Probably Approximately Correct learning (PAC learning)

E345811 UNEXPLORED

Probably Approximately Correct (PAC) learning is a foundational framework in computational learning theory that formalizes what it means for an algorithm to efficiently learn a concept from examples with high probability and small error.


Referenced by (3)
Subject (surface form when different) Predicate
Leslie Valiant
knownFor
Leslie Valiant ("“A Theory of the Learnable”")
notableWork
poverty of the stimulus argument ("Gold’s theorem in language learnability")
relatesTo

Please wait…