Neural network adaptive control with fuzzy rules confirming initial weights
Ren Guiyong, Qu Yancheng, Wang Changhong · 2002
A method, based on fuzzy rules, is presented to learn the initial values of a neural network's weight array. This neural network is used in an adaptive control architecture. Using the prior knowledge efficiently, it can ensure the stability of the adaptive control during the learning period of the neural network. Simulation results demonstrate the feasibility of this method.