A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement

2022-04-20 · Matias Valdenegro-Toro, Daniel Saromo

Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, some methods like Flipout produce zero epistemic uncertainty, aleatoric uncertainty is unreliable in the out-of-distribution setting, and Ensembles provide overall the best disentangling quality. We also explore the error produced by the number of samples hyper-parameter in the sampling softmax function, recommending N > 100 samples. We expect that our formulation and results help practitioners and researchers choose uncertainty methods and expand the use of disentangled uncertainties, as well as motivate additional research into this topic.

📄 PDF Abstract BibTeX arXiv:2204.09308

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementUncertainty Quantification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Looking at the posterior: accuracy and uncertainty of neural-network predictions

2022-11-26 · H. Linander, O. Balabanov, H. Yang, B. Mehlig

Bayesian inference can quantify uncertainty in the predictions of neural networks using posterior distributions for model parameters and network output. By looking at these posterior distributions, one can separate the o…

Active Learning Bayesian Inference Image Classification Uncertainty Quantification

Why Machine Learning Models Fail to Fully Capture Epistemic Uncertainty

2025-05-29 · Sebastián Jiménez, Mira Jürgens, Willem Waegeman

In recent years various supervised learning methods that disentangle aleatoric and epistemic uncertainty based on second-order distributions have been proposed. We argue that these methods fail to capture critical compon…

Uncertainty Quantification

Intrinsic Randomness in Epidemic Modelling Beyond Statistical Uncertainty

2022-10-25 · Matthew J. Penn, Daniel J. Laydon, Joseph Penn, Charles Whittaker 외

Uncertainty can be classified as either aleatoric (intrinsic randomness) or epistemic (imperfect knowledge of parameters). The majority of frameworks assessing infectious disease risk consider only epistemic uncertainty.…

Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning

2022-06-03 · Bertrand Charpentier, Ransalu Senanayake, Mykel Kochenderfer, Stephan Günnemann

Characterizing aleatoric and epistemic uncertainty on the predicted rewards can help in building reliable reinforcement learning (RL) systems. Aleatoric uncertainty results from the irreducible environment stochasticity …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

The Hidden Uncertainty in a Neural Networks Activations

2020-12-05 · Janis Postels, Hermann Blum, Yannick Strümpler, Cesar Cadena 외

The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution moreover correlates with a model's epist…

Density Estimation Out of Distribution (OOD) Detection