There are other more specialised projects that facilitate modular neural
networks. The idea in scikit-learn is to provide useful out-of-the-box
components for well-established solutions to certain types of tasks that
fit a simple interface. This often means limiting their flexible use from
the perspective of ML research.

But there are other projects that are designed to be more flexible in the
context of algorithmic experimentation, such as pylearn2.

On 19 March 2015 at 16:23, Vishwajeet Narwal <vnarwa...@gmail.com> wrote:

> Hi,
>
> I have gone through documentation of Pull 3306. I am glad that ELM will
> soon be part of scikit-learn. But It is just working as an simple ML
> algorithm,
> which can be fitted to data and can predict based on the trained model. I
> was considering to develop something different. My plan is to implement ELM
> or its variant as an object which can be used as a layer in Deep Learning
> algorithms or semi-supervised algorithms wherever possible (some of which
> are not yet published, but I have developed codes on Matlab and I will soon
> submit them). It may be modification of previous implementations, depending
> on the code. (I haven't gone through codes yet)
>
> What do you think about this idea ? Please give suggestion with and without
> considering GSoC.
>
> Secondly, can anyone tell me how to reply to a thread ? I am getting my
> reply only through general Digest and not an individual mail.
>
> thanks
>
> --
> *Vishwajeet Narwal*
> Event Organiser,IEEE LNMIIT SB
> Core Member, SRIG Research Interest Group
> DIP Mentor, Phoenix Club,LNMIIT
> 2nd Year, Computer Science & Engineering
> The *LNMIIT, Jaipur*
>
>
> ------------------------------------------------------------------------------
> Dive into the World of Parallel Programming The Go Parallel Website,
> sponsored
> by Intel and developed in partnership with Slashdot Media, is your hub for
> all
> things parallel software development, from weekly thought leadership blogs
> to
> news, videos, case studies, tutorials and more. Take a look and join the
> conversation now. http://goparallel.sourceforge.net/
> _______________________________________________
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
>
------------------------------------------------------------------------------
Dive into the World of Parallel Programming The Go Parallel Website, sponsored
by Intel and developed in partnership with Slashdot Media, is your hub for all
things parallel software development, from weekly thought leadership blogs to
news, videos, case studies, tutorials and more. Take a look and join the 
conversation now. http://goparallel.sourceforge.net/
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to