（已有30条评价）基本信息
内容简介
书籍
计算机书籍
本书被全世界89个国家的900多所大学用作教材。.
本书以详尽和丰富的资料，从理性智能体的角度，全面阐述了人工智能领域的核心内容，并深入介绍了各个主要的研究方向。全书分为8大部分：第一部分“人工智能”，第二部分“问题求解”，第三部分“知识与推理”，第四部分“规划”，第五部分“不确定知识与推理”，第六部分“学习”，第七部分“通信、感知与行动”，第八部分“结论”。本书既详细介绍了人工智能的基本概念、思想和算法，还描述了其各个研究方向最前沿的进展，同时收集整理了详实的历史文献与事件。另外，本书的配套网址http://aima.cs.berkeley.edu/为教师和学生提供了大量教学和学习资料。..
本书适合于不同层次和领域的研究人员及学生，是高等院校本科生和研究生人工智能课的首选教材，也是相关领域的科研与工程技术人员的重要参考书。...
计算机书籍
本书被全世界89个国家的900多所大学用作教材。.
本书以详尽和丰富的资料，从理性智能体的角度，全面阐述了人工智能领域的核心内容，并深入介绍了各个主要的研究方向。全书分为8大部分：第一部分“人工智能”，第二部分“问题求解”，第三部分“知识与推理”，第四部分“规划”，第五部分“不确定知识与推理”，第六部分“学习”，第七部分“通信、感知与行动”，第八部分“结论”。本书既详细介绍了人工智能的基本概念、思想和算法，还描述了其各个研究方向最前沿的进展，同时收集整理了详实的历史文献与事件。另外，本书的配套网址http://aima.cs.berkeley.edu/为教师和学生提供了大量教学和学习资料。..
本书适合于不同层次和领域的研究人员及学生，是高等院校本科生和研究生人工智能课的首选教材，也是相关领域的科研与工程技术人员的重要参考书。...
目录
I Artificial Intelligence .
1 Introduction
2 Intelligent Agents
II Problem-solving
3 Solving Problems by Searching
4 Informed Search and Exploration
5 Constraint Satisfaction Problems
6 Adversarial Search
III Knowledge and reasoning
7 Logical Agents
8 First-Order Logic
9 Inference in First-Order Logic
10 Knowledge Representation
IV Planning
11 Planning
12 Planning and Acting in the Real World ..
V Uncertain knowledge and reasoning
13 Uncertainty
14 Probabilistic Reasoning
15 Probabilistic Reasoning over Time
1 Introduction
2 Intelligent Agents
II Problem-solving
3 Solving Problems by Searching
4 Informed Search and Exploration
5 Constraint Satisfaction Problems
6 Adversarial Search
III Knowledge and reasoning
7 Logical Agents
8 First-Order Logic
9 Inference in First-Order Logic
10 Knowledge Representation
IV Planning
11 Planning
12 Planning and Acting in the Real World ..
V Uncertain knowledge and reasoning
13 Uncertainty
14 Probabilistic Reasoning
15 Probabilistic Reasoning over Time
前言
Artificial Intelligence (Al) is a big field, and this is a big book. We have tried to explore the full breadth of the field, which encompasses logic, probability, and continuous mathematics; perception, reasoning, learning, and action; and everything from microelectronic devices to robotic planetary explorers. The book is also big because we go into some depth in presenting results, although we strive to cover only the most central ideas in the main part of each chapter. Pointers are given to further results in the bibliographical notes at the end of each chapter. .
The subtitle of this book is "A Modern Approach." The intended meaning of this rather empty phrase is that we have tried to synthesize what is now known into a common framework, rather than trying to explain each subfield of Al in its own historical context. We apologize to those whose subfields are, as a result, less recognizable than they might otherwise have been.
The main unifying theme is the idea of an intelligent agent. We define Al as the study of agents that receive percepts from the environment and perform actions. Each such agent implements a function that maps percept sequences to actions, and we cover different ways to represent these functions, such as production systems, reactive agents, real-time conditional planners, neural networks, and decision-theoretic systems. We explain the role of learning as extending the reach of the designer into unknown environments, and we show how that role constrains agent design, favoring explicit knowledge representation and reasoning. We treat robotics and vision not as independently defined problems, but as occurring in the service of achieving goals. We stress the importance of the task environment in determining the appropriate agent design.
