学术报告报告主题: Topological deep learning: The past, present, and future
报 告 人: Guowei Wei 教授（Michigan State University）
报告时间: 2024年6月21日（星期五）下午16:00-17:00
报告地点: 37号楼3A01
邀 请 人: 王帅灵副教授
欢迎广大师生前往！
数学学院
2024年 6月12日
报告摘要：
In the past few years, topological deep learning (TDL), a term coined by us in 2017, has become an emerging paradigm in artificial intelligence (AI). TDL is built on persistent homology (PH), an algebraic topology technique that bridges the gap between complex geometry and abstract topology through multiscale analysis. While TDL has made huge strides in a wide variety of scientific and engineering disciplines, its most compelling success was observed in biosciences with intrinsically high dimensional and intricately complex data. I will discuss the limitations and challenges of TDL. I will also discuss how algebraic topology is enabling AI and how AI is assisting topological reasoning.
专家简介：
Guowei Wei received his Ph.D. degree from the University of British Columbia and is currently an MSU Research Foundation Professor at Michigan State University. He has pioneered novel computational methods that integrate profound mathematical structures with deep learning, leading to victories in D3R Grand Challenges, a worldwide competition series in computer-aided drug design, and the discovery of SARS-CoV-2 evolutionary mechanisms. He has earned numerous awards and honors, including the elected fellow of AIMBE. In addition, he has partnered with world premier pharmaceutical companies and the U.S. Food and Drug Administration (FDA) on drug discovery. Dr. Wei has served extensively on various national and international panels, committees, and journal editorships. Many of his former trainees now hold faculty positions in research universities worldwide.