BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Denoising for Scientific Discovery - Carlos Fernandez-Granda 
 (NYU)
DTSTART:20211201T140000Z
DTEND:20211201T150000Z
UID:TALK164455@talks.cam.ac.uk
CONTACT:Hamza Fawzi
DESCRIPTION:Deep-learning approaches to denoising achieve impressive resul
 ts when trained on standard image-processing datasets in a supervised fash
 ion. However\, unleashing their potential in practice will require develop
 ing unsupervised or semi-supervised approaches capable of learning from re
 al data\, as well as understanding the strategies learned by these models 
 to perform denoising. In this talk\, we will describe recent advances in t
 his direction motivated by a real-world application to electron microscopy
 . \n\n\n\n\n*Join Zoom Meeting*\nhttps://maths-cam-ac-uk.zoom.us/j/9753721
 4061?pwd=MmthTUpDK1VVQ2RoWG8wU3BDdjVMQT09\n\nMeeting ID: 975 3721 4061\nPa
 sscode: 010263
LOCATION:Virtual (Zoom details under abstract)
END:VEVENT
END:VCALENDAR