Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Want to contribute in Open source implementation of research papers

news.ycombinator.com

Post reply on HN
Print view View original

11–16 of 16 posts

Re: Ask HN: Want to contribute in Open source implementation of research papers

#11

Post by ganarajpr »

I would suggest you to have a look at http://www.gitxiv.com

Gitxiv is an online list combining research papers from arxiv and their implementations in github. So I would say its a great resource for what you are looking for.

Also, they run some kind of competitive implementation runs where you can collaborate with others to implement papers :

https://github.com/GitXiv/DeepQA

I am a JS dev as well interested in Deep Learning. I dont know your specific interest in this domain but I am happy to collaborate with you - if you are interested. You can reach me at raj at dhi dot io. I would suggest you to pick up python or lua. Lua is quite close to JS and Python is extremely easy to pick up as well.

Re: Ask HN: Want to contribute in Open source implementation of research papers

#13

Post by gamekathu »

ganarajpr wrote: post #11

I would suggest you to have a look at http://www.gitxiv.com Gitxiv is an online list combining research papers from arxiv and their implementations in github. So I would say its a great resource for what you are looking for. Also, they run some kind of competitive implementation runs where you can collaborate with others to implement papers : https://github.com/GitXiv/DeepQA I am a JS dev as well interested in Deep L…

nice! I know python at a beginner level, i can work on it. Yes i am also interested to collaborate and learn, will mail you shortly! :)

Re: Ask HN: Want to contribute in Open source implementation of research papers

#14

Post by dennybritz »

polakallen wrote: post #7
gamekathu wrote: post #5

Earlier quoted context omitted.

specific field would be machine learning. I regularly follow Karpathy's blog and his convnetjs library [1], and also Harthur's brain library [2]. yes, I also found a lot of papers cryptic and hard to follow [1] https://github.com/karpathy/convnetjs [2] https://github.com/harthur/brain

What have you done so far in terms of learning machine learning? There's quite a few resources for getting a good foundation, if that's something you might need. Ironically, looking dennybritz's comment, JS is particularly ill-suited for this, as, as far as I'm aware, there are no libraries for working on the GPU, which is tremendously useful for working with machine learning algorithms which usually are crunching lo…

You're right that JS is pretty ill-suited for implementing production-level Deep Learning architectures that operate on a lot of data, I think it's still well suited for explaining the concepts in a clear way. A lot of the models have intuitive (and visual) interpretations, something that can be nicely visualized with JS.

As for Karpathy's implementation, you're right, he chose JS for that reason. His library is meant as a tool for experimenting and teaching, not to deploy these models in production.

Op: Send me an email if you're interested in this (email in profile). I actually started something similar just recently at http://www.wildml.com/.

Re: Ask HN: Want to contribute in Open source implementation of research papers

#15

Post by gamekathu »

dennybritz wrote: post #14
polakallen wrote: post #7

Earlier quoted context omitted.

What have you done so far in terms of learning machine learning? There's quite a few resources for getting a good foundation, if that's something you might need. Ironically, looking dennybritz's comment, JS is particularly ill-suited for this, as, as far as I'm aware, there are no libraries for working on the GPU, which is tremendously useful for working with machine learning algorithms which usually are crunching lo…

You're right that JS is pretty ill-suited for implementing production-level Deep Learning architectures that operate on a lot of data, I think it's still well suited for explaining the concepts in a clear way. A lot of the models have intuitive (and visual) interpretations, something that can be nicely visualized with JS. As for Karpathy's implementation, you're right, he chose JS for that reason. His library is mean…

Nice blog! Yes I am interested in Deep learning, although am just a newbie. Right now I just read around in several blogs to get the idea. As for JS visualizations, TonicDev[1] is a nice option if someone wants a IPython style notebook in JS

[1] https://tonicdev.com

Re: Ask HN: Want to contribute in Open source implementation of research papers

#16

Post by mammo »

ganarajpr wrote: post #11

I would suggest you to have a look at http://www.gitxiv.com Gitxiv is an online list combining research papers from arxiv and their implementations in github. So I would say its a great resource for what you are looking for. Also, they run some kind of competitive implementation runs where you can collaborate with others to implement papers : https://github.com/GitXiv/DeepQA I am a JS dev as well interested in Deep L…

www.gitxiv.com gives "Modulus | Application Not Found". http://gitxiv.com/ works.
Post reply on HN