Applied Machine Learning (MSc)
Informatics (INFR11211), Semester 1, 2026
Week 0 Announcement
Greetings AML students!
This is an announcement for all those registered for Applied Machine Learning (AML - INFR11211) in semester one. Please read this carefully as it contains important information.
The full course schedule and lectures are available on this page.
Class Sessions
The first class meeting is next week (Tuesday 22nd September) at 4:10pm in Appleton Tower - Lecture Theatre 5.
Make sure to attend this session on time as we will discuss many of the logistics of the course and you will also have an opportunity to ask questions there. It will be recorded in case you cannot make it.
Lectures, Labs, and Tutorials
The lectures for AML are pre-recorded and will be available from our course website one week in advance of each topic. There will also be an in-person tutorial or lab session held every other week, with labs in weeks 3, 5, 7, 9, and tutorials in weeks 4, 6, 8, 10. We will discuss this in more detail in our class session on Tuesday.
Questions
For any queries, please come to the class session or post on Piazza, i.e. don’t respond to this email.
We hope that you will learn a lot about machine learning and how to apply it over the semester!
Best wishes
Oisin Mac Aodha and Siddharth N.
AML Course Organisers
In this course we will be introducing a number of machine learning methods and concepts, helping to understand how they work, and how to apply them.
Those wanting to conduct research in, and develop, machine learning methods should consider taking PML (INFR11298) instead. For general information on different machine learning courses at Informatics, see here.
On successful completion of this course, you should be able to:
- Explain the scope, goals and limits of ML, and the main sub-areas of the field.
- Describe the various techniques covered and where they fit within the structure of the discipline.
- Apply the taught techniques to data, to solve ML problems, using appropriate software.
- Analyse ML techniques in terms of their limitations and applicability to different problems, as well as potential ethical concerns.
- Compare and evaluate the performance of ML techniques using systematic approaches to conducting experiments and assessing scientific hypotheses.