BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Learn2Solve: A Deep Learning Framework for Real-Time Solutions of 
 forward\, inverse\, and UQ Problems
DTSTART:20240703T111500
DTSTAMP:20260416T095040Z
UID:7188850c47b654ec62b110c61e3788c83fafed4f1de896a36c3050f9
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Tan Bui Thanh\, The University of Texas at Austin\nAbstr
 act:\nDigital models (DMs) are designed to be replicas of systems and proc
 esses. At the core of a digital model (DM) is a physical/mathematical mode
 l that captures the behavior of the real system across temporal and spatia
 l scales. One of the key roles of DMs is enabling “what if” scenario t
 esting of hypothetical simulations to understand the implications at any p
 oint throughout the life cycle of the process\, to monitor the process\, t
 o calibrate parameters to match the actual process and to quantify the unc
 ertainties. In this talk\, we will present various (faster than) real-time
  Scientific Deep Learning (SciDL) approaches for forward\, inverse\, and U
 Q problems. Both theoretical and numerical results for various problems in
 cluding transport\, heat\, Burgers\, (transonic and supersonic) Euler\, an
 d Navier-Stokes equations will be presented.
LOCATION:CM 1 517 https://plan.epfl.ch/?room==CM%201%20517
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR