BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Similarity search meets GPUs and learning
DTSTART:20171127T161500
DTEND:20171127T173000
DTSTAMP:20260506T080518Z
UID:2df96d0c95a39e818690a31efd2200c6d432741e2694fe1d2e52fc36
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Hervé Jegou - Facebook AI Research\nVideo of the talk\n\
 nAbstract :\nThis talk will discuss how high efficient nearest neighbor s
 earch can leverage several learning computer vision and natural language 
 processing tasks. After briefly presenting some works conducted at FAIR 
 on similarity search on CPUs and GPUs\, I will present recent work on sem
 i-supervised learning at a massive scale. Then I will present a few works 
 related to natural language processing involving similarity search strateg
 ies. In particular\, I will present a work employing nearest neighbor mat
 ching and adversarial training to perform word translation without any par
 allel data. \n\nBio :\nHerve Jégou is a Research Manager with Facebook A
 I Research since 2015. He is a former student of the Ecole Normale Supér
 ieure de Cachan\, holding a M.S. (2002) and PhD (2005) from University of 
 Rennes I. During his PhD\, he worked on source/channel coding. After that
 \, he turned out to Computer Vision and Pattern Recognition and joined INR
 IA as a permanent researcher in 2006\, mostly working and leading severa
 l projects related to large image and video collections. His current inter
 ests at FAIR include large-scale processing\, computer vision and natural 
 language processing. \n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR