Image for post
Image for post

Hi Everyone!

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:

  1. VGG16/19 Network (https://github.com/raghav9-97/model-zoo/blob/sparse/sparsification/vgg16_19.jl)
  2. MobileNet Network (https://github.com/raghav9-97/model-zoo/blob/sparse/sparsification/mobilenet.jl)
  3. Sparsification Logic (https://github.com/raghav9-97/model-zoo/blob/sparse/sparsification/mobilenet.jl)
  4. ResNet Network (*yet to be implemented)

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

Raghvendra Gupta

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store