BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250919T032200EDT-7883u8uOFs@132.216.98.100
DTSTAMP:20250919T072200Z
DESCRIPTION:Shallow and Deep Metrics for Machine Learning and Computer Visi
 on\n\nSimilarity functions and distance metrics are used in many machine l
 earning and computer vision contexts such as clustering\, k-nearest neighb
 ors classification\, support vector machine\, information/image retrieval\
 , visualization etc. Traditionally\, machine learning methods fixed sample
  representations and the used metric before learning a model optimized for
  the target task. Metric learning approaches\, which learn the employed me
 tric in a supervised way\, have been proposed to increase performance on t
 asks such as clustering. In particular\, they have shown great generalizat
 ion performance to compare objects from categories that were not seen duri
 ng training (for instance in face verification or few-shot learning). In t
 his talk\, I will talk about different shallow and deep metric learning ap
 proaches optimized for clustering and reducing model complexity. In the cl
 ustering task\, I will present efficient approaches to learn a metric in a
  supervised or weakly supervised way. In the model complexity context\, I 
 will present approaches to limit the rank of shallow approaches\, or reduc
 e the dimensionality of a pretrained deep neural network to perform visual
 ization or increase zero-shot learning performance.\n
DTSTART:20180220T160000Z
DTEND:20180220T170000Z
LOCATION:Room PCM Z240\, CA\, Laboratoire d'informatique des systemes adapt
 atifs
SUMMARY:Marc Law\, University of Toronto
URL:/mathstat/channels/event/marc-law-university-toron
 to-285186
END:VEVENT
END:VCALENDAR