[mlpack] GSoC MLPack - Inquiry

[Marcus Edel]

Hello Ahmed,

thanks for getting in touch and welcome!

Andrew Ng's Coursera course is a really good start. As long as you are willing
to learn the necessary knowledge I don't see any reason against an application.
Anyway here are some papers that you could read. A good theoretical
understanding of what these models do and why they work is a necessity to be
able to implement these well.

Restricted Boltzmann Machines (RBM)
- https://www.cs.toronto.edu/~hinton/absps/guideTR.pdf
- http://deeplearning.net/tutorial/rbm.html

Deep Belief Networks (DBN)
- http://www.cs.toronto.edu/~rsalakhu/papers/science.pdf
- http://deeplearning.net/tutorial/DBN.html

Radial Basis Function Networks (RBFN)
- http://www.cc.gatech.edu/~isbell/tutorials/rbf-intro.pdf

Bidrectional Recurrent networks (BRN)
Note: mlpack provides already an implementation for recurrent network
- http://www.di.ufpe.br/~fnj/RNA/bibliografia/BRNN.pdf

Convolutional Auto-Encoders (CAE)
- http://people.idsia.ch/~masci/papers/2011_icann.pdf

Hopfield neural networks (HNN)
- http://page.mi.fu-berlin.de/rojas/neural/chapter/K13.pdf

Keep in mind that you don't have to implement all models; A good project
will select a handful of architectures and implement them with tests and
documentation. Writing good tests is often the hardest part, so keep that in
mind when you create your project timeline.

Let me know if you have any more questions I can answer.

Thanks,
Marcus


> On 08 Mar 2016, at 23:52, Ahmed El-Hinidy <ahmed.el-hinidy.2014 at ieee.org> wrote:
> 
> Dear Sir,
> 
> I am Ahmed El-Hinidy, a Computer Engineering student at Cairo University.
> 
> I am very interested in GSoC, and of working on MLPack and being part of its community.
> 
> I am interested in working in the following project:
> "Essential Deep Learning Modules"
> 
> I want to inquire about something if I may:
> 
> 1- Required technical knowledge:
> I have experience with c++ due to studying it both at university and alone and using it in several projects during university.
> I am also self-studying machine learning and data science through 2 tracks right now:
> I. Stanford's Machine Learning course on Coursera (self paced):
> https://www.coursera.org/learn/machine-learning <https://www.coursera.org/learn/machine-learning>
> Which covers many topics including Neural Networks And I will finish it soon
> II. Johns Hopkins University's Data Science Specialization on Coursera (Self Paced):
> https://www.coursera.org/specializations/jhu-data-science <https://www.coursera.org/specializations/jhu-data-science>
> I also have knowledge of Software Engineering (currently enrolled in a SW course at my university)
> 
> So is this knowledge enough and suitable that I can begin to work on the project and proceed on learning while working? And if not, could you please suggest any sources or topics that I can study to better prepare myself.
> 
> Sorry for the long message, and thanks for your precious time.
> 
> Sincerely,
> Ahmed Hamada El-Hinidy
> **********************************************************
> Student - Cairo University - Faculty of Engineering
> Computer and Communications Engineering
> Ahmed.El-Hinidy.2014 at ieee.org <mailto:Ahmed.El-Hinidy.2014 at ieee.org>
> +201227417171
> _______________________________________________
> mlpack mailing list
> mlpack at cc.gatech.edu
> https://mailman.cc.gatech.edu/mailman/listinfo/mlpack

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cc.gatech.edu/pipermail/mlpack/attachments/20160309/758f6566/attachment-0002.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 5233 bytes
Desc: not available
URL: <http://mailman.cc.gatech.edu/pipermail/mlpack/attachments/20160309/758f6566/attachment-0002.bin>