BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250718T215659EDT-3276o0uaDU@132.216.98.100
DTSTAMP:20250719T015659Z
DESCRIPTION:Machine Learning and Neural Networks: Foundations and Some Fund
 amental Questions.\n\n\n	Abstract:\n\n\nStatistical learning theory is by n
 ow a mature branch of data science that hosts a vast variety of practical 
 techniques for tackling data-related problems. In this talk we present som
 e fundamental concepts upon which statistical learning theory has been bas
 ed. Different approaches to statistical inference will be discussed and th
 e main problem of learning from Vapnik’s point of view will be explained. 
 Further we discuss the topic of function estimation as the heart of Vapnik
 -Chervonenkis theory. There exist several state-of-the-art methods for est
 imating functional dependencies\, such as maximum margin estimator and art
 ificial neural networks. While for some of these methods\, e.g.\, the supp
 ort vector machines\, there has already been developed a profound theory\,
  others require more investigation. Accordingly\, we pay a closer attentio
 n to the so-called mapping neural networks and try to shed some light on c
 ertain theoretical aspects of them. We highlight some of the fundamental c
 hallenges that have attracted the attention of researcher and they are yet
  to be fully resolved. One of these challenges is estimation of the intrin
 sic dimension of data that will be discussed in detail. Another challenge 
 is inferring causal direction when the training data set is not representa
 tive of the target population.\n\n\n	Speaker\n\n\nMasoud Asgharian is a Pro
 fessor of Statistics in the Department of Mathematics and Statistics at Mc
 Gill University. His research interests include survival analysis\, change
 -point problems\, classification and clustering\, causal inference and opt
 imization.\n\nDamoon Robatian is a PhD student and Zedian Xiao is undergra
 duate student working with Professor Masoud Asgharian.\n\nZoom Link\n\nMee
 ting ID: 924 5390 4989\n\nPasscode: 690084\n\n \n\n \n
DTSTART:20201009T193000Z
DTEND:20201009T203000Z
SUMMARY:Professor Masoud Asgharian\, Damoon Robatian and Zedian Xiao 
URL:/mathstat/channels/event/professor-masoud-asgharia
 n-damoon-robatian-and-zedian-xiao-325218
END:VEVENT
END:VCALENDAR