Cooperative Coevolutionary Ensemble Learning

Abstract. A new optimization technique is proposed for classifiers fusion — Cooperative Coevolutionary Ensemble Learning (CCEL). It is based on a specific multipopulational evolutionary algorithm — cooperative coevolution. It can be used as a wrapper over any kind of weak algorithms, learning procedures and fusion functions, for both classification and regression tasks. Experiments on the real-world problems from the UCI repository show that CCEL has a fairly high generalization performance and generates ensembles of much smaller size than boosting, bagging and random subspace method.

• Type: Conference
• Year: 2007
• Where: MCS
• Authors: Daniel Kanevskiy, Konstantin Vorontsov
• Keywords: Cooperative Coevolutionary Ensemble, MCS 2007, Multipopulational Evolutionary Algorithm, Pattern Recognition, Random Subspace Method