Show simple item record

dc.contributor.advisorZhang, Hao H.
dc.contributor.authorPerkins-Ollila, Justin W.
dc.creatorPerkins-Ollila, Justin W.
dc.date.accessioned2021-06-22T03:13:31Z
dc.date.available2021-06-22T03:13:31Z
dc.date.issued2021
dc.identifier.citationPerkins-Ollila, Justin W. (2021). Improving Generative Adversarial Networks with Image Quality Assessment (Master's thesis, University of Arizona, Tucson, USA).
dc.identifier.urihttp://hdl.handle.net/10150/660241
dc.description.abstractThe research to find new ways to improve Generative Adversarial Networks (GANs) and ways to evaluate the data they produce is quite active. However, approaches to directly using those evaluation steps to improve Generative Adversarial Networks are quite sparse. I propose a modification to the correction step of the stochastic gradient descent algorithm for the generator of a Generative Adversarial Net using the Structural Image Similarity Measure in order to increase the efficiency of a Generative Adversarial Network.
dc.language.isoen
dc.publisherThe University of Arizona.
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction, presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/
dc.subjectGAN
dc.subjectMachine Learning
dc.subjectSSIM
dc.titleImproving Generative Adversarial Networks with Image Quality Assessment
dc.typetext
dc.typeElectronic Thesis
thesis.degree.grantorUniversity of Arizona
thesis.degree.levelmasters
dc.contributor.committeememberLin, Kevin
dc.contributor.committeememberRychlik, Marek
thesis.degree.disciplineGraduate College
thesis.degree.disciplineMathematics
thesis.degree.nameM.S.
refterms.dateFOA2021-06-22T03:13:31Z


Files in this item

Thumbnail
Name:
azu_etd_18794_sip1_m.pdf
Size:
2.572Mb
Format:
PDF
Thumbnail
Name:
azu_etd_18794_GAN_SSIM_Modific ...
Size:
875.2Kb
Format:
Microsoft Excel

This item appears in the following Collection(s)

Show simple item record