Ilan has long been driven by two passions – social justice on the one hand, and the joint power of mathematics and computing on the other. He has an interdisciplinary background in applied mathematics and philosophy, and took two years out to run a youth movement before returning to do his masters in Mathematics at Oxford University in 2016. He later worked as a research assistant at Oxford’s Mathematical Institute, before beginning his PhD there in October 2018.
Since 2016, Ilan has picked up a growing interest in machine learning and its potential to change the world for the better, substantial risks notwithstanding. Alongside his PhD studies, he is also currently a co-director of the Rhodes Artificial Intelligence Lab (RAIL), a student group which, among other things, works pro-bono with NGOs, Governments and companies to develop machine learning solutions which have social impact.
Deep learning research has seen a massive surge in research and applications over the last six years. It achieves state-of-the-art (and sometime even super-human) performance on classical supervised learning tasks, and is the basis many of the applications of machine learning that we all interact with every day. However, despite these successes there remain a large number of crucial open questions. Why do these methods generalise (and therefore perform) as well as they do? Are there more principles ways of designing deep neural networks? And can we guarantee when they will work? Ilan’s research will contribute to this growing body of theory for deep learning, with a particular focus on understanding adversarial examples - datapoint engineered to trick well trained models - with a view to building safer, more robust algorithms.