Sensitivity analysis for predictive uncertainty
By Stefan Depeweg, José Miguel Hernández-Lobato, Steffen Udluft, Thomas A. Runkler. 2017
8 citations recorded by the source corpus.
© ESANN 2018 - Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. We derive a novel sensitivity analysis of input variables for predictive epistemic and aleatoric uncertainty. We use Bayesian neural networks with latent variables as a model class and illustrate the usefulness of our sensitivity analysis on real-world datasets. Our method increases the interpretability of complex black-box probabilistic models.
Subfields: Artificial Intelligence, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Adrian Weller
- Lucy R. Chai
- Umang Bhatt
- Javier Antorán Cabiscol
- Javier Antorán
- Tameem Adel
- Muhammad Shahzad
- José Miguel Hernández-Lobato
In Control and Systems Engineering
- Lucy R. Chai
- Javier Antorán Cabiscol
- Muhammad Shahzad
- José Miguel Hernández-Lobato
- Adrian Weller
- Tameem Adel
- Rudolph Triebel
Citations in the corpus
- Getting a CLUE: A Method for Explaining Uncertainty Estimates (2020, methodology): “For approaches that do not use an auxiliary DGM, like Uncertainty Sensitivity Analysis, the orange element will not be present. sources of uncertainty in the data, as opposed to exploiting adversarial vulnerabilities in the BNN.”
- Uncertainty Estimation in Bayesian Neural Networks And Links to Interpretability (2018, methodology): “High aleatoric uncertainty suggests that we do not have enough information to predict the output value for an input with fixed weight settings, due to unobserved or latent variables that the model cannot capture [16, 17].”
- A survey of uncertainty in deep neural networks (2021, background): “Other approaches, e.g. BNNs, still converge to one single optimum, but additionally take the uncertainty on this local optimum into account [227].”
- Understanding Uncertainty in Bayesian Neural Networks (2019, methodology): “3, we discuss uncertainty sensitivity analysis (Depeweg et al., 2017) which, to the best of our knowledge, is the only existing method for interpreting uncertainty estimates in BNNs.”