Radial Basis Function Network in Reproducing Kernel Hilbert Space with Application to System Identification

This paper presents two novel radial basis functions and their comparison. Both radial basis functions are based on an idea of 8upport Vector Machine (8VM) by mapping data into a high dimensional feature space, which is known as Reproducing Kernel Hilbert 8pace and then performing Radial Basis Function (RBF) network in the feature space. Orthogonal Least 8quares (OL8) method is employed to select a suitable set of centers (regressors) from a large set of candidates in order to obtain a sparse regression model in the feature space. The proposed method is applied to a nonlinear system identification problem by simulations.