Recent submissions

Comment · 10 years ago
There is a difference between downvote and ignoring the comment.
Comment · 10 years ago
Downvoted for what?
Comment · 10 years ago
beautiful
Comment · 10 years ago
Is MIT for fun?
Comment · 10 years ago
Why? Is there any remote need to generate scary faces? Or is it done just to have catchy PR title. I hope there is some real motivation to do this line of research.
Comment · 10 years ago
In fact there is no correct answer to that and it depends on your current state of knowledge and needs for your project. It also changes over time.

I would be careful to claim that with theoretical approach you will always get better understanding.

Comment · 10 years ago
Nice list, but there are too many papers like this and it is easy to get stuck in theory. I would suggest to grab some simple neural network (Darknet is great for that) code and read that first. If something does not make sense, find the theory from papers.
Comment · 10 years ago
So what is the message? Honestly, I didn't get any information form the article.
Comment · 10 years ago
'WTF' really?
Comment · 10 years ago
I wander how many people still implement their own networks as opposed to use these prepared frameworks. Or do you guys stick to single framework or use some sort of mixture of tools?
Comment · 10 years ago
Bug: 3x3 blur kernel, e.g. [1 1 1; 1 1 1; 1 1 1], outputs white image.
Comment · 10 years ago
Can we expect the price of "old" Titan X to drop after this announcement? I would like to upgrade 4x SLI.
Comment · 10 years ago
Inspired by Silicon Valley?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton