Designing Neural Network Ensembles by Minimizing Mutual Information
Yong Liu (The University of Aizu, Japan), Xin Yao (The University of Birmingham, UK) and Tetsuya Higuchi (National Institute of Advanced Industrial Science and Technology, Japan)
Copyright: © 2003
This chapter describes negative correlation learning for designing neural network ensembles. Negative correlation learning has been firstly analysed in terms of minimising mutual information on a regression task. By minimising the mutual information between variables extracted by two neural networks, they are forced to convey different information about some features of their input. Based on the decision boundaries and correct response sets, negative correlation learning has been further studied on two pattern classification problems. The purpose of examining the decision boundaries and the correct response sets is not only to illustrate the learning behavior of negative correlation learning, but also to cast light on how to design more effective neural network ensembles. The experimental results showed the decision boundary of the trained neural network ensemble by negative correlation learning is almost as good as the optimum decision boundary.