A survey of cutting-edge recent research in MIR using Deep Learning. Students will build state-of-the art models using tensorflow* and GPU computing. Emphasis on generative models and reinforcement learning. Topics covered: music and speech synthesis, beat-tracking, music-recomendation, and semantic analysis. Students solve a real problem of their choice using state-of-the-art Deep Learning Models. This course is meant for individuals who want to gain experience applying Deep Learning to solve current problems in MIR.