Skip to content

Introduction to Artificial Intelligence

Self-study notes for a solid foundation in AI — search, neural networks, reinforcement learning and metaheuristics. Inspired by UNSW COMP9814 Extended Artificial Intelligence (24T3).

Start with Chapter 1 Jump to a chapter

You'll need: Python, sophomore-level maths (calculus, linear algebra, probability), and basic data structures & algorithms.

Pick a path

  • Full course

    Read in order. Each chapter builds on the last.

    1 → 2 → 3 → 4 → 5

  • Learning systems

    Neural nets and RL, then build one.

    3 → 4 → Gym project

  • Search & optimisation

    How agents search and how to optimise when exact search is too slow.

    2 → 5

Chapters

Chapter Covers Read
1 Introduction What intelligence means, a short history of AI, agent types, knowledge representation 17 min
2 Search States and actions, search spaces, BFS / DFS / iterative deepening, informed search 7 min
3 Artificial Neural Networks Neurons, perceptrons, MLPs, network-design workflow 18 min
4 Reinforcement Learning Exploration vs exploitation, action values, returns, value functions, Monte Carlo & TD 21 min
5 Metaheuristics Gradient methods, complexity classes, simulated annealing, tabu search, genetic algorithms 31 min

Projects: Mountain Car with Gym · Feedforward Neural Network

Coming later: computer vision · language processing · reasoning under uncertainty · human-aligned robotics.

Work in progress

Notes are still being written, so expect changes. Spotted a mistake? Open an issue.