An Improvement of the RAN Learning Algorithm

An improved learning algorithm for Resource Allocating Network (RAN) is presented in this paper,which is called IRAN algorithm.It allocates hidden neurons of network by a four-part novelty criterion,removes redundant neurons according to their error reduction rates,and updates output-layer weights by a recursive least-squares algorithm with Givens-QR decomposition. Simulations on two Benchmark problems in the function approximation area indicate that the IRAN algorithm can provide smaller networks and consume less training time than RAN, RANEKF and MRAN algorithms.