Hi Arasu,
Deep learning requires a rich vocabulary to define an architecture, and
the use of GPUs for computing. Neither of these fit in the design
constraints of scikit-learn. Hence deep learning is currently
out-of-scope for scikit-learn. That's not a problem, there are excellent
existing deep-learning libraries.
Cheers,
Gael
On Wed, Dec 16, 2015 at 06:30:23PM +0530, Arasu Arun wrote:
> Hello Mentors!
> I'm interested in deep learning and wanna contribute to scikit-learn and try
> out for GSoC next summer. I was wondering if scikit-learn is looking to expand
> its neural nets package.
> If so, could you please point me to some related tasks that I can start
> contributing on?
> Thank you!
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-08-79-68
http://gael-varoquaux.info http://twitter.com/GaelVaroquaux
------------------------------------------------------------------------------
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
