News for hackers. Stuff that matters.
Re:Learning to write programs that generate images by DanielBMarkham on Tuesday March 27, 2018 @04:01PM (#16692219)
This is still a GAN, right? It's running an adversarial system at a level higher than pixel-poking.
Re:Learning to write programs that generate images by gwern on Tuesday March 27, 2018 @06:26PM (#16693357)
Depends on whether you see the glass half-full or half-empty. Is it a DRL actor-critic where the reward & critic happen to be half of a GAN, or is it a GAN where the generator happens to receive a RL-style loss instead of the normal discriminator loss? Actor-critic and GANs have always been hard to tell apart: https://arxiv.org/pdf/1610.01945.pdf
Re:Learning to write programs that generate images by dbranes on Tuesday March 27, 2018 @04:09PM (#16692268)
It's a neural network trained in an adversarial manner which generates things, so yes.