Linear Regression Model-Guided Clustering for Training RBF Networks for Regression Problems

@inproceedings{Staiano2003LinearRM,
  title={Linear Regression Model-Guided Clustering for Training RBF Networks for Regression Problems},
  author={Antonino Staiano and Roberto Tagliaferri and Witold Pedrycz},
  booktitle={WILF},
  year={2003}
}
In this paper, we describe a novel approach to fuzzy cluster-ing which organizes the data in clusters on the basis of the input data and builds a 'prototype' regression function as a summation of linear local regression models to guide the clustering process. This methodology is shown to be effective in the training of RBFNN's. It is shown that the performance of such networks is better than other types of networks. 

Topics from this paper.