Top posts

Every blog post that took off on Hacker News, ranked by the votes of its best submission. 6,335 posts.

AI & Machine Learning
Any year
4852

A New Angle on L2 Regularization

Deep neural networks have been shown to be vulnerable to the adversarial example phenomenon: all models tested so far can have their classifications dramatically altered by small image perturbations . The following predictions were for instance made by a state-of-the-art network trained to recognize celebrities :