Based on grey relational analysis, this study attempts to propose a grey adaptive quantization approach for one-dimensional cerebellar model articulation controller (1D CMAC) network. Even though the target function is unknown in advance, the proposed approach still could be utilized to determine whether the input space needs to be repartitioned or not. Once the input space is determined to be repartitioned, some new knots are inserted for further quantization, and then the number of states is gradually increased during the learning process. Hence, the proposed approach not only possesses the adaptive quantization ability in the input space, but also has the growing feature in the number of states. Simulation results show that the proposed approach not only has the adaptive quantization ability, but also can achieve a better learning accuracy and a faster convergence speed.