Time Series Prediction by Using Negatively Correlated Neural Networks

Negatively correlated neural networks (NCNNs) have been proposed to design neural network (NN) ensembles [1]. The idea of NCNNs is to encourage different individual NNs in the ensemble to learn different parts or aspects of a training data so that the ensemble can learn the whole training data better. The cooperation and specialisation among different individual NNs are considered during the individual NN design. This provides an opportunity for different NNs to interact with each other and to specialise. In this paper, NCNNs are applied to two time series prediction problems (i.e., the Mackey-Glass differential equation and the chlorophyll-a prediction in Lake Kasumigaura). The experimental results show that NCNNs can produce NN ensembles with good generalisation ability.