Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Regularization Methods in Neural Networks
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Statistics.
2020 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Overfitting is a common problem in neural networks. This report uses a simple neural network to do simulations relevant for the field of image recognition. In this report, four common regularization methods for dealing with overfitting are evaluated. The methods L1, L2, Early stopping and Dropout are first tested with the MNIST data set and then with the CIFAR-10 data set. All methods are compared to a baseline where no regularization is used at sample sizes ranging from 500 to 50 000 images. The simulations in the report show that all four methods have repetitive patterns throughout the study and that Dropout continuously is superior to the other three methods as well as the baseline.

Place, publisher, year, edition, pages
2020. , p. 31
Keywords [en]
Neural Networks, Overfitting, Regularization methods, MNIST, CIFAR-10
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:uu:diva-403486OAI: oai:DiVA.org:uu-403486DiVA, id: diva2:1389238
Subject / course
Statistics
Educational program
Bachelor Programme in Business and Economics
Supervisors
Examiners
Available from: 2020-02-05 Created: 2020-01-29 Last updated: 2020-02-05Bibliographically approved

Open Access in DiVA

The full text will be freely available from 2020-02-20 12:09
Available from 2020-02-20 12:09

By organisation
Department of Statistics
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 20 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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