Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Domain Adaptation for Networking
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
2022 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

This thesis explores domain adaptation methods to improve machine learning models in a networking environment where the domain of the data changes after initial data gathering. The applied methods make use of Generative Adversarial Nets and aim to create a model to predict service performance on a client machine using resource utilisation data collected from a server cluster that provides the service. However, since the models were originally designed for image classification, they were changed to work on the problem at hand, because it is a regression task with tabular data. The report explores the theory behind these methodologies and presents the implementations and their results in this project. Unfortunately, the chosen methods did not provide an improvement compared to a regular model, therefore the report also examines the possible causes for this, and provides informed reasons. 

Place, publisher, year, edition, pages
2022. , p. 44
Series
IT ; 22 067
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:uu:diva-484286OAI: oai:DiVA.org:uu-484286DiVA, id: diva2:1694445
Educational program
Master's Programme in Data Science
Supervisors
Examiners
Available from: 2022-09-09 Created: 2022-09-09 Last updated: 2023-07-12Bibliographically approved

Open Access in DiVA

fulltext(1832 kB)259 downloads
File information
File name FULLTEXT01.pdfFile size 1832 kBChecksum SHA-512
def9b11e47b77d239d24211e1d8748033ee6464d44395c85769cde247ecb0fb84b8785f10cb9d8c15e53adc7003759e2324a389dd005436d1c27ac618dcf8ad3
Type fulltextMimetype application/pdf

By organisation
Department of Information Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 259 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: 204 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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