COMP61011 : Foundations of Machine Learning



Lab sessions


Additional resources

Maintained by G.Brown

Course lecturers: Gavin Brown and David Wong

What is this module about?

This is module 1 in the Learning from Data theme. Machine Learning is concerned with creating mathematical "data structures" that allow a computer to exhibit behaviour that would normally require a human. Typical applications might be spam filtering, speech recognition, medical diagnosis, or weather prediction. The data structures we use (known as "models") come in various forms, e.g. trees, graphs, algebraic equations, and probability distributions. The emphasis is on constructing these models automatically from data---for example making a weather predictor from a datafile of historical weather patterns. This course will introduce you to the concepts behind various Machine Learning techniques, including how they work, and use existing software packages to illustrate how they behave.

I studied ML in my undergrad degree, so should I do this module?

If you have sat an undergraduate ML course (particularly my COMP24111) then you may feel you know all this material. In fact we will cover virtually the same topics - however, you almost certainly will not have covered this material in the same depth as we will cover it. We will study why and how these methods work, at a very deep level. This is not a course on how to use ML techniques. It is a course on the foundations, the deeper aspects, and will prepare you for more advanced modules later in the year, as well as MSc projects next summer.

Do I have to know any maths?

This course has a fairly high mathematical content. We will be making extensive use of matrix algebra, probability theory, and calculus. Take a look at the Mathematics Primer for the course. It should be stressed that you are not expected to have all this before the start - however if you think with some hard work you could get to grips with most of it, then fine, if not, then maybe the course is not for you.