Change search
CiteExportLink to record
Permanent link

Direct link
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Classification Performance of Convolutional Neural Networks
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Systems and Control.
2016 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

The purpose of this thesis is to determine the performance of convolutional neural networks in classifications per millisecond, not training or accuracy, for the GTX960 and the TegraX1. This is done through varying parameters of the convolutional neural networks and using the Python framework Theano's function profiler to measure the time taken for different networks. The results show that increasing any parameter of the convolutional neural network also increases the time required for the classification of an image. The parameters do not punish the network equally, however. Convolutional layers and their depth have a far bigger negative impact on the network's performance than fully-connected layers and the amount of neurons in them. Additionally, the time needed for training the networks does not appear to correlate with the time needed for classification.

Place, publisher, year, edition, pages
2016. , 46 p.
UPTEC F, ISSN 1401-5757 ; 16060
Keyword [en]
Deep Learning, Convolutional Neural Networks, Performance
National Category
Information Systems
URN: urn:nbn:se:uu:diva-305342OAI: diva2:1037364
External cooperation
High Performance Consulting Sweden
Educational program
Master Programme in Engineering Physics
Available from: 2016-10-21 Created: 2016-10-14 Last updated: 2016-10-21Bibliographically approved

Open Access in DiVA

fulltext(2964 kB)