Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Image Classification, Deep Learning and Convolutional Neural Networks: A Comparative Study of Machine Learning Frameworks
Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap.
Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap.
2017 (Engelska)Självständigt arbete på grundnivå (kandidatexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
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.

Ort, förlag, år, upplaga, sidor
2017. , s. 79
Nyckelord [en]
machine learning, deep learning, neural networks, convolutional neural networks, tensorflow, cntk, keras, frameworks
Nyckelord [sv]
maskininlärning, neurala nätverk, ramverk
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:kau:diva-55129OAI: oai:DiVA.org:kau-55129DiVA, id: diva2:1111144
Externt samarbete
ÅF
Ämne / kurs
Datavetenskap
Utbildningsprogram
Dataingenjör
Handledare
Examinatorer
Tillgänglig från: 2017-06-20 Skapad: 2017-06-17 Senast uppdaterad: 2018-01-13Bibliografiskt granskad

Open Access i DiVA

fulltext(748 kB)915 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 748 kBChecksumma SHA-512
b9e2901259fe5ba555c1326084ebc9b8d77f3d7d515e92a0340557c0ce5363443419dd2856949df38f51603d788b6dd58b268d46cf7a6612a64bf11f1f01b5fe
Typ fulltextMimetyp application/pdf
Arkivfil(728 kB)276 nedladdningar
Filinformation
Filnamn FULLTEXT02.pdfFilstorlek 728 kBChecksumma SHA-512
adc9324c38ce4a2c8de7417179248bddfd9043bd2fc70724fae5e995859d06e36386c720d2ca2ce1f5300ccf9c959d4ee69a93d1915e53492d1eb772e5fd20eb
Typ fulltextMimetyp application/pdf

Sök vidare i DiVA

Av författaren/redaktören
Airola, RasmusHager, Kristoffer
Av organisationen
Institutionen för matematik och datavetenskap
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 1191 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 3851 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf