Differences
This shows you the differences between two versions of the page.
— |
label_smoothing [2016/12/13 16:20] (current) |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | https://arxiv.org/abs/1606.03498v1 Improved Techniques for Training GANs | ||
+ | |||
+ | Label smoothing, a technique from the 1980s recently independently re-discovered by Szegedy et. | ||
+ | al [17], replaces the 0 and 1 targets for a classifier with smoothed values, like .9 or .1, and was | ||
+ | recently shown to reduce the vulnerability of neural networks to adversarial examples [18]. | ||
+ | |||
+ | [17] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. Rethinking the Inception Architecture for | ||
+ | Computer Vision. ArXiv e-prints, December 2015. | ||
+ | [18] David Warde-Farley and Ian Goodfellow. Adversarial perturbations of deep neural networks. In Tamir | ||
+ | Hazan, George Papandreou, and Daniel Tarlow, editors, Perturbations, Optimization, and Statistics, chapter | ||
+ | 11. 2016. Book in preparation for MIT Press. | ||