GAN
Generative Adversarial Nets
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio · NeurIPS 2014
Implement the discriminator's two independently averaged expectations and the stable differentiable non-saturating generator objective.
What you will implement
Complete logit losses; a supplied one-dimensional Gaussian location game performs actual alternating training. Image GANs, complete networks and convergence guarantees are outside scope.
- 102. GAN: Stable Adversarial and Non-saturating Losses
Implement the discriminator's two independently averaged expectations and the stable differentiable non-saturating generator objective.
Complete logit losses; a supplied one-dimensional Gaussian location game performs actual alternating training. Image GANs, complete networks and convergence guarantees are outside scope.