Course syllabus
AI and Deep Learning: the course outline
This is the official outline for Week 2. It states what the course covers, what you should be able to do at the end of it, how it is taught and assessed, and what to read. The slides and student papers are on the materials page.
Course description
Deep learning powers modern artificial intelligence, from image recognition to large language models. This course is a rigorous, hands-on introduction to deep learning that builds directly on the machine-learning workflow: framing a problem, fitting flexible models, evaluating them honestly, and deploying them responsibly.
Students will see how neural networks compose simple, differentiable units into powerful models trained by gradient descent and backpropagation; how convolutional networks learn from images; how the attention mechanism and the transformer architecture lie behind today's large language models; and how retrieval, agents, and AI-assisted coding fit into real systems. Throughout, the course keeps the discipline of classical machine learning: honest validation, awareness of failure modes and hallucination, and the safety, evaluation, and governance questions that responsible deployment demands.
Course aims
The course aims to give students a clear, practical understanding of how deep learning works and when to trust it. Through worked examples, Python labs, and discussion of real systems, students will develop the tools to build and train neural networks, choose architectures suited to a task, evaluate generative systems for grounding and failure, and reason about the safety and governance of deployed AI.
Learning outcomes
On successful completion, you will be able to:
- explain how a neural network composes simple units into a flexible, differentiable model, and how it is trained by gradient descent and backpropagation;
- diagnose and control training (learning rate, regularisation, and overfitting) using held-out validation;
- explain how convolutional networks exploit spatial structure in images, and apply transfer learning and data augmentation without leakage;
- describe the attention mechanism and the transformer architecture behind modern large language models;
- distinguish prompting, retrieval-augmented generation, and fine-tuning, and choose appropriately for a given task;
- evaluate generative systems for factuality, grounding, and failure modes, and recognise when a simpler model is the better choice;
- assess the safety, monitoring, and governance of deployed and agentic AI systems, and use AI coding tools responsibly, with evidence and reproducibility.
Teaching and assessment
WorcesterCrimsonTeaching method.0.3emStudents are taught according to the Oxford Socratic model, where class participation is central. Teaching combines lectures, guided discussion, hands-on Python labs, and group work in and outside class. Each idea is built intuition-first and then made concrete with a small worked example before any formula.
WorcesterCrimsonPrerequisites.0.3emThe course assumes comfort with basic vectors and matrices, derivatives and the chain rule, and elementary probability; some Python familiarity helps with the labs. No previous deep-learning experience is required: it builds on the AI and Machine Learning week, but core ideas are reviewed so that motivated newcomers can follow.
WorcesterCrimsonAssessment.0.3emAssessment takes place on Friday at the end of the course.
9
Course sessions
| Day | Topic |
|---|---|
| Monday | Neural networks |
| Tuesday | Computer vision and CNNs |
| Wednesday | Transformers, LLMs, and retrieval |
| Thursday | Agentic AI, deployment, and governance |
| Friday | Final assessment |
Session overview
Neural Networks
This session builds the neural network from a single neuron (logistic regression with an activation) up to a multilayer perceptron. We cover what depth buys, how backpropagation computes gradients, and how gradient descent trains the model, then return to the familiar discipline of train/validation/test and regularisation to keep flexible models honest.\\ OxfordBlueKey idea: a neural network is a differentiable function fit by gradient descent, and we trust it only if it generalises.
Computer Vision and CNNs
Images become tensors, and we introduce the convolution and pooling operations that let a network exploit spatial structure. We discuss convolutional architectures, why transfer learning works, and how to augment data without letting validation or test images leak into training.\\ OxfordBlueKey idea: a CNN sees an image by sliding the same small pattern-detector everywhere, reusing weights instead of relearning them.
Transformers, LLMs, and Retrieval
This session introduces the attention mechanism and the transformer architecture behind modern large language models. We compare prompting, retrieval-augmented generation, and fine-tuning, and discuss why grounding through retrieval matters when factuality is at stake.\\ OxfordBlueKey idea: attention lets every word look at every other word, and a language model is next-word prediction at scale: fluent, but not necessarily right.
Agentic AI, Deployment, and Governance
The final session covers tool-using agents and AI-assisted coding, how to evaluate generative systems for grounding and failure, and the safety, monitoring, and governance questions, from drift to accountability, that responsible deployment of AI systems demands.\\ OxfordBlueKey idea: an AI system is a model plus tools, memory, and guardrails: the more it can do, the more it must be evaluated and governed.
Core bibliography and reading list
Every item below is freely and publicly available online.
- Prince, Simon J.\,D. Understanding Deep Learning. MIT Press, 2023. Free PDF: https://udlbook.github.io/udlbook/
- Zhang, Aston, Zachary C. Lipton, Mu Li, and Alexander J. Smola. Dive into Deep Learning. Cambridge University Press, 2023. Free interactive book: https://d2l.ai/
- Goodfellow, Ian, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press, 2016. Free online: https://www.deeplearningbook.org/
- Deisenroth, Marc Peter, A. Aldo Faisal, and Cheng Soon Ong. Mathematics for Machine Learning. Cambridge University Press, 2020. Free PDF: https://mml-book.github.io/
- Sanderson, Grant (3Blue1Brown). Neural Networks (visual video series). https://www.3blue1brown.com/lessons/neural-networks
- Stanford CS231n. Deep Learning for Computer Vision (course notes). https://cs231n.github.io/
- Jurafsky, Dan, and James H. Martin. Speech and Language Processing. 3rd ed. (draft), covering transformers and large language models. https://web.stanford.edu/~jurafsky/slp3/
- Alammar, Jay. The Illustrated Transformer. https://jalammar.github.io/illustrated-transformer/
- Google. Machine Learning Crash Course (neural networks, embeddings, and LLM modules). https://developers.google.com/machine-learning/crash-course
- National Institute of Standards and Technology (NIST). Artificial Intelligence Risk Management Framework (AI RMF 1.0). 2023. https://www.nist.gov/itl/ai-risk-management-framework
