Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

It's always been interesting to me that someone publishing a paper in computer science (especially someone working at a University) would not want to open source the code that produced those results. It's the best kind of repeatable experiment.

I recently went looking for any code published by Hinton, since I've been doing some neural network research as a hobby, but was unable to find any at all.



Speaking from personal experience, a lot of academics see programming as a hurdle---an unpleasantry that must be overcome as quickly as possible before going back to the real interesting bits.

This tends to result in very poor code, since the people who write it do not practice their craft. And very poor code isn't usually released because people are embarrassed.

I'm certainly generalizing here, but this seems to be the trend as I see it. It is a sorry state of affairs, and I try to do my best to encourage publishing code with the people I work with. (Code reviews are great.)


Actually, Alex Krizhevsky published some of the code they have been using @ http://code.google.com/p/cuda-convnet/

It seems from my experience that generally Hinton and team seem very open to sharing quite abit of their code, data and results.


You'll probably have to contact him (or the graduate student who did the work, realistically), but if you do you'll probably get it.




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: