Skip to content

Resources: Module 02 — Mathematics for Machine Learning

Primary References

  1. "Mathematics for Machine Learning" by Deisenroth, Faisal, and Ong (https://mml-book.github.io) Free online. The definitive ML-focused math textbook. Chapters 2 (Linear Algebra), 5 (Vector Calculus), and 6 (Probability and Distributions) directly correspond to this module.

  2. 3Blue1Brown — "Essence of Linear Algebra" series (https://www.youtube.com/playlist?list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab) Visual, geometric intuition for linear algebra. Highly recommended before or alongside reading. The eigenvalue/eigenvector episode is especially good.

  3. 3Blue1Brown — "Essence of Calculus" series (https://www.youtube.com/playlist?list=PLZHQObOWTQDMsr9K-rj53DwVRMYO3t5Yr) Visual calculus from first principles. Builds the intuition needed to understand gradients and backpropagation.

  4. Stanford CS229 Lecture Notes — Linear Algebra Review (http://cs229.stanford.edu/section/cs229-linalg.pdf) Andrew Ng's concise reference for the linear algebra used in ML. Freely available.

  5. numpy documentation — Linear algebra routines (https://numpy.org/doc/stable/reference/routines.linalg.html) Reference for np.linalg.eig, np.linalg.solve, np.linalg.inv, and related functions.