Artificial intelligence in fundamental physics: from modeling to understanding

Artificial intelligence tools are becoming ubiquitous in everyday life as a tool for facilitating and speeding up tasks, such as retrieving information. In fundamental physics they are instead being used as tools for discovery. Specifically drawing from examples in high-energy physics, I show that AI and machine learning are enabling the access to hidden structures of physical systems, through modeling, performing inference, generalizing, and finding connections that would otherwise be very difficult or impossible to unravel.