汇报标题 (Title)：Towards Third Wave AI: Interpretable, Robust Trustworthy Machine Learning for Diverse Applications in Science and Engineering (迈向第三波人为智能：可诠释、稳重、值得信任的机械进建在科学和工程中的各类利用)
汇报人 (Speaker)：林光 教授(Purdue University，美国)
汇报功夫 (Time)：2023年11月13日10:00
汇报地址 (Place)：腾讯会议 207-598-084
约请人(Inviter)：李常品、蔡敏
主办部门：理学院数学系
汇报提要：This talk aims to close the gap by developing new theories and scalable numerical algorithms for complex dynamical systems that can be realistically predicted and validated. We are creating new technologies that can be translated into more secure and reliable new trustworthy AI systems that can be deployed for real-time complex dynamical system prediction, surveillance, and defense applications to improve the stability and efficiency of complex dynamical systems and national security of the United States. We will introduce new NNs that learn functionals and nonlinear operators from functions with simultaneous uncertainty estimates. We present a series of multi-fidelity, federated, Bayesian neural operator network architectures in scientific machine learning. In addition, we will discuss how to incorporate Physics Knowledge and AI to design new interpretable models for science and engineering. In particular, we will present two data-science cases: (1) predicting the COVID-19 pandemic with uncertainties using trustworthy data-driven epidemiological models; (2) Data-driven causal model discovery and personalized prediction in Alzheimer’s disease.
