Math for AI
In simple words
The specific mathematics that appears in practice, and nothing beyond it.
The fuller explanation
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.
Sources
Where this came from, so you can go past us.
Where does this sit on your route?
The free assessment places you on the same map and names which terms stand between you and the role you want.
Take the free assessmentSee it in context
The Atlas shows this term with everything that leads into it and everything that follows, as one picture.
Open the map