My research focuses on “Responsible AI”. The key research goal of "Responsible AI" is to develop new artificial intelligence and machine learning models that embed fairness, accountability, transparency, and trustworthiness into them for ensuring ethical outcomes and long-term public confidence in the deployment of automated systems.

The three research strands are:
1. “Ethical and Trustworthy AI” (auditing and mitigating inappropriate bias against protected subgroups, and improving transparency of algorithmic systems);

2. “Safe and Robust AI” (ensuring reliably good performance even when encountering extreme situations); and

3. “Interactive AI” (facilitating a deep mutual understanding between a user and an algorithmic system via argumentative interactive lifelong learning).

The three research strands have received funding from EPSRC (EthicalML) and ERC (BayesianGDPR).