Skip to Main Content
Different methods for combining multiple neural networks in order to improve model long range prediction performance are compared in this paper. It is shown that combining multiple non-perfect neural networks can improve model predictions, especially long range predictions. Among the different approaches, the principal component regression based approaches generally give very good performance. Selective combination is also very beneficial to the improvement of model predictions.
Control Applications, 2002. Proceedings of the 2002 International Conference on (Volume:2 )
Date of Conference: 2002