Online adaptive policies for ensemble classifiers

被引:18
作者
Dimitrakakis, C [1 ]
Bengio, S [1 ]
机构
[1] IDIAP, CH-1920 Martigny, Switzerland
关键词
neural networks; supervised learning; reinforcement learning; ensembles; mixture of experts; boosting; Q-learning;
D O I
10.1016/j.neucom.2004.11.031
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Ensemble algorithms can improve the performance of a given learning algorithm through the combination of multiple base classifiers into an ensemble. In this paper, we attempt to train and combine the base classifiers using an adaptive policy. This policy is learnt through a Q-learning inspired technique. Its effectiveness for an essentially supervised task is demonstrated by experimental results on several UCI benchmark databases. (c) 2005 Elsevier B.V. All rights reserved.
引用
收藏
页码:211 / 221
页数:11
相关论文
共 16 条
[1]  
ANDERSON C, 1994, REINFORCEMENT LEARNI
[2]  
[Anonymous], 2000, P 17 INT C MACHINE L
[3]  
Blake C.L., 1998, UCI repository of machine learning databases
[4]   Bagging predictors [J].
Breiman, L .
MACHINE LEARNING, 1996, 24 (02) :123-140
[5]  
Breiman L., 1997, Berkeley Statistics, V26, P1683
[6]  
Dimitrakakis C., 2004, 12 EUR S ART NEUR NE
[7]  
DIMITRI JNT, 1996, NEURO DYNAMIC PROGRA
[8]   A decision-theoretic generalization of on-line learning and an application to boosting [J].
Freund, Y ;
Schapire, RE .
JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 1997, 55 (01) :119-139
[9]   Adaptive Mixtures of Local Experts [J].
Jacobs, Robert A. ;
Jordan, Michael I. ;
Nowlan, Steven J. ;
Hinton, Geoffrey E. .
NEURAL COMPUTATION, 1991, 3 (01) :79-87
[10]   HIERARCHICAL MIXTURES OF EXPERTS AND THE EM ALGORITHM [J].
JORDAN, MI ;
JACOBS, RA .
NEURAL COMPUTATION, 1994, 6 (02) :181-214