Lecture Courses

I teach two Undergraduate lecture courses in the Department of Computer Science and Technology.

For 2021/22 Machine Learning and Bayesian Inference will be given as pre-recorded lectures. These are the same as the lectures for 2020/21 and are available here.

Artificial Intelligence will be lectured in-person, however the syllabus is as for 2020/21 so the videos at the same location remain relevant.

Artificial Intelligence

In the second year I teach Artificial Intelligence. This is a fairly standard introduction to AI in general, covering core material such as search, game playing, constraint satisfaction, knowledge representation and reasoning, plannning and machine learning.

You can find the teaching materials here.

Machine Learning and Bayesian Inference

In the third year, I teach a more specialized course on Machine Learning and Bayesian Inference. This is quite a detailed, foundational course covering fundamental algorithms such as maximum likelihood and maximum a posteriori, support vector machines, Bayesian regression, Gaussian processes and Bayesian networks. All this is lectured from a mathematical/probabilistic perspective. (If you don't understand linear regression, then you really don't understand anything involving the word "deep".)

You can find the teaching materials here.

Suggestions for Projects

My suggestions for Part II and Part III projects are here.

(Local access only.)

The department has a collection of Dissertations from previous years that you may want to look at for inspiration here.