News for hackers. Stuff that matters.
Re:Anti-AI AI: A device that notifies the wearer when a synt... by david-gpu on Tuesday May 30, 2017 @09:49AM (#14445318)
I wouldn't say trivial. First, in order to use GAN training you need access not only to the adversarial discriminator, but also to it's derivatives. Second, the derivatives need to be reasonably bounded and reasonably smooth, otherwise your voice generator won't be able to converge to a successful solution.
Re:Anti-AI AI: A device that notifies the wearer when a synt... by Houshalter on Tuesday May 30, 2017 @01:05PM (#14446746)
You don't really need access to the other model. By just using your own NN as a discriminator, it will train to be very good at fooling it. And so it should be just as good at fooling other NNs.
Re:Anti-AI AI: A device that notifies the wearer when a synt... by backpropaganda on Tuesday May 30, 2017 @10:45AM (#14445712)
GANs can be trained without gradients using reinforcement learning. Even without GANs, just being able to tune hyper-parameters with such a discriminator should be a strong signal for the synthesizer.