Sign inSign in

Learning with Contamination

A supervised learning setting where an adversary can arbitrarily remove an eta fraction of the training set and replace both labels and feature locations.
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.

Contamination models1Error rate1Halfspace learning1Robust statistics1Supervised learning1

Lecturers

1

    Connections

    3

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

    Concepts2

    1 lecturer. 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.