Sign inSign in
ConceptAI & ML

Double descent

The phenomenon where test error initially decreases, then increases, and then decreases again as model capacity increases.
Watch it explained

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.

Model capacity2Generalization1Overfitting1Test risk1Training risk1

Lecturers

2

Each in their own terms, from the easiest level.

  • Sara Beery

    MIT · Graduate

    A modern phenomenon where over-parameterized models past the interpolation threshold achieve better generalization performance despite high capacity.
    • 44:47Introduction to Deep Learning

Connections

4

The lectures that define it or assume it, and the concepts next to it.

Concepts2

Lectures2

2 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.