5,337
edits
Unsupervised Learning: Difference between revisions
→Wasserstein GAN
(→GANs) |
|||
| Line 222: | Line 222: | ||
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 | |||
{{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> | ||