University of Cambridge > Talks.cam > Churchill CompSci Talks > Introduction to GANs

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Introduction to GANs

Download to your calendar using vCal

If you have a question about this talk, please contact Matthew Ireland .

Since the research paper on Generative Adversarial Nets (GANs) was first published less than 10 years ago, their usage has rapidly risen. GANs are able generate increasingly more accurate examples of images and sounds which are often able to fool many people into thinking they are real. During this talk, I will explain the concept and structure of GANs which makes them so effective, and we will use a GAN to generate images of hand-written digits. I will also describe the ways in which the GAN model has been expanded on to turn photographs into paintings as well as other uses.

This talk is part of the Churchill CompSci Talks series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 8945.67939815 kWh Average on weekdays: 9024.81568627 kWh EE Seminar Room, CAPE, 9 JJ Thomson Avenue, Cambridge, CB3 0FA

Other talks

TBC title abstract tbc Geometry and Generalization: The case of Grokking Evolutionary constraints shape the evolution of mammalian tooth classes There is no such thing as weather: a historical and cultural geography of weather (and health) Differences between Robin and Neumann eigenvalues
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity