latest | popular

Filter by
Smooth Adversarial Training
ReLU activation function significantly weakens adversarial training due to its non-smooth nature. Hence we propose smooth adversarial training (SAT).
adversarial-training adversarial-learning relu sat
projects 1 - 1 of 1
Topic experts
Share your project
Discover, build and share what you've made with ML.
Share someone else's project
Share something interesting you found that's made with ML.