Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Prediction of training time for deep neural networks in TensorFlow
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2018 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Förutsägning av träningstider för djupa artificiella neuronnät i TensorFlow (Swedish)
Abstract [en]

Machine learning has gained a lot of interest over the past years and is now used extensively in various areas. Google has developed a framework called TensorFlow which simplifies the usage of machine learning without compromising the end result. However, it does not resolve the issue of neural network training being time consuming. The purpose of this thesis is to investigate with what accuracy training times can be predicted using TensorFlow. Essentially, how effectively one neural network in TensorFlow can be used to predict the training times of other neural networks, also in TensorFlow. In order to do this, training times for training different neural networks was collected. This data was used to create a neural network for prediction. The resulting neural network is capable of predicting training times with an average accuracy of 93.017%.

Abstract [sv]

Maskininlärning har fått mycket uppmärksamhet de senaste åren och används nu i stor utsträckning inom olika områden. Google har utvecklat ramverket TensorFlow som förenklar användningen av maskininlärning utan att kompromissa slutresultatet. Det löser dock inte problemet med att det är tidskrävande att träna neurala nätverk. Syftet med detta examensarbete är att undersöka med vilken noggrannhet träningstiden kan förutsägas med TensorFlow. Alltså, hur effektivt kan ett neuralt nätverk i TensorFlow användas för att förutsäga träningstiderna av andra neurala nätverk, även dessa i TensorFlow. För att göra detta samlades träningstider för olika neurala nätverk. Datan användes sedan för att skapa ett neuralt nätverk för förutsägelse. Det resulterande neurala nätverket kan förutsäga träningstider med en genomsnittlig noggrannhet på 93,017%.

Place, publisher, year, edition, pages
2018. , p. 28
Series
TRITA-EECS-EX ; 2018:251
Keywords [en]
Machine Learning, TensorFlow
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-229423OAI: oai:DiVA.org:kth-229423DiVA, id: diva2:1212698
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2018-08-29 Created: 2018-06-03 Last updated: 2018-08-29Bibliographically approved

Open Access in DiVA

bachelor-thesis(875 kB)168 downloads
File information
File name FULLTEXT01.pdfFile size 875 kBChecksum SHA-512
cd07de2ce55ba337e8173611e14ef776f0483cf846c742039caf2fb9d68a5f3c5fe407d28115da0c3753d0d9f8e4238f0d4924f5a5a8aa9abbccd02e707bf669
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Adlers, JacobPihl, Gustaf
By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 168 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: 928 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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