We study challenges using reinforcement learning in controlling energy
s...
Covariate shift may impact the operational safety performance of neural
...
Out-of-distribution (OoD) detection techniques are instrumental for
safe...
While autonomous vehicles (AVs) may perform remarkably well in generic
r...
Uncertainty estimation is crucial in safety-critical settings such as
au...
This work aims to explore and identify tiny and seemingly unrelated
pert...
We propose a method for deploying a safety-critical machine-learning
com...
State-of-the-art object detectors have been shown effective in many
appl...
For safety assurance of deep neural networks (DNNs), out-of-distribution...
In this paper, we consider the imperfection within machine learning-base...
We investigate the issues of achieving sufficient rigor in the arguments...
ComOpT is an open-source research tool for coverage-driven testing of
au...
Within the context of autonomous driving, safety-related metrics for dee...
While object detection modules are essential functionalities for any
aut...
Continuous engineering of autonomous driving functions commonly requires...
For deep neural networks (DNNs) to be used in safety-critical autonomous...
Deploying deep neural networks (DNNs) as core functions in autonomous dr...
We study how state-of-the-art neural networks for 3D object detection us...
We consider the problem of engineering robust direct perception neural
n...
We study the problem of safety verification of direct perception neural
...
We provide a summary over architectural approaches that can be used to
c...
nn-dependability-kit is an open-source toolbox to support safety enginee...
For using neural networks in safety critical domains, it is important to...
For using neural networks in safety critical domains, it is important to...
Neural networks and other data engineered models are instrumental in
dev...
Systematically testing models learned from neural networks remains a cru...
We study the problem of formal verification of Binarized Neural Networks...
We study the problem of formal verification of Binarized Neural Networks...
We propose a methodology for designing dependable Artificial Neural Netw...
The deployment of Artificial Neural Networks (ANNs) in safety-critical
a...