Eleanor Ruth Mill

I am interested in the way we use artificial intelligence in society, for the benefit of society. Specifically, how do we make sure that it is used in an ethical way? That we are confident that no bias is creeping in? How do we make sure that it does no harm - either to people or the world around us? My research explores the opportunities and challenges associated with the explainability of artificial intelligence - a strategy to ensure that we can interrogate and understand the intricate workings of complex machine learning models. Through the use of explainability techniques we can retain an element of control over these complex models and be confident in the fairness of their outputs.