Every model learned by gradient descent is approximately a kernel machine (2020)arxiv.org/abs/2012.00152
100 sats \ 1 comment \ @hn 25 Feb tech
write
preview
related posts
10 sats \ 0 replies \ @hn OP 25 Feb
This link was posted by Anon84 5 hours ago on HN. It received 99 points and 49 comments.
reply