My project proposal for Google Summer of Code 2016 has been accepted at CERN. It’s always been my passion to work in the field of Machine Learning and I am very grateful to CERN community for providing me this bright opportunity. I’ll be working on Toolkit for Multivariate Data Analysis (TMVA), a ROOT-integrated Machine Learning environment for the processing and parallel evaluation of sophisticated multivariate classification techniques. My project primarily focuses on Deep Learning which involves implementing an unsupervised feature extraction method with Autoencoders in TMVA toolkit. I’ll be also implementing dimensionality reduction techniques like Local Linear Embedding, Feature Agglomeration etc. which are useful for data analysis in high-energy physics. You can have a look at my project page here. Don’t forget to bookmark this page if you are following my project closely. I intend to use this blog to track and document progress of my project.
I’ll be mentored by Sergei Glyezer, Lorenzo Moneta and Omar Zapata. Sergei Gleyzer is programme administrator and his area of expertise is Machine Learning. He works at CERN and is one of the key researchers at University of Florida. Lorenzo Moneto is also programme administrator and vital part of ROOT project at CERN. Omar Zapata has been GSoC student at CERN for three years and also part of CERN Summer Student Programme this summer. He will be providing technical assistance and support.
Community bonding period is going on and I had my first Skype meet with Sergei and Lorenzo on May 13, 2016. It was an introductory meet and went pretty well. We planned to have weekly Skype meet on Fridays. I have started reading source codes of
TMVA::VariableTransformBase class to implement a basic feature extraction method: Variance Threshold. I’ll soon post update about it. Official coding period starts on May 23, 2016.