(Chan_05TNN_Fast Neural Network Ensemble Learning via Negat–)

Abstract

This letter proposes a new Negative Correlation (NC) learning method that is both easy to implement and has the advantages that (i) it requires much lesser communication overhead than the standard NC method; and (ii) it is applicable to ensembles of heterogenous networks.

3 Figures and Tables

Cite this paper

@inproceedings{Preprint2005Chan_05TNN_FastNN, title={(Chan_05TNN_Fast Neural Network Ensemble Learning via Negat–)}, author={KEDRI Preprint and Zeke S. H. Chan and Nik Kasabov}, year={2005} }