PAC Learning

Definition

Probably Approximately Correct learning: a framework specifying that successful learning from examples means being able to predict future examples accurately, achieved with a moderate (polynomial) amount of effort, where accuracy improves as an algebraic function of effort. The promise holds on average over many cases but is weak for any single case.

Cast within

No topic-region cast yet — this appears once PAC Learning's compiled claims are aligned into a topic region's argument tree.

Claims mentioning PAC Learning (4)

Your notes

Loading notes...