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
_______________________________________________ mlpack mailing list [email protected] http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
