Title: NIPS 2016 Tutorial: Generative Adversarial Networks Paper Link
Authors: Ian Goodfellow
Association: OpenAI
Submission: 2016
a generator minimizes the divergence between its generative distribution and the data distribution
WHILE
the discriminator tries to distinguish the samples from the generator’s distribution and the real data samples
AND THEN
the generator “wins” when the discriminator performs no better than random guess.
What’s Wasserstein GANs
people have used Wasserstein distance to measure the divergence between two distribution
Why GAN
What and How GAN
Where GAN
With GAN
