In the present study, the natural frequency of functionally graded graphene nanoplatelets (FG-GPL)-reinforced porous plate is predicted using an artificial neural network (ANN)-based model. The plate is reinforced with GPL and is modeled in a functionally graded fashion by varying the size and density of pores in the thickness direction. The effective property such as modulus of elasticity is obtained using the Halpin–Tsai model while mass density, and Poisson’s ratio are estimated by the Voigt model. Governing equations and finite element model are developed in the framework of higher-order shear deformation theory (HSDT). The data is generated for the selective features keeping natural frequencies of FG-GPL porous plates as the desired output. The database is split into a training set with 70% of the data and 30% of the data is considered for testing and validation purposes. A regression-based ANN model is employed to train the existing data and the trained model is further utilized to predict natural frequencies for the unseen values of the features, i.e., thickness ratio, porosity coefficient, and weight fraction of GPL. It is observed that the ANN-based algorithm predicts the natural frequencies with a significant low error (<1%). It can be concluded that the ANN-based model is quite efficient to handle large databases, various features, and function complexity associated with material modeling.