教学目标：
The objective of this course is to teach students modern Artificial Intelligence (AI). Students will learn basic AI techniques and methods. We also expect to excite students about many fields of AI.

课程内容：
Chapter 1. Artificial Intelligence and Intelligent Agents
1.1. Introduction to AI
1.2. Agents and Environments
1.3. The Structure of Agents
Chapter 2. Solving Problems by Search
2.1.Problem-solving Agents
2.2. Problem Types
2.3. Problem Formulation
2.4. Basic Search Algorithms
2.5 Informed (Heuristic) Search Strategies
Chapter 3. Local Search
3.1.Hill-Climbing Search
3.2. Simulated Annealing Search
3.3. Tabu Search
3.4. Local Beam Search
3.5.Genetic Algorithms
Chapter 4. Constraint Satisfaction Problems
4.1.Constraint Satisfaction Problems (CSPs) Definition
4.2. Backtracking Search for CSPs
4.3. Local Search for CSPs
Chapter 5. Propositional Logic
5.1.Basic Definitions in Logical Agents
5.2. Syntactic Transformations
5.3. Semantic Transformations
5.4. Application of Inference Rules
Chapter 6. Probability and Uncertainty
6.1.Acting under Uncertainty
6.2. Basic Probability Notation
6.3. Inference Using Full Joint Distributions
6.4. Bayes’ Rule and Its Use
Chapter 7. Probabilistic Reasoning
7.1.Representing Knowledge in an Uncertain Domain
7.2. The Semantics of Bayesian Networks
7.3. Exact Inference in Bayesian Networks
7.4. Approximate Inference in Bayesian Networks
7.5. Other Approaches to Uncertain Reasoning
Chapter 8. Making Simple Decision
8.1.Combining Beliefs and Desires under Uncertainty
8.2. The Basis of Utility Theory
8.3. Utility Functions
8.4. The Value of Information
Chapter 9. Introduction to Machine Learning
9.1.The Importance of AGood Representation
9.2. Different Types of Learning Problems
9.3. Different Types of Learning Algorithms
9.4. Supervised Learning
9.5. Unsupervised Learning

适用学生：
全日制硕士    非全日制硕士    留学硕士    进修硕士    硕博连读    本科直博    全日制博士    留学博士    进修博士    在职专硕    其他    

预修课程：
Preparatory Courses（预修课程）：
Discrete mathematics, Probability theory, Linear algebra, Algorithm design and analysis

参考书目：
Referencing Textbooks and Required References for Students (参考书及学生必读参考资料)：
[1] Russell and Norvig. Artificial Intelligence:A Modern Approach. Prentice Hall. This book is a comprehensive reference for all the AI topics that will be covered in this course.
[2] Koller and Friedman.Probabilistic Graphical Models: Principles and Techniques. The MIT Press.This book covers factor graphs and Bayesian networks.
[3] Sutton and Barto. Reinforcement Learning: An Introduction.The MIT Press. Covers Markov decision processes and reinforcement learning.
[4] Hastie, Tibshirani, and Friedman. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer. This book covers machine learning.
[5] Tsang. Foundations of Constraint Satisfaction. Springer. This book covers constraint satisfaction problems.

备注：