Explore the intersection of machine learning and knot theory in this 1-hour 48-minute lecture by Mark Hughes from Brigham Young University. Delve into the current state of machine learning applications in knot theory, focusing on the challenges of learning 4-dimensional topological invariants such as slice genus, Khovanov homology, and the Rasmussen s-invariant from the Jones polynomial. Examine how these techniques have uncovered subtle relationships between topological invariants and provided optimal solutions for complex problems. Gain insights into what these findings reveal about the underlying structure of 4D invariants and discover new approaches for studying knot theory through machine learning methodologies.