A smoothing algorithm with momentum for training the max-min fuzzy neural networks is constructed to speed up the learning process in this paper. Specifically, we apply a smooth function to approximate max-min functions and use all partial derivatives of the smooth approximation function with respect to weight to substitute those of the actual network output. Then, the smoothing algorithm with momentum is constructed by the gradient descent method. Finally, two numerical examples are provided to show the effectiveness of this algorithm for training max-min fuzzy neural networks by comparing wi...
