The Artificial Intelligence Modelling Lab (AIML) engages in a range of theoretical and applied research in Artificial Intelligence (AI) and Machine Learning (ML). Particular areas of interest include interactive theorem proving, formal modelling and verification, machine learning and its combination with higher level symbolic reasoning, as well as its application to healthcare and other complex, real-world domains.
- Survey pre-print on Neurosymbolic AI for Reasoning on Graph Structures is out on arXiv
- Job Opportunity: Research Research Associate in Neurosymbolic AI
- New Project funded by the Edinburgh Laboratory for Integrated Artificial Intelligence (ELIAI)
- Opportunity: Multimorbidity PhD Programme for Health Professionals
- Job Opportunity: Research Fellow in Knowledge Representation for Medical Artificial Intelligence
Some of our External Engagement
I will present ongoing work on building SaSSY-CLEVR, a heterogeneous benchmark suite which can serve as a common testing ground for different neuro-symbolic reasoners to compare their strengths and limitations. If time allows, I will also share a series of experiments to assess NeSy models on CLEVR-Hans3.
Speaker: Xuelong An
I will discuss some work that I plan to do involving neurosymbolic AI on a biomedical knowledge graph to unveil the most likely paths by which these compounds execute their mechanism of action.
Speaker: Lauren DeLong
In recent years there has been increasing interest in AI applications in Plastic Surgery. I will report on a review I am conducting which explores the current legislative environment for AI research that uses patient image datasets and summarises key ethical considerations that are raised in existing AI burns care research. A basic framework for the reporting of burns image datasets that are used for AI research will also be suggested.
Speaker: Fiona Smith