[mlpack] [GSOC 2016] Contribute for MLPack

[Ryan Curtin]

On Mon, Mar 07, 2016 at 01:41:03PM +0530, Parijat Dewangan wrote:
> Hello Marcus and Ryan,
> 
> I am working on the first idea  - Implement tree types. I went through the
> archive mails, followed the instructions provided there.
> 
> Following are the things I worked on till now -
> 1. Building of MLPack.
> 2. Going through the library of MLPack and using the already implemented
> algorithms through command line.
> 3. Having a sound knowledge of the paper "Tree-Independent Dual-Tree
> Algorithms". Since I have a good command over data structures and
> algorithms, I understood the concept of space trees and the way it is used
> in implementing algorithms like k-nearest neighbors, range search etc as
> explained in the paper. I have qualified for various algorithmic
> competitions so understanding various trees and its implementation won't be
> a problem as I have used many trees algorithms before.
> 
> Currently, I am going through the codes of the already implemented tree
> types in src/mlpack/core/tree/ as the new algorithms would be based on the
> same template and style. Could you specify any tree type I should start
> reading about?

Hi Parijat,

There are lots of possible tree types you could implement.  Vantage
point trees (also known as metric trees) might be a good place to start,
but it's certainly not the only possibility.  I don't have a particular
preference as to the type of tree that you pick (as long as it's not
already implemented), so feel free to do your own literature search and
find the tree you are most interested in.

> While I am very interested in the previously mentioned project, I am also
> eager to work on Decision trees' and 'Fast k-centers algorithms and its
> implementation'.

Here are some mailing list links (in case you haven't already seen
them), but be aware that each of these projects have significant amounts
of background material to comprehend and it may therefore be useful to
focus on only one project.

https://mailman.cc.gatech.edu/pipermail/mlpack/2016-March/000751.html
https://mailman.cc.gatech.edu/pipermail/mlpack/2016-March/000796.html

> Is there any work/reading that you think I should do in order to be better
> prepared to write a good proposal for GSOC 2016.

There's the application guide, and you can also read a useful student
manual too:

https://github.com/mlpack/mlpack/wiki/Google-Summer-of-Code-Application-Guide
http://write.flossmanuals.net/gsocstudentguide/what-is-google-summer-of-code/

> I appreciate the documentation of MLPack. It is well written and
> systematic. :)

Thanks!  I am glad you found the documentation useful.

Ryan

-- 
Ryan Curtin    | "You got to stick with your principles."
ryan at ratml.org |   - Harry Waters