Sequential growing and pruning of radial basis function network

Abstract

In this paper, we propose an algorithm for sequential structure adaptation of Radial Basis Function (RBF) network. Our main goal is to obtain the model of the unknown time varying nonlinear mapping. Both parameter and structure adaptation are incorporated into the framework of extended Kalman filter. Two approaches: construction (growing) and pruning are combined during adaptation of RBF network structure. The examples of nonstationary nonlinear dynamical system modeling are presented to illustrate the proposed algorithm.