Gradient stiffened plates are widely used in aerospace， automotive， transportation and other fields for their excellent performance. Aiming at the gradient structure of gradient plate which leads to the problem of excessive computation and low efficiency of homogenization and two-scale optimization design， this paper adopts a machine learning method to build an artificial neural network with microstructure deformation parameters as input and equivalent stiffness coefficients as output， to realize the efficient prediction of equivalent stiffness. In the optimization process， this paper introduces unit design variables characterizing the deformation of the single cell to achieve explicit control of the local deformation of the gradient plate， and introduces mapping function node design variables to ensure that the local deformation of the single cell during the optimization process is consistent with the mapping function， which facilitates the decoupling of the two-scale optimization results. Numerical examples verify the effectiveness and correctness of the proposed method.