ConceptAI & ML
Two questions of learning
Learning is split into two questions: ensuring out-of-sample error is close to in-sample error, and ensuring in-sample error is small enough.
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
1Connections
4The lectures that define it or assume it, and the concepts next to it.