[mlpack] GSOC proposal for Profiling for parallelism.

[Param Mirani]

Hello Marcus/Ryan,

I am Param Mirani and I want to contribute to MLpack by participating in
GSOC 2020 in Profiling for Parallelism project. I have made some pull
requests in trying to improve performance of the algorithms on multi-core
processors using OpenMP. I had an idea and wanted to know your view on the
same.

I wanted to work on following algorithms in the 12 week program based on my
knowledge of machine learning algorithms.

1)KNN

2)Decision Trees

3)Perceptron

4)Back-propagation

I expect these algorithms to have an excellent speed-up when they use
OpenMP.

However I feel we would have a difficulty in deciding which parts of the
algorithm based on various programs I write for benchmarking of these
algorithms. There are some more algorithms which could use OpenMP but
speed-up may not be that significant.

Along with these I would also like to understand 2-3 more algorithms and
work with them in a similar way.

I'd like to know if the timeline I've proposed is realistic, if all
assumptions are correct, and if there are any more algorithms that you
would like me to work on while working on this project.

Thanks,

Param Mirani.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20200315/27b8c196/attachment.htm>