AI & machine learning2019 · shared on Hacker News
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
Explore Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ygyang ·
Wide Neural Networks of Any Architecture Are Gaussian Processes
144 points34 comments
Yiron0013 ·
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
3 points0 comments
Ygballan ·
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
2 points0 comments