Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Error tolerance (PAC learning)
open-in-new
<p>In <a href="/facts/Probably_approximately_correct_learning/vBQlvDV1">PAC learning</a>, error tolerance refers to the ability of an <a href="/facts/Algorithm/fnl5NmRt">algorithm</a> to learn when the examples received have been corrupted in some way. In fact, this is a very common and important issue since in many applications it is not possible to access noise-free data. Noise can interfere with the learning process at different levels: the algorithm may receive data that have been occasionally mislabeled, or the inputs may have some false information, or the classification of the examples may have been maliciously adulterated. </p>