by
DrZiming Liu
(Massachusetts Institute of Technology)
→
Asia/Shanghai
408 (CHEP)
408
CHEP
South Building, School of Physics, PKU
Description
Physics-guided AI is an emerging paradigm of research that aims to principally integrate physics in AI models and algorithms to learn patterns and relationships from data that are not only accurate on validation data but are also physically consistent with known scientific theories. In this talk, I will cover both directions between AI and physics: (1) AI for physics: how to exploit AI to extract information (dynamical equation, conservation laws etc.) from physical systems; (2) Physics for AI: how physical insights help symbolic regression and “pregression”.