ogdan
Joined 9 years ago
Karma
17
Submissions
9
Member since
Jan 18
Recent submissions
Comment · 8 years ago
If f has small K complexity, then f^-1 has small K complexity.
Comment · 9 years ago
For some background, see https://arxiv.org/pdf/1412.1897.pdf which has some cool visuals of pictures that make neural networks to strange things.
Looks like this group might have solved adversarial examples (or rather, found that they're not a problem in practice after all) for self driving cars!
Yann LeCun seems confident about it: https://mobile.twitter.com/ylecun/status/885384106418294784
Comment · 9 years ago
You can use Tor to post to HN anonymously.
Comment · 9 years ago
The specification is a lot smaller than the code, and so it's easier to read and manually verify that it's correct.
Comment · 9 years ago
Here's a recent research paper discussing the security implications of typo tolerant authentication schemes: http://www.arijuels.com/wp-content/uploads/2016/07/CAAJ16.pd...