This post is all about the contributions I have made to the Julia organization and will briefly summarize my project titled “Sparsifying Neural Networks using Sensitivity driven Regularization”. Although, the project is not fully completed it will serve as a good starting point for someone who wants to delve deeper into the topic or making advancement to the codebase.
My project comprised the implementation of the following models:
Contributions to The Julia Language
I have been contributing to JuliaLang repository prior to the start of GSoC. My pull requests were majorly focused on resolving minor issues (good first issues) and later shifted to issues related to sparse arrays and more. Lately, I started working on Reinforcement Learning examples implementation in Julia like Pendulum problem, CartPole problem & Acrobot problem. Here are the three linked PRs for your reference: https://github.com/FluxML/model-zoo/pull/93 , https://github.com/FluxML/model-zoo/pull/84, https://github.com/FluxML/model-zoo/pull/105 …
This is the first post of my GSoC series, in fact, my first blog on medium.
TL;DR: This post is based on my experience with the Julia Language Community and contains tips about the application process and getting selected.
Firstly a little background about myself, I am a final year undergrad student majoring in Electronics and Telecommunication Engineering. Regardless of this, I love working on ML problems and have a knack for programming. Having said that, I learned about the GSoC from my two batchmates who were already selected for GSoC’18 and hence it was an easy path for me as they guided me throughout the process. …