#pac #probably #approximately #ktu #cs #machine #learning
Probably approximately correct learning (PAC) is the mathematical framework for analysing a learning algoritham. With high probability a pac learning algorithm find a hypothesis that is approximately identical to the hidden target concept.
Definition and examples of pac is discussed in this video. Differece between the concept class and hypothesis class is well described here.
what is concept in pac?
what is true error in hypothesis?
Definition of pac?
notes
https://drive.google.com/file/d/1EcA0JhATjdK7yZAg0ZSmcG-Qm6kDf3KO/view?usp=drivesdk
