Learning Operators (Atlas Talk)
|Dates:||7 June 2022|
|Times:||14:00 - 15:00|
|What is it:||Seminar|
|Organiser:||Department of Computer Science|
|Who is it for:||University staff, Adults, Current University students|
Join us for the next Computer Science Seminar with speaker Siddhartha Mishra
Operators are mappings between infinite-dimensional spaces. They arise in a variety of context, particularly in scientific computing, where the input-output map for the underlying differential equations (ordinary or partial) is an operator. Learning operators from data is challenging on account of the intrinsic infinite-dimensional nature of the underlying task. In this talk, we briefly review several different recently proposed architectures for operator learning, particularly in the context of PDEs and elucidate some of the open questions in this field.
Biography: Siddhartha Mishra is the (chair) Professor for applied Mathematics at Seminar for Applied Mathematics, D-MATH, ETH Zurich. He is also the director of Computational Science Zurich and a core faculty member of the ETH AI Center. Mishra's research interests are in numerical analysis, scientific computing, computational fluid dynamics, computational astrophysics, computational climate science, machine learning and modeling and simulation of complex systems. His research has been recognized with various prizes such as ICIAM Collatz Prize, Infosys Prize, Richard vonMises prize, Jacques Louis Lions Medal, and the starting and consolidator grants of the European Research Council. He has been invited speaker at leading conferences including the International Congress of Mathematicians in Rio 2018.
Travel and Contact Information
on line Zoom
https://zoom.us/j/92481872736 Meeting ID: 924 8187 2736 Passcode: 818580