Results 41 to 50 of about 7,687 (182)

Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images using Bayesian Deep Learning

, 2018
Optical coherence tomography (OCT) is commonly used to analyze retinal layers for assessment of ocular diseases. In this paper, we propose a method for retinal layer segmentation and quantification of uncertainty based on Bayesian deep learning.
A Carass, A Lang, A Mishra, J Novosel, JE Iglesias, JH Acton, KA Vermeer, L Fang, MK Garvin, O Ronneberger, Pratul P. Srinivasan, Sina Farsiu, SJ Chiu   +12 more
core   +1 more source

Uncertainty Estimation of Lake Ice Cover Maps From a Random Forest Classifier Using MODIS TOA Reflectance Data

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
This article presents a method to improve the usability of lake ice cover (LIC) maps generated from moderate resolution imaging spectroradiometer (MODIS) top-of-atmosphere reflectance data by providing estimates of aleatoric and epistemic uncertainty. We
Nastaran Saberi, Mohammad Hossein Shaker, Claude R. Duguay, K Andrea Scott, Eyke Hullermeier   +4 more
doaj   +1 more source

An Alarm System For Segmentation Algorithm Based On Shape Model

, 2019
It is usually hard for a learning system to predict correctly on rare events that never occur in the training data, and there is no exception for segmentation algorithms. Meanwhile, manual inspection of each case to locate the failures becomes infeasible
Liu, Fengze, Xia, Yingda, Xu, Daguang, Yang, Dong, Yuille, Alan   +4 more
core   +1 more source

A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement

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,
Valdenegro-Toro, Matias, Saromo, Daniel
openaire   +2 more sources

Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting

Sensors, 2021
Data-driven forecasts of air quality have recently achieved more accurate short-term predictions. However, despite their success, most of the current data-driven solutions lack proper quantifications of model uncertainty that communicate how much to ...
Abdulmajid Murad, Frank Alexander Kraemer, Kerstin Bach, Gavin Taylor   +3 more
doaj   +1 more source

Identifying Drivers of Predictive Aleatoric Uncertainty

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence
Explainability and uncertainty quantification are key to trustable artificial intelligence. However, the reasoning behind uncertainty estimates is generally left unexplained. Identifying the drivers of uncertainty complements explanations of point predictions in recognizing model limitations and enhancing transparent decision-making.
Iversen, Pascal, Witzke, Simon, Baum, Katharina, Renard, Bernhard Y.   +3 more
openaire   +2 more sources

Spintronic Bayesian Hardware Driven by Stochastic Magnetic Domain Wall Dynamics

Advanced Science, EarlyView.
Magnetic Probabilistic Computing (MPC) utilizes intrinsic stochastic dynamics in domain walls to establish a hardware foundation for uncertainty‐aware artificial intelligence. Thermally driven domain‐wall fluctuations, voltage‐controlled magnetic anisotropy, and TMR readout enable fully electrical, tunable probabilistic inference.
Tianyi Wang, Bingqian Dai, Shijie Xu, Kin Wong, Yaochen Li, Yang Cheng, Qingyuan Shu, Haoran He, Puyang Huang, Hanshen Huang, Xixiang Zhang, Kang L. Wang   +11 more
wiley   +1 more source

Taguchi–Bayesian Sampling: A Roadmap for Polymer Database Construction Toward Small Representative Machine Learning

Advanced Intelligent Discovery, EarlyView.
This article establishes a Taguchi–Bayesian sampling strategy to reconstruct polymer processing–property landscape at minimal sampling cost, generically building the roadmap for materials database construction from sampling their vast design space. This sampling strategy is featured by an alternating lesson between uniformity and representativeness ...
Han Liu, Liantang Li
wiley   +1 more source

One Step Closer to Unbiased Aleatoric Uncertainty Estimation

Proceedings of the AAAI Conference on Artificial Intelligence
Neural networks are powerful tools in various applications, and quantifying their uncertainty is crucial for reliable decision-making. In the deep learning field, the uncertainties are usually categorized into aleatoric (data) and epistemic (model) uncertainty.
Zhang, Wang, Ma, Ziwen, Das, Subhro, Weng, Tsui-Wei, Megretski, Alexandre, Daniel, Luca, Nguyen, Lam M.   +6 more
openaire   +2 more sources

Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning

, 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
Charpentier, Bertrand, Senanayake, Ransalu, Kochenderfer, Mykel, Günnemann, Stephan   +3 more
openaire   +2 more sources