One neural net is creating counterfeit bills and passing them off to a second neural net, which is trying to distinguish the real money from the fakes.  Result: two neural nets that are better than either one would have been without the competition.

Relevant links:
http://arxiv.org/pdf/1406.2661v1.pdf
http://arxiv.org/pdf/1412.6572v3.pdf
http://soumith.ch/eyescream/

One neural net is creating counterfeit bills and passing them off to a second neural net, which is trying to distinguish the real money from the fakes. Result: two neural nets that are better than either one would have been without the competition. Relevant links: http://arxiv.org/pdf/1406.2661v1.pdf http://arxiv.org/pdf/1412.6572v3.pdf http://soumith.ch/eyescream/

Neural nets play cops and robbers (AKA generative adverserial networks)

Demystifying AI for the intelligently curious

Share Neural nets play cops and robbers (AKA generative adverserial networks)

Sign up to save your podcasts

Neural nets play cops and robbers (AKA generative adverserial networks)

Neural nets play cops and robbers (AKA generative adverserial networks)