Hacker News Reader

I've long wondered about this - I see and understand the comments by people pointing out this paper may a bit shallow - in the same sort of vein, I have this on my desk to grind thru - interested if anyone else has looked at it -- https://arxiv.org/abs/1806.07366

View on HN

Very interesting from mathematical point of view. Too bad no SOTA. When they compare to ResNet result, that last 0.01% accuracy can cost more, than they expect, which would render the result useless.

I'm wondering if it might not be a good solution for >some< layers in a deep network, i.e. it's just another building block - practically I'm wondering just how far this puppy can distribute over gpus, and if you could pipeline the whole thing - i dunno tho, as far as I've gotten is that it might be an interesting experiment - and I don't want to get completely sidetracked by an ODE solver :-)

I just looked at the paper you linked to, and I can't get past the introduction - the idea is pretty mind-blowing! Have to read the whole thing now...

My problem too - have to haul out paper, crayons, Wolfram.....

Relevant xkcd comic: https://www.xkcd.com/356/

Reply on news.ycombinator.com