Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Investigation of generative adversarial network training: The effect of hyperparameters on training time and stability
University of Skövde, School of Informatics.
University of Skövde, School of Informatics.
2021 (English)Independent thesis Basic level (degree of Bachelor), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Generative Adversarial Networks (GAN) is a technique used to learn the distribution of some dataset in order to generate similar data. GAN models are notoriously difficult to train, which has caused limited deployment in the industry. The results of this study can be used to accelerate the process of making GANs production ready.

An experiment was conducted where multiple GAN models were trained, with the hyperparameters Leaky ReLU alpha, convolutional filters, learning rate and batch size as independent variables. A Mann-Whitney U-test was used to compare the training time and training stability of each model to the others’.

Except for the Leaky ReLU alpha, changes to the investigated hyperparameters had a significant effect on the training time and stability. This study is limited to a few hyperparameters and values, a single dataset and few data points, further research in the area could look at the generalisability of the results or investigate more hyperparameters.

Place, publisher, year, edition, pages
2021. , p. 53, xi
Keywords [en]
Generative adversarial networks, hyperparameters, training, neural networks, deep learning, EMNIST
National Category
Information Systems, Social aspects
Identifiers
URN: urn:nbn:se:his:diva-19847OAI: oai:DiVA.org:his-19847DiVA, id: diva2:1567525
Subject / course
Informationsteknologi
Educational program
Computer Science - Specialization in Systems Development
Supervisors
Examiners
Available from: 2021-06-16 Created: 2021-06-16 Last updated: 2021-06-16Bibliographically approved

Open Access in DiVA

fulltext(5410 kB)327 downloads
File information
File name FULLTEXT01.pdfFile size 5410 kBChecksum SHA-512
4d2413ca98f71fd2c9e74ac035098dd6b480ceb460b9969f9e917be70a6e4595c14eb9d2d6a1101bb5e045a9369d7209fbbcfd16a665d059de41193a6c0565d2
Type fulltextMimetype application/pdf

By organisation
School of Informatics
Information Systems, Social aspects

Search outside of DiVA

GoogleGoogle Scholar
Total: 327 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 654 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf