BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Applications of Generative Adversarial Networks in Environmental D
 ata Science - Herbie Bradley | University of Cambridge
DTSTART:20210202T110000Z
DTEND:20210202T123000Z
UID:TALK155380@talks.cam.ac.uk
CONTACT:Tudor Suciu
DESCRIPTION:Generative adversarial networks (GANs) are a type of generativ
 e model that can generate realistic data in many domains\, such as images\
 , language\, and music. These models have been extensively studied in the 
 last few years\, resulting in a wide variety of applications\, particularl
 y in computer vision. However\, there are several common challenges that m
 ust be solved to successfully apply GANs to real-world problems\, such as 
 being able to generate diverse images and ensure stable training. In the f
 irst part of this presentation I will introduce the theory that underpins 
 the current understanding of why GANs work well\, before describing the mo
 st common types of GAN model and some of their applications in computer vi
 sion.\nEnvironmental Data Science often deals with large amounts of 2D mul
 ti-channel data\, such as satellite images or maps of climate variables. G
 ANs are ideally suited for any application that involves generating this k
 ind of data\, and in the second part of this presentation I will summarise
  the work that has been done with GANs in this area.\n\nA longer\, more de
 tailed lecture introducing GANs is available at https://www.youtube.com/wa
 tch?v=wFsI2WqUfdA.\n\n\nJoin Zoom Meeting\nhttps://zoom.us/j/6708259482?pw
 d=Qk03U3hxZWNJZUZpT2pVZnFtU2RRUT09\n\nMeeting ID: 670 825 9482\nPasscode: 
 9fkTAc
LOCATION:https://zoom.us/j/6708259482?pwd=Qk03U3hxZWNJZUZpT2pVZnFtU2RRUT09
END:VEVENT
END:VCALENDAR