Our primary aim is to convey the ideas that have emerged over the past fifty years of Al research and the past two millenia of related work. We have tried to avoid excessive formality in the presentation of these ideas while retaining precision. Wherever appropriate, we have included pseudocode
algorithms to make the ideas concrete; our pseudocode is described briefly in Appendix B. Implementations in several programming languages are available on the book's Web site, aima.cs.berkeley, edu. This book is primarily intended for use in an undergraduate course or course sequence. It can also be used in a graduate-level course (perhaps with the addition of some of the primary sources suggested in the bibliographical notes). Because of its comprehensive coverage and large number of detailed algorithms, it is useful as a primary reference volume for Al graduate students and professionals wishing to branch out beyond their own subfield. The only prerequisite is familiarity with basic concepts of computer science (algorithms, data structures, complexity) at a sophomore level. Freshman calculus is useful for understandingneural networks and statistical learning in detail. Some of the required mathematical background is supplied in Appendix A.
Overview of the book
The book is divided into eight parts. Part I, Artificial Intelligence, offers a view of the AI enterprise based around the idea of intelligent agents--systems that can decide what to do and then do it. Part II, Problem Solving, concentrates on methods for deciding what to do when one needs to think ahead several steps--for example in navigating across a country or playing chess. Part III, Knowledge and Reasoning, discusses ways to represent knowledge about the world--how it works, what it is currently like, and what one's actions might do---and how to reason logically with that knowledge. Part IV, Planning, then discusses how to use these reasoning methods to decide what to do, particularly by constructing plans. Part V, Uncertain Knowledge and Reasoning, is analogous to Parts llI and IV,but it concentrates on reasoning and decision making in the presence of uncertaino, about the world,as might be faced, for example, by a system for medical diagnosis and treatment.
Together, Parts II-V describe that part of the intelligent agent responsible for reaching decisions.Part VI, Learning, describes methods for generating the knowledge required by these decision-making
components. Part VII, Communicating, Perceiving, and Acting, describes ways in which an intelligent agent can perceive its environment so as to know what is going on, whether by vision, touch, heating, or understanding language, and ways in which it can turn its plans into real actions, either as robot motion or as natural language utterances. Finally, Part VIII, Conclusions, analyzes the past and future of Al and the philosophical and ethical implications of artificial intelligence.Changes from the first edition
Much has changed in A1 since the publication of the first edition in 1995, and much has changed in this book. Every chapter has been significantly rewritten to reflect the latest work in the field, to reinterpret old work in a way that is more cohesive with new findings, and to improve the pedagogical flow of ideas. Followers of AI should be encouraged that current techniques are much more practical than those of 1995; for example the planning algorithms in the first edition could generate plans of only dozens of steps, while the algorithms in this edition scale up to tens of thousands of steps. Similar orders-of-magnitude improvements are seen in probabilistic inference, language processing, and other subfields. The following are the most notable changes in the book:
● In Part I, we acknowledge the historical contributions of control theory, game theory, economics, and neuroscience. This helps set file tone for a more integrated coverage of these ideas in subsequent chapters.
● In Part II, online search algorithms are covered and a new chapter on constraint satisfaction has been added. The latter provides a natural connection to the material on logic.
● In Part III, propositional logic, which was presented as a stepping-stone to first-order logic in the first edition, is now presented as a useful representation language in its own right, with fast inference algorithms and circuit-based agent designs. The chapters on first-order logic have been reorganized to present the material more clearly and we have added the Internet shopping domain as an example. ..
● In Part IV, we include newer planning methods such as GRAPHPLAN and satisfiability-based planning, and we increase coverage of scheduling, conditional planning, hierarchical planning,and multiagent planning.
● In Part V, we have augmented the material on Bayesian networks with new algorithms, such as variable elimination and Markov Chain Monte Carlo, and we have created a new chapter on uncertain temporal reasoning, covering hidden Markov models, Kalman filters, and dynamic Bayesian networks. The coverage of Markov decision processes is deepened, and we add sections on game theory and mechanism design.
● In Part VI, we fie together work in statistical, symbolic, and neural learning and add sections on boosting algorithms, the EM algorithm, instance-based learning, and kernel methods (support vector machines).
