In this talk, two classical problems in molecular dynamics, modeling the atomic interaction and the computing the free energy, are studied with the deep learning technique. The Deep Potential Molecular Dynamics (DeePMD) method is based on a many-body potential generated by a carefully crafted deep neural network trained with ab initio data. The neural network model preserves all the natural symmetries in the atomic energy. It is "first principle-based" in the sense that there are no ad hoc components aside from the network model. We show that the proposed scheme provides an efficient and accurate protocol in a variety of systems, including bulk materials and molecules. The reinforced dynamics enhances the sampling of the configurational space and computes the free energy by applying a biasing potential, which is adaptively trained with data collected judiciously from the exploration. Parameterization using neural networks makes it feasible to handle cases with a large set of collective variables. This has the potential advantage that selecting precisely the right set of collective variables has now become less critical for capturing the structural transformations of the system. The method is illustrated by studying the full-atom, explicit solvent models of alanine dipeptide and tripeptide, as well as the system of a polyalanine-10 molecule with 20 collective variables.