[mlpack] How to get started on CF idea of GSoC 2018

[Wenhao Huang]

Thanks a lot Ryan! I am going through the code in the cf module. And do you
know any current relevant issues that I can have a look or even start
working on, to better my understanding of the the implementation of cf
algorithm in mlpack?

Best,
Wenhao


On Tue, Feb 6, 2018 at 4:23 AM Ryan Curtin <ryan at ratml.org> wrote:

> On Mon, Feb 05, 2018 at 11:58:31AM +0000, Wenhao Huang wrote:
> > Hi,
> >
> > My name is Wenhao and I am a senior computer science student at Peking
> > University (Beijing, China). I plan to apply for GSoC and contribute to
> > mlpack library so I guess it's better to start early.
> >
> > I took several courses on Machine Learning and I have research experience
> > concerning application of machine learning on knowledge base. And I
> > interned at an AI startup focused on CV for 4 months. C/C++ and python
> are
> > the languages I use most.
> >
> > Recently I am interested in recommender systems and I took a course on
> > collaborative filtering. Thus I want to work on the CF project for GSoC
> > 2018. So far I have installed mlpack and successfully run a few programs.
> > Can someone give me some pointers on what to do next to get started on
> the
> > CF idea? Thanks!
>
> Hi Wenhao,
>
> I think the best thing to do would be to familiarize yourself with the
> mlpack code.  I might suggest building a CF model in C++ that uses
> different factorizers, or, perhaps, tuning the parameters of a CF<>
> model you have built to give maximum RMSE on something like the
> GroupLens dataset.
>
> Once you are familiar with the code, you might look at discussions from
> years past on this project.  Here's an example search that returns some
> results:
>
>
> https://www.google.com/search?ei=8rx4WqrsI6SpjwSMp56IAg&q=site%3Aknife.lugatgt.org+collaborative+filtering&oq=site%3Aknife.lugatgt.org+collaborative+filtering&gs_l=psy-ab.3...3125.4482.0.4529.17.14.0.0.0.0.128.1043.9j4.13.0....0...1c.1.64.psy-ab..11.0.0....0.csynPi-oRIc
>
> (and many of those results will themselves be linked to other posts)
>
> You can also browse the archives manually:
>
> http://knife.lugatgt.org/pipermail/mlpack/
>
> I hope this is helpful!
>
> Thanks,
>
> Ryan
>
> --
> Ryan Curtin    | "Avoid the planet Earth at all costs."
> ryan at ratml.org |   - The President
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20180206/a0fbcfd6/attachment.html>