The neural activity of the brain is intimately coupled to the dynamics of the body. Yet how our hierarchical sensorimotor system dynamically orchestrates the generation of movement while adapting to incoming sensory information remains unclear. To tackle this question, we have developed a series of deep learning tools that have enabled us to measure 3D kinematics and jointly model neural and behavioral dynamics. In this talk, I will briefly discuss these tools and then show how our lab uses them to dissect the neural contributions to motor control and learning.