Channel Equalization and the Bayes Point Machine
Harrington, Edward; Kivinen, Jyrki; Williamson, Robert
Description
Equalizers trained with a large margin have an ability to better handle noise in unseen data and drift in the target solution. We present a method of approximating the Bayes optimal strategy which provides a large margin equalizer, the Bayes point equalizer. The method we use to estimate the Bayes point is to average N equalizers that are run on independently chosen subsets of the data. To better estimate the Bayes point we investigated two methods to create diversity amongst the N equalizers....[Show more]
dc.contributor.author | Harrington, Edward | |
---|---|---|
dc.contributor.author | Kivinen, Jyrki | |
dc.contributor.author | Williamson, Robert | |
dc.coverage.spatial | Hong Kong China | |
dc.date.accessioned | 2015-12-13T23:07:11Z | |
dc.date.available | 2015-12-13T23:07:11Z | |
dc.date.created | April 1 2003 | |
dc.identifier.isbn | 0780376633 | |
dc.identifier.uri | http://hdl.handle.net/1885/86097 | |
dc.description.abstract | Equalizers trained with a large margin have an ability to better handle noise in unseen data and drift in the target solution. We present a method of approximating the Bayes optimal strategy which provides a large margin equalizer, the Bayes point equalizer. The method we use to estimate the Bayes point is to average N equalizers that are run on independently chosen subsets of the data. To better estimate the Bayes point we investigated two methods to create diversity amongst the N equalizers. We show experimentally that the Bayes point equalizer for appropriately large step sizes offers improvement on LMS and LMA in the presence of channel noise and training sequence errors. This allows for shorter training sequences albeit with higher computational requirements. | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE Inc) | |
dc.relation.ispartofseries | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2003) | |
dc.source | Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2003 Volume IV | |
dc.subject | Keywords: Bayes point machines (BPM); Gaussian noise (electronic); Gradient methods; Least squares approximations; Monte Carlo methods; Probability distributions; Random processes; Signal to noise ratio; White noise; Equalizers | |
dc.title | Channel Equalization and the Bayes Point Machine | |
dc.type | Conference paper | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
dc.date.issued | 2003 | |
local.identifier.absfor | 090609 - Signal Processing | |
local.identifier.ariespublication | MigratedxPub14840 | |
local.type.status | Published Version | |
local.contributor.affiliation | Harrington, Edward, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Kivinen, Jyrki, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Williamson, Robert, College of Engineering and Computer Science, ANU | |
local.bibliographicCitation.startpage | 493 | |
local.bibliographicCitation.lastpage | 496 | |
dc.date.updated | 2015-12-12T08:08:13Z | |
local.identifier.scopusID | 2-s2.0-0141521780 | |
Collections | ANU Research Publications |
Download
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator