ConceptAI & ML
Double descent
The phenomenon where test error initially decreases, then increases, and then decreases again as model capacity increases.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
2Each in their own terms, from the easiest level.
Sara Beery
A modern phenomenon where over-parameterized models past the interpolation threshold achieve better generalization performance despite high capacity.
Connections
4The lectures that define it or assume it, and the concepts next to it.