Generate Different Neural Networks by Negative Correlation Learning

• Published in: Advances in Natural Computation pp. 149 - 156
• Main Author: Liu, Yong
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Exact sciences and technology; Individual Network; Negative Correlation Learning; Neural Network; Neural Network Ensemble; Simple Average; Classification; Cross correlation; Replacement; Cross validation; Neural network; Distributed system; Aggregate model
• ISBN: 3540283234; 9783540283232
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11539087_17

This paper describes two methods on how to generate different neural networks in an ensemble. One is based on negative correlation learning. The other is based on cross-validation with negative correlation learning, i.e., bagging with negative correlation learning. In negative correlation learning, all individual networks are trained simultaneously on the same training set. In bagging with negative correlation learning, different individual networks are trained on the different sampled data set with replacement from the training set. The performance and correct response sets are compared between two learning methods. The purpose of this paper is to find how to design more effective neural network ensembles.