BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251006T010230EDT-8568vXkmmK@132.216.98.100
DTSTAMP:20251006T050230Z
DESCRIPTION:Title: Targeted use of deep learning for physics and engineerin
 g\n\nAbstract:\n\nMachine learning and artificial intelligence algorithms 
 are now being used to automate the discovery of governing physical equatio
 ns and coordinate systems from measurement data alone. However\, positing 
 a universal physical law from data is challenging: (i) An appropriate coor
 dinate system must also be advocated and (ii) simultaneously proposing an 
 accompanying discrepancy model to account for the inevitable mismatch betw
 een theory and measurements must be considered. Using a combination of dee
 p learning and sparse regression\, specifically the sparse identification 
 of nonlinear dynamics (SINDy) algorithm\, we show how a robust mathematica
 l infrastructure can be formulated for simultaneously learning physics mod
 els and their coordinate systems. This can be done with limited data and s
 ensors. We demonstrate the methods on a diverse number of examples\, showi
 ng how data can maximally be exploited for scientific and engineering appl
 ications.\n\nFor Zoom meeting information please contact tim.hoheisel [at]
  mcgill.ca\n
DTSTART:20210125T210000Z
DTEND:20210125T220000Z
SUMMARY:Nathan Kutz (University of Washington)
URL:/mathstat/channels/event/nathan-kutz-university-wa
 shington-327955
END:VEVENT
END:VCALENDAR