Class-switching neural network ensembles

NEUROCOMPUTING

卷:71

Article

Martinez-Munoz, Gonzalo¹  Sanchez-Martinez, Aitor¹  Hernandez-Lobato, Daniel¹  Suarez, Alberto¹ 

[1] Univ Madrid, Dept Comp Sci, Escuela Politecn Super, E-28049 Madrid, Spain

关键词: ensembles of classifiers;    neural networks;    class-switching;    bagging;    boosting;    decision trees;   

DOI  :  10.1016/j.neucom.2007.11.041

来源: Elsevier

【 摘 要 】

This article investigates the properties of class-switching ensembles composed of neural networks and compares them to class-switching ensembles of decision trees and to standard ensemble learning methods, such as bagging and boosting. In a class-switching ensemble, each learner is constructed using a modified version of the training data. This modification consists in switching the class labels of a fraction of training examples that are selected at random from the original training set. Experiments on 20 benchmark classification problems, including real-world and synthetic data, show that class-switching ensembles composed of neural networks can obtain significant improvements in the generalization accuracy over single neural networks and bagging and boosting ensembles. Furthermore, it is possible to build medium-sized ensembles (approximate to 200 networks) whose classification performance is comparable to larger class-switching ensembles (approximate to 1000 learners) of unpruned decision trees. (C) 2008 Elsevier B.V. All rights reserved.

【 授权许可】

Free