3.2k citations · 9.8k across the 51 of their papers we have counts for
Showing 2016 · cs.LGShow all
3 papers · 2 filters
cs.LG2016★ 122 cited
Early Methods for Detecting Adversarial Images
Dan Hendrycks, Kevin Gimpel
Many machine learning classifiers are vulnerable to adversarial perturbations. An adversarial perturbation modifies an input to change a classifier's prediction without causing the…
cs.LG2016★ 16 cited
Adjusting for Dropout Variance in Batch Normalization and Weight Initialization
Dan Hendrycks, Kevin Gimpel
We show how to adjust for the variance introduced by dropout with corrections to weight initialization and Batch Normalization, yielding higher accuracy. Though dropout can preserv…
cs.LG2016★ 3.2k cited
Gaussian Error Linear Units (GELUs)
Dan Hendrycks, Kevin Gimpel
We propose the Gaussian Error Linear Unit (GELU), a high-performing neural network activation function. The GELU activation function is , where the standard Gaussian…