News for hackers. Stuff that matters.
Re:Regularization is all you need: simple neural nets can ex... by melling on Tuesday June 22, 2021 @03:13PM (#27595865)
Isn’t it a reference to the “Attention is All You Need” machine learning paper?

https://arxiv.org/abs/1706.03762

Re:Regularization is all you need: simple neural nets can ex... by toxik on Tuesday June 22, 2021 @04:10PM (#27596547)
Yes, and this is the fourth or fifth paper I see copying that format. The attention paper was pretty damn significant. This won’t be, because it just shows that hyperparameters are important. We know that.