On Fri, Nov 4, 2011 at 10:34, Lars Buitinck <[email protected]> wrote:
> 2011/11/4 Alexandre Passos <[email protected]>:
>> I have a question: why not just use Theano for this? I doubt that we
>> can write neural network code that's as fast as their automatically
>> generated code.
>
> Would that mean an extra run-time dependency?


Yes, as theano needs a compiler (gcc or nvcc if you want to use cuda)
available at run time, but even still it's faster even than most
hand-coded implementations of neural networks. James Bergstra reads
this list occasionally, and he's one of the main people behind theano,
so he can give more info here.


-- 
 - Alexandre

------------------------------------------------------------------------------
RSA(R) Conference 2012
Save $700 by Nov 18
Register now
http://p.sf.net/sfu/rsa-sfdev2dev1
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to