Project Overview
Above is the poster we made to explain our research and what my team and I worked on throughout the Winlab Summer Internship. Here is a link to our final presentation at the end of the internship.
The purpose of this project was to use ORBIT in order to design experiments which will analyze the training and prediction of various ML models across multiple edge devices. Additionally, students will develop a latency profiling framework for MEC-assisted machine learning using cutting edge techniques such as splitting model computing and early exit. They will then analyze these models for latency and accuracy tradeoff analysis, along with measuring network delays.
We were able to accomplish this task across the 10 week internship. For an in-depth overview of all the technologies and methods we used to accomplish this task please refer to the website I made for our team.