BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250814T150353EDT-204707dcik@132.216.98.100
DTSTAMP:20250814T190353Z
DESCRIPTION:Learning underlying structure with neuroimaging data and traini
 ng generative models with iterative refinement.\n\nGenerative models can b
 e used to infer latent structure of observed data for the purpose of advan
 cing domain-specific goals. This is demonstrable with functional and struc
 tural magnetic resonance imaging (fMRI / sMRI)\, where inferred structure 
 can reveal brain function and aid in diagnosis of disease. Further advance
 s in training and inference will increase the applicability of machine lea
 rning as a tool for scientific analysis\, and the considerable flexibility
  and capacity allowed by deep learning greatly favor these goals. While de
 ep\, continuously-differentiable functions trained by back-propagation hav
 e been very successful\, local\, iterative inference in directed graphical
  models and generative adversarial networks (GANs) can aid in training\, e
 xpanding beyond the model's default capacity.\n
DTSTART:20170206T203000Z
DTEND:20170206T203000Z
LOCATION:room 6214\, CA\, QC\, Montreal\, H3T 1J4\, Pavillon André-Aisensta
 dt\, 2920\, Chemin de la tour\, 5th floor
SUMMARY:Devon Hjelm\, Université de Montréal
URL:/mathstat/channels/event/devon-hjelm-universite-de
 -montreal-265557
END:VEVENT
END:VCALENDAR