Changes between Version 85 and Version 86 of Other/Summer/2023/Inference


Ignore:
Timestamp:
Jul 20, 2023, 3:19:03 PM (16 months ago)
Author:
tm897
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • Other/Summer/2023/Inference

    v85 v86  
    66<p><span style="color:#800000; font-weight: bold;">Team:</span> Shreya Venugopaal, Haider Abdelrahman, Tanushree Mehta, Lakshya Gour, Yunhyuk Chang</p>
    77
    8 <p><span style="color:#800000; font-weight: bold;">Objective:</span> 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.</p>
     8<p><span style="color:#800000; font-weight: bold;">Overview:</span> As machine learning models become increasingly advanced and complex, running these models on less powerful devices is becoming increasingly difficult, especially when accounting for latency. However, it is also not efficient to run everything using only the cloud as it creates too much traffic. A viable solution to this problem is edge computing, where we use the edge (the networks in between user devices and the cloud) for computation.
    99
    10 <p><span style="color:#800000; font-weight: bold;">Description:</span>
     10
     11<p><span style="color:#800000; font-weight: bold;">Objective:</span> The purpose of this project is 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.</p>
     12
    1113
    1214}}}
     
    9395<a href="https://docs.google.com/presentation/d/13Lkpe6GTxxFsbYqxPZ0sVprFMsdpvdkVQ7GSKM9dSU4/edit?usp=sharing">Week 5 - Cumulative</a> &nbsp
    9496<a href="https://docs.google.com/presentation/d/1_M2XA6lpAAv6jwCO1kn8ropHb14uPuDAMzLT5sg5IvM/edit?usp=sharing">Week 6</a> &nbsp
     97
     98<a href="https://docs.google.com/presentation/d/1_iHN8IiqXU5rljfGRi2lQuaFMVv3BE5edFPcXJi2Q/edit?usp=sharing">Week 7</a> &nbsp
     99
    95100</p>
    96101}}}