北京大学

图片
课程概述

        人工智能是国内外著名大学计算机专业设置的骨干课之一,也是国内外著名高校和研究机构的主要研究方向之一。人工智能研究如何用计算机软件和硬件去实现Agent的感知、决策与智能行为,其理论基础表现为搜索、推理、规划和学习,应用领域包括计算机视觉、图像分析、模式识别、专家系统、自动规划、智能搜索、计算机博弈、智能控制、机器人学、自然语言处理、社交网络、数据挖掘、虚拟现实等。

       本课程在系统回顾人工智能发展历程的基础上,重点介绍人工智能的核心思想基本理论基本方法部分应用。 课程以该英文原版教材为主,并根据人工智能、特别是机器学习领域的发展和变化,编撰和充实了大量的内容。本课程共有12讲,采用双语教学,即中英文PPT和中英文作业等、中文讲授和交流。

证书要求

课程采用百分制,达到60分算“合格”,达到85分以上算“优秀”。由任课教师签发课程证书,其中成绩“优秀”者将颁发优秀证书


其中:

    单元测试30% 【12个单元测试,共100道题目,占总成绩30分】

    单元作业30% 【两次作业,每个作业占总成绩的15分,共计30分】
    考试40%【最后一周进行,共计40分】

预备知识

学习者最好具备一定的数据结构、算法等计算机知识,概率论、线性代数等数学知识,以及机器学习的基础知识。

授课大纲

Week 1: Part I. Basics: Chapter 1. Introduction

1周:第一部分 基础:第1 导论

In which we try to explain why we consider artificial intelligence to be a subject most worthy of study, and to decide what exactly it is.

 

Week 2: Part I. Basics: Chapter 2. Intelligent Agents

2周:第一部分 基础:第2 智能体

In which we discuss the nature of agents, the diversity of environments, and the resulting menagerie of agent types.

 

Week 3: Part II. Searching: Chapter 3. Solving Problems by Search

3周:第部分 搜索:第3 通过搜索求解问题

In which we see how an agent can find a sequence of actions that achieves its goals.

 

Week 4: Part II. Searching: Chapter 4. Local Search and Swarm Intelligence

第4周:部分 搜索:第4章 局部搜索与群体智能

In which we relax the simplifying assumptions of the previous chapter, thereby getting closer to the real world.

 

Week 5: Part II. Searching: Chapter 5. Adversarial Search

第5周:部分 搜索:第5章 对抗性搜索

In which we examine the problems that arise when we try to plan ahead in a world where other agents are planning against us.

 

Week 6: Part II. Searching: Chapter 6. Constraint Satisfaction Problem

第6周:部分 搜索:第6章 约束满足问题

In which we see how treating states as more than just little black boxes so that it leads to the invention of a range of powerful new search methods and a deeper understanding of problem structure and complexity.

 

Week 7: Part III. Reasoning: Chapter 7. Reasoning by Knowledge

7周:第部分 推理:第7 知识推理

In which we design agents that can form representations of a complex world, use a process of inference to derive new representations about the world.

 

Week 8: Part IV. Planning: Chapter 8. Classic and Real-world Planning

第8周:部分 规划:第8章 经典与现实世界规划

In which we introduce a representation for classical planning problems, then for planning and acting in the real world.

 

Week 9: Part V. Learning: Chapter 9. Perspectives about Machine Leaning

第9周:部分 学习:第9章 研读机器学习的视角

In which we describe agents that can improve their behavior through learning of their own experiences, and discuss the perspectives on so many learning algorithms we have been faced with.

 

Week 10: Part V. Learning: Chapter 10. Tasks in Machine Learning

第10周:部分 学习:第10章 机器学习的任务

In which we discuss in detail about the tasks that can be solved with machine learning.

 

Week 11: Part V. Learning: Chapter 11. Paradigms in Machine Learning

第11周:部分 学习:第11章 机器学习的范式

In which we discuss in detail about the paradigms that have been proposed in machine learning.

 

Week 12: Part V. Learning: Chapter 12. Models in Machine Learning

第12周:第部分 学习:第12章 机器学习的模型

In which we discuss in detail about the models that have been used in machine learning.

参考资料

[1] Stuart Russell, Peter Norvig. "Artificial Intelligence: A Modern Approach (3rd Edition)". Prentice Hall, Dec. 11, 2009.

注:这本书被认为是最经典的人工智能教材,已被全球100多个国家的1200多所著名大学选用。

[2] Stuart Russell等著,殷建平等译:《人工智能:一种现代的方法 (第3版)》,清华大学出版社,2013年11月1日。

注:这本书是上述英文教材的中译本,我国已将其作为“世界著名计算机教材精选”之一。

[3] Artificial Intelligence: A Modern Approach, http://aima.cs.berkeley.edu/

注:这是上述英文教材的网站,有许多相关的资源。

[4] Mehryar Mohri, Afshin Rostamizadeh and Ameet Talwalkar. "Foundations of Machine Learning". The MITPress, Aug. 17, 2012.

授课老师
王文敏

王文敏

教授

分享