课程大纲
COURSE SYLLABUS
1.
课程代码
/
名称
Course Code/Title
统计前沿选讲
I
2.
课程性质
Compulsory/Elective
专业选修课 Major Elective Course
3.
课程学分
/
学时
Course Credit/Hours
3/48
4.
授课语言
Teaching Language
双语
5.
授课教师
Instructor(s)
胡延 HU Yanqing
6.
是否面向本科生开放
Open to undergraduates
or not
Open to undergraduates
7.
先修要求
Pre-requisites
(如面向本科生开放,请注明区分内容 If the course is open to
undergraduates, please indicate the difference.)
1、MA215 概率论 或者 MA212 概率论与数理统计
2、CS102A 计算机程序设计基础 A 或者 CS107 计算机程序设计基础 A(H)
8.
教学目标
Course Objectives
(如面向本科生开放,注明区分内容。 If the course is open to undergraduates, please indicate the
difference.)
本课程主要介绍模型一些基本理论算法及其互联网社交媒体、推荐系统、生物领域一些应用。这是
具有鲜明交叉学科特色课程数学方法涉及到,图论、生成函数、分枝过程、贝叶斯网络、因子图模型空腔
理论、渗流、相变、信息论机器学习大数据
This course introduces some basic theories and algorithms of graphical models and their applications in
the Internet, social media, recommendation systems, biology and other fields. This is a course with
distinctive interdisciplinary characteristics. Mathematical methods will involve graph theory,
generating function, branching process, Bayesian network, factor graph, cavity method, percolation,
phase transition, information theory, machine learning, big-data, etc.
9.
教学方法
Teaching Methods
(如面向本科生开放,请注明区分内容。 If the course is open to undergraduates, please indicate the
difference.)
讲授 Lectures
10.
教学内容
Course Contents
(如面向本科生开放,请注明区分内容。 If the course is open to undergraduates, please indicate the
difference.)
Section 1
简介(2 学时
Introduction
Section 2
图论与概率论一些基础知识点(2 学时
Basic knowledge about graph and probability theory
Section 3
大规模图中的搜索(12 学时Searching in large scale graph
超链接环境中的搜索 Searching in hyperlink environment
面向主题搜索 Subject-oriented searching
链接作弊与斗 Link spam
导航页与权威页 Hubs and authorities
小世界网络六度空间 Small world and 6-degrees of separation
空间图上的分散式搜索 Decentralized searching on spatial graph
二分图上的分散式搜索 Decentralized searching on binary graph
Section 4
大规模图上的传播(12 学时Spreading in large scale graph
母函数与分枝过程 Generating function and branching process
疾病传播 Epidemic contagion
渗流 Percolation
图结构的脆弱性与鲁棒性 Vulnerability and robustness
超临界传播 Supercritical spreading
社交媒上的信息传播 Information spreading on social media
病毒式营销 Viral marketing
3 度影响 3-degrees of influence
高阶传播 High order spreading
Section 5
社团识别(6 学时Community Detection
分析Spectral analysis
贝叶斯推断,Bayesian inferences
编码与社团 Encoding and community
大规模网络上的快速算法 Fast algorithm for large scale graph
Section 6
结构预测(8 学时Graph Structure Prediction
推荐系统 Recommendation system
预测 Link prediction
机图编码 Encoding of random graph
结构预测极限 Structure predictability
点的向量表示 Node to vector
神经网络 Graph neural network
物预测 Drug prediction
Section 7
图上的推断(6 学时Inference in Graphical Models
贝叶斯网络 Bayesian networks
图模型 Pairwise graphical models
子图 Factor Graphs,
传播算法 Belief propagation algorithm
Section 8
Section 9
Section 10
11.
课程考核
Course Assessment
1 考核形 Form of examination
2 .分数构成 grading policy
3 如面向本科生开放,请注明区分内容。
If the course is open to undergraduates, please indicate the difference.)
堂表现 10%+时作 40%+课程项目 50%
12.
教材及其它参考资料
Textbook and Supplementary Readings
References
Shlomo Havlin and Reuven Cohen, Complex Networks, Cambridge University Press 2010
Jure Leskovec,Anand Rajaraman, Jeffrey D. Ullman, Mining of Massive Datasets Cambridge University Press
2010
Marc Mezard, Andrea Montanari, Information, Physics and Computation, OXFORD University Press 2009
Andrea Montanari ,Lecture Notes for Inference in Graphical Models, 2011