9 citations · 21 across the 4 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 5 cited
L 1-norm double backpropagation adversarial defense
Ismaïla Seck, Gaëlle Loosli, Stephane Canu
Adversarial examples are a challenging open problem for deep neural networks. We propose in this paper to add a penalization term that forces the decision function to be at in some…
cs.LG2019★ 4 cited
TrIK-SVM : an alternative decomposition for kernel methods in Krein spaces
Gaëlle Loosli
The proposed work aims at proposing a alternative kernel decomposition in the context of kernel machines with indefinite kernels. The original paper of KSVM (SVM in Kreǐn spaces) u…