Wasserstein GAN
id:
wasserstein-gan-302-9663887
title:
Wasserstein GAN
text:
The Wasserstein Generative Adversarial Network (WGAN) is a variant of generative adversarial network (GAN) proposed in 2017 that aims to "improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches". Compared with the original GAN discriminator, the Wasserstein GAN discriminator provides a better learning signal to the generator. This allows the training to be more stable when generator is lear
brand slug:
wiki
category slug:
encyclopedia
description:
Proposed generative adversarial network variant
original url:
https://en.wikipedia.org/wiki/Wasserstein_GAN
date created:
date modified:
2024-03-07T11:21:44Z
main entity:
{"identifier":"Q113331561","url":"https://www.wikidata.org/entity/Q113331561"}
image:
fields total:
13
integrity:
14