Optical EngineeringMultilayer neural network with a fuzzy controlled learning method for optical pattern training
|Format||Member Price||Non-Member Price|
A fast learning method for neural networks learning system using fuzzy controlling is proposed. By the fuzzy controlled theory, the learning rate and the nonlinear gain of the output function in the back- propagation algorithm are adjusted based on training error and training time. The effectiveness of this learning method is demonstrated in optical pattern training.