I'm a research scientist at Google DeepMind working on problems related to artificial intelligence.

My research is focused on getting computers to learn generative models of images that not only produce good samples but also good explanations. This typically involves a mix of machine learning, deep learning, approximate probabilistic inference, and increasingly, elements of reinforcement learning.

In 2014 I was a post-doctoral researcher at Microsoft Research Cambridge, and a member of the Machine Learning and Perception group led by Christopher Bishop.

I did my PhD at the University of Edinburgh, where I was a Carnegie scholar. My supervisors were Christopher Williams, Bob Fisher and Amos Storkey.

During my PhD I was also at Oxford University working with Andrew Zisserman, and at Microsoft Research working with John Winn and Nicolas Heess.

Since 2012 I have helped organise the PASCAL Visual Object Classes challenge. In 2014 I also helped run the MSc industry project programme at University College London with Thore Graepel.

NIPS workshop

I co-organised the NIPS 2015 workshop on Black Box Learning and Inference, that was held in Montréal, Canada on December 12, 2015. Videos of the talks and panels will be made available shortly.

Curriculum Vitae

Last updated 22 Dec 2015: Short CV, Long CV.

Publications

Theses

Selected talks

Other things