The Bayesian Artificial Intelligence research lab was established in late 2018, as part of the EPSRC Fellowship project “Bayesian Artificial Intelligence for Decision Making under Uncertainty”, and is part of the wider MInDS (Machine Intelligence and Decision Systems) research group.
The lab’s main research focuses on unsupervised machine learning algorithms for causal structure learning. Our work extends to learning causal Bayesian Networks (BNs) for prediction and optimal decision-making under uncertainty, including approaches that combine data with knowledge, and learn in the presence of missing data and latent confounders.
Broadly, the lab’s research activities include:
- Explainable Artificial Intelligence
- Bayesian Inference
- Causal Machine Learning
- Causal Discovery
- Knowledge-Based Systems
- Intelligent Decision Making
- Statistics and Probability Theory
- Uncertainty Quantification
We apply our research to a wide range of fields including medicine and healthcare, sports, finance, forensics, and gaming.