Volltext-Downloads (blau) und Frontdoor-Views (grau)

Generative adversarial networks : project relevant overview

  • Generating synthetic data is a relevant point in the machine learning community. As accessible data is limited, the generation of synthetic data is a significant point in protecting patients' privacy and having more possibilities to train a model for classification or other machine learning tasks. In this work, some generative adversarial networks (GAN) variants are discussed, and an overview is given of how generative adversarial networks can be used for data generation in different fields. In addition, some common problems of the GANs and possibilities to avoid them are shown. Different evaluation methods of the generated data are also described.

Export metadata

Additional Services

Share in Twitter Search Google Scholar


Author:Rodion KraftORCiD, Natividad Martínez MadridORCiD, Ralf SeepoldORCiDGND
Parent Title (English):Hardware and software supporting physiological measurement (HSPM-2022), Workshop, October 27-28, 2022, Konstanz, Germany
Publisher:Hochschule Reutlingen
Place of publication:Reutlingen
Document Type:Conference Proceeding
Year of Publication:2022
Release Date:2023/01/10
Tag:Generative Adversarial Networks; Synthetic Data; Machine Learning
First Page:23
Last Page:25
Institutes:Institut für Angewandte Forschung - IAF
Open Access?:Ja
Relevance:Sonstige Publikation
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International