[mlpack] GSoC2017

[Marcus Edel]

Hello Aman,

thanks for your interest, you are welcome to get involved.

> It would be great if you can explain more about ideas and the expected work to
> be done as part of GSoC 2017. I am really looking forward to contribute to this
> project as part of GSoC.

What I really like about the "Essential Deep Learning Modules" project is you
can dive into some really interesting ideas and you have the chance to learn
about some fundamental deep learning models from a practical perspective. Also,
it is likely that people and developer will use your code or use the code that
you wrote as the basis for their own models.

Anyway, as stated in the project description, the focus of the project is to
improve the traditional models based on recent ideas. I've linked some recent
papers on the ideas pages, that revisit some of the traditional models like
"Spike and slab restricted boltzmann machine" by Courville et al. or "Back to
the Future: Radial Basis Function Networks Revisited" by Que and Belkin. There
are a couple more references for the mentioned models, especially for GAN there
are a bunch of really interesting papers that are definitely worth a look.
However, the literature highly depends on the network models you like to
implement over the summer.

Also, to be successful at this project, you should have a good knowledge of deep
learning; i.e., you should be familiar with the way deep neural networks are
typically built and trained, and certainly you should be familiar with the
individual components that you plan to implement.

> My area of interest lies in Unsupervised learning, specifically Deep auto-
> encoders as i am currently involved in the same during my master thesis work.

I'd be interested to hear more about what you are doing in your thesis if you'd
like to elaborate. Perhaps, implementing Deep Autoencoders is something you like
to work on over the summer?

In case you haven't already seen it; these pages are also helpful:

http://www.mlpack.org/involved.html
http://www.mlpack.org/gsoc.html

I hope this is helpful; let me know if I can clarify anything.

Thanks,
Marcus


> On 23 Feb 2017, at 19:16, Aman Gautam <a_gautam14 at informatik.uni-kl.de> wrote:
> 
> Hi Marcus,
> 
> I am a Master's student in computer science and my area of specialization lies in Intelligent systems at TU Kaiserslautern, Germany. I am interested in doing Essential Deep Learning Modules project as mentioned on this page: https://github.com/mlpack/mlpack/wiki/SummerOfCodeIdeas
> 
> My area of interest lies in Unsupervised learning, specifically Deep auto-encoders as i am currently involved in the same during my master thesis work. As part of GSoC2017 I am interseted in working with Restricted Boltzmann Machines (RBM) and also Generative Adversarial Networks (GAN) if time allows.
> 
> It would be great if you can explain more about ideas and the expected work to be done as part of GSoC 2017. I am really looking forward to contribute to this project as part of GSoC.
> 
> Thanks & Regards,
> Aman Gautam