Machine Learning

Increasing amounts of data are being captured, stored and made available electronically. Courses in this topic and the related topics listed below will train students in techniques to analyse, interpret and exploit such data, and to understand when particular methods are suitable and/or applicable.

If you want to specialize in machine learning, we recommend taking at least 30 credits from the “Foundations and methods” list below. In addition, we recommend taking at least 20 credits from one of the lists of Related Topics (either “Applications” or “Algorithms and Infrastructure”). These courses will broaden your knowledge of how machine learning relates to other areas, and may also help you by providing more flexibility when it comes to choosing a dissertation topic.

Please click on the course links to check the “other requirements” in the descriptor of each course to be sure it is suitable for you. You can select your courses before you arrive, and will be able to discuss your choices with your Student Adviser/Cohort Lead.

Semester 1:

• Applied Machine Learning (AML) INFR11211 (20 credits): This course will equip students with knowledge and a set of practical tools that can be applied to solve real-world machine learning problems. It will introduce a number of machine learning methods and concepts, help you understand how they work, and how to apply them. This course is a stand alone introduction to machine learning but is also suitability for students who have some limited prior machine learning experience.
• Probabilistic Modelling and Reasoning (PMR) INFR11134 (20 credits): The course covers foundational material in probabilistic machine learning with a focus on unsupervised learning. It will provide you with tools and skills to understand many different methods from first principles and develop new ones. The course is suitable for students who are comfortable with mathematical derivations or have taken a first course in machine learning already.

Semester 2:

• Methods for Casual Inference INFR11207 (10 credits)

This course explores causal inference techniques that allow us to move away from merely associational statements and instead towards cause-effect statements. This is a relatively advanced course and students are expected to be familiar with foundations of probability, statistics, and calculus. PMR is a recommended co-requisite.

• Advanced Topics in Machine Learning (20 credits) 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.

Full year:

• Machine Learning Practical INFR11132 (20 credits): This course focusses on the implementation and evaluation of deep learning methods. It is recommended for most students specialising in machine learning. But please note that it is not a stand-alone introduction to machine learning. It assumes prior knowledge with the maths commonly used in machine learning and prior programming experience. An alternative are application courses starting in semester 2 that cover considerable material on neural networks (e.g., NLU+ or ASR in the Natural Language Processing topic area).

The following topics provide examples of domains where machine learning concepts and methods are applied, and courses in these topics discuss specific machine learning models relevant to that domain. Some courses are more engineering-focused while others explore ways to apply machine learning and related computational models to scientific questions.

Even if your main interest is core machine learning, we recommend taking at least 20 credits from this list or the Algorithms list, and students interested in applied machine learning or data science may do more of these application courses. Note that several application areas have two-course sequences. In most cases it is recommended, but not required, that you take the first course in the sequence if you want to take the second one. The topic pages below provide more details.

Cognitive Science and Neuroinformatics

Computation in Social Systems

Natural Language Processing

Vision, Robotics, and Autonomous Agents

In addition, the following course discusses applications of AI more generally:

Case Studies in AI Ethics INFR11206 (10 credits, Semester 2)

These courses cover intermediate-level knowledge of algorithms and data structures, as well as more advanced methods for optimisation and dealing with big data, all of which can potentially be useful for the research and practice of machine learning.

Databases and Data Management courses

Additional related courses:

Algorithmic Game Theory and its Applications INFR11020 (10 credits, Semester 2)

You can also consider courses from the Statistics with Data Science MSc, especially if you are looking for additional theoretical background for (e.g.) PhD study. As this MSc is hosted in the School of Mathematics, these options are for those with a stronger mathematical background.

Statistics with Data Science MSc

Register as early as possible for external courses (in induction week). They can have limited numbers, earlier deadlines than Informatics, and course materials on Learn are only available after registering.

Machine learning is a very popular area right now and can be useful in other areas of Informatics, but you shouldn’t feel you must do it just because others are. If you do want to learn a bit about it, we recommend one of two options:

1. Take Applied Machine Learning, which provides a general background and introduction to the common tools and methods.

OR

2. Take one or more of the courses from the machine learning application topics. Although some courses may not have “machine learning” in the title, most of them will introduce you to some basic machine learning methods and how they apply to a particular domain.

In both cases, check beforehand that you meet the requirements and prerequisites (e.g. see math and programming sections below).