Enforcing negativity in negative correlation learning
Yong Liu · 2016
Two different implementations of negative correlation learning with λ > 1 are discussed in this paper. In the first implementation, every learner is forced to learn to be different to the ensemble on every data point no matter what have been learned by the ensemble and itself. In the second implementation, every learner is selectively to learn to be different to the ensemble on every data point. It is to hope that such selective learning could balance well between the learning accuracy and the low correlations among the ensemble. Experimental results were carried out to show how the correlation penalty should be enforced in order to achieve the better generalization.