Learning

Mathematics & Statistics

The foundations under everything else in this directory.

Where to start

If you are here because machine learning needs it, the order is linear algebra, then calculus, then probability — and 3Blue1Brown before any of them, for the intuition. Khan Academy is the right choice if you need to rebuild school mathematics properly; there is no shame in starting there and it is the fastest route.

Rebuild the foundations3

  • Complete school and early university mathematics with practice and mastery tracking. The best place to fill a gap you are embarrassed about.

    Khan Academykhanacademy.org

  • Algebra through differential equations, written for students who are stuck. Worked examples rather than proofs.

    Lamar Universitytutorial.math.lamar.edu

  • OpenStax MathematicsStart hereFree

    Peer-reviewed, openly licensed textbooks. Real books, free, with exercises and answers.

    Rice Universityopenstax.org

Intuition first3

  • 3Blue1BrownStart hereFree

    Visual intuition for linear algebra, calculus and neural networks. Watch Essence of Linear Algebra before any ML course.

    Grant Sanderson3blue1brown.com

  • A linear algebra textbook where every figure is interactive. Good alongside a more formal course.

    Immersive Mathimmersivemath.com

  • Seeing TheoryStart hereFree

    Probability and statistics as interactive visualisations.

    Brown Universityseeing-theory.brown.edu

Do it properly3

  • Full lecture courses with notes, assignments and exams. 18.06 Linear Algebra is the famous one and deserves to be.

    MITocw.mit.edu

  • Exactly the mathematics ML needs and none of what it does not. Free PDF, and the right book for this purpose.

    Deisenroth, Faisal & Ongmml-book.github.io

  • An open statistics library covering introductory through graduate level, useful as a reference.

    LibreTextsstats.libretexts.org

About this list

9 resources, checked automatically every week so dead links do not sit here unnoticed. Nothing on this page is sponsored and none of these links pay us — which is the only reason a recommendation on it is worth anything. Every link goes to the original source, and we take nothing with you when you leave.

Other subjects