Regional Models for Nonlinear System Identification Using the Self-Organizing Map
Global modelling is a common approach to the problem of learning nonlinear dynamical input-output mappings. It consists in training a single multilayer neural network model using the whole dataset. On the other side of the spectrum stands the local modelling approach, in which the input space is divided into very small partitions and simpler (e.g. linear) models are trained, one per partition. In this paper, we propose a novel approach, called Regional Models (RM), that stands in between the global and local modelling ones. By following the approach by Vesanto and Alhoniemi , we first partition the input-output space using the Self-Organizing map (SOM), and then perform clustering over the prototypes of the trained SOM in order to find clusters of prototypes. Finally, a regional model is built for each cluster using the data vectors mapped to that cluster. The proposed approach is evaluated on two benchmarking problems and its performance is compared to those achieved by standard global and local models.
KeywordsRegional Model Extreme Learn Machine Hide Neuron Extreme Learn Machine Model Extreme Learn Machine Network
Unable to display preview. Download preview PDF.
- 4.Cho, J., Principe, J., Erdogmus, D., Motter, M.: Quasi-sliding mode control strategy based on multiple linear models. Neurocomputing 70(4-6), 962–974 (2007)Google Scholar
- 8.Norgaard, M., Ravn, O., Poulsen, N.K., Hansen, L.K.: Neural Networks for Modelling and Control of Dynamic Systems. Springer (2000)Google Scholar
- 12.Walter, J., Ritter, H., Schulten, K.: Non-linear prediction with self-organizing map. In: Proceedings of the IEEE International Joint Conference on Neural Networks, IJCNN 1990, vol. 1, pp. 587–592 (1990)Google Scholar