In this paper, a physiological fuzzy neural network is proposed, which shows more improved learning time and convergence property than that of the conventional fuzzy neural network. First, we investigate the structure of physiological neurons of the nervous system and propose new neuron structure based on fuzzy logic. And by using the proposed fuzzy neuron structures, the model and learning algorithm of physiological fuzzy neural network are proposed. We applied the proposed algorithm to 3-bit parity problem. The experiment results showed that the proposed algorithm reduces the possibility of local minima more than the conventional single layer perceptron does, and improves the time and convergence for learning.