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

Generative Adversarial Networks

Add to your list(s) 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.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity