Uncertainty, epistemics and active inference [PDF]
Journal of The Royal Society Interface, 2017 Abstract Biological systems—like ourselves—are constantly faced with uncertainty. Despite noisy sensory data, and volatile environments, creatures appear to actively maintain their integrity. To account for this remarkable ability to make optimal decisions in the face of a capricious world, we propose a generative model that ...
Thomas Parr, Karl J. Friston
openaire +3 more sources
Looking at the posterior: accuracy and uncertainty of neural-network predictions
Machine Learning: Science and Technology, 2023 Bayesian inference can quantify uncertainty in the predictions of neural networks using posterior distributions for model parameters and network output.
Hampus Linander +3 more
doaj +1 more source
Epistemic Uncertainty Sampling [PDF]
, 2019 Various strategies for active learning have been proposed in the machine learning literature. In uncertainty sampling, which is among the most popular approaches, the active learner sequentially queries the label of those instances for which its current prediction is maximally uncertain.
Vu-Linh Nguyen +2 more
openaire +2 more sources
Communicating uncertainty about facts, numbers and science [PDF]
Royal Society Open Science, 2019 Uncertainty is an inherent part of knowledge, and yet in an era of contested expertise, many shy away from openly communicating their uncertainty about what they know, fearful of their audience's reaction.
Anne Marthe van der Bles +6 more
doaj +1 more source
JOINT ESTIMATION OF DEPTH AND ITS UNCERTAINTY FROM STEREO IMAGES USING BAYESIAN DEEP LEARNING [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022 The necessity to identify errors in the context of image-based 3D reconstruction has motivated the development of various methods for the estimation of uncertainty associated with depth estimates in recent years.
M. Mehltretter
doaj +1 more source
Using Explainable AI to Measure Feature Contribution to Uncertainty
Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2022 The application of artificial intelligence techniques in safety-critical domains such as medicine and self-driving vehicles has raised questions regarding its trustworthiness and reliability.
Katherine Elizabeth Brown +1 more
doaj +1 more source
Handling epistemic and aleatory uncertainties in probabilistic circuits [PDF]
Machine Learning, 2022 Under submission to ...
Federico Cerutti 0001 +3 more
openaire +4 more sources
Tolerance analysis approach based on the classification of uncertainty (aleatory / epistemic) [PDF]
, 2012 Uncertainty is ubiquitous in tolerance analysis problem. This paper deals with tolerance analysis formulation, more particularly, with the uncertainty which is necessary to take into account into the foundation of this formulation.
Qureshi, A.J. +9 more
core +1 more source
Epistemic cooperation scripts in online learning environments [PDF]
, 2005 Using online learning environments in higher education offers innovative possibilities to support collaborative learning. However, online learning creates new kinds of problems for participants who have not previously worked with each other. One of these
Weinberger, Armin +4 more
core +1 more source
Children's sensitivity to their own relative ignorance : handling of possibilities under epistemic and physical uncertainty [PDF]
, 2006 Children were more likely correctly to specify possibilities when uncertainty resided in the physical world, and more likely to guess the outcome when objectively identical uncertainty arose from their own perspective of ignorance (epistemic uncertainty).
Apperly, Ian +18 more
core +1 more source