine Zerguine Ma.a.mar Bettayeb
School of Eiectrica.1 & Computer Eng. Dept. of Physics Dept. of Electrical Eng.
Georgia~Institute of Technology KFUPM KFUPM
Atlanta., Ga.30332 Dha.hran 31261 Dha,hra.n 31261
E-mail: gte69662prism.gakech.edu Saudi Ara.bia. Saudi Arabia.
Abstract
This paper presents a unifying view of various
error nonlinearities that are used in least mean
square (LMS) adaptation such as the least mean
fourth (LMF) algorithm and its family and the
least-mean mixed-norm algorithm. Specifically,
it is shown that the LMS algorithm and its error-
modified variants are approximations of two re-
cently developed optimum nonlinearities which
are expressed in terms of the additive noise prob-
ability density function (pdf). This is demon-
strated through an approximation of the opti-
mum nonlinearities by expanding the noise pdf

  

Source: Al-Naffouri, Tareq Y. - Electrical Engineering Department, King Fahd University of Petroleum and Minerals

 

Collections: Engineering