The restricted Boltzmann machine (RBM) has received an increasing amount of interest in recent years. It determines good mapping weights that capture useful latent features in an unsupervised manner. The RBM and its generalizations have been successfully applied to a variety of image classification and speech recognition tasks. However, most of the existing RBM-based models disregard the preservation of the data manifold structure. In many real applications, the data generally reside on a low-dimensional manifold embedded in high-dimensional ambient space. In this brief, we propose a novel graph regularized RBM to capture features and learning representations, explicitly considering the local manifold structure of the data. By imposing manifold-based locality that preserves constraints on the hidden layer of the RBM, the model ultimately learns sparse and discriminative representations. The representations can reflect data distributions while simultaneously preserving the local manifold structure of data. We test our model using several benchmark image data sets for unsupervised clustering and supervised classification problem. The results demonstrate that the performance of our method exceeds the state-of-the-art alternatives.