[mlpack] Regarding Participation in GSoC'19

[Subham Barnwal]

Hi,

I  am an third year (Junior) undergraduate student at the Indian Institute
of Technology, Kanpur at the Department of Computer Science and
Engineering.I have worked at Microsoft Research,India and my team was
awarded to be winner for the project there.I am highly interested in
participating in GSoC, and am deeply interested in (and have worked in) AI
research from both bayesian and non-bayesian point of view.

My work has been focused on Deep Learning for Computer Vision and Natural
Language Processing as well as Bayesian Machine Learning.I have worked in
Computer Vision and has submitted a paper at IROS-2019.I am also interested
in optimization of latent variables where models lack local conjugacy.I
also have past internship experience with a Solar industry where i worked
for solar energy optimization by classifying the roof-tops(code
proprietary).I have worked/working on several other projects during this
semester(like Bayesian Recsys involving causal inference and cold start
problem).


I have done and currently doing several courseworks in Machine Learning and
have also read a number of research papers pertaining to fields like
Gaussian Processes, Latent Variable Models(LVMs) and Inference in LVMs for
locally conjugate models,VI for non-conjugate models,Stochastic and Online
VI for scalability, MCMC etc.I am also well versed with most of the state
of the art models for Image Classification, Object detection, and Image
Segmentation as well as have been able to implement Expectation
Maximization(both batch and online) from scratch.Please look at my github
account <https://github.com/subham913?tab=repositories> for some of my
approaches to state-of-art bayesian as well as Deep Learning based ML
algorithms(Some repositories are private as they are part of my ongoing
coursework).

I would love to build some "Bayesian Methods Based Libraries" which i guess
except TensorFlow probability people don't have too much options.Some of
the things I am planning is to implement BlackBox VI,GP with
scalability,EM(I see GMM is already there but may be I can try coding a
more general purpose EM) etc.I am open to any other suggestions (Both
bayesian and non-bayesian).I would appreciate your guidance on the
same.Please help me over the same.

Thanks and regards,

Subham Kumar

Undergraduate Student

Computer Science and Engineering

Indian Institute of Technology, Kanpur
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20190314/d7bbb61c/attachment.html>