If distribution D assigns zero probability to instances where h not equal to c, then an error will be ______

🎲 Try a Random Question  |  Total Questions in Quiz: 8  |  🧠 Study this quiz with Flashcards
This question is part of a full practice quiz:
Machine Learning 101 Practice Test: Fundamental Theorem of PAC Learning — practice the complete quiz, review flashcards, or try a random question.

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.


If distribution D assigns zero probability to instances where h not equal to c, then an error will be ______