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
Image Classification, Deep Learning and Convolutional Neural Networks: A Comparative Study of Machine Learning Frameworks
Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Mathematics and Computer Science.
Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Mathematics and Computer Science.
2017 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

The use of machine learning and specifically neural networks is a growing trend in software development, and has grown immensely in the last couple of years in the light of an increasing need to handle big data and large information flows. Machine learning has a broad area of application, such as human-computer interaction, predicting stock prices, real-time translation, and self driving vehicles. Large companies such as Microsoft and Google have already implemented machine learning in some of their commercial products such as their search engines, and their intelligent personal assistants Cortana and Google Assistant.

The main goal of this project was to evaluate the two deep learning frameworks Google TensorFlow and Microsoft CNTK, primarily based on their performance in the training time of neural networks. We chose to use the third-party API Keras instead of TensorFlow's own API when working with TensorFlow. CNTK was found to perform better in regards of training time compared to TensorFlow with Keras as frontend. Even though CNTK performed better on the benchmarking tests, we found Keras with TensorFlow as backend to be much easier and more intuitive to work with. In addition, CNTKs underlying implementation of the machine learning algorithms and functions differ from that of the literature and of other frameworks. Therefore, if we had to choose a framework to continue working in, we would choose Keras with TensorFlow as backend, even though the performance is less compared to CNTK.

Place, publisher, year, edition, pages
2017. , p. 79
Keywords [en]
machine learning, deep learning, neural networks, convolutional neural networks, tensorflow, cntk, keras, frameworks
Keywords [sv]
maskininlärning, neurala nätverk, ramverk
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kau:diva-55129OAI: oai:DiVA.org:kau-55129DiVA, id: diva2:1111144
External cooperation
ÅF
Subject / course
Computer Science
Educational program
Computer Science
Supervisors
Examiners
Available from: 2017-06-20 Created: 2017-06-17 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(748 kB)860 downloads
File information
File name FULLTEXT01.pdfFile size 748 kBChecksum SHA-512
b9e2901259fe5ba555c1326084ebc9b8d77f3d7d515e92a0340557c0ce5363443419dd2856949df38f51603d788b6dd58b268d46cf7a6612a64bf11f1f01b5fe
Type fulltextMimetype application/pdf
Arkivfil(728 kB)266 downloads
File information
File name FULLTEXT02.pdfFile size 728 kBChecksum SHA-512
adc9324c38ce4a2c8de7417179248bddfd9043bd2fc70724fae5e995859d06e36386c720d2ca2ce1f5300ccf9c959d4ee69a93d1915e53492d1eb772e5fd20eb
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Airola, RasmusHager, Kristoffer
By organisation
Department of Mathematics and Computer Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 1126 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: 3600 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