BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Academics,Lectures/Seminars
DESCRIPTION:Dr. Susan Janiszewski\, MTRI\n\nTITLE: Graph Convolutional Neur
al Networks and the Graph Laplacian\n\nABSTRACT: Convolutional Neural Netwo
rks (CNNs) have unlocked several capabilities related to object identificat
ion and classification\, especially in the field of image processing. The r
elatively new Graph Convolutional Neural Network is a generalization of the
traditional image processing CNN\, which allows for many of the techniques
developed for images to be applied in an analogous way to graphs. This tal
k will introduce GraphCNNs\, discuss the link between GraphCNNs and traditi
onal CNNs\, and present hypotheses on how we can further improve GraphCNN p
erformance by exploiting the graph's spectral properties through the graph
Laplacian.
DTEND:20201113T190000Z
DTSTAMP:20240419T163408Z
DTSTART:20201113T180000Z
LOCATION:
SEQUENCE:0
SUMMARY:Mathematical Sciences Colloquium
UID:tag:localist.com\,2008:EventInstance_35111666457607
URL:https://events.mtu.edu/event/mathematical_sciences_colloquium_5328
END:VEVENT
END:VCALENDAR