kth.sePublications
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
A sample of sampling strategies for audio similarity learning
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science.
2022 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Ett urval av urvalssmetoder för inlärning av ljudlikhet (Swedish)
Abstract [en]

Training of machine learning models often require sampling when the dataset is large. The manner in which one samples data points, for the mini-batches as well as for the loss function, has been shown to have an impact on the performance of the model as well as on its convergence during training. We set out to measure the impact of sampling strategies on an audio similarity model developed by Epidemic Sound. To this purpose, we evaluate using distance weighted sampling for the triplet loss and Poisson Disk Sampling for the mini-batch sampling. While we did not find that the alternative strategy for gathering mini-batches improved the model, the alternative triplet mining strategy showed promising results and opened up for further exploration into this area.

Abstract [sv]

Träning av maskininlärningsmodeller kräver ofta att urval sker när datamängden är stor. Hur detta urval sker, för antingen mini-batches eller kostnadsfunktionen, har visats ha en inverkan på modellens slutgiltiga prestation samt på konvergenstid. Vi har valt att utvärdera urvalsstrategins inverkan på en ljudlikhetsmodell utvecklad av Epidemic Sound. I detta syfte har vi valt att utvärdera distance weighted sampling för trillingkostnadsfunktionen och Poissondiskurval som urvalsprocess för mini-batches. Vi fann ej att en alternativ urvalsprocess för mini-batches gav bättre resultat men däremot att den alternativa trillingsurvalsprocessen gav lovande resultat som öppnar upp för vidare forskning.

Place, publisher, year, edition, pages
2022. , p. 25
Series
TRITA-EECS-EX ; 2022:523
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-320171OAI: oai:DiVA.org:kth-320171DiVA, id: diva2:1703898
Subject / course
Computer Science
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2022-10-17 Created: 2022-10-15 Last updated: 2022-11-09Bibliographically approved

Open Access in DiVA

fulltext(1135 kB)194 downloads
File information
File name FULLTEXT02.pdfFile size 1135 kBChecksum SHA-512
40cf1eb244b723e6960346ad838be218e0faf1fcbe198dc5a5aff5c26141b569bdc0df16db2bd09700de2de654410d447b53cd6a957baf0741b7720836434005
Type fulltextMimetype application/pdf

By organisation
Computer Science
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 203 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: 360 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