BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Tutorial: Self-supervised learning\, BYOL\, and friends - Michal V
 alko (INRIA Lille - Nord Europe Research Centre)
DTSTART:20251105T140000Z
DTEND:20251105T170000Z
UID:TALK235621@talks.cam.ac.uk
DESCRIPTION:In this talk\, we will discuss self-supervised representation 
 learning and then more specifically BYOL. BYOL relies on two neural networ
 ks\, referred to as online and target networks\, that interact and learn f
 rom each other. From an augmented view of an image\, we train the online n
 etwork to predict the target network representation of the same image unde
 r a different augmented view. At the same time\, we update the target netw
 ork with a slow-moving average of the online network. While state-of-the a
 rt methods had intrinsically relied on negative pairs\, BYOL achieved a ne
 w state of the art without them. We will also describe follow-ups of BYOL 
 that we have explored within DeepMind\, BGRL (for graphs)\, MYOW (for new 
 uncharted domains such as neural readings)\, and BAS/BEAST (for multi-moda
 l domains). Finally\, we will explore different takes on the analysis of B
 YOL and other open questions.\n&nbsp\;
LOCATION:Enigma Room\, The Alan Turing Institute
END:VEVENT
END:VCALENDAR