Regularized discrete optimal transport (OT) is a powerful tool to measur...
Gate functions in recurrent models, such as an LSTM and GRU, play a cent...
Defending deep neural networks against adversarial examples is a key
cha...
Few-shot learning for neural networks (NNs) is an important problem that...
Pruning the weights of randomly initialized neural networks plays an
imp...
Deep neural networks are vulnerable to adversarial attacks. Recent studi...
We propose a method for improving adversarial robustness by addition of ...
We propose Absum, which is a regularization method for improving adversa...
Residual Networks with convolutional layers are widely used in the field...
Adaptive learning rate algorithms such as RMSProp are widely used for
tr...