On Hadamard-Type Output Coding in Multiclass Learning

Aijun Zhang*, Zhi Li Wu, Chun Hung Li, Kai Tai Fang

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

12 Citations (Scopus)

Abstract

The error-correcting output coding (ECOC) method reduces the multiclass learning problem into a series of binary classifiers. In this paper, we consider the dense ECOC methods, combining an economical number of base learners. Under the criteria of row separation and column diversity, we suggest the use of Hadamard matrices to design output codes and show them better than other codes of the same size. Comparative experiments based on the support vector machines are made for some real datasets from the UCI machine learning repository.

Original languageEnglish
Title of host publicationIntelligent Data Engineering and Automated Learning
Subtitle of host publication4th International Conference, IDEAL 2003 Hong Kong, China, March 21–23, 2003 Revised Papers
EditorsJiming Liu, Yiu-ming Cheung, Hujun Yin
Place of PublicationBerlin, Heidelberg
PublisherSpringer
Pages397-404
Number of pages8
Edition1st
ISBN (Electronic)9783540450801
ISBN (Print)9783540405504
DOIs
Publication statusPublished - 29 Jul 2003
Event4th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2003 - , Hong Kong
Duration: 21 Mar 200323 Mar 2003
https://link.springer.com/book/10.1007/b11717

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume2690
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameIDEAL: International Conference on Intelligent Data Engineering and Automated Learning

Conference

Conference4th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2003
Country/TerritoryHong Kong
Period21/03/0323/03/03
Internet address

Scopus Subject Areas

  • Theoretical Computer Science
  • Computer Science(all)

User-Defined Keywords

  • Error-correcting output codes
  • Hadamard matrix
  • Multiclass learning
  • Support vector machines

Fingerprint

Dive into the research topics of 'On Hadamard-Type Output Coding in Multiclass Learning'. Together they form a unique fingerprint.

Cite this