Hacker News new | ask | show | jobs
by hooloovoo_zoo 3700 days ago
These changes are not random. The whole reason neural networks work at all is because probable differences do not mislead the network.
1 comments

This is not true at all. Adversarial input can indeed be probable input depending on your definitions and I haven't seen anything yet that describes the probability distributions of inputs. Everyone takes a bunch of training examples and extrapolates from there.