BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251104T220121EST-25587udC32@132.216.98.100
DTSTAMP:20251105T030121Z
DESCRIPTION:Hi\, everyone\,\n\n \n\nThe Mathematics & Statistics Graduate S
 tudent Seminar will convene at 1:00pm this Friday\, November 23\, in the M
 ain Lounge (Burnside 1025). As usual\, there will be pizza.\n\n \n\nThis w
 eek\, Aram will talk to us about how optimal transport and neural networks
  can generate photos of anime characters:\n\n \n\nThis is another talk abo
 ut how mathematical tools can be used in Deep Learning. We will begin with
  a brief introduction on Optimal Transport and generative adversarial netw
 orks\, their connection and how they can be applied to anime characters.\n
 	\n	Optimal Transport (OT) is a concept that has been around since Gaspard M
 onge published ''Sur la théorie des déblais et des remblais' in the late 1
 700s. Roughly\, this translates to taking a pile of sand and moving it som
 ewhere else (it's not actually about sand but probability measures).\n	\n	Ho
 w can this possibly tie into deep neural networks? Generative adversarial 
 models (GANs) are an application of deep neural networks\; as the name ind
 icates\, the goal is to generate a distribution that resembles that of 're
 al' data. GAns are in their infancy\, as they were introduced in 2014. GAn
 s require a 'loss function' to train the networks to do a better job at ge
 nerating the data. Researches last winter introduced OT into training GANs
 \, giving some better convergence properties!\n\n \n\nSee you all there!\n
 \n \n\nAll graduate students are invited. As with all talks in the graduat
 e student seminar\, this talk will be accessible to all graduate students 
 in math and stats.This seminar was made possible by funding from the McGil
 l Mathematics and Statistics Department and PGSS.\n
DTSTART:20181123T180000Z
DTEND:20181123T190000Z
LOCATION:Room 1025\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Mathematics & Statistics Graduate Student Seminar:  how optimal tra
 nsport and neural networks can generate photos of anime characters
URL:/mathstat/channels/event/mathematics-statistics-gr
 aduate-student-seminar-how-optimal-transport-and-neural-networks-can-29187
 1
END:VEVENT
END:VCALENDAR