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:3009@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20190621T140000
DTEND;TZID=Europe/Paris:20190621T150000
DTSTAMP:20190606T120000Z
URL:https://www.i2m.univ-amu.fr/evenements/deep-neural-networks-and-variat
 ional-inequalities/
SUMMARY: (...): Deep neural networks and variational inequalities
DESCRIPTION:: Motivated by structures that appear in deep neural networks\,
  we investigate nonlinear composite models alternating proximity and affin
 e operators defined on different spaces. We first show that a wide range o
 f activation operators used in neural networks are actually proximity oper
 ators. We then establish conditions for the averagedness of the proposed c
 omposite constructs and investigate their asymptotic properties. It is sho
 wn that the limit of the resulting process solves a variational inequality
  which\, in general\, does not derive from a minimization problem. The ana
 lysis relies on tools from monotone operator theory and sheds some light o
 n the asymptotic properties of a class of neural networks structures.http:
 //pesquet.info
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20190331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR