Nov 24, 2023 Friday
Abstract:
Physics-informed scientific computing is a paradigm that combines data-driven and physics-driven computing, aiming to use large-scale data and physical mechanisms to collaborate with each other to solve complex scientific problems. Physics-informed scientific computing can make full use of the data, improve the accuracy and efficiency of computing, and effectively use physics constraints to enhance the reliability and interpretability, achieving the complementary effects of data and physics. This talk will also introduce the typical methods of scientific computing driven by both data and physics, including physics-informed neural networks, neural operators, and illustrate the application of these methods in fields such as fluid mechanics. This talk will demonstrate the recent progress and future trends of scientific computing.
Time:
Nov 24, 2023 Friday
11:00-11:50
Location:
RmE1-134, GZ Campus
Zoom:
628 334 1826 (PW: 234567)
Bilibili Live
ID: 30748067
Speaker Bio:
Prof. Linchao Zhu
School of Computer Science and Technology, Zhejiang University
Linchao Zhu is ZJU100 Professor with the School of Computer Science and Technology, Zhejiang University. He was a Lecturer (Assistant Professor) at the University of Technology, Sydney, Australia. He is the recipient of the prestigious Google Research Scholar award in 2021. His main research focuses are artificial intelligence, multi-modal analysis and foundation models. He has won the first place in THUMOS action recognition competition (2015), TRECVID LOC competition (2016), CVPR EPIC-KITCHENS first-person action recognition competition (2019, 2020), CVPR MABe multi-agent competition.