ECE 554
News:
- 08/28/2025 The course websites at instructor’s [Web] and canvas [Home] are active now.
- 08/28/2025 [Lab 1] has been released on canvas.
- 08/28/2025 Please complete [Poll 1] in the class.
Schedule and Documents
W | Date | Topic | Documents | Reading Material |
---|---|---|---|---|
1 | Aug 28 | Course Information & Introduction to ML | [Handson1] | |
2 | Sep 04 | MLP Programming with Pytorch | [Lab1] | [Pytorch],[Tensor],[Model],[Train] |
3 | Sep 11 | Train Neural Networks | ||
4 | Sep 18 | Deep CNN - Part 1 | ||
5 | Sep 25 | Deep CNN - Part 2 | ||
6 | Oct 02 | Transformer | ||
7 | Oct 09 | Model Compression - Part 1 | ||
8 | Oct 16 | Model Compression - Part 2 | ||
9 | Oct 23 | Mid-Term Exam | ||
10 | Oct 30 | ML System Optimization | ||
11 | Nov 06 | Reinforcement Learning | ||
12 | Nov 13 | Neural Architecture Search | ||
13 | Nov 20 | Hardware-Aware NAS | ||
14 | Dec 04 | Co-Design & Final Project |
Coure Inforamtion
Instructor | Dr. Weiwen Jiang |
---|---|
wjiang8@gmu.edu | |
Lecture Time | Thursday 16:30 pm – 19:10 pm |
In-person Session Location | Room 2413, Peterson Hall |
Office Hour | Thursday 14:00 - 15:00 |
Place | Room 3247, Nguyen Engineering Building |
TA | Hanhan Wu |
---|---|
hwu28@gmu.edu |
Course Materials
Course materials will be posted before or after the class. No formal textbook is required. This e-book will be referred to on the course.
Course Description
Machine learning (ML) has gradually become the core component of wide applications in different computing scenarios, ranging from edge computing to cloud computing. This course focuses on resource-constrained edge computing, in particular the embedded systems, and introduces techniques for developing energy/time efficient ML algorithms and models for the embedded systems. Topics that are covered include (i) commonly used ML algorithms, (ii) ML model compression techniques, (iii) hardware-aware machine learning, (iv) hardware and neural architecture co-design. The course also provides a comprehensive team-based research and development experience through projects and presentations. Offered by Electrical & Comp. Engineering. May not be repeated for credit.
Prerequisites
The course topics are self-contained so that a background in machine learning is not required. Students should be familiar with programming and embedded systems to complete the course projects.
Tools for Lab
- Google Colab
- Xilinx High-Level Synthesis