On the optimal design of fuzzy neural networks with robust learning for function approximation

A novel robust learning algorithm for optimizing fuzzy neural networks is p roposed to address two important issues: how to reduce the nuttier effects and how to optimize fuzzy neural networks, in the function approximation. T his algorithm is able to reduce the outlier effects by cooperating with a c onventional robust approach, and then to optimize fuzzy neural networks by determining the optimal learning rates which can minimize the next-step mea n error at each iteration of our algorithm.