Scientific Machine Learning: when Fundamental Sciences meet Artificial Intelligence
With Alfio Quarteroni - PoliMi, EPFL
Aula Magna Budinich
Abstract:
Despite the extraordinary progress made by artificial intelligence systems in recent years, they remain prone to inaccuracies, uncertainties, and often a lack of transparency. For this reason, they are sometimes referred to as "black box algorithms." Scientific machine learning, which combines data-driven machine learning algorithms with digital models based on physical principles, represents an ideal platform for a virtuous synergy between artificial intelligence and human knowledge, grounded in natural laws and rigorous scientific principles. In my presentation, these concepts will be illustrated within the context of a specific application: the development of a mathematical simulator that fully reproduces cardiac function.
Alfio Quarteroni is an internationally renowned Italian mathematician specializing in numerical analysis, mathematical modeling, and computational sciences. He is Professor Emeritus at the Swiss Federal Institute of Technology in Lausanne (EPFL) and a Professor Emeritus at the Politecnico di Milano.