For the nonlinearity of neural network with same activation functions in all the hidden nodes is limited, this paper presents a fuzzy-tuned neural network, which is trained by genetic algorithm (GA). The fuzzy-tuned neural network consists of a neural-fuzzy network and a feed-forward neural network. The neural-fuzzy network modifies some of the parameters of the three-layer feed-forward neuron network. All the connecting weighting coefficients and some parameters of the fuzzy-tuned neural network are trained by GA, thus increasing nonlinearity of the network. Simulation shows that the proposed fuzzy-tuned neural network can increase the degree of freedom of the network function.