1. Imagenet classification with deep convolutional neural networks;Alex Krizhevsky;Advances in neural information processing systems,2012
2. Adversarial training for free;Ali Shafahi;Proceedings of the 33rd International Conference on Neural Information Processing Systems,2019
3. A simple weight decay can improve generalization;Anders Krogh;Advances in neural information processing systems,1992
4. Attention is all you need;Ashish Vaswani;Advances in Neural Information Processing Systems,2017