Neural nets play cops and robbers (AKA generative adverserial networks) - podcast episode cover

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

Mar 21, 201619 min
--:--
--:--
Listen in podcast apps:

Episode description

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) | Linear Digressions podcast - Listen or read transcript on Metacast