Dynamic self-organized learning for optimizing the complexity growth of radial basis function neural networks

This paper proposes a framework of automatically exploring the optimal size of a radial basis function (RBF) neural network. A dynamic self-organized learning algorithm is presented to adapt the structure of the network. The algorithm generates a new hidden unit based on the steady state error of network and the nearest distance from input data to the center of hidden unit. Furthermore, it also detects and removes any insignificant contributing hidden units. For optimizing the complexity growth of RBF neural network, the growing and pruning are combined during adaptation of RBF neural network structure. The examples of nonlinear dynamical system modeling are presented to illustrate the performance of the proposed algorithm.