AI models learn from data that is noisy, incomplete, and uncertain, so they need a precise way to reason about uncertainty. That language is probability. A classifier does not just say "cat": it says how likely it thinks "cat" is.
The lessons start with the basics: events and how likely they are, then conditional probability and independence, which describe how learning one fact changes what you expect about another. From there they cover Bayes' theorem, a rule for updating beliefs as evidence arrives, and finish with expectation and variance, the average outcome and how much it varies.
Watch the lessons in order, then continue on to Random Variables & Distributions.
An overview of the probability ideas you need to know for machine learning.
Video 41minIntroduces conditional probability and what it means for events to be independent.
Video 3minA visual explanation of conditional probability that leads into Bayes' theorem.
Video 5minExplains expected value and variance, the average outcome and how spread out outcomes are.
Video 3minCovers expected value and variance for both discrete and continuous random variables.
Video 31min