[scikit-learn] MLP Maxout activation proposal

Siddharth Gupta siddharthgupta234 at gmail.com
Sun Sep 25 08:40:08 EDT 2016


Yes, Ryosuke the link works. Lets start by creating an issue where we can
discuss the dos and don'ts. Something on these lines
https://github.com/scikit-learn/scikit-learn/issues/6175 ! You create the
issue, we'll see what others think and then we'll proceed further.

Regards Siddharth Gupta,
Ph: 9871012292
Linkedin <https://www.linkedin.com/in/sidgupta234/> | Github
<https://github.com/sidgupta234> | Codechef
<https://www.codechef.com/users/sidgupta234> | Twitter
<https://twitter.com/SidGupta234> | Facebook
<https://www.facebook.com/profile.php?id=1483695876>

On Sun, Sep 25, 2016 at 5:16 PM, 深谷亮祐 <nannyakannya at gmail.com> wrote:

> Thanks for your reply!
> I look forward to working with you.
>
> In my environment, the file link works, but I found another.
> Please try this URL-> ( https://arxiv.org/abs/1302.4389 )
>
> Regards Ryosuke,
>
> 2016-09-25 18:51 GMT+09:00, Siddharth Gupta <siddharthgupta234 at gmail.com>:
> > It seems like a great idea to me. I would love to co-work on this
> feature.
> > Also could you check the file link, it does not seem to be opening the
> > document.
> >
> > Regards Siddharth Gupta,
> > Ph: 9871012292
> > Linkedin <https://www.linkedin.com/in/sidgupta234/> | Github
> > <https://github.com/sidgupta234> | Codechef
> > <https://www.codechef.com/users/sidgupta234> | Twitter
> > <https://twitter.com/SidGupta234> | Facebook
> > <https://www.facebook.com/profile.php?id=1483695876>
> >
> > On Sun, Sep 25, 2016 at 3:14 PM, 深谷亮祐 <nannyakannya at gmail.com> wrote:
> >
> >> Hi everyone,
> >>
> >> My name is Ryosuke Fukatani.
> >> I'm joining a scikit-learn community and really excited to work with
> all.
> >>
> >> Today I propose new feature "maxout activation" for MLP.
> >> Maxout activation achived high performance
> >> classification.(http://www.jmlr.org/proceedings/papers/
> >> v28/goodfellow13.pdf).
> >>
> >> And it seemed that only a few layers are needed to use maxout.
> >> I think it is suitable feature for light weight MLP by scikit learn.
> >>
> >> If it's OK, I'd work on it.
> >> Best regards
> >> _______________________________________________
> >> scikit-learn mailing list
> >> scikit-learn at python.org
> >> https://mail.python.org/mailman/listinfo/scikit-learn
> >>
> >
>
>
> --
> ********************************
>
> ********************************
> _______________________________________________
> scikit-learn mailing list
> scikit-learn at python.org
> https://mail.python.org/mailman/listinfo/scikit-learn
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/scikit-learn/attachments/20160925/805ef7ea/attachment-0001.html>


More information about the scikit-learn mailing list