It is an exciting time for the field of nuclear fusion energy. The National Ignition Facility at Lawrence Livermore National Lab has been consistently demonstrating ignition since 2022, Tokamak reactors like the Joint European Torus have posted record energy yields as late as 2023, and unprecedented private investment in fusion has begun to pour into the field, approaching $10 billion. Many interesting concepts for achieving net fusion gain have surfaced, but magnetic confinement systems like the tokamak, spheromak, and stellarator remain the most mature technologies and are most likely to be the first to reach commercialization. While we have come very far in our understanding of these magnetically confined fusion plasmas, there remain a host of instabilities that we cannot accurately predict and mitigate using the reactor plasma control system. This is where AI/Deep Learning has been applied most fruitfully in fusion research. In this talk, we will spend time discussing some of the landmark papers in the application of deep learning to fusion, as well as some of the fundamental physics behind the phenomena that we wish to understand, predict, and actively mitigate.