Researcher in Artificial Intelligence
In my work I want to build AI systems that work in more human-like ways. I explore how people choose to represent their problems and how they solve them using informal techniques. I combine AI reasoning with machine learning techniques in order to obtain explainable model predictions as well as to be able to apply them in applications where it is important to understand the machine's output. I am also interested in combining neural techniques (including LLMs) with symbolic methods in reasoning, in particular for mathematical discovery. I apply my theoretical work to clinical decision support systems in personalised cancer medicine as well as in education to personalised tutoring systems.
Some research projects:
I am a member of the Artificial Intelligence research group and also of the Programming, Logic, and Semantics Group. I am also an associate fellow at the Leverhulme Centre for the Future of Intelligence.
Here are some suggestions for student projects (local access only).