ImageNet Replication Project

Title: ImageNet Replication Project

January 2018 - April 2018


We will replicate systems from recent deep learning papers and apply them to the ImageNet image classification dataset. You and your teammates will first pick one paper to replicate, and then try to recreate the results from the paper. After you recreate the original results, you will run at least one new experiment using your replicated system. This new experiment may aim to further analyze the system you've replicated, or it may attempt to improve upon the previous system by changing or adding a new component. The goal of this project is two-fold: (1) to familiarize yourself with current deep learning frameworks and literature, and (2) to practice running focused experiments on large datasets. This is a purely educational project to help you learn new skills.

Because our GPU resources are limited, we will only allow a few teams to work on this project concurrently. Sign up soon!

Deliverables: Code and a blog post, by the end of the semester

Prize: Knowledge (_priceless_)


How to Join: Fill out this google form.

Leader(s): TBD

MDST Participants: TBD

Link to the Code: TBD

Link to the Dataset: