[mlpack] GSoC - 2017

[Prasanna Patil]

Hi Marcus,

I was thinking of introducing couple of new module in mlpack myself. I have
PReLU <https://arxiv.org/pdf/1502.01852.pdf> activation function and maxout
<https://arxiv.org/pdf/1302.4389.pdf> layer in my mind. So should I proceed
with this?

This is to get batter idea of ann module of mlpack.

Thanks,
Prasanna

On Sat, Feb 11, 2017 at 5:32 PM, Prasanna Patil <prasannapatil08 at gmail.com>
wrote:

> Hi Marcus,
>
> Thanks for your response.
>
> 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 paper. There are a couple more references
>> for the
>> mentioned models, especially for GAN there are some really interesting
>> papers
>> that are definitely worth a look.
>>
>
>
> Yup I checked them out. Currently I am reading the "Back to the Future:
> Radial Basis Function Networks Revisited" paper. I am planning to go
> through all of them in coming month. Also one of the papers in RBF sections
> is paid so just wanted to check if you have some other source for learning
> methods of RBF networks.
>
>
> As stated in the project description, all models mentioned are just
>> examples
>> that could be implemented, we don't expect you to implement all models or
>> any of
>> the models. Meaning if you like to implement another network model that
>> mlpack
>> currently doesn't have, we are open to discuss the ideas with you.
>>
>
>
> So basically it is up to participant to decide which model he will be
> implementing during project? If that's the case then how much models you
> guys are expecting to be implemented during 3 months of project
> (implementing models + documenting them)? I don't have first hand
> experience with implementing models in actual open source library so I
> can't estimate days needed to implement a well tested model.
>
> Also is reading research papers part of the project or something to be
> done before project period starts? This will help me to get my expected
> timeline.
>
>
> If you like to implement machine learning algorithms that mlpack currently
>> doesn't have, contributions like that are more than welcome. If you can
>> provide
>> a fast, well-tested implementation it would be great to include it in
>> mlpack.
>> Also, we are open for own project ideas, however, we have to make sure
>> it's
>> enough work and someone is able to mentor the project. The GRU layer and
>> batch
>> norm is definitely an interesting idea that when extended by some other
>> methods
>> could build up an interesting GSoC project.
>>
>
>
> That's great. Let me research about other methods I can implement
> alongside GRU and batch norm so that it can turn into proper GSoC project.
> If I can get enough work to do with this proposal I will go with my own
> project otherwise I will apply for Essential Deep Learning Modules.
>
>
> I'll see if I can open some ann related issues, that could be a great
>> start to
>> dive into the codebase.
>>
>
>
> That's great. Familiarising myself with mlpack codebase is certainly hard
> without working with it and getting hand dirty. I am looking forward to
> issues related with ann. Until then I will try to understand mlpack coding
> style and read research papers referenced on project ideas page. I
> apologise if any of the questions I asked above are inappropriate.
>
> Thanks,
> Prasanna
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20170214/19e79a89/attachment.html>