You don't need a math degree to work with AI, but a handful of ideas from linear algebra, calculus, and statistics show up constantly once you start looking under the hood. This module builds just enough intuition for those ideas — no proofs, no exams — so that terms like "vector," "gradient," and "distribution" stop feeling like jargon.
The lessons start with vectors and matrices, the language machine learning uses to represent data, move through derivatives and gradients — the mechanism models use to learn — and close with the statistics that let us describe data and judge whether a model's predictions are any good. The last video ties all three together inside a real, beginner-friendly machine learning course.
Watch the lessons in order. If a video runs long, feel free to treat it as a reference you dip back into later rather than something to finish in one sitting.
3Blue1Brown's famously intuitive introduction to vectors — arrows in space, lists of numbers, and why both views matter once you start working with data.
Video 9minThe same visual, intuition-first treatment applied to calculus — how derivatives and integrals fall naturally out of a simple geometry question.
Video 17minfreeCodeCamp's deep-dive crash course: vectors, matrices, dot products, and solving linear systems, all tied directly to how ML and generative AI models represent data.
Video 6h 5minA college-level statistics course covering distributions, central tendency, correlation, the normal distribution, and sampling — the vocabulary you need to reason about data and model results.
Video 8h 15minfreeCodeCamp's hands-on ML course, taught by Kylie Ying — see vectors, gradients, and statistics stop being abstract and start driving real models like linear regression and neural networks.
Video 3h 53min