Quantized, piecewise linear filter network

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

285 Downloads (Pure)

Abstract

A quantization based piecewise linear filter network is defined. A method for the training of this network based on local approximation in the input space is devised. The training is carried out by repeatedly alternating between vector quantization of the training set into quantization classes and equalization of the quantization classes linear filter mean square training errors. The equalization of the mean square training errors is carried out by adapting the boundaries between neighbor quantization classes such that the differences in mean square training errors are reduced
Original languageEnglish
Title of host publicationProceedings of the IEEE-SP Workshop Neural Networks for Signal Processing
PublisherIEEE
Publication date1993
Pages470-474
ISBN (Print)07-80-30928-6
DOIs
Publication statusPublished - 1993
Event1993 IEEE-SP Workshop of Neural Networks for Signal Proceesing - Linthicum Heights, MD, United States
Duration: 6 Sep 19939 Sep 1993
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3312

Workshop

Workshop1993 IEEE-SP Workshop of Neural Networks for Signal Proceesing
Country/TerritoryUnited States
CityLinthicum Heights, MD
Period06/09/199309/09/1993
Internet address

Bibliographical note

Copyright 1993 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Fingerprint

Dive into the research topics of 'Quantized, piecewise linear filter network'. Together they form a unique fingerprint.

Cite this