| Version 2 (modified by , 3 years ago) ( diff ) |
|---|
High Speed Training Using Binary Neural Networks
Group Members
- Daniel Chen
- Thomas Forzani
- Daniel Maevsky
- Sachin Mathew
- Serena Zhang
Project Objective
Training machine learning systems is currently very slow. Recent work has shown promise by using simpler representations of numbers than the commonly used floating point ones. In this project, you will create and measure neural networks which use only binary or integer numbers for both training and inference.
Development Tools Tutorials
Week 1 Activities
Week 2 Activities
Week 3 Activities
Week 4 Activities
Week 5 Activities
Week 6 Activities
Week 7 Activities
Week 8 Activities
Final Presentation
[ Final Presentation]
Research Poster
[ Research Poster]
Attachments (5)
- danm.jpg (1.4 MB ) - added by 3 years ago.
- danc.jpg (184.2 KB ) - added by 3 years ago.
- sachin.jpg (292.1 KB ) - added by 3 years ago.
- serena.jpg (201.7 KB ) - added by 3 years ago.
- thomas.jpg (173.0 KB ) - added by 3 years ago.
Note:
See TracWiki
for help on using the wiki.
