Input Variable Selection Using Parallel Processing of RBF Neural Networks

In this paper we propose a new technique focused on the selection of the important input variable for modelling complex systems of function approximation problems, in order to avoid the exponential increase in the complexity of the system that is usual when dealing with many input variables. The proposed parallel processing approach is composed of complete radial basis function neural networks that are in charge of a reduced set of input variables depending in the general behaviour of the problem. For the optimization of the parameters of each radial basis function neural networks in the system, we propose a new method to select the more important input variables which is capable of deciding which of the chosen variables go alone or together to each radial basis function neural networks to build the parallel structure, thus reducing the dimension of the input variable space for each radial basis function neural networks. We also provide an algorithm which automatically finds the most suitable topology of the proposed parallel processing structure and selects the more important input variables for it. Therefore, our goal is to find the most suitable of the proposed families of parallel processing architectures in order to approximate a system from which a set of input/output. So that the proposed parallel processing structure outperforms other algorithms not only with respect to the final approximation error but also with respect to the number of computation parameters of the system.