Neural network ensemble based on rough sets reduction and selective strategy
Yaonan Wang, Dongbo Zhang, Huixian Huang · 2008
Based on rough sets reducts, a new neural network ensemble method is proposed. Reducts with robustness and good generalization ability are achieved by a dynamic reduction technology. Then according to different reducts, multiple BP neural networks are designed as base classifiers. And with the idea of selective ensemble, the best neural network ensemble can be found by some search strategies. Finally, by combining the predictions of component networks with voting rule, classification can be implemented. Compared with conventional ensemble feature selection algorithms, less time and lower computing complexity is needed of the method in this paper.