skip to primary navigationskip to content

Department of Computer Science and Technology



Course pages 2023–24

Advanced topics in machine learning

Principal lecturers: Prof Mateja Jamnik, Dr Carl Henrik Ek
Taken by: MPhil ACS, Part III
Code: R255
Term: Lent
Hours: 16
Format: In-person lectures and seminars
Prerequisites: Machine learning experience essential, like from L48, L101, L46 or similar
Moodle, timetable


This course explores current research topics in machine learning in sufficient depth that, at the end of the course, participants will be in a position to contribute to research on their chosen topics. Each topic will be introduced with a lecture which, building on the material covered in the prerequisite courses, will make the current research literature accessible. Each lecture will be followed by up to three sessions which will typically be run as a reading group with student presentations on recent papers from the literature followed by a discussion, or a practical, or similar.


Each student will attend 3 topics and each topic's sessions will be spread over 5 contact hours. Students will be expected to undertake readings for their selected topics. There will be some group work.

There will be a briefing session in Michaelmas term.


Students choose five topics in preferential order from a list to be published in Michaelmas term. They will be assigned to three topics out of their list. Students are assessed on one of these topics which may not necessarily be their first choice topic.

The topics to be offered in 2023-24 are yet to be decided but to give an indicative idea of the types of topics, the ones offered in 2022-23 were:

  1. Imitation learning Dr A. Vlachos
  2. Machine Learning for Collective intelligence Prof A. Prorok
  3. Bias in datasets Dr M. Tomalin
  4. Probabilistic Numerics: Computation as Machine Learning Dr C. H. Ek
  5. Explainable AI Prof M. Jamnik
  6. Unconventional approaches to AI Dr S. Banerjee
  7. Bias, Variance and Fairness: Stochasticity in Decision Making Prof N. Lawrence
  8. Physics and Geometry in Machine Learning Dr C. Mishra
  9. AI Safety Dr F. Huszar and N. Rajkumar
  10. Diffusion Models and SDEs Dr C. H. Ek and F. Vargas

On completion of this module, students should:

  • be in a strong position to contribute to the research topics covered;
  • understand the fundamental methods (algorithms, data analysis, specific tasks) underlying each topic;
  • and be familiar with recent research papers and advances in the field.


Students will typically work in groups to give a presentation on assigned papers. Alternatively, a topic may include practical sessions. Each topic will typically consist of one preliminary lecture followed by 3 reading and discussion sessions, or several lectures followed by a practical session. A typical topic can accommodate up to 9 students presenting papers. There will be at least 10 minutes general discussion per session.

Full coursework details will be published by October.


Coursework will be marked by the topic leaders and second marked by the module conveners.

  • Participation in all assigned topics, 10%
  • Presentation or practical work or similar (for one of the chosen topics), 20%
  • Topic coursework (for one of the chosen topics), 70%

Individual topic coursework will be published late Michaelmas term.

Assessment criteria for topic coursework will follow project assessment criteria here:

Please note that students will be assessed on one of their three chosen topics but this may not be their first choice.

Recommended reading

To be confirmed by each topic convenor.