Course syllabus
AI and Machine Learning: the course outline
This is the official outline for the course: what it covers, what you should be able to do at the end of it, how it is taught and assessed, how deep it goes into each method, and what to read. The lecture slides for each session are on the four days page.
Course description
Machine learning lets computers find patterns in data and turn them into predictions and decisions. This course is a rigorous, hands-on introduction to modern artificial intelligence and machine learning, organised around the full workflow: framing a decision, preparing data, fitting models, evaluating them honestly, and using them responsibly.
You will see how supervised models (linear and logistic regression, decision trees, random forests, and boosting) are built and judged; how unsupervised methods such as clustering and principal component analysis reveal structure without labels; and how modern AI systems (embeddings, retrieval, and generative tools) sit alongside classical methods. Throughout, the course emphasises honest evaluation, the danger of data leakage, the difference between prediction and causation, and the fairness, interpretability and governance questions that responsible deployment requires.
Course aims
The course aims to give you a clear, practical understanding of how machine learning works and when to trust it. Through worked examples, Python labs and the discussion of real decisions, you will develop the analytical tools needed to choose appropriate models, evaluate them with the right metrics, audit them for leakage and bias, and communicate both your conclusions and their limitations clearly.
Learning outcomes
On successful completion, you will be able to:
- frame a real decision as a supervised learning problem, and identify which variables are genuinely available before the decision is made;
- explain and apply the core supervised models (linear and logistic regression, decision trees, random forests, and boosting) and the bias–variance trade-off that governs them;
- evaluate models with metrics matched to the decision (accuracy, precision and recall, ROC–AUC, calibration) using train/validation/test splits and cross-validation;
- diagnose data leakage, and distinguish predictive association from causal effect;
- use unsupervised methods (K-means clustering and principal component analysis) to find and interpret structure in unlabelled data;
- explain how embeddings, retrieval-augmented generation, and other modern AI workflows relate to classical machine learning;
- assess the fairness, interpretability, monitoring and governance of a deployed model, and use AI tools responsibly, with evidence and reproducibility.
Teaching and assessment
Teaching method. You 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. No prior programming experience is assumed, though it is welcome.
Assessment. Assessment takes place on Friday at the end of the course.
Course sessions
| Day | Topic |
|---|---|
| Monday | Foundations: data, prediction, and trust |
| Tuesday | Regression and classification: from models to decisions |
| Wednesday | Flexible models and honest evaluation |
| Thursday | Unsupervised learning, modern AI, and responsible use |
| Friday | Assessment |
Session overview
Foundations of Machine Learning
This session sets up the workflow we reuse all week: turning a decision into a prediction problem, separating signal from noise, splitting data honestly, and choosing a loss. We stress what is known before a decision is made, and why data leakage and the gap between prediction and causation matter from the very start.
Regression and Classification
We turn to the baseline supervised models: linear regression for numbers and logistic regression for probabilities. We discuss coefficients, uncertainty, and how a predicted probability becomes an action through a cost-based threshold rather than a default cut-off.
Flexible Models and Honest Evaluation
This session introduces decision trees, random forests and boosting, together with the bias–variance trade-off that controls overfitting. The added flexibility is paired with stricter evaluation: cross-validation, the right metric for imbalanced problems, and a disciplined leakage audit.
Unsupervised Learning and Responsible AI
The final session moves from prediction to structure discovery with K-means clustering and PCA, connects classical tools to modern AI through embeddings and retrieval, and closes with the fairness, interpretability, monitoring and governance questions that responsible deployment demands.
How deep we go
The course does not claim the same level of mastery for every method it names. The distinctions below are part of the learning design, not a gap in it. Some methods you will fit, calculate or operate yourself; others you will inspect without training them from scratch.
| Day | You fit, calculate or operate | You inspect without training from scratch |
|---|---|---|
| Day 1 | loss-matched constant baselines; an editable rule-based text classifier with abstention | an optional, unscored zero-shot structured-output call |
| Day 2 | simple and multiple linear regression; the analytical structure of logistic regression | cost-sensitive decisions and the boundary between response prediction and causal uplift |
| Day 3 | logistic regression as a comparator; a decision tree; a random forest | gradient boosting as a lecture benchmark and conceptual extension |
| Day 4 | K-means; PCA; BM25; TF-IDF/LSA and cosine-similarity retrieval | learned embeddings and a retrieve-then-generate system |
This vocabulary is deliberate. A deterministic regular-expression classifier is a rule system, not machine learning. PCA is a representation method rather than a predictive model. Retrieval-augmented generation (RAG) is a system that combines retrieval and generation, not a single model.
Deep-network and transformer training, reinforcement learning, production MLOps, and causal effect estimation remain outside the four-day course.
Core bibliography and reading list
Every item below is freely and publicly available online; links are provided.
- James, Gareth, Daniela Witten, Trevor Hastie, Robert Tibshirani, and Jonathan Taylor. An Introduction to Statistical Learning with Applications in Python. Springer, 2023. Free PDF: statlearning.com
- Hastie, Trevor, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning. 2nd ed. Springer, 2009. Free PDF: hastie.su.domains/ElemStatLearn
- Deisenroth, Marc Peter, A. Aldo Faisal, and Cheng Soon Ong. Mathematics for Machine Learning. Cambridge University Press, 2020. Free PDF: mml-book.github.io
- scikit-learn developers. scikit-learn User Guide. scikit-learn.org/stable/user_guide.html
- VanderPlas, Jake. Python Data Science Handbook. 2nd ed. O'Reilly, 2022. Free online: jakevdp.github.io/PythonDataScienceHandbook
- Google. Machine Learning Crash Course. developers.google.com/machine-learning/crash-course
- Goodfellow, Ian, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press, 2016. Free online: deeplearningbook.org
- Sanderson, Grant (3Blue1Brown). Neural Networks (visual video series). 3blue1brown.com/lessons/neural-networks
- Molnar, Christoph. Interpretable Machine Learning. 2nd ed., 2022. Free online: christophm.github.io/interpretable-ml-book
- National Institute of Standards and Technology (NIST). Artificial Intelligence Risk Management Framework (AI RMF 1.0). 2023. nist.gov/itl/ai-risk-management-framework