● In Part VII, coverage of language processing adds sections on discourse processing and grammar induction, as well as a chapter on probabilistic language models, with applications to in formation retrieval and machine translation. The coverage of robotics stresses the integration of Uncertain sensor data, and the chapter on vision has updated material on object recognition.
● In Part VIII, we introduce a section on the ethical implications of Al.Using this book
The book has 27 chapters, each requiring about a week's worth of lectures, so working through the whole book requires a two-semester sequence. Alternatively, a course can be tailored to suit the interests of the instructor and student. Through its broad coverage, the book can be used to support such
courses, whether they are short, introductory undergraduate courses or specialized graduate courses on advanced topics. Sample syllabi from the more than 600 universities and colleges that have adopted the first edition are shown on the Web at aima.cs.berkeley, edu, along with suggestions to help you find a sequence appropriate to your needs.
The subtitle of this book is "A Modern Approach." The intended meaning of this rather empty phrase is that we have tried to synthesize what is now known into a common framework, rather than trying to explain each subfield of Al in its own historical context. We apologize to those whose subfields are, as a result, less recognizable than they might otherwise have been.
The main unifying theme is the idea of an intelligent agent. We define Al as the study of agents that receive percepts from the environment and perform actions. Each such agent implements a function that maps percept sequences to actions, and we cover different ways to represent these functions, such as production systems, reactive agents, real-time conditional planners, neural networks, and decision-theoretic systems. We explain the role of learning as extending the reach of the designer into unknown environments, and we show how that role constrains agent design, favoring explicit knowledge representation and reasoning. We treat robotics and vision not as independently defined problems, but as occurring in the service of achieving goals. We stress the importance of the task environment in determining the appropriate agent design.
Our primary aim is to convey the ideas that have emerged over the past fifty years of Al research and the past two millenia of related work. We have tried to avoid excessive formality in the presentation of these ideas while retaining precision. Wherever appropriate, we have included pseudocode
algorithms to make the ideas concrete; our pseudocode is described briefly in Appendix B. Implementations in several programming languages are available on the book's Web site, aima.cs.berkeley, edu. This book is primarily intended for use in an undergraduate course or course sequence. It can also be used in a graduate-level course (perhaps with the addition of some of the primary sources suggested in the bibliographical notes). Because of its comprehensive coverage and large number of detailed algorithms, it is useful as a primary reference volume for Al graduate students and professionals wishing to branch out beyond their own subfield. The only prerequisite is familiarity with basic concepts of computer science (algorithms, data structures, complexity) at a sophomore level. Freshman calculus is useful for understandingneural networks and statistical learning in detail. Some of the required mathematical background is supplied in Appendix A.
Overview of the book
The book is divided into eight parts. Part I, Artificial Intelligence, offers a view of the AI enterprise based around the idea of intelligent agents--systems that can decide what to do and then do it. Part II, Problem Solving, concentrates on methods for deciding what to do when one needs to think ahead several steps--for example in navigating across a country or playing chess. Part III, Knowledge and Reasoning, discusses ways to represent knowledge about the world--how it works, what it is currently like, and what one's actions might do---and how to reason logically with that knowledge. Part IV, Planning, then discusses how to use these reasoning methods to decide what to do, particularly by constructing plans. Part V, Uncertain Knowledge and Reasoning, is analogous to Parts llI and IV,but it concentrates on reasoning and decision making in the presence of uncertaino, about the world,as might be faced, for example, by a system for medical diagnosis and treatment.
Together, Parts II-V describe that part of the intelligent agent responsible for reaching decisions.Part VI, Learning, describes methods for generating the knowledge required by these decision-making
components. Part VII, Communicating, Perceiving, and Acting, describes ways in which an intelligent agent can perceive its environment so as to know what is going on, whether by vision, touch, heating, or understanding language, and ways in which it can turn its plans into real actions, either as robot motion or as natural language utterances. Finally, Part VIII, Conclusions, analyzes the past and future of Al and the philosophical and ethical implications of artificial intelligence.Changes from the first edition
Much has changed in A1 since the publication of the first edition in 1995, and much has changed in this book. Every chapter has been significantly rewritten to reflect the latest work in the field, to reinterpret old work in a way that is more cohesive with new findings, and to improve the pedagogical flow of ideas. Followers of AI should be encouraged that current techniques are much more practical than those of 1995; for example the planning algorithms in the first edition could generate plans of only dozens of steps, while the algorithms in this edition scale up to tens of thousands of steps. Similar orders-of-magnitude improvements are seen in probabilistic inference, language processing, and other subfields. The following are the most notable changes in the book:
● In Part I, we acknowledge the historical contributions of control theory, game theory, economics, and neuroscience. This helps set file tone for a more integrated coverage of these ideas in subsequent chapters.
