Results 11 to 20 of about 1,009,621 (180)
A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement [PDF]
LatinX in AI at Computer Vision and Pattern Recognition Conference 2022, 2022 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,
Matias Valdenegro-Toro +1 more
openaire +5 more sources
Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning [PDF]
CoRR, 2022 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 leading to inherently risky states and actions. Epistemic uncertainty results from the limited information accumulated during learning
Bertrand Charpentier +3 more
core +5 more sources
Aleatoric and Epistemic Uncertainty with Random Forests [PDF]
, 2020 10 pages, 4 ...
Shaker, Mohammad Hossein +1 more
openaire +6 more sources
Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation [PDF]
IEEE Transactions on Big Data, 2023 Historical interactions are the default choice for recommender model training, which typically exhibit high sparsity, i.e., most user-item pairs are unobserved missing data. A standard choice is treating the missing data as negative training samples and estimating interaction likelihood between user-item pairs along with the observed interactions.
Chenxu Wang 0010 +5 more
core +5 more sources
Towards Reducing Aleatoric Uncertainty for Medical Imaging Tasks [PDF]
2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 2022 Accepted in IEEE International Symposium on Biomedical Imaging (ISBI ...
Abhishek Singh Sambyal +2 more
openaire +4 more sources
Evaluating Aleatoric Uncertainty via Conditional Generative Models
CoRR, 2022 Aleatoric uncertainty quantification seeks for distributional knowledge of random responses, which is important for reliability analysis and robustness improvement in machine learning applications. Previous research on aleatoric uncertainty estimation mainly targets closed-formed conditional densities or variances, which requires strong restrictions on
Ziyi Huang +2 more
openaire +4 more sources
Aleatoric and Epistemic Uncertainty in Conformal Prediction. [PDF]
Recently, there has been a particular interest in distinguishing different types of uncertainty in supervised machine learning (ML) settings (Hullermeier and Waegeman, 2021). Aleatoric uncertainty captures the inherent randomness in the data-generating process.
Sale, Yusuf +2 more
core +5 more sources
Achieving robustness to aleatoric uncertainty with heteroscedastic Bayesian optimisation [PDF]
Machine Learning: Science and Technology, 2021 Abstract Bayesian optimisation is a sample-efficient search methodology that holds great promise for accelerating drug and materials discovery programs. A frequently-overlooked modelling consideration in Bayesian optimisation strategies however, is the representation of heteroscedastic aleatoric uncertainty.
Ryan-Rhys Griffiths +4 more
openaire +9 more sources
Deep Modeling of Non-Gaussian Aleatoric Uncertainty [PDF]
IEEE Robotics and Automation LettersDeep learning offers promising new ways to accurately model aleatoric uncertainty in robotic state estimation systems, particularly when the uncertainty distributions do not conform to traditional assumptions of being fixed and Gaussian. In this study, we formulate and evaluate three fundamental deep learning approaches for conditional probability ...
Aastha Acharya +5 more
core +6 more sources
Label-wise Aleatoric and Epistemic Uncertainty Quantification [PDF]
CoRRUncertainty in Artificial Intelligence.
Sale, Yusuf +5 more
core +9 more sources