Undergraduate Course: Advanced Topics in Machine Learning (INFR11286)
Course Outline
| School | School of Informatics |
College | College of Science and Engineering |
| Credit level (Normal year taken) | SCQF Level 11 (Year 4 Undergraduate) |
Availability | Available to all students |
| SCQF Credits | 20 |
ECTS Credits | 10 |
| Summary | This is an advanced technical course intended for those who wish to be technical experts in their future machine learning roles, enter research in machine learning or develop new ideas and technologies in the future. It should be taken after a more general introduction to machine learning.
Each year the course selects topics representative of current machine learning research and practice, such as algorithms behind generative AI, theoretical foundations of deep learning, and techniques for learning from structured data. By working through the foundations of these topics, students will develop the expertise required to discuss how the techniques work and could be applied, and to be able to consider potential variants and combinations of methods. |
| Course description |
The course consists of multiple independent topic tracks (usually three). Each track covers one important direction in machine learning, including its mathematical foundations and the ways in which it is applied and adapted in current research and practice.
Although topics may range from mainly theoretical to applied, a working knowledge of mathematical concepts (linear algebra, multivariate calculus, probability) and some programming experience are assumed.
Depending on the number of tracks, each track will consist of about one lecture hour per week. Each track will have a series of un-assessed questions for study, supported by tutor-supported study sessions, a class forum, and some targeted feedback.
The topics vary from year to year. Some examples of possible topic areas are: Graph neural networks, Deep generative models, Variational inference, Optimization and overparameterization in neural networks, etc. The course website describes the details for the current year.
The course will cover the algorithmic and mathematical principles that underlie machine learning methods. It complements other ML courses such as Applied Machine Learning (INFR11211) and Probabilistic Modelling and Reasoning (INFR11134) by introducing more advanced topics and recent developments in the field. We assume that students have taken a general introduction to machine learning either in Edinburgh, such as Applied Machine Learning (INFR11211) or Machine Learning (INFR10086), or similar courses elsewhere. This course is not a replacement for, but rather a complement to, domain-specific courses in Natural Language Processing, Computer Vision, or Robotics.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | This course is open to all Informatics students including those on joint degrees. For external students where this course is not listed in your DPT, please seek special permission from the course organiser.
This course requires practical mathematical application of algebra, vectors and matrices, calculus, probability, and problem solving. For example, topics may require you to differentiate linear algebra expressions with respect to vectors, interpret inner-products and quadratic forms geometrically, and compute expectations of linear algebra expressions under simple distributions. Some of the required details can be learned during the course, but some experience with most of these mathematical topics is required.
We assume that students have taken a basic introduction to machine learning that covers how to split and process data to apply, tune, and compare some baseline machine learning methods.
There are no assessed programming exercises in this course. However, we assume familiarity with programming and basic computer science (such as big-O complexity), so that we can consider questions about the practical implementation of methods. Students could be required to read short snippets of machine learning code using a popular framework (such as PyTorch or Jax in Python). |
Information for Visiting Students
| Pre-requisites | This course requires practical mathematical application of algebra, vectors and matrices, calculus, probability, and problem solving. For example, topics may require you to differentiate linear algebra expressions with respect to vectors, interpret inner-products and quadratic forms geometrically, and compute expectations of linear algebra expressions under simple distributions. Some of the required details can be learned during the course, but some experience with most of these mathematical topics is required.
We assume that students have taken a basic introduction to machine learning that covers how to split and process data to apply, tune, and compare some baseline machine learning methods.
There are no assessed programming exercises in this course. However, we assume familiarity with programming and basic computer science (such as big-O complexity), so that we can consider questions about the practical implementation of methods. Students could be required to read short snippets of machine learning code using a popular framework (such as PyTorch or Jax in Python).
This is a fourth-year honours level course; students are expected to have an academic profile equivalent to the first three years of this degree programme. Study equivalent to the following University of Edinburgh courses is recommended: Introductory Applied Machine Learning (INFR10069) OR Introductory Applied Machine Learning (INFR11182) OR Machine Learning and Pattern Recognition (INFR11130) |
Course Delivery Information
|
| Academic year 2025/26, Available to all students (SV1)
|
Quota: None |
| Course Start |
Semester 2 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
200
(
Lecture Hours 30,
Supervised Practical/Workshop/Studio Hours 10,
Summative Assessment Hours 2,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
154 )
|
| Assessment (Further Info) |
Written Exam
100 %,
Coursework
0 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
100% Examination |
| Feedback |
Targeted individual feedback will be provided on some of the formative work provided throughout the materials. Students are expected to engage with the course content in weekly workshop sessions with teaching assistants, and to discuss any unanswered questions on the class forum. |
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- identify how an aspect of an advanced machine learning topic applies to a given applied problem.
- derive mathematical details of machine learning methods in the topic area.
- critically compare and contrast alternative choices or variants of methods or approaches in the area.
- create accessible and useful explanations of the workings and failure modes of machine learning methods, including appropriate mathematical and implementation detail.
- identify the ethical and societal implications, including both benefits and risks, of the deployment of machine learning methods in the area.
|
Reading List
| Reading material such as papers and lecture notes will be provided via the course website. |
Additional Information
| Graduate Attributes and Skills |
Apply critical analysis, evaluation and synthesis to current issues, or issues that are informed by forefront developments in the subject / discipline / sector.
Identify, conceptualise, and define new and abstract problems and issues.
Develop original and creative responses to problems and issues.
Critically review, consolidate and extend knowledge, skills, practices and thinking in subject / discipline / sector.
Deal with complex issues and make informed judgements in situations in the absence of complete or consistent data / information. |
| Keywords | ATML,Machine learning,geometric learning,GenAI,representation learning,artificial intelligence |
Contacts
| Course organiser | Dr Rik Sarkar
Tel: (0131 6)50 4444
Email: Rik.Sarkar@ed.ac.uk |
Course secretary | Miss Toni Noble
Tel: (0131 6)50 2692
Email: Toni.noble@ed.ac.uk |
|
|
University Homepage