A survey on epistemic (model) uncertainty in supervised learning: Recent advances and applications
Quantifying the uncertainty of supervised learning models plays an important role in making
more reliable predictions. Epistemic uncertainty, which usually is due to insufficient …
more reliable predictions. Epistemic uncertainty, which usually is due to insufficient …
SqueezExpNet: Dual-stage convolutional neural network for accurate facial expression recognition with attention mechanism
Facial expression recognition (FER) using a deep convolutional neural network (DCNN) is
important and challenging. Although a substantial effort is made to increase FER accuracy …
important and challenging. Although a substantial effort is made to increase FER accuracy …
Quantification of uncertainty and its applications to complex domain for autonomous vehicles perception system
K Wang, Y Wang, B Liu, J Chen - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Over the last decades, deep neural networks (DNNs) have penetrated all fields of science
and the real world. As a result of the lack of quantifiable data and model uncertainty, deep …
and the real world. As a result of the lack of quantifiable data and model uncertainty, deep …
Uncertainty-aware prediction validator in deep learning models for cyber-physical system data
The use of Deep learning in Cyber-Physical Systems (CPSs) is gaining popularity due to its
ability to bring intelligence to CPS behaviors. However, both CPSs and deep learning have …
ability to bring intelligence to CPS behaviors. However, both CPSs and deep learning have …
Towards robust autonomous driving systems through adversarial test set generation
Correct environmental perception of objects on the road is vital for the safety of autonomous
driving. Making appropriate decisions by the autonomous driving algorithm could be …
driving. Making appropriate decisions by the autonomous driving algorithm could be …
Are elevator software robust against uncertainties? results and experiences from an industrial case study
Industrial elevator systems are complex Cyber-Physical Systems operating in uncertain
environments and experiencing uncertain passenger behaviors, hardware delays, and …
environments and experiencing uncertain passenger behaviors, hardware delays, and …
Uncertainty quantification for deep neural networks: An empirical comparison and usage guidelines
Deep neural networks (DNN) are increasingly used as components of larger software
systems that need to process complex data, such as images, written texts, audio/video …
systems that need to process complex data, such as images, written texts, audio/video …
Evolve the model universe of a system universe
Uncertain, unpredictable, real-time, and lifelong evolution causes operational failures in
intelligent software systems, leading to significant damages, safety and security hazards …
intelligent software systems, leading to significant damages, safety and security hazards …
REAL-SAP: Real-time Evidence Aware Liable Safety Assessment for Perception in Autonomous Driving
Self-evaluation and monitoring are critical components in autonomous driving applications,
especially for safety purposes, and yet there is no systematic framework to estimate the …
especially for safety purposes, and yet there is no systematic framework to estimate the …
A forgotten danger in dnn supervision testing: Generating and detecting true ambiguity
Deep Neural Networks (DNNs) are becoming a crucial component of modern software
systems, but they are prone to fail under conditions that are different from the ones observed …
systems, but they are prone to fail under conditions that are different from the ones observed …