[mlpack] Hello Everyone

[Vivek Pal]

> Welcome to the community.

Thanks Ryan.

> Being a machine learning expert is certainly
> helpful for a GSoC student but what's sometimes more important is a good
> background in C++ and software development along with a willingness to
> learn.

Yes, I completely agree with you.

> I'm still willing to mentor the CF idea.  If you search the mailing list
> archives, I seem to remember there being a lot of discussion about the
> idea last year, and maybe you can find some insights there.

It's great that CF idea is still open. I will certainly look into the list
archives to
gather some useful information regarding the project. If I'm not wrong this
idea
was not one of the selected project last year, so I think it'd be worth
finding out
what was lacking. May be you want to add some input on that?

>  In the end, anything that helps the CF code get easier to use or more
functional
> so that users can easily build a recommendation system would be a great
project.

Will the focus be on making existing CF code more functional this year as
compared
to last year's focus on implementing alternatives to k-NN based CF?

> I also remember a lot of discussion about the deep learning modules
> project; I'm sure you can find a lot about that one in the archives too.

Yes, I'll look through the list to gain some insights. I also noticed that
there's one open
PR (#831) with major changes for ANN module lined up. Since, it looks like
it will be
merged soon can you comment on this year's focus for the deep learning
modules
idea after this PR is finally merged or will it remain same as last year's
of implementing
RBM, DBN etc.?

Thanks,

Vivek

On Wed, Jan 25, 2017 at 9:52 PM, Ryan Curtin <ryan at ratml.org> wrote:

> On Wed, Jan 25, 2017 at 07:03:39PM +0530, Vivek Pal wrote:
> > I am Vivek Pal, a senior year undergraduate student with major in
> Computer
> > Science at Delhi Technological University in New Delhi, India. I'm
> looking
> > forward to be a part of mlpack in GSoC 2017 and beyond. I'm just getting
> > started afresh with mlpack, although I've used it for some hackish ML
> > experiments in the past.
> >
> > I do have some experience with ML through some academic projects that
> I've
> > done over the past 1-2 years ranging from building a recommender system
> to
> > working on sentiment analysis of tweets etc. and thus, I have developed
> > strong interests in ML. However, I hope being an ML practitioner or
> expert
> > is not a primary requirement for a GSoC student in mlpack. :)
> >
> > Also, last semester I took a course that was entirely based on NNs and it
> > got me really interested into this subset of machine learning. I was able
> > to publish an article based on single layer neural net intended for
> > beginners here: http://www.geeksforgeeks.org/implementing-ann-training-
> > process-in-python/
> >
> > Since this year's project ideas are not out yet, I have looked up
> previous
> > year ideas and find two interesting and feel confident enough to work on
> > (if they're planned to be continued this year):
> >
> > 1. Alternatives to neighborhood-based collaborative filtering
> > 2. Essential Deep Learning Modules
> >
> > I'd appreciate advice based on these project ideas to help me explore
> more
> > about these and be able to finally make sound decision of choosing
> between
> > two.
> >
> > I've already started to familiarise myself with the related codebase and
> > will find some warm up tasks right away from issues list. However, it'd
> be
> > great if I could get some pointers for going ahead that would help me
> > understand codebase and tests better.
> >
> > I should probably also mention that I was a part of GSoC last year. I
> > worked with Xapian which is a probabilistic search engine library written
> > in C++. Broadly, my work was focused on improving the existing weighting
> > schemes in Xapian which basically started with reading a bunch of
> research
> > papers. I was able to successfully complete all the set out goals of the
> > project and the work product was merged in the Xapian codebase.
>
> Hi Vivek,
>
> Welcome to the community.  Being a machine learning expert is certainly
> helpful for a GSoC student but what's sometimes more important is a good
> background in C++ and software development along with a willingness to
> learn.
>
> I'm still willing to mentor the CF idea.  If you search the mailing list
> archives, I seem to remember there being a lot of discussion about the
> idea last year, and maybe you can find some insights there.  In the end,
> anything that helps the CF code get easier to use or more functional so
> that users can easily build a recommendation system would be a great
> project.
>
> I also remember a lot of discussion about the deep learning modules
> project; I'm sure you can find a lot about that one in the archives too.
>
> Thanks,
>
> Ryan
>
> --
> Ryan Curtin    | "Kill them, Machine... kill them all."
> ryan at ratml.org |   - Dino Velvet
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20170125/8fc14b47/attachment.html>