ECE 499/ECE 590
Coure Inforamtion
Instructor | Dr. Weiwen Jiang |
---|---|
wjiang8@gmu.edu | |
Lecture Time | Monday 4:30 pm – 7:10 pm |
Location | Horizon Hall (HORIZON) 2010 |
Office Hour | Monday 14:30 - 15:30 |
Office | Room 3247, Nguyen Engineering Building |
Zoom | http://go.gmu.edu/zoom4weiwen |
TA | Zhepeng Wang |
---|---|
zwang48@gmu.edu | |
Office Hour | Wensday 15:00 - 17:00 (in person) & Friday 15:00 - 17:00 (via Zoom) |
In-person Location | Room 3208, Nguyen Engineering Building |
Online Zoom Link | https://zoom.us/j/9935038408?pwd=QVpuQ3M1QW1LYXhoL3JyMk95RkxHQT09 |
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.
Prerequisites
CS 222 and ECE 231 and ECE 350 with the minimum grade of C
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.
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.
Tools for Lab
- Google Colab
- Xilinx High-Level Synthesis
Schedule and Documents
W | Date | Topic | Documents | Note |
---|---|---|---|---|
1 | Aug 23 | Course Information & Introduction to Machine Learning | [Slides] | Lab1 releases |
2 | Aug 30 | Train Neural Networks | [Slides] [Code@Lec2] | Lab 1 Due: 1 pm, Sep 3 |
3 | Sep 13 | Deep Convolutional Neural Networks (CNN) | [Slides] [Code@Lec3] | Lab2 releases on Sep. 15 |
4 | Sep 20 | Deep Convolutional Neural Networks (CNN) - Part 2 | [Slides] [Code@Lec4] | |
5 | Sep 27 | Natural Langue Processing | [Slides] [Code@Lec5] | Lab 2 Due: 7 pm, Oct 1 |
6 | Oct 04 | Reinforcement Learning | [Slides] [Code@Lec6] | |
7 | Oct 12 | Mid-Term Exam & Finaly Project Discussion | [Slides] | |
8 | Oct 18 | ML Accelerator Design | [Slides] [Code@Lec8] | |
9 | Oct 25 | FPGA Implementation and Optimization Invited Talk (Xinyi Zhang from FB) & Paper Presentation |
[Slides] | [Vote] |
10 | Nov 01 | Model Compression Invited Talk (Xiaolong Ma from NE) & Papre Presentation |
[Slides] | [Vote] |
11 | Nov 08 | DNN Design and Compression Review & Papre Presentation |
[Slides] | [Vote] |
12 | Nov 15 | Neural Architecture Search | [Slides] | |
13 | Nov 22 | Hardware-Aware Neural Architecture Search | [Slides] | |
14 | Nov 29 | HW/SW Co-Design with Neural Architecture Search | [Slides] | |
15 | Dec 13 | Course Project Demonstration |
Readings and Tutorial
| W | Date | Reading (R) & Paper (P) & Tutorial (TT) |
|—————–|————–|————–|——————|————-|
| 1 | Aug 23 | [R1] |
| 2 | Aug 30 | [R2] [TT1] [TT1 Codes] |
| 3 | Sep 13 | [R3, 9.1-9.3] [TT2, Train CIFAR10]|
| 4 | Sep 20 | |
| 5 | Sep 27 | [R5, 10] [R5-2] |
| 6 | Oct 04 | |
| 7 | Oct 12 | |
| 8 | Oct 18 | [P1] |
| 9 | Oct 25 | |
| 10 | Nov 01 | |
| 11 | Nov 08 | |
| 12 | Nov 15 | |
| 13 | Nov 22 | |
| 14 | Nov 29 | [R] [TT3, HLS] |
| 15 | Dec 06 | |