Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10361813 | Pattern Recognition Letters | 2005 | 8 Pages |
Abstract
Error-correcting output codes (ECOC) are used to design diverse classifier ensembles. Diversity within ECOC is traditionally measured by Hamming distance. Here we argue that this measure is insufficient for assessing the quality of code for the purposes of building accurate ensembles. We propose to use diversity measures from the literature on classifier ensembles and suggest an evolutionary algorithm to construct the code.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Ludmila I. Kuncheva,