publications. Most of my current research focusses on machine learning, especially fundamental theoretical and algorithmic contributions. This includes Deep Bayesian learning, k-shot and transfer learning, deep learning for small data, learning using simulators (e.g. approximate Bayesian computation), Gaussian processes and new forms of approximate inference including online inference.
On the neuroscience / cognitive science / signal processing side I do remain actively involved in:
1. Bayesian inference as models of perception and cognition
2. Machine learning methods for neuroscience
3. The intersection between inference and signal processing
The background that I look for is typically one of the following: engineering (esp. information engineering / electrical engineering), physics (esp. theoretical / statistical physics), maths (statistics), computer science. Strong continuous maths skills are essential. Except in very special cases, you will need to have a first class degree or equivalent and typically successful applicants were at or near the top of their cohort. Some practical experience with machine learning is strongly desired either through a research project, coursework or in industry.
Information about the admissions procedure
For general information about PhD admissions, please see here. You should carefully check information about deadlines for applications. Also, be aware that if you apply late on in the year (after January), I may have already offered as many places as I am prepared to, so don't leave it too late to apply.
You should carefully check the funding page to ascertain what funding sources you can apply for. You will need to tick the correct boxes on the application form to be eligible for these. In some circumstances, it is possible that I will have funds to allocate directly, but this is rare as most funding is centrally allocated.
Information about the admissions forms
We have to assess your application on three criteria:
1. academic performance (make sure to ensure evidence for strong academic achievement e.g. position in year, awards etc.)
2. references (clearly your references will need to be strong, they should also mention evidence of excellence as quotes will be drawn from them)
3. research (detail your research experience, especially that which relates to machine learning)
You will also need to put together a research proposal. We do not offer individual support for this. It is part of the application assessment i.e. ascertaining whether you can write about a research area in a sensible way and pose interesting questions. It is not a commitment to what you want to work on during your PhD?. It should be 250 words long. This aspect of the application does not carry a huge amount of weight so do not spend a large amount of time on it. A good way to generate ideas for topics is to look at my recent publications or those from the machine learning group more generally.
If you want to find out more about the core technical material that is relevant to the Group's reseach, please see the Group's recommended reading list.