Constructing macroscopic dynamics using deep learning

Abstract We discuss some recent work on constructing stable and interpretable macroscopic dynamics from trajectory data using deep learning. We adopt a modelling approach: instead of generic neural networks as functional approximators, we use a model-based ansatz for the dynamics following a suitable generalisation of the classical Onsager principle for non-equilibrium systems. This allows the construction of macroscopic dynamics that are physically motivated and can be readily used for subsequent analysis and control. We discuss applications in the analysis of polymer stretching in elongational flow. Moreover, we will also discuss some algorithmic challenges associated with learning (macroscopic) dynamics for scientific applications.

Biography Assistant professor in the Department of Mathematics, National University of Singapore. He graduated with a BA in mathematics from the University of Cambridge and a PhD in applied mathematics from Princeton University in 2016. His research interests include the interplay of machine learning and dynamical systems, control theory, stochastic optimization algorithms and data-driven methods for science and engineering. He is a recipient of the PSTA Young Scientist Award, National Research Foundation Singapore. Qianxiao has published in top material science and machine learning venues, such as Journal of Machine Learning Research, International Conference on Machine Learning, and Matter.