mlsanityData to 14 Oct 2026

The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning

arXiv 1811.12535 ↗First posted 29 Nov 2018cs.LG cs.AI stat.MLcited by 13

Not on the map. Why?

Abstract (arXiv)

One of the main challenges of deep learning tools is their inability to capture model uncertainty. While Bayesian deep learning can be used to tackle the problem, Bayesian neural networks often require more time and computational power to train than deterministic networks. Our work explores whether fully Bayesian networks are needed to successfully capture model uncertainty. We vary the number and position of Bayesian layers in a network and compare their performance on active learning with the MNIST dataset. We found that we can fully capture the model uncertainty by using only a few Bayesian layers near the output of the network, combining the advantages of deterministic and Bayesian networks.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 2; 2023: 0; 2024: 4; 2025: 2; 2026: 1.

13 papers.

Sort:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  2. 2021Deep Ensembles from a Bayesian Perspectivecited by 27
  3. 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
  4. 2024Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysiscited by 8
  5. 2021Bayesian Neural Networks: Essentialscited by 7
  6. 2024TapType: Ten-finger text entry on everyday surfaces via Bayesian inferencecited by 4
  7. 2024Focused Active Learning for Histopathological Image Classificationcited by 3
  8. 2022Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Visioncited by 1
  9. 2024Information-Geometric Barycenters for Bayesian Federated Learningcited by 1
  10. 2022Model Architecture Adaption for Bayesian Neural Networkscited by 0
  11. 2025B-PL-PINN: Stabilizing PINN Training with Bayesian Pseudo Labelingcited by 0
  12. 2025Partial Trace-Class Bayesian Neural Networkscited by 0
1 more
  1. 2026Hidden Axis of Uncertainty: Latent-Posterior Alignment in Graph Neural Networks with Bayesian Output Layerscited by 0