Changes between Version 28 and Version 29 of Other/Summer/2023/Inference
- Timestamp:
- Jul 12, 2023, 2:27:41 PM (16 months ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Other/Summer/2023/Inference
v28 v29 6 6 <p style="font-weight: bold;"><span style="color:#800000;"> Project Advisor and Mentors: </span> Professor Anand Sarwate, Professor Waheed Bajwa, Nitya Sathyavageeswaran, Vishakha Ramani, Yu Wu, Aliasghar Mohammadsalehi, Muhammad Zulqarnain </p> 7 7 <p style="font-weight: bold;" ><span style="color:#800000;">Team:</span> Shreya Venugopaal, Haider Abdelrahman, Tanushree Mehta, Lakshya Gour, Yunhyuk Chang 8 9 **Objective:** The purpose of this project is to use ORBIT in order to design and run 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 models across multiple orbit nodes and networks, as well as early exit. They will then analyze these models for latency and accuracy tradeoff analysis, along with measuring network delays. 10 11 <ul> <h2> Table of Contents / Links to Presentations </h2> 12 <li>Week 1</li> 13 <li>Week 2</li> 14 <li>Week 3</li> 15 <li>Mid-Sem</li> 16 </ul> 17 8 18 }}} 9 19 10 20 11 **Objective:** The purpose of this project is to use ORBIT in order to design and run 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 models across multiple orbit nodes and networks, as well as early exit. They will then analyze these models for latency and accuracy tradeoff analysis, along with measuring network delays.12 21 13 {Table of Contents14 22 15 23