Lee Sharkey

PhD Student
Google scholar
Personal website
CV (pdf)


I’m interested in building safe, generally intelligent machines that can solve humanity’s problems: To help understand how to make intelligent systems safe, I focus on interpreting what neural networks have learned; to understand how to build general intelligence, I connect systems neuroscience, deep reinforcement learning, and cognitive science using computational models. I did an initial degree in preclinical medical studies at the University of Cambridge, where I majored in neuroscience. I subsequently dropped out of medical school to work for several years in international public health, which exposed me to the deeply tangled web of humanitarian problems that the world faces. Discontent with working on only one of those problems, I switched to study artificial intelligence, which motivated MSc degrees in Data Analytics (University of Glasgow) and Neural Systems and Computation (University of Zurich/ETH Zurich) and my current research PhD here in the Human and Machine Cognition lab.