5,337
edits
Unsupervised Learning: Difference between revisions
→GANs
(→GANs) |
|||
| Line 215: | Line 215: | ||
}} | }} | ||
==GANs== | ===GANs=== | ||
{{main | Generative adversarial network}} | {{main | Generative adversarial network}} | ||
===Wasserstein GAN=== | ====Wasserstein GAN==== | ||
[https://arxiv.org/abs/1701.07875 Paper]<br> | [https://arxiv.org/abs/1701.07875 Paper]<br> | ||
The main idea is to ensure the that discriminator is lipschitz continuous and to limit the lipschitz constant (i.e. the derivative) of the discriminator.<br> | The main idea is to ensure the that discriminator is lipschitz continuous and to limit the lipschitz constant (i.e. the derivative) of the discriminator.<br> | ||
If the correct answer is 1.0 and the generator produces 1.0001, we don't want the discriminator to give us a very high loss.<br> | If the correct answer is 1.0 and the generator produces 1.0001, we don't want the discriminator to give us a very high loss.<br> | ||
====Earth mover's distance==== | =====Earth mover's distance===== | ||
{{main | wikipedia:earth mover's distance}} | {{main | wikipedia:earth mover's distance}} | ||
The minimum cost of converting one pile of dirt to another.<br> | The minimum cost of converting one pile of dirt to another.<br> | ||