DB004112-统计学习理论（全英文）

研究生课程开设申请表

开课院（系、所）：    金沙js800000   

课程申请开设类型： 新开√     重开□     更名□（请在□内打勾，下同）

一、课程介绍（含教学目标、教学要求等）（300字以内）

本课程涵盖机器学习领域的基础理论方面，包含监督学习的PAC模型，PAC可学性，过拟合，统一收敛性，奥卡姆剃刀，VC维数，Rademacher复杂度，性能增强，统计询问方法和二进制傅立叶方法，隐私保护或通信约束下的学习算法复杂度等。希望通过本课程，同学可以对于机器学习算法的可学性和复杂度理论得到初步的认识，对于后续机器学习方面的科研起到帮助的作用。

二、教学大纲（含章节目录）：（可附页）

1. PAC模型和PAC 可学性

2. 过拟合问题和奥卡姆剃刀

3. 统一收敛性

4. VC理论和无限维问题的可学性

5. Radamacher 复杂度

6. 性能增强

7. 统计询问和傅立叶方法

8. 隐私保护或通信约束下的学习算法

三、教学周历

注：1.以上一、二、三项内容将作为中文教学大纲，在研究生院中文网页上公布，四、五内容将保存在研究生院。2.开课学期为：春季、秋季或春秋季。3.授课语言为：汉语、英语或双语教学。4.适用学科范围为：公共，一级，二级，三级。5.实践环节为：实验、调研、研究报告等。6.教学方式为：讲课、讨论、实验等。7.学位课程考试必须是笔试。8.课件地址指在网络上已经有的课程课件地址。9.主讲教师简介主要为基本信息（出生年月、性别、学历学位、专业职称等）、研究方向、教学与科研成果，以100至500字为宜。

四、主讲教师简介：

康维，1979年8月生，男，博士学历，金沙js800000，信息与信号处理系教授。研究方向为信息论及其应用，信息安全和隐私保护，和统计学习理论。教学工作目前承担本科生课程《数据安全与隐私保护》，博士生课程《网络信息论》。科研方面多年来连续主持国家自然科学基金项目，发表高等级论文多篇。

五、任课教师信息（包括主讲教师）：

六、课程开设审批意见

说明：1．研究生课程重开、更名申请也采用此表。表格下载：http:/seugs.seu.edu.cn/down/1.asp

2．此表一式三份，交研究生院、院（系）和自留各一份，同时提交电子文档交研究生院。

Application Form For Opening Graduate Courses

School (Department/Institute)：School of Information Science and Engineering

Course Type: New Open √   Reopen □   Rename □（Please tick in □, the same below）

1. Course Introduction (including teaching goals and requirements) within 300 words:

We cover the basic theories of the area of machine learning, including PAC model for supervised learning, PAC learnability, overfitting, uniform convergence, Ocam’s razor, VC dimension, Rademacher complexity, boosting, statistical querya and binary fourier methods, learning complexity under privacy or communication constraints. Through this course, the students hopefully can obtain the basic understanding of the theories of the learnability and the complexity of machine learning and prepare for the future researches in the area of machine learning.

2. Teaching Syllabus (including the content of chapters and sections. A sheet can be attached):

1. PAC model and PAC learnability

2. Overfitting and Occam’s razor

3. Uniform convergence

4. VC theory and learnabitliy of infinite hypothesis space

5. Radamacher complexity

6. Boosting

7. Statistical query and fourier methods

8. Learning under privacy or communication constraints.

3. Teaching Schedule:

Note: 1.Above one, two, and three items are used as teaching Syllabus in Chinese and announced on the Chinese website of Graduate School. The four and five items are preserved in Graduate School.

 2. Course terms: Spring, Autumn , and Spring-Autumn term.   

 3. The teaching languages for courses: Chinese, English or Chinese-English.  

 4. Applicable range of discipline: public, first-class discipline, second-class discipline, and third-class discipline.  

 5. Practice includes: experiment, investigation, research report, etc.  

 6. Teaching methods: lecture, seminar, practice, etc.  

 7. Examination for degree courses must be in paper.  

 8. Teaching material websites are those which have already been announced.  

 9. Brief introduction of chief lecturer should include: personal information (date of birth, gender, degree achieved, professional title), research direction, teaching and research achievements. (within 100-500 words)  

4. Brief Introduction of Chief lecturer:

 Wei Kang, born in Aug. 1979, male,  PhD., Professor in Department of information and signal processing, School of information science and Engineering. Research areas include information theory and its applications, information security and privacy protection, and statistical learning theory. Current teaching includes undergraduate course <Data security and privacy protection> and Phd course <Network information theory>. Prof. Kang is the PI for multiple projects for Natural science foundation of China and has published multiple high-level journal papers.  

5. Lecturer Information (include chief lecturer)