University of Cambridge > Talks.cam > Churchill CompSci Talks > Generative Adversarial Networks

  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

ℹ️ Information

Generative Adversarial Networks

Download to your calendar using vCal

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

Generative Adversarial Networks (GANs) consist of a pair of neural networks: a generator and a discriminator. The two compete in a minimax game where the generator aims to create data which the discriminator is unable to distinguish from a genuine dataset. This game enables the creation of deep generative models, a research topic which previously had little success.

I will be summarising the original game as proposed by Goodfellow et al. and will be looking at how such a game may be modified to fit more specific criteria with a particular focus on an image-to-image translation system called CycleGAN.

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

Lord Ashcroft Building (LAB113), Anglia Ruskin University, Cambridge Average on weekdays: 8911.32613169 kWh The Humanitarian Centre, Fenner’s, Gresham Road, CB1 2ES

Other talks

Morning Tea and Coffee Strange New Worlds Ice in a mostly-Arctic Context Title to be confirmed Online Causal Inference Seminar Coexisting with carnivores? The lynx and wolf reintroduction debate
 

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