Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Self-Normalizing Neural Networks.
Edits:
Looks impressive, best or near best on most, but I wish they had bolded best of set.
Still not sure how the regularization squares with the rapid precision fitting to the training set data in Figure 1.
There are no comments on this comment yet.
Edits:
Looks impressive, best or near best on most, but I wish they had bolded best of set.
Still not sure how the regularization squares with the rapid precision fitting to the training set data in Figure 1.