Machine Learning

Information on the specialist area Machine Learning.

Prior to 2015/16 this specialism was called “Learning from Data”.

Increasing amounts of data are being captured, stored and made available electronically. The aim of the Machine Learning specialist area is to train students in techniques to analyze, interpret and exploit such data, and to understand when particular methods are suitable and/or applicable. Machine learning techniques include probabilistic and statistical modelling, pattern recognition and neural networks, and exploratory analysis or data mining. The specialist area will prepare students for entry into PhD programmes or for employment in commercial environments and/or scientific/engineering research.

Students registered in this Specialist Area are recommended to select at least fifty credit points from these courses, including both the core courses. Please note courses are subject to availability.

Video introduction to the specialism (.mp4)


Semester 1 Semester 2
Core Courses

Machine Learning and Pattern Recognition (20 credits)

Probabilistic Modelling and Reasoning (20 credits)

Optional Courses

Bioinformatics 1

Extreme Computing

Introductory Applied Machine Learning (20 credits, level 10)

Machine Learning Practical (20 credits, full year)

Social and Technological Networks

Advanced Vision

Applied Databases

Bioinformatics 2

Data Mining and Exploration

Neural Information Processing

Randomness and Computation

Reinforcement Learning


See also guidance from one of the machine learning lecturers. The guidance includes external statistics courses that could be of interest, and general course selection advice. In particular, Introductory Applied Machine Learning (IAML) is strongly recommended unless you have taken a similar course before. Both core courses have extensive mathematical pre-requisites. These requirements are outlined, with preparatory material, on their webpages. If you do not have the required mathematical background you can still do a significant number of courses involving learning from data while following another specialism.


Related links

Informatics sortable course list

Informatics course timetable