A comparative study of statistical ensemble methods on mismatch conditions

Author

Luo, Dingsheng ; Chen, Ke

Author_Institution

Nat. Lab. on Machine Perception, Peking Univ., Beijing, China

Volume

1

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

59

Lastpage

64

Abstract

Unlike previous comparative studies, we present an empirical evaluation on three typical statistical ensemble methods - boosting, bagging and combination of weak perceptrons - in terms of speaker identification where miscellaneous mismatch conditions are involved. During creating an ensemble, moreover, different combination strategies are also investigated. As a result, our studies present their generalization capabilities on mismatch conditions, which provides an alternative insight to understand those methods

Keywords

generalisation (artificial intelligence); pattern classification; perceptrons; speaker recognition; statistical analysis; vector quantisation; generalization; mismatch conditions; pattern classification; speaker identification; statistical ensemble; vector quantization; weak perceptrons; Aging; Bagging; Boosting; Computer science; Databases; Information science; Laboratories; Learning systems; Mood; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1005442

Filename

1005442