2 papers
cs.LG2022
Adversarial Detection by Approximation of Ensemble Boundary
T. Windeatt
Despite being effective in many application areas, Deep Neural Networks (DNNs) are vulnerable to being attacked. In object recognition, the attack takes the form of a small perturb…
cs.LG2021
A unifying approach on bias and variance analysis for classification
Cemre Zor, Terry Windeatt
Standard bias and variance (B&V) terminologies were originally defined for the regression setting and their extensions to classification have led to several different models / defi…