BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Physics-Enhanced Machine Learning (with sampling) - Iryna Burak (T
 UM)
DTSTART:20241003T140000Z
DTEND:20241003T150000Z
UID:TALK222232@talks.cam.ac.uk
CONTACT:Matthew Colbrook
DESCRIPTION:I will present the recent work done by Felix Deitrich's group 
 in Munich. The talk will specifically focus on the SWIM method [1]\, a sam
 pling algorithm that allows fast and accurate construction of neural netwo
 rk weights. I will cover the basic SWIM method and its recent developments
 : SWIM-PDE to solve partial differential equations [2] and SWIM-RNN to lea
 rn dynamical systems with a combination of neural networks and the Koopman
  operator.\n\n[1] Bolager\, E.L.\, IB\, Datar\, C.\, Sun\, Q. and Dietrich
 \, F.\, 2024. Sampling weights of deep neural networks. Advances in Neural
  Information Processing Systems\, 36.\n[2] Datar\, C.\, Kapoor\, T.\, Chan
 dra\, A.\, Sun\, Q.\, IB\, Bolager\, E.L.\, Veselovska\, A.\, Fornasier\, 
 M. and Dietrich\, F.\, 2024. Solving partial differential equations with s
 ampled neural networks. arXiv preprint arXiv:2405.20836.\n
LOCATION:Centre for Mathematical Sciences\, MR14
END:VEVENT
END:VCALENDAR