BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//6.4.7.2//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:0-1093@lptms.universite-paris-saclay.fr
DTSTART;TZID=Europe/Paris:20260109T160000
DTEND;TZID=Europe/Paris:20260109T170000
DTSTAMP:20260105T094922Z
URL:http://www.lptms.universite-paris-saclay.fr/seminars/mlpp-seminars-cyr
 il-furtlehner-lisn-2/
SUMMARY:MLP@P seminars : Cyril Furtlehner  (LISN) - LISN\, bat 660 salle 20
 14 (2° étage) - 9 Jan 26 16:00
DESCRIPTION:Learning in low dimensional space: the case of physics informed
  neural networks\nCyril Furtlehner\nLISN\, Paris Saclay University\n\nSemi
 nar of the Series MLP@P (Machine Learning Physics @ Plateau)\, joint with 
 LISN and IPhT.\nWhere: LISN\, bat 660 salle 2014 (2° étage)\n\nIn this t
 alk we will introduce physics informed neural networks (PINNs) which are n
 eural networks designed to solve PDE. We will discuss some of their specif
 icity related to  the low-dimensionality of the input data and a strong sp
 ectral bias issue which require to identify and address separately  optimi
 zation and learning shortcomings.\nThe analysis of the geometric structure
  of the NN tangent space will lead us to propose state of the art optimiza
 tion\nalgorithms to these problem and to design a principled active learni
 ng strategy.\n
CATEGORIES:MLP@P
LOCATION:LISN\, bat 660 salle 2014 (2° étage)\, 660 Av. des Sciences\,  9
 1190 Gif-sur-Yvette\, France\, Gif-sur-Yvette\, 91190 \, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=660 Av. des Sciences\,  911
 90 Gif-sur-Yvette\, France\, Gif-sur-Yvette\, 91190 \, France;X-APPLE-RADI
 US=100;X-TITLE=LISN\, bat 660 salle 2014 (2° étage):geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR