CART/CMAC hybrid: regression trees with interpolation

This paper presents a new algorithm for non-linear regression. It involves combining a modified regression tree with a CMAC network in a way which retains the most desirable properties of both these algorithms. The new algorithm is compared with a conventional regression tree as described in the CART book (Breiman et al., 1984). It consistently performs better on the Boston Housing Data task. The CMAC consists of a fixed non-linear mapping followed by a single layer of adaptive links. The non-linear mapping has uniform sensitivity across the whole of the input space. The essence of the new hybrid algorithm is to use a regression tree to produce a more efficient design for the CMAC non-linear mapping