BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Deep Adaptive sampling for numerical PDEs
DTSTART:20240304T161500
DTEND:20240304T171500
DTSTAMP:20260406T211552Z
UID:6f4b9aae24d299d1a2a4338ca91b54085b120ccd1bb7344f5d9f8eca
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Tao Zhou (Academy of Mathematics and Systems Sciences\, 
 Chinese Academy of Sciences\, Beijing)\nComputational Mathematics Seminar\
 n\nAbstract:  We present a deep adaptive sampling method for solving PDE
 s where deep neural networks are utilized to approximate the solutions. Mo
 re precisely\, we propose the failure informed adaptive sampling for PINNs
  and an adaptive important sampling scheme for deep Ritz. Both approaches 
 can adaptively refine the training set with the goal of reducing the failu
 re probability. Applications to both forward and inverse PDEs problems wil
 l be presented.
LOCATION:CM 1 517 https://plan.epfl.ch/?room==CM%201%20517
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR