FUZZY CLUSTERING NETWORKS - DESIGN CRITERIA FOR APPROXIMATION AND PREDICTION

In previous papers the building of hierarchical networks made up of co mponents using fuzzy rules was presented. It was demonstrated that thi s approach could be used to construct networks to solve classification problems, and that in many cases these networks were computationally less expensive and performed at least as well as existing approaches b ased on feedforward neural networks. It has also been demonstrated how this approach could be extended to real-valued problems, such as func tion approximation and time series prediction. This paper investigates the problem of choosing the best network for real-valued approximatio n problems. Firstly, the nature of the network parameters, how they ar e interrelated, and how they affect the performance of the system are clarified. Then we address the problem of choosing the best values of these parameters. We present two model selection tools in this regard, the first using a simple statistical model of the network, and the se cond using structural information about the network components. The re sulting network selection methods are demonstrated and their performan ce tested on several benchmark and applied problems. The conclusions l ook at future research issues for further improving the performance of the clustering network.