Skip to content

We show that adversarially training (Fast Gradient Sign Method and Projected Gradient Descent) reduces the empirically sample complexity rate for MLP and a variety of CNN architectures on MNIST and CIFAR-10.

chrisliu298/adversarial-sample-complexity

About

We show that adversarially training (Fast Gradient Sign Method and Projected Gradient Descent) reduces the empirically sample complexity rate for MLP and a variety of CNN architectures on MNIST and CIFAR-10.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages