Change search
ReferencesLink to record
Permanent link

Direct link
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.
Series
UPTEC F, ISSN 1401-5757 ; 16060
Keyword [en]
Deep Learning, Convolutional Neural Networks, Performance
National Category
Information Systems
Identifiers
URN: urn:nbn:se:uu:diva-305342OAI: oai:DiVA.org:uu-305342DiVA: diva2:1037364
External cooperation
High Performance Consulting Sweden
Educational program
Master Programme in Engineering Physics
Supervisors
Examiners
Available from: 2016-10-21 Created: 2016-10-14 Last updated: 2016-10-21Bibliographically approved

Open Access in DiVA

fulltext(2964 kB)93 downloads
File information
File name FULLTEXT02.pdfFile size 2964 kBChecksum SHA-512
1546fad30b9a5a7d0241b823ee282b0797ecaca83ada094d5fd7c2a4d11218463cea03fb276b365d27687385c5f6a0c20915236eb4e8e52fc7c91a97e4638cea
Type fulltextMimetype application/pdf

By organisation
Division of Systems and Control
Information Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 93 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

Total: 55 hits
ReferencesLink to record
Permanent link

Direct link