van der Schaar Lab

Inspiration Exchange: Frontiers in ML Interpretability

The van der Schaar Lab’s 21st Inspiration Exchange session took place on October 25, 2022. The session covered Frontiers in ML Interpretability. This session was particularly engaging and interactive, with more than 150 participants joining the session live.

To start the session, Prof. Mihaela van der Schaar presented a tutorial and introduction to ML interpretability, motivating their use in the context of healthcare and medicine. Subsequently, Ph.D. student Jonathan Crabbé presented his recent work on Concept Activation Regions, a generalised framework for concept-based explanations. Additionally, Ph.D. student Alicia Curth presented the ITErpretability benchmark, which utilises interpretability as a means to benchmark treatment effect models.

We then held our roundtable discussion, where our industry guests Dr Been Kim (Google Brain) and Dr Jianying Hu (IBM) shared their perspectives on ML and medical impacts of the presented works. The session was then opened up to the audience for Q&A and general discussion.

Inspiration Exchange – Frontiers in ML Interpretability

Sign up for our upcoming sessions: https://www.vanderschaar-lab.com/engagement-sessions/inspiration-exchange/#

The lab’s publications are here: https://www.vanderschaar-lab.com/publications/

Sam Holt

Sam holds a M.Eng. in Engineering Science from the University of Oxford, where he graduated with a first-class degree and numerous awards for academic excellence (placing 2nd in the year for his master’s thesis).

In the course of his studies, Sam undertook two machine learning research internships at the University of Oxford: one researching detecting and tracking cars in noisy radar data (for a self-driving car), and the other in economic time-series forecasting. He also initiated his own original research into noise reduction on propellers, developing a propeller design that emits 44% less noise.

Upon graduating, Sam worked for an Oxford spin out, Mind Foundry, investigating dialogue systems for an industrial client. He has also authored and taught an online machine learning course covering recent work, and shared his passion for machine learning through teaching students in a classroom at a London-based tech-MBA program. Previously, he has collaborated and led three quantitative financial research projects, alongside working in data science and software engineering for a quantitative finance startup, Fifth Row Technologies. He has also created proof-of-concept automation ML tools to help doctors in GP practices.

Sam’s research is supported by funding from AstraZeneca.