Can we discover fundamental laws from data using AI?

Mihaela van der Schaar

University of Cambridge

Thursday 10th April 2025

14:30:00

Aula IV - Edificio 11 - Architettura

Discovering fundamental laws governing systems from observational data has long been a hallmark of scientific inquiry. In this talk, I will discuss how recent advances in AI and machine learning enable the automated discovery of scientific laws and governing equations directly from data, revolutionizing the way we unravel system dynamics in numerous domains, including medicine and pharmacology. I will highlight how AI-driven methods uncover underlying principles, from classical physics to biological systems to medicine, and offer insights into future possibilities—transforming data-driven observations into interpretable and actionable scientific knowledge. Yet, can we push this boundary further—going beyond equations entirely? I will introduce direct semantic modeling, a novel paradigm where AI learns the behavior of dynamical systems directly from data without relying on closed-form equations. This semantic approach offers intuitive, human-interpretable insights into system evolution, marking a transformative leap in scientific discovery. (This talk is based on recent research with Krzysztof Kacprzyk, Tennison Liu and Sam Holt.)

Mihaela van der Schaar is the John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge. In addition to leading the van der Schaar Lab, Mihaela is founder and director of the Cambridge Centre for AI in Medicine (CCAIM). Mihaela was elected IEEE Fellow in 2009 and Fellow of the Royal Society in 2024. She has received numerous awards, including the Johann Anton Merck Award (2024), the Oon Prize on Preventative Medicine from the University of Cambridge (2018), a National Science Foundation CAREER Award (2004), 3 IBM Faculty Awards, the IBM Exploratory Stream Analytics Innovation Award, the Philips Make a Difference Award and several best paper awards, including the IEEE Darlington Award. She was a Turing Fellow at The Alan Turing Institute in London between 2016 and 2024. Mihaela is personally credited as inventor on 35 USA patents, many of which are still frequently cited and adopted in standards. She has made over 45 contributions to international standards for which she received 3 ISO Awards. In 2019, a Nesta report determined that Mihaela was the most-cited female AI researcher in the U.K.