Self-paced course

Mathematics for Artificial Intelligence

A plain-English course covering optimization, machine learning, neural networks, reinforcement learning, and generative AI. Every concept explained with what it is and why it matters.

Chapter 00 — Start Here

Math Foundations You Need First

If you have zero math background, start here. Covers variables, functions, equations, derivatives, summation notation, probability — everything you need to understand the rest of the course.

variables functions derivatives summation probability sets

Chapter 01

Optimization for AI

How AI finds the best solution among many possibilities. Algorithms, heuristics, convex functions, gradient descent, and the math tools that make it all work.

algorithms heuristics vectors & matrices convex optimization gradient descent quadratic forms

Chapter 02

AI and Machine Learning

How machines learn patterns from data. From linear regression to neural networks, perceptrons to deep learning architectures like CNN, RNN, and LSTM.

loss functions linear regression perceptron backpropagation CNN RNN LSTM

Chapter 03

Reinforcement Learning & Generative AI

How AI learns by trial-and-error and creates new content. Multi-armed bandits, Q-learning, GANs, and diffusion models.

reinforcement learning multi-armed bandit Q-learning SARSA GANs diffusion models