Search Results for author:
Found 2 papers, 0 papers with code
Noise Sensitivity and Stability of Deep Neural Networks for Binary Classification
A first step is taken towards understanding often observed non-robustness phenomena of deep neural net (DNN) classifiers.
Robust Neural Network Classification via Double Regularization
Here we propose a novel double regularization of the neural network training loss that combines a penalty on the complexity of the classification model and an optimal reweighting of training observations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
