MAS8607 : Foundations of Machine Learning with Advanced Topics
- Offered for Year: 2025/26
- Module Leader(s): Professor Chris Oates
- Owning School: Mathematics, Statistics and Physics
- Teaching Location: Newcastle City Campus
Semesters
Your programme is made up of credits, the total differs on programme to programme.
| Semester 2 Credit Value: | 10 |
| ECTS Credits: | 5.0 |
| European Credit Transfer System | |
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. Additional advanced topics such as Bayesian optimisation, causal inference, Gaussian processes, generalised Bayesian inference, gradient flows, large language models, reproducing kernel Hilbert spaces, reinforcement learning, and Stein discrepancies may also be considered.
Teaching Methods
Teaching Activities
| Category | Activity | Number | Length | Student Hours | Comment |
|---|---|---|---|---|---|
| Scheduled Learning And Teaching Activities | Lecture | 5 | 1:00 | 5:00 | Problem Classes |
| Scheduled Learning And Teaching Activities | Lecture | 2 | 1:00 | 2:00 | Revision Lectures |
| Scheduled Learning And Teaching Activities | Lecture | 20 | 1:00 | 20:00 | Formal Lectures |
| Guided Independent Study | Assessment preparation and completion | 1 | 2:00 | 2:00 | Unseen exam |
| Guided Independent Study | Assessment preparation and completion | 2 | 4:00 | 8:00 | Completion of in course assessments |
| Guided Independent Study | Directed research and reading | 15 | 1:00 | 15:00 | Directed reading of advanced topic(s) |
| Guided Independent Study | Independent study | 2 | 1:30 | 3:00 | Review of Coursework |
| Guided Independent Study | Independent study | 13 | 1:00 | 13:00 | Revision for unseen exam |
| Guided Independent Study | Independent study | 22 | 1:00 | 22:00 | Preparation time for lectures |
| Guided Independent Study | Independent study | 10 | 1:00 | 10:00 | Background Reading on lectured content |
| Total | 100:00 |
Jointly Taught With
| Code | Title |
|---|---|
| MAS3919 | Foundations of Machine Learning |
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. In addition, directed research and reading of an advanced topic is used to develop the students’ ability to learn independently.
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 Methods
The format of resits will be determined by the Board of Examiners
Exams
| Description | Length | Semester | When Set | Percentage | Comment |
|---|---|---|---|---|---|
| Written Examination | 120 | 2 | A | 80 | 2 hour written exam, comprising a Section A and a Section B |
Exam Pairings
| Module Code | Module Title | Semester | Comment |
|---|---|---|---|
| Foundations of Machine Learning | 2 | N/A |
Other Assessment
| Description | Semester | When Set | Percentage | Comment |
|---|---|---|---|---|
| Prob solv exercises | 2 | M | 20 | Coursework 2. Up to 6 page typeset report based upon a set assignment comprising open-ended questions. |
Formative Assessments
Formative Assessment is an assessment which develops your skills in being assessed, allows for you to receive feedback, and prepares you for being assessed. However, it does not count to your final mark.
| Description | Semester | When Set | Comment |
|---|---|---|---|
| Prob solv exercises | 2 | M | Coursework 1. 40 minute class test, conducted during one of the timetabled one hour lecture slots. |
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.
Reading Lists
Timetable
- Timetable Website: www.ncl.ac.uk/timetable/
- MAS8607's Timetable