Sökning: WFRF:(Mehlig Bernhard 1964) >
Bayesian Posterior ...
Bayesian Posterior Approximation With Stochastic Ensembles
-
- Balabanov, Oleksandr (författare)
- Stockholms universitet,Stockholm University
-
- Mehlig, Bernhard, 1964 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för fysik (GU),Department of Physics (GU)
-
- Linander, Hampus, 1985 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för fysik (GU),Department of Physics (GU)
-
(creator_code:org_t)
- 2023
- 2023
- Engelska.
-
Ingår i: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. - 1063-6919. - 9798350301298 ; 2023-June, s. 13701-13711
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://research.cha...
-
https://gup.ub.gu.se...
-
visa färre...
Abstract
Ämnesord
Stäng
- We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochas-tic ensembles are formulated as families of distributions and trained to approximate the Bayesian posterior with variational inference. We implement stochastic ensembles based on Monte Carlo dropout, DropConnect and a novel non-parametric version of dropout and evaluate them on a toy problem and CIFAR image classification. For both tasks, we test the quality of the posteriors directly against Hamil-tonian Monte Carlo simulations. Our results show that stochastic ensembles provide more accurate posterior esti-mates than other popular baselines for Bayesian inference.
Ämnesord
- NATURVETENSKAP -- Matematik -- Beräkningsmatematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Computational Mathematics (hsv//eng)
- NATURVETENSKAP -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Probability Theory and Statistics (hsv//eng)
Nyckelord
- Deep learning architectures and techniques
- Deep learning architectures and techniques
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas