BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:1600@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20170227T153000
DTEND;TZID=Europe/Paris:20170227T163000
DTSTAMP:20170212T143000Z
URL:https://www.i2m.univ-amu.fr/evenements/learning-metrics-with-controlle
 d-behaviour/
SUMMARY: (...): Learning Metrics with Controlled Behaviour
DESCRIPTION:: The goal in Machine Learning is to acquire new knowledge from
  data. To achieve this many algorithms make use of a notion of distance or
  similarity between examples. A very representative example is the nearest
  neighbour classifier which is based on the idea that two similar examples
  should share the same label: it thus critically depends on the notion of 
 metric considered. Depending on the task at hand these metrics should have
  different properties but manually choosing an adapted comparison function
  can be tedious and difficult. The idea behind Metric Learning is to autom
 atically tailor such metrics to the problem at hand.One of the main limita
 tion of standard methods is that the control over the behaviour of the lea
 rned metrics is often limited. In this talk I will present two approaches 
 specifically designed to overcome this problem. In the first one we consid
 er a general framework able to take into account a reference metric acting
  as a guide for the learned metric. We are then interested in theoreticall
 y studying the interest of using such side information. In the second appr
 oach we propose to control the underlying transformation of the learned me
 tric. Specifically we use some recent advances in the field of Optimal Tra
 nsport to force it to follow a particular geometrical transformation.http:
 //perso.univ-st-etienne.fr/pem82055/
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20161030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR