Konu "White box" için listeleme
Toplam kayıt 1, listelenen: 1-1
-
Unreasonable effectiveness of last hidden layer activations for adversarial robustness
(Institute of Electrical and Electronics Engineers Inc., 2022)In standard Deep Neural Network (DNN) based classifiers, the general convention is to omit the activation function in the last (output) layer and directly apply the softmax function on the logits to get the probability ...