<html><head></head><body dir="auto" style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">Hello Nikhil,<br><br>What I really like about the "Essential Deep Learning Modules" project is that<br>it offers the chance to learn about various fundamental deep learning models<br>from a practical perspective. As the usual suspects are the most commonly used<br>algorithms by the community, it is likely that people and developer will execute<br>your code or use the code that you wrote as basis for their own structures.<br><br>Since you already build mlpack, one place to start is to look at the tutorials<br>and try to compile and run simple mlpack programs.<br><br>http://www.mlpack.org/tutorials.html<br><br>Then, you could look at the list of issues on Github and maybe you can find an<br>easy and interesting bug to solve.<br><br>https://github.com/mlpack/mlpack/issues<br><br>The issues are labeled with difficulty, so you may be able to find some<br>which are suited to your level of experience with mlpack.<br><br>The literature for the Essential Deep Learning Modules project depends on the<br>network models you like to implement over the summer. But here are some<br>hopefully useful links to get information about the basics:<br><br>- "Deep learning reading list" (http://deeplearning.net/reading-list/)<br>- "Neural Networks for Machine Learning" by Geoffrey Hinton (https://www.coursera.org/course/neuralnets)<br>- "Deep learning" by Yoshua Bengio, Ian Goodfellow and Aaron Courville (http://www.deeplearningbook.org/)<br><br>If you have found network models you're interested in, you<br>could start reading about them and we can go from there.<br><br>Since Ryan is the mentor of the "Improvement of tree traversers" and the expert,<br>I go and just make a quote here:<br><br>"A good place to start is by working through the mlpack tutorials and<br>making sure you can get mlpack to compile and understand how to use it.<br>Once you've done that, you should probably read about the ideas behind<br>dual-tree algorithms, since your interest is in the 'improvement of tree<br>traversers' project. You might start here:<br><br>http://machinelearning.wustl.edu/mlpapers/paper_files/icml2013_curtin13.pdf<br><br>There are a lot of references in that document, and you should probably<br>read most of them to get a good idea of what is going on (especially the<br>cover tree paper by Langford)."<br><br>Since you said you are working on a python to c++ translator, you might be also<br>interested in the automatic bindings project. That project would give a way to<br>automatically generate MATLAB, Python, and R bindings, which would be much<br>easier to maintain than having to maintain each binding individually:<br><br>https://github.com/mlpack/mlpack/wiki/SummerOfCodeIdeas#automatic-bindings<br><br>Let me know if you have any more questions that I can answer.<br><br>Thanks!<br>Marcus<br><br><blockquote type="cite">On 16 Feb 2016, at 22:40, Nikhil Yadala <nikhil.yadala@gmail.com> wrote:<br><br>Hi,<br><br> I am nikhil yadala, pursuing 2nd year of my Btech at dept of CSE at Indian Institute of Technology Guwahati( IIT Guwahati). I am very much interested in machine learning particularly in computational biology. Currently i am doing research in Gene profiling using deep learning methods.<br><br> I am interested in two of the projects that are floated as potential ones for the GSOC,2016<br> 1)Improvement of Tree traversers<br> 2)Essential Deep Learning Modules<br> I have enough expertise in C,C++,python,Currently iam developing a PYTHON TO C++ TRNSLATOR In c++.<br>I would be glad if any one over there would guide me as to get enough knowledge to get going with these projects. I have already built mlpack over my ubuntu and started to understand the code.<br><br>Thanks,<br>NIkhil yadala<br><br>_______________________________________________<br>mlpack mailing list<br>mlpack@cc.gatech.edu<br>https://mailman.cc.gatech.edu/mailman/listinfo/mlpack<br></blockquote><br></body></html>