Foundations
Math for AI
The specific mathematics that appears in practice, and nothing beyond it.
Grasp
The honest version: you need much less mathematics to build AI systems than the field's reputation suggests, and much more than zero.
Three areas do real work. Linear algebra because every model input, weight and activation is a tensor, and every operation is a matrix multiplication. Probability and statistics because models output distributions, and because evaluation is entirely a statistical exercise. Calculus and optimisation because training is gradient descent, and understanding why training fails means understanding gradients.
Notably absent: real analysis, abstract algebra, topology. Those matter if you intend to do research. For building, they do not. Learn the three areas below to the depth where you can read a paper's equations without panic, then return here only when a specific problem demands more.