[mlpack] Reinforcement Learning

S.NARAYAN ee15b108 ee15b108 at smail.iitm.ac.in
Sun Mar 5 01:53:34 EST 2017


Thanks a lot Marcus ,

I pulled an all nighter and went through the list of projects again ( lot
of readings ) and i think more than Deep Learning implementations i can
make a good contribution by adding the Cross Validation Modules for
training algorithms as i felt it suits my existing skill set more than
others.I drafted a rough plan of action and also mailed the mentor : Ryan
regarding the same.

So this is what i did as of now ,

1.Built the code and ran Linear and Logistic Regression.
2.Went through the Linear Regression Module and read the design guidelines
page throughly.

As its a new one , no relevant issues exist as of now so I would like to
start by adding a Cross-Validation module to Linear Regression (will start
working on it now) , and once i get accustomed to ML-Packs coding style and
API designs i can add further modules for other training algorithms and
also optimize my approaches (through better pre-computation etc ).

I would love to have your valuable feedback on the plan , would you suggest
i do something else that can result in a more productive outcome?. Guidance
, suggestions are welcome .

Thanking You.
Narayan.
Indian Institute of Technology , Madras.

On Sat, Mar 4, 2017 at 6:13 PM, Marcus Edel <marcus.edel at fu-berlin.de>
wrote:

> Hello Narayan,
>
> I went through the Project Ideas and the following projects intrigued me
> "Essential Deep Learning Modules" and "Reinforcement Learning". I am
> reading up
> on the models in those topics so that i make an informed decision.
>
>
> Great that you liked the ideas, let us know once you decided which project
> you
> like to work on so that we can probably brainstorm some ideas.
>
> Also, The Reinforcement learning and Essential deep learning modules
> project has
> been discussed at on the mailing list before:
>
> http://mlpack.org/pipermail/mlpack/2017-March/003095.html
> http://mlpack.org/pipermail/mlpack/2017-March/003098.html
> http://mlpack.org/pipermail/mlpack/2017-February/003087.html
>
> http://mlpack.org/pipermail/mlpack/2017-March/003107.html
> http://mlpack.org/pipermail/mlpack/2017-February/003092.html
>
> Note that there are many more posts on this in the mailing list archive
> to search for; those are only some places to get started.
>
> Kindly guide me in getting started with understanding the codebase.I have
> it
> cloned it , compiled it from source in my local machine and also
> implemented few
> simple programs from the "getting involved" page.
>
>
> There are some easy issues on GitHub that you might find interesting, we
> will
> see if we can add more in the next days. Besides that, any contributions
> of new
> techniques or efficiency improvements for existing implementations are
> always
> welcome.
>
> I hope this is helpful, let us know if you have any more questions.
>
> Thanks,
> Marcus
>
> On 3 Mar 2017, at 19:34, S.NARAYAN ee15b108 <ee15b108 at smail.iitm.ac.in>
> wrote:
>
> Hello,
>
> I am Narayan , an undergraduate student at IIT-Madras.I am interested in
> participating in GSoC 2017 with mlpack.I am not new to Machine Learning and
> i have worked on a Project in BioInformatics at University of
> Angers,France during my summer.
>
> I am new to ML-Pack and i am really interested in being a long-term
> contributor and working on it during summer with or without GSOC stipend.I
> went through the Project Ideas and the following projects intrigued me *"Essential
> Deep Learning Modules" and "Reinforcement Learning".*
> I am reading up on the models in those topics so that i make an informed
> decision.
>
> Kindly guide me in getting started with understanding the codebase.I have
> it cloned it , compiled it from source in my local machine and also
> implemented few simple programs from the "getting involved" page.
>
> and Congrats to ML-Pack for getting accepted to GSOC again.Hoping to have
> an eventful summer.
>
> Thanking You.
> Narayan.
> _______________________________________________
> mlpack mailing list
> mlpack at lists.mlpack.org
> http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20170305/6df5066e/attachment.html>


More information about the mlpack mailing list