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:6300@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20211015T143000
DTEND;TZID=Europe/Paris:20211015T150000
DTSTAMP:20241120T201358Z
URL:https://www.i2m.univ-amu.fr/evenements/taking-into-account-periodicity
 -in-deep-denoisers/
SUMMARY:Jules RIO (Laboratoire Hubert Curien\, Université Jean Monnet\, Sa
 int-Étienne): Taking into account periodicity in deep denoisers
DESCRIPTION:Jules RIO: In recent years\, deep learning based methods have e
 stablished a new state of the art in multiple tasks\, including denoising.
  Additionally to their better performances compared to most of conventiona
 l algorithms\, deep learning based methods are relatively fast once traine
 d. Generally\, they also do not require much a priori knowledge\, which is
  advantageous in most cases as information such as the initial signal-to-n
 oise ratio are rarely available before denoising.\nIn our case\, we are de
 aling with periodic signals. Even though deep learning based methods alrea
 dy provide good results on these signals\, they hardly exploit the periodi
 city. Here\, we propose a new method allowing the consideration of periodi
 city in deep neural networks. Our proposed method allows generalisation to
  various frequencies\, including the ones that were not in the training se
 t. We show the improvements obtained with our methods\, and discuss its cu
 rrent limitations.\n&nbsp\;\n\n&nbsp\;
ATTACH;FMTTYPE=image/jpeg:https://www.i2m.univ-amu.fr/wp-content/uploads/2
 021/10/Jules_Rio.jpg
CATEGORIES:Séminaire,Signal et Apprentissage
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20210328T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR