Geoff Keeling

Associate Fellow (former Research Assistant, 2019 - September 2020)


Geoff was a Research Assistant on the Understanding Medical Black Boxes project. He was awarded a PhD from the University of Bristol in June 2020, working with Richard Pettigrew and Brad Hooker on the ethics of automated vehicles. His main research interest is moral philosophy. In particular, how tools from formal epistemology, decision theory and philosophy of science can help us address novel ethical questions presented by emerging technologies.

In September 2020 he took up the post of Interdisciplinary Ethics Fellow at Stanford University. Geoff is now based between the Center for Ethics in Society and the Institute for Human-Centered Artificial Intelligence

Geoff also holds an MA in Philosophy from the University of Bristol, and a BSc in Philosophy, Logic and Scientific Method from the London School of Economics.

More information about Geoff’s research can be found on his webpage.

Back to people

Geoff Keeling


Geoff Keeling

Medical Black Boxes and AI Explainability

While modern AI systems can display impressive accuracy in medical tasks, it can be difficult to fully explain how they work or why they make individual decisions. The development of techniques for making systems “intelligible” or “explainable” is a growing focus of research within machine learning. However, there is still no consensus on what “understanding” […]