Course Information
Welcome to Applied Machine Learning 2025-26.
This is a new course which is similar in content to the S1 offering of AML but online in S2.
Your Course Organiser is Dr Heather Yorston.
Course Outline
This course is delivered using "flipped-classroom" methods. Intellectual content will be delivered via a combination of online short video segments (overall, per topic, approximately the same length as a traditional lecture). Some of the topics have online quizzes associated with them, intended for you to review your understanding. During most of the lecture slots we will have other activities to review the topic material, also available by online recording.
We expect to cover the following general areas, although exact content will vary from year to year:
- Introduction to machine learning: The learning problem, supervised vs unsupervised learning
- Representing data: Categorical vs real valued attributes, feature extraction, basis expansion
- Classification: Naive Bayes, logistic regression, nearest neighbours, decision trees, neural networks
- Regression: Linear regression
- Ethics of machine learning: Fairness, biases in data, responsible application of machine learning methods
- Fitting models to data: Optimization, generalization
- Unsupervised learning: Dimensionality reduction, PCA, clustering
- Evaluating machine learning models: Accuracy, precision and recall, ROC curves
We will use a modern machine learning programming environment and industry-standard libraries.
Learning Objectives
- explain the scope, goals, and limits of machine learning, and the main sub-areas of the field
- describe and critically compare the various techniques covered in the syllabus, and explain where they fit within the structure of the discipline
- apply the taught techniques to data sets to solve machine learning problems, using appropriate software
- analyse machine learning techniques in terms of their limitations and applicability to different machine learning problems and potential ethical concerns
- compare and evaluate the performance of applicable machine learning techniques in a systematic way