Single-Model Uncertainties for Deep Learning

By Natasa Tagasovska, David Lopez-Paz. 2018

321 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

1. Shreyas Padhy
2. Balaji Lakshminarayanan
3. Zi Lin
4. Mohammad Ghavamzadeh
5. Xiaochun Cao
6. Saeid Nahavandi
7. Tania Bedrax-Weiss
8. Rudolph Triebel

In Probabilistic & Bayesian Methods

1. Balaji Lakshminarayanan
2. Muhammad Shahzad
3. Dana Rezazadegan
4. Zi Lin
5. Vladimir Makarenkov
6. Abbas Khosravi
7. Cedrique Rovile Njieutcheu Tassi
8. Shreyas Padhy

Citations in the corpus

• Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness (2020, methodology): “[72] N.”
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, background): “[221] proposed single-model estimates for DNNs of epistemic and aleatoric uncertainty.”
• A survey of uncertainty in deep neural networks (2021, background): “Tagasovska and LopezPaz [103] presented an approach to estimate data and model uncertainty.”