BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260415T071948EDT-4102k9cd1I@132.216.98.100
DTSTAMP:20260415T111948Z
DESCRIPTION:Linear Unsupervised and Active Learning\n\nThis talk is compose
 d of two parts\, linear unsupervised learning\, and linear active learning
 . Part 1: Unsupervised machine learning\, or clustering\, divides a hetero
 geneous data into homogenous subsets. Here we develop a clustering algorit
 hm for linear regressions\, with direct application in clustering shapes. 
 Looking at physical shapes as a closed surface\, and employing this algori
 thm allows us to treat clustering shapes through mathematical functions. T
 his new view extends the Bayesian information criterion for clustering pur
 pose. Part 2: Active learning is concerned about requesting specific data 
 points to increase prediction power\, combining machine learning with desi
 gn of experiments. I develop linear active learning\, and will discuss the
  challenges of applying the method in practice on empirical modelling of o
 ptical fibre amplifiers.\n
DTSTART:20180405T190000Z
DTEND:20180405T200000Z
LOCATION:Room PK-5115 \, CA\, Pavillon President-Kennedy
SUMMARY:Vahid Partovi Nia\, Huawei Technologies and Ecole Polytechnique Mon
 treal
URL:https://www.mcgill.ca/mathstat/channels/event/vahid-partovi-nia-huawei-
 technologies-and-ecole-polytechnique-montreal-286317
END:VEVENT
END:VCALENDAR