BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Weinan E (Princeton University)
DTSTART:20200914T130000Z
DTEND:20200914T140000Z
DTSTAMP:20260423T035735Z
UID:SNPDEA/4
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/SNPDEA/4/">P
 DE problems that arise from machine learning</a>\nby Weinan E (Princeton U
 niversity) as part of "Partial Differential Equations and Applications" We
 binar\n\n\nAbstract\nTwo kinds of PDE problems arise from machine learning
 . The continuous formulation of machine learning naturally gives rise to s
 ome very elegant and challenging PDE (more precisely partial differential 
 and integral equations) problems.  It is likely that understanding these P
 DE problems will become fundamental issues in the mathematical theory of m
 achine learning.\nMachine learning-based algorithms for PDEs also lead to 
 new questions about these PDEs\, for example\, new kinds of a priori estim
 ates that are suited for the machine learning model. I will discuss both k
 inds of problems.\n
LOCATION:https://researchseminars.org/talk/SNPDEA/4/
END:VEVENT
END:VCALENDAR