An improved learning algorithm of RBF networks

In this paper the systematic analysis and research has been made to the various learning methods of RBFNN (Radial Basis Function Neural Network). The clustering method is introduced to RBFNN. Some main methods are combined to enhance the performance in some degree. Then the improved GLVQ center learning method is put forward on the basis of ERPCL and GLVQ. Finally the GLVQ-RGLS method is the union of the above two methods. Simulation results show that the method has a good learning performance.