AN ONLINE TRAINING ALGORITHM FOR RBF NEURAL NETWORK AND ITS APPLICATION IN NONLINEAR CONTROL

A novel online training algorithm for RBF neural network is presented.Some problems related to the algorithm are discussed in detail.It is shown by simulations that the algorithm is very effective and can overcome the shortcomings existing in the so-called offline algorithm.Furthermore,the algorithm is used to train a RBF neural network so as to realize a control of the complex nonlinear system.The final result is excellent.