In this paper a comparison is carried out in order between fuzzy logic controller and adaptive neuro-fuzzy controller. We make use of these two control systems to regulate the temperature of the water bath system. We see that the Fuzzy controller is designed to work with knowledge in the form of linguistic control rules. But the translation of these linguistic rules into the framework of fuzzy set theory depends on the choice of certain parameters, for which no formal method is known. So the training of these parameters can be carried out by neural networks, which are designed to learn from training data, but which are in general not able to profit from structural knowledge. Thus combining fuzzy controllers and neural networks. The structure of the controller is based on the gradient error back propagation function (BPF) and least square error (LSE), neural network with Gaussian membership functions. We conclude that the proposed adaptive neurofuzzy controller is better than fuzzy controller.