I am a final year PhD student in machine learning advised by Prof. Carl Rasmussen at the University of Cambridge. My research focuses on improving uncertainty quantification in neural networks (NNs) using Bayesian principles. To do that, we need to understand our choice of prior affects the properties of trained NNs, and how to do accurate approximate inference. I’m also interested in AI safety.
I was a co-organiser of the ICLR 2019 workshop “Safe Machine Learning: Specification, Robustness and Assurance”.
I used to run the Engineering Safe AI reading group about technical approaches to ensuring AI has a positive impact in society, as part of Effective Altruism Cambridge.