Sign inSign in
ConceptAI & ML

Out-of-distribution generalization

The ability of a machine learning model to correctly classify or perform tasks on inputs that come from a different probability distribution than the training data.
as Irina Rish defines itUniversité de Montréal, MILAThe wording closest to all 3 definitions
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.

Machine learning3Data distributions2Generalization2Generalization in statistics1Neural network training1Probability distribution1Training distribution1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

3

Each in their own terms, from the easiest level.

  • Sara Beery

    MIT · Graduate

    The ability of a machine learning model to generalize to data that is not explicitly covered within the training distribution.
    • 0:18Generalization: Out-of-Distribution (OOD)
  • Yoshua Bengio

    MILA, Université de Montréal · Research

    The ability of a model to perform well on data whose distribution differs from the training distribution.
    • 2:01From System 1 to System 2 Deep Learning

Lectures that assume it

1

Connections

8

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

3 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.