Math for AI
Full opens every explanation and proof on the page.
A course in the mathematics used by machine learning: linear algebra, calculus, probability, statistics, optimisation and information theory. Every topic starts from a precise definition and builds forward, with each step proved or explained.
Each idea comes with four things textbooks tend to skip: what it is not (non-examples that break one condition at a time), where it fits among the ideas around it, who uses it and in which field, and why it matters in AI.
The course is organised by subject, so it can be read on its own. The AI course links into it at the exact definition or theorem each build needs.
Units so far
Section titled “Units so far”| Unit | Topic | Needs |
|---|---|---|
| F1 | Sets, families and intersections | nothing |
| LA1 | Vector spaces: fields, axioms, examples and non-examples, subspaces | F1 |
| LA2 | Span: two definitions, why they agree, the infinite case | F1, LA1 |
The full plan is on the syllabus. New to the reading modes? See how to read this site.