Inherent Uncertainty

Inherent uncertainty, the quantification and mitigation of unpredictable variations in data or models, is a critical challenge across diverse scientific and engineering domains. Current research focuses on developing methods to estimate and incorporate uncertainty, particularly within machine learning models like neural networks, employing techniques such as Bayesian inference and adaptive control algorithms to improve robustness and reliability. This work is crucial for enhancing the trustworthiness of predictions in applications ranging from automated vehicles and medical image analysis to complex control systems, ultimately leading to more reliable and safer technologies. Addressing inherent uncertainty is vital for improving the validity and interpretability of scientific findings and technological applications.

Papers

November 14, 2024

Robot Tasks with Fuzzy Time Requirements from Natural Language Instructions
Sascha Sucker, Michael Neubauer, Dominik Henrich
Natural Language Robot Person Human Instruction Robotic Task Task Boundary Inherent Uncertainty Temporal Fuzzy Utility

October 29, 2024

Uncertainty Quantification via Hölder Divergence for Multi-View Representation Learning
an Zhang, Ming Li, Chun Li, Zhaoxia Liu, Ye Zhang, Fei Richard Yu
Representation Learning Uncertainty Quantification Multi View Robust Version Kullback Leibler Divergence Prediction Uncertainty Dempster Shafer Theory Inherent Uncertainty

March 4, 2024

A prediction rigidity formalism for low-cost uncertainties in trained neural networks
Filippo Bigi, Sanggyu Chong, Michele Ceriotti, Federico Grasselli
Neural Network Bayesian Inference Regression Task Rigid Transformation Arbitrary Machine Learning Model Inherent Uncertainty

February 23, 2024

Improving Explainable Object-induced Model through Uncertainty for Automated Vehicles
Shihong Ling, Yue Wan, Xiaowei Jia, Na Du
High Uncertainty Anticipation Uncertainty Estimation Automated Driving Evidential Deep Learning Data Reweighting Inherent Uncertainty

November 9, 2023

Dynamic Adaptation Gains for Nonlinear Systems with Unmatched Uncertainties
Brett T. Lopez, Jean-Jacques Slotine
Nonlinear Dynamic Adaptive Control Dynamic Adaptation Temporal Adaptation Inherent Uncertainty Co Stabilizability

April 22, 2023

Unmatched uncertainty mitigation through neural network supported model predictive control
Mateus V. Gasparino, Prabhat K. Mishra, Girish Chowdhary
Neural Network Full Model Predictive Control Time Scale Inherent Uncertainty

November 8, 2022

Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty
Jeroen Bertels, David Robben, Dirk Vandermeulen, Paul Suetens
Experimental Validation Automatic Volume Segmentation Map Differentiable Surrogate Dice Similarity Coefficient Inherent Uncertainty

Inherent Uncertainty

Papers

Robot Tasks with Fuzzy Time Requirements from Natural Language Instructions

Uncertainty Quantification via Hölder Divergence for Multi-View Representation Learning

A prediction rigidity formalism for low-cost uncertainties in trained neural networks

Improving Explainable Object-induced Model through Uncertainty for Automated Vehicles

Dynamic Adaptation Gains for Nonlinear Systems with Unmatched Uncertainties

Unmatched uncertainty mitigation through neural network supported model predictive control

Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty