Math for AI: Can Mathematics provide a solid foundation for AI? by Assoc Prof Xia Kelin| IAS Discovery Science Seminar

About the talk

Artificial intelligence (AI) has begun to gain momentum due to the great advancement in experimental data, computational power and learning models. However, a major issue that remains for all these AI-based learning models is the efficient data representations and featurisation. Here we propose advanced mathematics-based data representations and featurisation for molecular sciences. Molecular structures and their interactions are represented by high-order topological and algebraic models. Mathematical invariants are used as molecular descriptors for learning models. Further, we develop geometric and topological deep learning models to systematically incorporate molecular high-order, multiscale, and periodic information, and use them for analysing molecular data from chemistry, biology, and materials.

Our distinguished speaker

Prof Xia Kelin's research focuses on Mathematical AI for molecular sciences. He has published over 80 papers in journals such as SIAM Review, Science Advances, npj Computational Materials, and ACS Nano. He has served as an associate editor for Computational Physiology and Medicine – Frontiers, Computational and Structural Biotechnology Journal, and Computational and Mathematical Biophysics. He is also on the editorial boards of Theory in Biosciences, Scientific Reports, and Journal of Physics: Complexity, and the editorial advisory boards of Journal of Chemical Information and Modeling and Patterns.

He obtained his PhD from the Chinese Academy of Sciences. From 2009 to 2012, he was a visiting scholar in the Department of Mathematics at Michigan State University. He then worked as a visiting assistant professor at Michigan State University. In 2016, he joined Nanyang Technological University and was promoted to associate professor in 2023.

Co-Organisers

IAS@NTU and the Graduate Students' Clubs of SPMS and CCDS.