1
课程大纲
COURSE SYLLABUS
1.
课程名称(中英文)
Course Title(Chinese
and English)
机器学习和人工智能 Machine Learning & Artificial Intelligence
2.
课程类别 Course Type
选修
3.
授课院系
Originating Department
电子与电气工程系
4.
课程学时 Credit Hours
48
5.
课程学分 Credit Value
3
6.
授课语言
Teaching Language
英语为主,辅以中文解释
English with Detailed Explanations in Chinese
7.
授课教师 Instructor(s)
王琦,郝祁
8.
先修课程、其它学习要求
Pre-requisites or Other
Academic Requirements
随机信号处 Stochastic Signal Processing
优化方法 Optimization Methods
9.
10.
教学方法及授课创新 Teaching Methods and Innovations
1. to obtain fundamental knowledge and concepts about machine learning and artificial intelligence in
terms of statistics and algebra through lectures and assignments
2. to grasp skills of machine learning and complex computing problem solving with MATLAB languages
and related libraries through labs and projects
3. to obtain insights for intelligent system design with pattern recognition, data modeling, and
knowledge formulation through the final project, literature surveys and reports
11.
教学内容及学时分配 Course Contents and Course Schedule
2
week 01-01 CH01-CH01 (HW0 Lab0) Course Introduction and Preliminaries
week 02-02 CH02-CH02 (HW1 Lab1) Probability Distribution
week 03-03 CH03-CH03 (HW2 Lab2) Linear Models for Regression
week 04-04 CH04-CH04 (HW2 Lab2) Linear Models for Classification
week 05-05 CH05-CH05 (HW3 Lab3) Neural Networks I
week 06-06 CH05-CH05 (HW3 Lab3) Neural Networks II
week 07-07 CH06-CH06 (HW4 Lab4) Kernel Methods
week 08-08 CH07-CH07 (HW4 Lab4) Sparse Kernel Machines
week 09-09 CH01-CH04 (HW5 Lab5) Review
week 10-10 CH01-CH04 (HW5 Lab5) Midterm-exam
week 11-11 CH01-CH04 (HW6 Lab6) Exam Revisit and Review
week 12-12 CH08-CH08 (HW6 Lab6) Graphical Models
week 13-13 CH09-CH09 (HW7 Lab7) Mixture Models and EM
week 14-14 CH10-CH10 (HW7 Lab7) Approximate Inference
week 15-15 CH11-CH11 (HW8 Lab8) Sampling Methods
week 16-16 CH12-CH12 (HW8 Lab8) Continuous Latent Variables
week 17-17 CH13-CH13 (HW9 Lab9) Sequential Data
week 18-18 CH01-CH11 (HW9 Lab9) Final Project Presentation
12.
课程考核 Course Assessment
评估形式 占考试总成绩百分比 % 违纪处罚 备注 Notes
出勤 Attendance
课堂表现 Class Performance
小测验 Quiz 3
课程项目 Projects 20
平时作业 Assignments 7
期中考试 Mid-Term Test 20
期末考试 Final Exam 40
期末报告 Final Presentation 10
其它(可根据需要改写以上评估方式)Others (The above may be modified as necessary)
13.
教材及其它参考资料 Textbook and Supplementary Readings
1. Pattern Recognition and Machine Learning, by C. Bishop, Springer (required)
2. Artificial Intelligence:Structures And Strategies For Complex Problem Solving, 6th Ed.,
by G. F. Luger, 机械工业出版社