Computational Learning Theory Fall Semester , 2010 Lecture 3 : October 31

In this lecture we will talk about the PAC model. The PAC learning model is one of the important and famous learning model. PAC stands for Probably Approximately Correct, our goal is to learn a hypothesis from a hypothesis class such that in high con dence we will have a small error rate (approximately correct). We start the lecture with an intuitive example to explain the idea behind the PAC model and the di erences between the PAC model and the Bayesian learning that we studied last week. Then, we continue to formal the PAC model, review Occam's Razor principle and give a few examples.