Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wieluch, Sabine, Schwenker, Friedhelm
Format: Preprint
Publié: 2019
Sujets:
Accès en ligne:https://arxiv.org/abs/1909.04474
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929485159333888
author Wieluch, Sabine
Schwenker, Friedhelm
author_facet Wieluch, Sabine
Schwenker, Friedhelm
contents This paper demonstrates how Dropout can be used in Generative Adversarial Networks to generate multiple different outputs to one input. This method is thought as an alternative to latent space exploration, especially if constraints in the input should be preserved, like in A-to-B translation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_1909_04474
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Dropout Induced Noise for Co-Creative GAN Systems
Wieluch, Sabine
Schwenker, Friedhelm
Machine Learning
This paper demonstrates how Dropout can be used in Generative Adversarial Networks to generate multiple different outputs to one input. This method is thought as an alternative to latent space exploration, especially if constraints in the input should be preserved, like in A-to-B translation tasks.
title Dropout Induced Noise for Co-Creative GAN Systems
topic Machine Learning
url https://arxiv.org/abs/1909.04474