Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Wasserstein GAN
610
Zitationen
3
Autoren
2017
Jahr
Abstract
We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to other distances between distributions.
Ähnliche Arbeiten
A modified uronic acid carbazole reaction
1962 · 6.235 Zit.
The tumour suppressor protein VHL targets hypoxia-inducible factors for oxygen-dependent proteolysis
1999 · 5.178 Zit.
HIFα Targeted for VHL-Mediated Destruction by Proline Hydroxylation: Implications for O <sub>2</sub> Sensing
2001 · 4.664 Zit.
The biology and function of fibroblasts in cancer
2016 · 4.159 Zit.
Osteoblastic cells regulate the haematopoietic stem cell niche
2003 · 3.400 Zit.