Skip to content

GET READY

How do I get ready for the AI master program?

See our class list for M1 and M2.

So, for M1, see below, and consider if you are 100% sure you will be comfortable with the refreshers announced in T1.

For M2:You should check the M1 classes (that ~2/3 students will have got already, since 2/3 students in M2 come from our M1), and fill the gaps if you have some.

Content may be outdated

Parts of this page have not been fully updated for 2026–27. Some teachers and course details may have changed — check Classes for the latest information.

If you want to prepare yourself over the summer, there are several classes that we recommend, which can help you:

  • At M1 entry level, prepare for striving in the program

  • At M2 entry level, replace missing prerequisites:

We HIGHLY RECOMMEND at least reading the THREE CRASH COURSES highlighted in red.

Replace, review, or prepare for:

  • PRE1: Applied statistics

[CRASH COURSE]Crash Course on Basic Statistics, Marina Wahl (28 pages + questions)

[ON-LINE BOOK w. exercises] Computational and Inferential Thinking, By Ani Adhikari and John DeNero

[BOOK] Think stats, AB Downey.

[BOOK] An Introduction to Statistical Learning (ISLR, 2nd ed.). James, Witten, Hastie & Tibshirani — the modern standard, free, with Python labs.

[VIDEO SERIES] StatQuest with Josh Starmer — hugely popular YouTube channel for intuitive explanations of statistics and ML concepts.

  • PRE2: Mathematics for Data Science

A) LINEAR ALGEBRA

[CRASH COURSE]Linear Algebra Review and Reference. Zico Kolter and Chuong Do (26 pages)

[VIDEO SERIES] 3Blue1Brown – Essence of Linear Algebra — beautiful visual intuitions (~2 hours total)

[SHORT COURSES] Linear Algebra, Khan Academy

[COURSE] Mathematics for Machine Learning: Linear Algebra, David Dye, Coursera (19 hours)

B) CALCULUS

[CRASH COURSE]The matrix calculus you need for deep learning, T Parr, J Howard (33 pages)

[VIDEO SERIES] 3Blue1Brown – Essence of Calculus — visual intuitions for derivatives and integrals

[COURSE] Mathematics for Machine Learning: Multivariate Calculus,

Samuel J. Cooper, Coursera (19 hours)

[BOOK] Matrix Computations. Gene Golub and Charles van Loan

C) ALL-IN-ONE

[BOOK] Mathematics for Machine Learning. Deisenroth, Faisal & Ong (Cambridge UP, 2020) — free; covers linear algebra, calculus, and probability in one ML-focused package.

  • PRE3: Datacomp1

[COURSE] Databases and SQL for Data Science. Rav Ahuja

  • PRE4: Scientific programming

[COURSE] Data Analysis with Python. Joseph Santarcangelo

[MICRO-COURSES] Kaggle Learn — free in-browser exercises on Python, Pandas, SQL, and ML intro.

  • TC0 and TC1: Machine Learning

[CRASH COURSE] Google Machine Learning Crash Course — free, concise, and hands-on.

[TOTAL BEGINNER COURSE] Introduction to machine learning, Sebastian Thrun, Katie Malone, Udacity (10 lessons)

[BEGINNER COURSE] Machine Learning Specialization, Andrew Ng, Coursera (3 courses, updated 2022 with Python)

[BOOK] The Hundred-Page Machine Learning Book. Andriy Burkov.

[PRACTICAL COURSE] fast.ai – Practical Deep Learning for Coders — free, top-down practical approach, very well regarded.

[VIDEO SERIES] Andrej Karpathy – Neural Networks: Zero to Hero — builds neural nets from scratch; extremely popular.

[INTERACTIVE BOOK] Dive into Deep Learning — free textbook with runnable code in PyTorch, TensorFlow, and JAX.

[BOOK] Understanding Deep Learning. Simon Prince (2023) — free; excellent theory-focused complement.

[REFERENCE] Papers With Code — for advanced students wanting to explore state-of-the-art methods with implementations.

  • TC2: Optimization

[COURSE] Introduction to optimization, by the instructors of TC2: Anne Auger and Dimo Brockhoff

  • OPT7: Advanced optimization

[COURSE] Advanced optimization, by former instructors of OPT7: Anne Auger and Dimo Brockhoff

  • OPT13: Information Theory

[COURSE] Information Theory, Inference, and Algorithms, David MacKay