On Fri, Nov 4, 2011 at 4:54 PM, Andreas Müller <[email protected]> wrote:
> On 11/04/2011 03:49 PM, Andreas Müller wrote:
>> On 11/04/2011 03:42 PM, Alexandre Passos wrote:
>>> 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.
>>>
>>>
>>
> As an afterthought: you could use the same argument for SGD,
> kmeans and many other algorithms inside sklearn.
> Do you want all of them to be replaced by theano implementations?

This is a great point. Also, I'd like to cite Gael's recent remark
"Machine learning should be a commodity", so if we could have simpler
code with less dependencies that would do just well enough, then a
niche would be filled, in my opinion.

Vlad

------------------------------------------------------------------------------
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