Basics of Maths - Machine Learning

Linear Algebra — how data is stored, transformed, and represented. Vectors, matrices, dot products, eigenvalues. Everything in ML is matrix operations underneath.

Calculus — specifically partial derivatives and the chain rule. This is how models learn — gradient descent is just calculus telling the model which direction to improve.

Probability & Statistics — understanding uncertainty, distributions, Bayes theorem, and hypothesis testing. ML models are probabilistic at heart, not deterministic.

Optimisation — how a model finds the best answer. Loss functions, convexity, and why gradient descent works at all.