Our People
Dr David Tena Cucala
Research Member of Common Room
Research Associate
Department of Computer Science
I work in the area of Knowledge Representation and Reasoning in the field of Artificial Intelligence (AI). I am trying to answer the question: what does it mean for intelligent systems to possess knowledge? How is it realised in practice? Traditionally, the field of AI has approached this question using logic; more precisely, knowledge expressed as logical statements explicitly stored in the system. However, many intelligent systems (brains, for example) do not follow this approach and yet they show impressive capabilities. More recently, researchers have attempted to answer these questions for machine learning (ML) models. My recent work looks at graph neural networks (GNNs) and tries to understand their operation in terms of logical rules that use human-understandable predicates. I am also interested to see whether a similar analysis can be applied to other ML models, such as transformers.