The presentation is intended as an introduction to deep learning and its applications in music. The presentation features the use deep auto-encoders for generating novel sounds from a hidden representation of an audio corpus, audio style transfer as shown by Ulyanov (https://dmitryulyanov.github.io/audio-texture-synthesis-and-style-transfer/), and future directions based on CycleGan, WaveNet, etc; as well as a high level introductions of some basic concepts in machine learning.