They need to be publicly available and differentiable to be able to use as an op... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

londons_explore on May 23, 2018 | parent | context | favorite | on: The US military is funding an effort to catch deep...

They need to be publicly available and differentiable to be able to use as an opponent for a GAN.

Pretty much nothing except other neural networks are differentiable, unless you put effort into designing them to be.

supermdguy on May 24, 2018 [–]

It's feasible to design a reinforcement learning based network that uses output from a non-differentiable deepfake detector as a component of the loss function.

Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact