1
课程详述
COURSE SPECIFICATION
以下课程信息可能根据实际授课需要或在课程检讨之后产生变动。如对课程有任何疑问，请联
系授课教师。
The course information as follows may be subject to change, either during the session because of unforeseen
circumstances, or following review of the course at the end of the session. Queries about the course should be
directed to the course instructor.
1.
课程名称 Course Title
集成电路前沿-机器学习芯片设计
Advanced integrated circuit design: machine learning on chip
2.
授课院系
Originating Department
电子与电气工程系
Department of Electrical and Electronic Engineering (EEE)
3.
课程编号
Course Code
EE334
4.
课程学分 Credit Value
3
5.
课程类别
Course Type
专业选修课 Major Elective Courses
6.
授课学期
Semester
秋季 Fall
7.
授课语言
Teaching Language
中英双语 English & Chinese
8.
授课教师、所属学系、联系方
式（如属团队授课，请列明其
他授课教师）
Instructor(s), Affiliation&
Contact
（For team teaching, please list
all instructors）
余浩，副教授，电子与电气工程系
办公室：第一教学楼 104 室
邮箱：yuh3@sustc.edu.cn
电话：0755-8801-8575
YU, Hao, Assoc. Prof., Department of Electrical and Electronic Engineering
Office: Room 104, Teaching Building 1
Email: yuh3@sustc.edu.cn
Telephone: 0755-8801-8575
9.
实验员/助教、所属学系、联系
方式
Tutor/TA(s), Contact
董龙涛/刘斌，硕士生，电子与电气工程系
邮箱：donglt@mail.sustc.edu.cn
电话：15039586999
10.
选课人数限额(可不填)
Maximum Enrolment
（Optional）
2
授课方式
Delivery Method
讲授
Lectures
习题/辅导/讨论
Tutorials
实验/实习
Lab/Practical
其它(请具体注明)
Other（Please specify）
总学时
Total
11.
学时数
Credit Hours
32
4
32
64
12.
先修课程、其它学习要求
Pre-requisites or Other
Academic Requirements
EE202-17 数字电路
EE202-17 Digital circuit
13.
后续课程、其它学习规划
Courses for which this course
is a pre-requisite
本课程为电子与电气工程系微电子专业选修课，主要系统机器学习算法及其硬件实现与应
用。其它专业学生如果想学习相关知识也可选修本课程。
This course is the elected course for undergraduate student in Microelectronics, and it
includes the basic theory, hardware implementation and application of machine learning.
It should however also be suitable for non-specialists, i.e. for all those students who
show interests in lasers to gain a certain amount of relevant knowledge.
14.
其它要求修读本课程的学系
Cross-listing Dept.
无
None
教学大纲及教学日历 SYLLABUS
15.
教学目标 Course Objectives
本课程旨在培养本科生在机器学习算法及其数字电路芯片设计的兴趣与能力。本课程分为三个部分：1. 对机器学习算
法理论的学习；2. 通过软件使用机器学习算法对模型进行训练（例如分类与聚类模型）；3. 对上述机器学习模型进行硬件
实现，包括嵌入式设计以及 FPGA 实现。
After the completion of this course, students should know the following items. (1) Familiar with the basic theory of
machine learning algorithms (2) Utilize software platforms to train and verify the machine learning algorithms and models,
including classification and clustering (3) Implement the machine learning models on hardware with embedded system or
FPGA.
16.
预达学习成果 Learning Outcomes
本课是微电子专业的主干专业课，学生将掌握机器学习与神经网络的基本原理，了解目前机器学习人工智能的研究热
点，通过实验课学会并培养分析解决机器学习问题的能力，最终将算法实现在硬件中学到机器学习在物体检测人脸识别的
重要了研究领域的结果的，为今后从事人工智能与芯片设计科研及开发工作打下良好的专业基础。
This course is the core course for students in Microelectronics. Students will learn the basic principle of machine learning
and neural network, learn and cultivate the ability to analyse and solve the problems in the field of machine learning, and
realize the algorithms on hardware，which provide the hardware implementation in face recognition and classification. It
is essential for students to engage in research and development of artificial intelligence and integrated circuit design in
the future.
3
17.
课程内容及教学日历 （如授课语言以英文为主，则课程内容介绍可以用英文；如团队教学或模块教学，教学日历须注明
主讲人）
Course Contents (in Parts/Chapters/Sections/Weeks. Please notify name of instructor for course section(s), if
this is a team teaching or module course.)
机器学习芯片设计课程安排
第 1 周：课程介绍，及集成电路设计导论
第 2 周：机器学习导论
第 3 周：机器学习基础知识讲解，包含神经网络的拟合本质 、不同的优化方法、以及过拟合欠拟合问题分析
第 4 周：卷积层介绍，结合图像滤波来介绍卷积层的特征提取功能
第 5 周：全连接层介绍，结合全连接层来讲解反向传播算法
第 6 周：使用卷积层和全连接层搭建简单的分类网络
第 7 周：网络近似，讲解网络的量化算法即多种 BNN 网络和 QNN 网络
第 8 周：应用算法：YOLO，SSD,MTCNN,FACENET
第 9 周：期中考试
第 10 周：计算机架构
第 11 周：机器学习加速器
第 12 周：SoC 实现方法
第 13 周：硬件设计语言 I
第 14 周：硬件设计语言 II
第 15 周：论文报告
第 16 周：论文报告
Week 1: Introduction of machine learning
Week 2: Introduction of neural network
Week 3 to 5: Lecture on various machine learning algorithms,include CNN,RNN YOLO
4
Week 6: Lecture on software and hardware platform of machine learning algorithms. Software platforms include Matlab
(matconvnet), python (tensorflow) and Lua (torch). Hardware platforms include the embedded systems and FPGA
Week 7 to 8: Mid-term quiz for students' understanding of the basic algorithms of machine learning. Students will run
some machine learning algorithms towards face detection and recognition, bio-image processing on software platforms
with provided workstations.
Week 9 to 10: Lecture on embedded system designs on the hardware platform with ARM core.
Week 11-12: Lecture on Verilog design on hardware platform
Week 13-16: Experiment of hardware implementation for machine learning algorithms. Students are required to
implement one of the algorithms on a hardware platform (embedded system). Students will do this project in groups of 2-
3. Students need to have a presentation and submit a report for evaluation of this project.
18.
教材及其它参考资料 Textbook and Supplementary Readings
<Machine Learning> by ZHOU Zhihua;
<Digital Fundamentals, Tenth Edition> by Thomas L.Floyd
课程评估 ASSESSMENT
19.
评估形式
Type of
Assessment
评估时间
Time
占考试总成绩百分比
% of final
score
违纪处罚
Penalty
备注
Notes
出勤 Attendance
10
课堂表现
Class
Performance
10
小测验
Quiz
0
课程项目 Projects
0
平时作业
Assignments
30
期中考试
Mid-Term Test
20
期末考试
Final Exam
30
期末报告
Final
Presentation
5
其它（可根据需要
改写以上评估方
式）
Others (The
above may be
modified as
necessary)
20.
记分方式 GRADING SYSTEM
A. 十三级等级制 Letter Grading
B. 二级记分制（通过/不通过） Pass/Fail Grading
课程审批 REVIEW AND APPROVAL
21.
本课程设置已经过以下责任人/委员会审议通过
This Course has been approved by the following person or committee of authority
