Measuring Diversity and Accuracy in ANN Ensembles

被引：1

作者：

Paz Sesmero, M. ^{[1
]}

Manuel Alonso-Weber, Juan ^{[1
]}

Giuliani, Alessandro ^{[2
]}

Armano, Giuliano ^{[2
]}

Sanchis, Araceli ^{[1
]}

机构：

[1] Univ Carlos III Madrid, Avd Univ 30, Madrid, Spain

[2] Univ Cagliari, Via Is Maglias 198, Cagliari, Italy

来源：

ADVANCES IN ARTIFICIAL INTELLIGENCE, CAEPIA 2018 | 2018年 / 11160卷

关键词：

Ensemble of classifiers; Diversity; Accuracy; ANN; CLASSIFICATION; ALGORITHM;

D O I：

10.1007/978-3-030-00374-6_11

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Performance of classifier ensembles depends on the precision and on the diversity of the members of the ensemble. In this paper we present an experimental study in which the relationship between the accuracy of the ensemble and both the diversity and the accuracy of base learners is analyzed. We conduct experiments on 8 different ANN ensembles and on 5 multiclass data sets. Experimental results show that a high diversity degree among the base learners does not always imply a high accuracy in the ensemble.

引用

页码：108 / 117

页数：10

共 24 条

[1] AN IMPROVED ALGORITHM FOR NEURAL-NETWORK CLASSIFICATION OF IMBALANCED TRAINING SETS [J].