{"id":1062,"date":"2022-05-06T10:45:24","date_gmt":"2022-05-06T14:45:24","guid":{"rendered":"https:\/\/sites.nd.edu\/jianxun-wang\/?p=1062"},"modified":"2022-05-17T21:42:03","modified_gmt":"2022-05-18T01:42:03","slug":"invited-talk-at-usacm-uq-virtual-seminar-series","status":"publish","type":"post","link":"https:\/\/sites.nd.edu\/jianxun-wang\/2022\/05\/06\/invited-talk-at-usacm-uq-virtual-seminar-series\/","title":{"rendered":"Invited Talk at USACM UQ Virtual Seminar Series"},"content":{"rendered":"\n

I will give invited talk at #USACM<\/a>#UQ<\/a> Virtual Seminar Organized by USACM UQ TTA. (Time: 15:00 PM-16:00 PM (EST US), 5\/12\/2022. Zoom Link: listed below). The topic is about “how to leverage physics in ML for computational mechanics — Physics-informed, PDE-structure preserved Learning for problems with complex geometries”. I am happy to have Prof. Michael Brenner<\/a> be my discussant sharing his great insights in the field of scientific machine learning #SciML<\/a>. Also thank the organization committee: Abani Patra<\/a>, Serge Prudhomme<\/a>, Johann Guilleminot.<\/p>\n\n\n\n

In this talk, I will discuss our recent developments of on SciML from several different aspects, including (1) how to leverage physics to inspire network architecture design (PDE-preserved deep learning #PPNN<\/a>), (2) use physics to inform network training #PINN<\/a>, (3) physics-informed geometric deep learning (#GeometricDL<\/a>) for complex geometries and irregular domains. This work is supported National Science Foundation (NSF)<\/a>#OAC<\/a>#CMMI<\/a>, Aerospace & Mechanical Engineering at Notre Dame<\/a>, Center for Sustainable Energy at Notre Dame<\/a>, ND-ECI, ND Lucy Institute of Data Science.<\/p>\n\n\n\n

Welcome to join us at https:\/\/lnkd.in\/gH6AHp3V<\/a>. See you on Thursday<\/p>\n\n\n\n

US Association for Computational Mechanics (USACM), TTA: Uncertainty Quantification and Probabilistic Modeling.<\/a><\/p>\n\n\n\n

Here is the talk recording<\/p>\n\n\n\n

\n