Robust pedestrian trajectory forecasting is crucial to developing safe
a...
Constraint solving is an elementary way for verification of deep neural
...
We present a practical verification method for safety analysis of the
au...
A trend has emerged over the past decades pointing to the harnessing of
...
Structural instability is a hazard that leads to catastrophic failure an...
The saturating counter is the basic module of the dynamic branch predict...
While dropout is known to be a successful regularization technique, insi...
In this paper, we propose a framework of filter-based ensemble of deep
n...
This paper proposes a black box based approach for analysing deep neural...
We propose a spurious region guided refinement approach for robustness
v...
We characterize the asymptotic performance of nonparametric one- and
two...
Deep neural networks (DNNs) have been shown lack of robustness for the
v...
We characterize the asymptotic performance of nonparametric goodness of ...