● In Part II, online search algorithms are covered and a new chapter on constraint satisfaction has been added. The latter provides a natural connection to the material on logic.
● In Part III, propositional logic, which was presented as a stepping-stone to first-order logic in the first edition, is now presented as a useful representation language in its own right, with fast inference algorithms and circuit-based agent designs. The chapters on first-order logic have been reorganized to present the material more clearly and we have added the Internet shopping domain as an example. ..
● In Part IV, we include newer planning methods such as GRAPHPLAN and satisfiability-based planning, and we increase coverage of scheduling, conditional planning, hierarchical planning,and multiagent planning.
● In Part V, we have augmented the material on Bayesian networks with new algorithms, such as variable elimination and Markov Chain Monte Carlo, and we have created a new chapter on uncertain temporal reasoning, covering hidden Markov models, Kalman filters, and dynamic Bayesian networks. The coverage of Markov decision processes is deepened, and we add sections on game theory and mechanism design.
● In Part VI, we fie together work in statistical, symbolic, and neural learning and add sections on boosting algorithms, the EM algorithm, instance-based learning, and kernel methods (support vector machines).
● In Part VII, coverage of language processing adds sections on discourse processing and grammar induction, as well as a chapter on probabilistic language models, with applications to in formation retrieval and machine translation. The coverage of robotics stresses the integration of Uncertain sensor data, and the chapter on vision has updated material on object recognition.
● In Part VIII, we introduce a section on the ethical implications of Al.Using this book
The book has 27 chapters, each requiring about a week's worth of lectures, so working through the whole book requires a two-semester sequence. Alternatively, a course can be tailored to suit the interests of the instructor and student. Through its broad coverage, the book can be used to support such
courses, whether they are short, introductory undergraduate courses or specialized graduate courses on advanced topics. Sample syllabi from the more than 600 universities and colleges that have adopted the first edition are shown on the Web at aima.cs.berkeley, edu, along with suggestions to help you find a sequence appropriate to your needs.
序言
《人工智能：一种现代方法》（英文，第1版）是一部人工智能（AI）的优秀教材，1995年问世后在世界各地出版、发行，很快成为一部畅销书。在我国，英文影印本于2002年出版，也很受大众的欢迎。.
事隔8年(2003年)，该书的第2版（作者Stuart Russell, Peter Norvig， Pearson Education出版集团出版）又出现在我们面前。作者是这样解释出版新书的原因，他说，自1995年该书第1版发行以来，AI有了很大的变化，它的技术更趋实用，因此新书的每一章都经过重写以反映该领域的最新成就，同时重新解释了原有的结果，使之更加符合新的发现。这充分反映了作者对新书的负责精神与严肃态度。
这部书的主要特点如下。
（1）在智能Agent（自主体，代理，行为者）的概念下，将AI中相互分离的领域统一起来，克服了以往AI教材中难以避免的内容零散且互不相关的现象，从而使AI变得更加理论化、系统化。
（2）理论与实际并重。作者在论述各个领域的原理与方法时，尽量运用数学（形式化）的语言，力图让它们建立在严格的理论基础之上。同时又介绍最新的实用算法，特别是能够解决现实世界问题的方法，尽量使AI从“玩具世界”中走向实用。..
