Our research covers assorted issues in both theoretical and applied machine learning. At present we are interested in: - Computational learning theory. How can we better understand the properties of machine learning algorithms in terms of, for example, the relationship between the number of training examples used and their performance? - Bayesian inference. This approach to machine learning continues to offer state-of-the-art performance in many applications. However the continuing problem of the analytical intractability of many of the fundamental calculations continues to provide opportunities for research into improved approximation techniques. - Quantum computation for machine learning. It is known that, should a practical quantum computer become viable, quantum computation will provide definite benefits in certain areas. However little is known about the extent to which it might benefit machine learning. - Machine learning techniques for automated theorem proving.
