BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Pim de Haan (Amsterdam)
DTSTART:20220711T130000Z
DTEND:20220711T134000Z
DTSTAMP:20260423T010620Z
UID:GaML/4
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/4/">Gau
 ge Equivariant Mesh Convolutional Neural Networks</a>\nby Pim de Haan (Ams
 terdam) as part of Workshop on Geometry and Machine Learning\n\n\nAbstract
 \nConvolutional neural networks are widely successful in deep learning on 
 image datasets. However\, some data\, like that resulting from MRI scans\,
  do not reside on a square grid\, but instead live on curved manifolds\, d
 iscretized as meshes. A key issue on such meshes is that they lack a local
  notion of direction and hence the convolutional kernel cannot be canonica
 lly oriented. By doing message passing on the mesh and defining a groupoid
  of similar messages that should share weights\, we propose a gauge equiva
 riant method of building a CNN on such meshes that is direction-aware\, ye
 t agnostic to how the directions are chosen. It is scalable\, invariant to
  how the mesh is rotated\, and performs state-of-the-art on a medical appl
 ication for estimating blood flow through human arteries.\n
LOCATION:https://researchseminars.org/talk/GaML/4/
END:VEVENT
END:VCALENDAR