BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Data-driven Approaches for Structural Optimisation - Ahmet Oguzhan
  Yuksel\, University of Cambridge
DTSTART:20220204T150000Z
DTEND:20220204T160000Z
UID:TALK169775@talks.cam.ac.uk
CONTACT:Mishael Nuh
DESCRIPTION:Structural optimisation is an integrated tool in the design pr
 ocess and is used to obtain more efficient structures. Popularly used fini
 te element models are computationally expensive and lacking gradient infor
 mation. Deep learning is a popular subset of machine learning\, which is a
  construction of neural networks. Providing physics information to the mod
 el makes the "black-box" neural network model into a "grey-box" one\, henc
 e turns the model into a physics-based one. This study aims to explore pos
 sible structural optimisation techniques using deep neural networks.
LOCATION:Zoom (email structures-admin@eng.cam.ac.uk for link)
END:VEVENT
END:VCALENDAR