Hierarchical radial basis function networks

Okan K. Ersoy and D. Hong have constructed a new neural network architecture called the parallel, self-organizing, hierarchical neural network (PSHNN) [1,2] that contains of a number of stage neural networks. In their papers, the stage networks are one-layer networks with delta rule learning. They report the result by using PSHNN in solving some classification problems, but how effective it is compared with other methods was not reported. In this paper we will construct a hierarchical network where stage networks are Radial Basis Function Networks (HRBFN) and using the nearest neighbor method as decision rule in stead of the approximation method used in Ersoy's papers. As applications, we will use our method to solve the medical diagnosis problems and some other difficult classification problems. While PSHNN is very sensitive to the number of iterations using in each stage network to train the network, it seems that our HRBFN does not depend on the number of centers for the starting stage network.