New

The latest blog posts to take off on Hacker News. 4,419 posts.

Any topic
2018
2102

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 :

2109

Lost in Math

Sabine Hossenfelder’s new book Lost in Math should be starting to appear in bookstores around now. It’s very good and you should get a copy. I hope that the book will receive a lot of a…

2127

AntiPolygraph.org appears to have been “de-listed” from Google on key searches

Search DuckDuckGo for “polygraph” and you’ll find AntiPolygraph.org, which hosts more documentation on polygraphs than any other site on the Internet, in the top 10 results. The same is true for searches on “polygraph” with Microsoft’s Bing search engine (in the United States), with Russia’s Yandex search engine, and…