本书所具有的以上特点正好反映了AI当前发展的大趋势。大家知道，人工智能从上个世纪中叶诞生以来，一直未能形成系统的理论体系。因此，有的人把AI看成是一门“工程”，有的则认为是一门“技术”，也有的甚至认为只是一门“艺术”。大家也许记得，上个世纪80年代，以斯坦福大学的N. J. Nilsson为代表与以耶鲁大学 R. C. Schank为代表，曾经展开过一场关于AI究竟是一门“工程技术”，还是一门“艺术”的争论。当时存在这种争论是很自然的。在AI发展的初期，大多数研究者采取的研究方法是，首先凭借直觉或者启发式建立起AI的相关假设，然后在“玩具世界”中论证假设的合理性，由此建立起一套AI的理论与方法。为了克服数学方法的“局限性”，他们总是避免使用数学工具，尽量与传统的严格科学保持距离。但是，随着AI走向成熟，AI的“传统”发生了变化，它们逐步向科学靠拢，向实用靠近。一方面，尽量使用现代科学工具，使AI逐步变成一门科学。一方面，尽量面向现实世界，提出可行的算法，使AI走向实际应用。该书作者将这两大趋势及时地反映在教材中，从而形成自己的特色。
作者在前言中特别说明了本书与第1版的区别。我认为，第2版加强并进一步突出了以上两个特点。作者在重写过程中，对于理论部分尽量采用已有的、成熟的科学方法，如数学、心理学、计算机工程、神经科学等。在第2版中，还进一步强调了经济学中决策理论、运筹学，以及控制理论、控制论等与AI的关系，将AI与其它科学领域联系起来。在各个章节中都补充了新的内容，将这期间所取得的研究成果尽量纳入到新书中。
尽管本书已由清华大学计算机系姜哲等老师译为中文，并于2004年出版，为了使读者能够读到英文原书，我以为出版第2版的影印本还是有必要的。...
中国科学院院士 清华大学教授
事隔8年(2003年)，该书的第2版（作者Stuart Russell, Peter Norvig， Pearson Education出版集团出版）又出现在我们面前。作者是这样解释出版新书的原因，他说，自1995年该书第1版发行以来，AI有了很大的变化，它的技术更趋实用，因此新书的每一章都经过重写以反映该领域的最新成就，同时重新解释了原有的结果，使之更加符合新的发现。这充分反映了作者对新书的负责精神与严肃态度。
这部书的主要特点如下。
（1）在智能Agent（自主体，代理，行为者）的概念下，将AI中相互分离的领域统一起来，克服了以往AI教材中难以避免的内容零散且互不相关的现象，从而使AI变得更加理论化、系统化。
（2）理论与实际并重。作者在论述各个领域的原理与方法时，尽量运用数学（形式化）的语言，力图让它们建立在严格的理论基础之上。同时又介绍最新的实用算法，特别是能够解决现实世界问题的方法，尽量使AI从“玩具世界”中走向实用。..
本书所具有的以上特点正好反映了AI当前发展的大趋势。大家知道，人工智能从上个世纪中叶诞生以来，一直未能形成系统的理论体系。因此，有的人把AI看成是一门“工程”，有的则认为是一门“技术”，也有的甚至认为只是一门“艺术”。大家也许记得，上个世纪80年代，以斯坦福大学的N. J. Nilsson为代表与以耶鲁大学 R. C. Schank为代表，曾经展开过一场关于AI究竟是一门“工程技术”，还是一门“艺术”的争论。当时存在这种争论是很自然的。在AI发展的初期，大多数研究者采取的研究方法是，首先凭借直觉或者启发式建立起AI的相关假设，然后在“玩具世界”中论证假设的合理性，由此建立起一套AI的理论与方法。为了克服数学方法的“局限性”，他们总是避免使用数学工具，尽量与传统的严格科学保持距离。但是，随着AI走向成熟，AI的“传统”发生了变化，它们逐步向科学靠拢，向实用靠近。一方面，尽量使用现代科学工具，使AI逐步变成一门科学。一方面，尽量面向现实世界，提出可行的算法，使AI走向实际应用。该书作者将这两大趋势及时地反映在教材中，从而形成自己的特色。
作者在前言中特别说明了本书与第1版的区别。我认为，第2版加强并进一步突出了以上两个特点。作者在重写过程中，对于理论部分尽量采用已有的、成熟的科学方法，如数学、心理学、计算机工程、神经科学等。在第2版中，还进一步强调了经济学中决策理论、运筹学，以及控制理论、控制论等与AI的关系，将AI与其它科学领域联系起来。在各个章节中都补充了新的内容，将这期间所取得的研究成果尽量纳入到新书中。
尽管本书已由清华大学计算机系姜哲等老师译为中文，并于2004年出版，为了使读者能够读到英文原书，我以为出版第2版的影印本还是有必要的。...
中国科学院院士 清华大学教授
