COMS20018 - Introduction to Artificial Intelligence

News

Unit Information

This unit introduces students to the foundations and contemporary landscape of Artificial Intelligence. We cover core machine learning concepts, large language models, causal inference, reinforcement learning and computer vision, alongside the philosophical foundations and ethical considerations that underpin the design of trustworthy AI systems.

Staff

Mengyan Zhang (Unit Director), Nan Lu, James Cussens

Teaching Assistants

Yuming Li, Siddhant Bansal, Leifan Lei

Unit Materials

The lecture slides and lab materials are linked on the unit webpage in Schedule. You can find the lecture recordings on Blackboard Replay.

The lab answers are available in the Blackboard Course Content - Lab Answers folder. We’ll release the answers for the previous week’s lab every Monday. To access the folder, please make sure you’re signed in to Blackboard in the same browser.

Schedule

Lecture 1: Mondays, 1100-1200, Fry Building G.09
Lecture 2: Tuesdays, 1500-1600, Fry Building G.09
Lab/Seminar: Wednesdays, 1100-1300, Merchant Venturer's Building 1.15 (Linux Computer Lab)

Week	Topic	Lecturer	Lecture 1 (Mon, 1100-1200)	Lecture 2 (Tue, 1500-1600)	Lab/Seminar (Wed, 1100-1300)
1 (w/c 21/09/26)	Introduction	MZ	Unit introduction; Introduction to AI	Linear Regression and Classification: Part I	Lab:Introduction to Python
2 (w/c 28/09/26)	Machine Learning	MZ	Linear Regression and Classification: Part II	Neural Networks: Introduction	Lab: Linear Regression
3 (w/c 05/10/26)	Deep Learning	NL / MZ	Neural Networks: CNNs, RNNs, and Transformers (MZ)	Generative Models (NL)	Lab: Neural Networks and Generative Models
4 (w/c 12/10/26)	Large Language Models	NL	Large Language Models I	Large Language Models II	Lab: Large Language Models
5 (w/c 19/10/26)	Philosophy of AI	JC	Philosophy of AI: Turing and Searle	Philosophy of AI: LLMs, Rationality and Understanding	Seminar
6 (w/c 26/10/26)	Consolidation week - no scheduled teaching
7 (w/c 02/11/26)	Ethics	NL	Ethics	Ethics	Lab
8 (w/c 09/11/26)	Causality and Decision Making	MZ	Causal Inference	Sequential Decision Making	Lab: Causality and Decision Making
9 (w/c 16/11/26)	Reinforcement Learning	MZ	Reinforcement Learning	Reinforcement Learning	Lab: Reinforcement Learning
10 (w/c 23/11/26)	Computer Vision	NL / Guest	Computer Vision	Computer Vision (Guest lecture: Ahmad Darkhalil)	Lab
11 (w/c 30/11/26)	Trustworthy AI	NL	Trustworthy AI	Trustworthy AI	Lab
12 (w/c 07/12/26)	Revision				No lab
13 (w/c 14/12/26)	Final Exam period

Assessment Details

Students will be assessed via three elements:

A mid-term video presentation (worth 20% of the unit): instructions
A series of laboratory-based assessments (worth 20% of the unit): lab submission instructions
An end-of-term exam (worth 60% of the unit)

Reading Materials

Readings are listed below for weeks with finalised lecture content; materials for the remaining weeks will be added as those lectures are finalised.

Week 2: Machine Learning

Bishop, C. M., Pattern Recognition and Machine Learning (2006) – our main textbook for Weeks 2–3. Free online. Chapter 1 (§1.1), Chapter 3 (§3.1), Chapter 4 (§4.3.2), Chapter 5: (§5.1, §5.2, §5.3). Free online.

Week 3: Deep Learning

Bishop & Bishop, Deep Learning: Foundations and Concepts (2024)
Goodfellow, Bengio, Courville, Deep Learning (2016), Chapters 6 and 8 – a more modern treatment (ReLU, Adam, and optimisation for deep nets). Free online (optional, further reading).
Vaswani et al. “Attention Is All You Need.” NeurIPS, 2017 (the original Transformer paper).
Stanford CS236, Deep Generative Models course notes: autoregressive models, VAEs and GANs. The best single companion to this lecture. Free online.
Google for Developers, Introduction to GANs: generator and discriminator training, and common problems such as mode collapse. Free online.
Weng, L., “What Are Diffusion Models?” (2021): forward noising and reverse denoising; the introductory sections are enough. Free online.
Kingma, D. P. & Welling, M., An Introduction to Variational Autoencoders (2019): latent-variable models and the ELBO (optional). arXiv:1906.02691.
Kingma, D. P. & Welling, M., Auto-Encoding Variational Bayes (2013): the original VAE paper (optional, advanced). arXiv:1312.6114.
Ho, J., Jain, A. & Abbeel, P., Denoising Diffusion Probabilistic Models (2020): the paper behind the diffusion slides (optional). arXiv:2006.11239.

Week 8: Causality and Decision Making

Spirtes, Glymour, Scheines, Causation, Prediction, and Search (2000), Chapter 5 (constraint-based discovery), or Peters, Janzing, Schölkopf, Elements of Causal Inference (2017), Chapter 7 (overview). Free online (Peters et al.).
Sutton & Barto, Reinforcement Learning: An Introduction (2nd ed.), Chapter 2: Multi-armed Bandits. Free online.
Lattimore & Szepesvári, Bandit Algorithms (2020), Chapters 1, 2 and 19 (linear bandits). Free online.

Week 9: Reinforcement Learning

Sutton & Barto, Reinforcement Learning: An Introduction (2nd ed.), Chapters 3 (MDPs), 6 (TD learning & Q-learning) and 13 (Policy Gradient methods). Free online.