Home > Machine Learning 101 > Quizzes > Machine Learning 101 Practice Test: Fundamental Theorem of PAC Learning
Machine Learning 101 Practice Test: Fundamental Theorem of PAC Learning
Fast practice, instant feedback. Timer auto-submits when time’s up.
Avg score: 0% Most missed: “Any ERM rule is a successful PAC learner for hypothesis space H.”

Probably Approximately Correct (PAC) learning defines a mathematical relationship between the number of training samples, the error rate, and the probability that the available training data are large enough to attain the desired error rate.

The PAC theory is about finding the relationship between the true error rate and the number of training samples.

A classical example of Probably Approximately Correct (PAC) learning is the concept class of rectangles, where each rectangle maps a point on the plane x ∈ R2 to +1 if it's in the rectangle and −1 otherwise.

Machine Learning 101 Practice Test: Fundamental Theorem of PAC Learning
Time left 00:00
8 Questions

1. Any ERM rule is a successful PAC learner for hypothesis space H.
2. If distribution D assigns zero probability to instances where h not equal to c, then an error will be ______
3. Error is defined over the _____________
4. If distribution D assigns zero probability to instances where h = c, then an error will be ______
5. When was PAC learning invented?
6. The error of h with respect to c is the probability that a randomly drawn instance will fall into the region where _________
7. PAC learning was introduced by ____________
8. Error strongly depends on distribution D.