Module Catalogue 2026/27

Pre Requisite Comment

N/A

Co Requisite Comment

N/A

Aims

To develop an understanding of modern machine learning methods, with particular focus on the mathematical foundations and statistical principles that enable machines to learn from complex datasets.

Outline Of Syllabus

Given the speed at which machine learning is being advanced, the specific module content will be adapted to reflect the current state of the art. At the time of writing, a typical module syllabus would include the following topics:

Introduction to machine learning. Introduction to the concepts of featurisation, regularisation, training, and performance assessment. Stochastic optimisation. Supervised learning methods, such as linear regression, support vector machines, and deep neural networks. Generative modelling methods, such as energy-based models, generative adversarial networks and diffusion models.

Intended Knowledge Outcomes

At the end of the module it is expected that a student will be able to:
- Outline the key mathematical and statistical ideas underpinning machine learning methods.
- Critically evaluate the strengths and limitations of machine learning methods.

Intended Skill Outcomes

At the end of the module it is expected that a student will be able to:
- Apply algebra and calculus to derive key formulae in the machine learning context.
- Analyse complex data using supervised learning techniques.
- Compare the performance of different machine learning methods.

Students will develop skills across the cognitive domain (Bloom’s taxonomy, 2001 revised edition): remember, understand, apply, analyse, evaluate and create.

Teaching Rationale And Relationship

Lectures are used for the delivery of theory and explanation of methods, illustrated with examples, and for giving general feedback on marked work. Problem classes are used to help develop the students’ abilities at applying the theory to solving problems.

The teaching methods are appropriate to allow students to develop a wide range of skills. From understanding basic concepts and facts to higher-order thinking.

Assessment Rationale And Relationship

A substantial formal unseen examination is appropriate for the assessment of the material in this module. The format of the examination will enable students to reliably demonstrate their own knowledge, understanding and application of learning outcomes.

Examination problems may require a synthesis of concepts and strategies from different sections, while they may have more than one way for solution. The examination time allows the students to test different strategies, work out examples and gather evidence for deciding on an effective strategy, while carefully articulating their ideas and explicitly citing the theory they are using.

The coursework assignments allow the students to develop their problem-solving techniques, to practise the methods learnt in the module, to assess their progress and to receive feedback; the summative assessment has a secondary formative purpose as well as its primary summative purpose.

Note: the exam for MAS8607 is more challenging than the exam for MAS3919.

General Notes

N/A