kth.sePublications
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
Real-time uncertainty estimation for deep learning
KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Realtidsosäkerhetsuppskattning för djupinlärning (Swedish)
Abstract [en]

Modern deep neural networks do not produce well calibrated estimates of their own uncertainty, unless specific uncertainty estimation techniques are applied. Common uncertainty estimation techniques such as Deep Ensembles and Monte Carlo Dropout necessitate multiple forward pass evaluations for each input sample, making them too slow for real-time use. For real-time use, techniques which require only a single-forward pass are desired. Evidential Deep Learning (EDL), and Multiple-Input Multiple-Output (MIMO) networks are prior art in the space of real-time uncertainty estimation. This work introduces EDL-MIMO, a novel real-time uncertainty estimation method which combines the two. The core of this thesis is dedicated to comparing the quality of this new method to the pre-existing baselines of EDL and MIMO alone.

Abstract [sv]

De neurala nätverk vi har idag har svårigheter med att bedöma sin egen osäkerhet utan särskilda metoder. Metoder som Deep Ensembles och Monte Carlo Dropout kräver flera beräkningar för varje indata, vilket gör dem för långsamma i realtid. För realtidstillämpning behövs metoder som endast kräver en beräkning. Det finns redan vetenskapliga artiklar om osäkerhetsmetoder som Evidential Deep Learning (EDL), och Multiple-Input Multiple-Output (MIMO) networks. Denna uppsats introducerar en ny metod som kombinerar båda. Fokus ligger på att jämföra kvaliteten på denna nya metod med EDL och MIMO när de används ensamma

Abstract [is]

Djúptauganet nútímans eiga erfitt með að meta sína eigin óvissu, án þess að sérstakar óvissumatsaðferðir séu notaðar. Algengar óvissumatsaðferðir líkt og Deep Ensembles, og Monte Carlo Dropout, krefjast þess að djúptauganetið sé reiknað oftar en einu sinni fyrir hvert inntak, sem gerir þessar aðferðir of hægar fyrir rauntímanotkun. Fyrir rauntímanotkun er leitast eftir aðferðum sem krefjast bara einn reikning. Evidential Deep Learning (EDL), og Multiple-Input Multiple-Output (MIMO) networks eru óvissumatsaðferðir sem hafa verið birtar í fyrri greinum. Þessi ritgerð kynnir í fyrsta sinn EDL-MIMO, nýja óvissumatsaðferð sem blandar þeim báðum saman. Kjarni þessarar ritgerðar snýst um að bera saman gæði þessarar nýju aðferðar í samanburð við að nota EDL eða MIMO einar og sér.

Place, publisher, year, edition, pages
2023. , p. 42
Series
TRITA-EECS-EX ; 2023:930
Keywords [en]
Machine Learning, Deep Learning, Uncertainty Estimation, Evidential Deep Learning, Computer Vision
Keywords [sv]
Maskininlärning, Djupinlärning, Osäkerhetsuppskattning, Evidential Deep Learning, Datorseende
Keywords [is]
Vélnám, Djúptauganet, Óvissumat, Evidential Deep Learning, Tölvusjón
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-344381OAI: oai:DiVA.org:kth-344381DiVA, id: diva2:1844440
External cooperation
Scania AB
Educational program
Master of Science - Machine Learning
Supervisors
Examiners
Available from: 2024-03-15 Created: 2024-03-13 Last updated: 2024-03-15Bibliographically approved

Open Access in DiVA

fulltext(1876 kB)155 downloads
File information
File name FULLTEXT01.pdfFile size 1876 kBChecksum SHA-512
700927b135fa4f3cf550e977d7dc86753763a8ef1f983d3c5f51433d83e2409687b1dfb1ab204569c5e8d66a08ba32bfc3a20ba569cd48699c74fd000ee067f0
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 155 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: 270 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