Dear All,

Thursday the 29th we will have the next speaker in our CWI seminar for machine learning and uncertainty quantification in scientific computing, at 16:15 CET. Nathaniel Trask from Sandia National Labs in New Mexico will present his work on structure preserving deep learning architectures. You can find the zoom link and abstract below. If you feel this talk would be of interest to any of your colleagues, feel free to share the zoom link.

Best regards,

Wouter Edeling

Join Zoom Meeting https://cwi-nl.zoom.us/j/82098750344?pwd=V1RwN0MyMnJCdWlCaW1tY1pBaDBTQT09

Meeting ID: 820 9875 0344 Passcode: 051962

29 Apr. 2021 16h15: Nathaniel Trask (Sandia): Structure preserving deep learning architectures for convergent and stable data-driven modeling

The unique approximation properties of deep architectures have attracted attention in recent years as a foundation for data-driven modeling in scientific machine learning (SciML) applications. The "black-box" nature of DNNs however require large amounts of data that generalize poorly in traditional engineering settings where available data is relatively small, and it is generally difficult to provide a priori guarantees about the accuracy and stability of extracted models. We adopt the perspective that tools from mimetic discretization of PDEs may be adapted to SciML settings, developing architectures and fast optimizers tailored to the specific needs of SciML. In particular, we focus on: realizing convergence competitive with FEM, preserving topological structure fundamental to conservation and multiphysics, and providing stability guarantees. In this talk we introduce some motivating applications at Sandia spanning shock magnetohydrodynamics and semiconductor physics before providing an overview of the mathematics underpinning these efforts.