Kagan Tumer's Publications

Display Publications by [Year] [Type] [Topic]


Input Decimated Ensembles. K. Tumer and N. C. Oza. Pattern Analysis and Applications, 6(1):65–77, 2003.

Abstract

Using an ensemble of classifiers instead of a single classifier has been shown to improve generalization performance in many pattern recognition problems. However, the extent of such improvement depends greatly on the amount of correlation among the errors of the base classifiers. Therefore, reducing those correlations while keeping the classifiers' performance levels high is an important area of research. In this article, we explore input decimation (ID), a method which selects feature subsets for their ability to discriminate among the classes and uses these subsets to decouple the base classifiers. We provide a summary of the theoretical benefits of correlation reduction, along with results of our method on two underwater sonar data sets, three benchmarks from the Proben1/UCI repositories, and two synthetic data sets. The results indicate that input decimated ensembles outperform ensembles whose base classifiers use all the input features; randomly selected subsets of features; and features created using principal components analysis, on a wide range of domains.

Download

[PDF]321.5kB  

BibTeX Entry

@article{tumer-oza_paa03,
    	author={K. Tumer and N. C. Oza},
    	title={Input Decimated Ensembles},
    	journal={Pattern Analysis and Applications},
    	volume={6},
    	number={1},
    	pages={65-77},
	abstract={Using an ensemble of classifiers instead of a single classifier has been shown to improve generalization performance in many pattern recognition problems. However, the extent of such improvement depends greatly on the amount of correlation among the errors of the base classifiers. Therefore, reducing those correlations while keeping the classifiers' performance levels high is an important area of research.  In this article, we explore <b> input decimation </b> (ID), a method which selects feature subsets for their ability to discriminate among the classes and uses these subsets to decouple the base classifiers. We provide a summary of the theoretical benefits of correlation reduction, along with results of our method on two underwater sonar data sets, three benchmarks from the Proben1/UCI repositories, and two synthetic data sets. The results indicate that input decimated ensembles outperform ensembles whose base classifiers use all the input features; randomly selected subsets of features; and features created using principal components analysis, on a wide range of domains.},
	bib2html_pubtype = {Journal Articles},
	bib2html_rescat = {Classifier Ensembles},
    	year={2003}
}

Generated by bib2html.pl (written by Patrick Riley ) on Tue Jun 26, 2018 19:10:42