📄️ Table of contents
Free discovery course on the mathematics behind Artificial Intelligence in 6 lessons. Linear algebra, calculus and probability explained through intuition rather than proofs, plus how to read the notation in papers without being intimidated.
📄️ 1. How much maths you need
Lesson 1 of the free Mathematics for AI course: what you genuinely need versus what you can skip, why school maths is a poor predictor of success, and the three levels of mathematical depth in this field.
📄️ 2. Linear algebra
Lesson 2 of the free Mathematics for AI course: vectors as data points, matrices as transformations, why the dot product measures similarity, and how embeddings turn words into geometry.
📄️ 3. Calculus
Lesson 3 of the free Mathematics for AI course: a derivative as a slope, the gradient as the steepest direction, how gradient descent trains a model, what a learning rate controls, and what backpropagation actually computes.
📄️ 4. Probability and statistics
Lesson 4 of the free Mathematics for AI course: predictions as distributions, what a probability of 0.7 commits you to, why accuracy misleads on imbalanced data, Bayes in plain terms, and how to tell a real difference from noise.
📄️ 5. Reading the notation
Lesson 5 of the free Mathematics for AI course: a decoder for the symbols used in machine learning papers, what the common Greek letters mean, how to read a loss function, and a strategy for reading a paper you do not fully understand.
📄️ 6. Recap and FAQ
Lesson 6 of the free Mathematics for AI course: a one-page synthesis of linear algebra, calculus, probability and statistics for machine learning, a realistic study order, and answers to the 12 questions asked most.
📄️ 7. Quiz and attestation
Test your understanding of the mathematics behind machine learning with a free 5-question quiz, corrected and explained: vectors, dot products, gradients, learning rates, probability and imbalanced data.