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
Human Understandable Interpretation of Deep Neural Networks Decisions Using Generative Models
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
2019 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Deep Neural Networks have long been considered black box systems, where their interpretability is a concern when applied in safety critical systems. In this work, a novel approach of interpreting the decisions of DNNs is proposed. The approach depends on exploiting generative models and the interpretability of their latent space. Three methods for ranking features are explored, two of which depend on sensitivity analysis, and the third one depends on Random Forest model. The Random Forest model was the most successful to rank the features, given its accuracy and inherent interpretability. 

Place, publisher, year, edition, pages
2019. , p. 44
Keywords [en]
Explainable AI, Deep Neural Networks, Interpretability, Disentangled Representation, Representation Learning
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:hh:diva-41035OAI: oai:DiVA.org:hh-41035DiVA, id: diva2:1373307
Subject / course
Computer science and engineering
Educational program
Master's Programme in Embedded and Intelligent Systems, 120 credits
Supervisors
Examiners
Available from: 2019-11-27 Created: 2019-11-26 Last updated: 2019-11-27Bibliographically approved

Open Access in DiVA

fulltext(10744 kB)10 downloads
File information
File name FULLTEXT02.pdfFile size 10744 kBChecksum SHA-512
4ff15e33956c73e92f9e9d0cc806e3ca49ff9dc71aca7c2dd9f640a1be050528e243b08294911cc017b19709d61021c5922e7f2c75a2f91c7309165befdfd059
Type fulltextMimetype application/pdf

By organisation
Halmstad Embedded and Intelligent Systems Research (EIS)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 10 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: 15 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