这是一本经典的人工智能教材，已被宾夕法尼亚州立大学、南加州大学、马里兰大学、杜克大学、布朗大学、乔治梅森大学等多所著名大学采用为人工智能课程的指定教材。
　　书中从人工智能(AI)的历史及其应用开始介绍，涵盖了AI问题求解的研究工具、AI和知识密集型问题求解的表示法、机器学习、重要的AI应用领域、AI编程语盲LISP和PROLOG等方面的内容，最后提到了智能系统科学的可能性问题，考虑了当前AI面临的挑战，讨论了目前AI的局限，并设计了AI的未来。
　　本书中的算法用类Pascal的伪代码描述，清晰易读。
　　阅读本书要求学生已经学过离散数学课程，包括谓词演算和图论概论，并且学过数据结构课程，包括树、图、递归搜索，会使用堆栈、队列和优先队列。

George F．Luger于1973年在宾夕法尼亚大学获得博士学位，并在之后的5年间在爱丁堡大学人工智能系进行博士后研究。现在他是新墨西哥大学计算机科学研究、语言学及心理学教授。

What we have to learn to do we learn by doing
　　　　　　　　　　　　　 ----ARISTOTLE, Ethics
　　Welcome to the Fourth Edition!
　　I was very pleased to be asked to produce a fourth edition of our artificial intelligence book. It is a compliment to the earlier editions, started more than a decade ago, that our approach to Al has been widely accepted. It is also exciting that, as new developments in the field emerge, we are able to present much of it in each new edition. We thank our readers, colleagues, and students for keeping our topics relevant and presentation up to date.
　　Many sections of the earlier editions have endured remarkably well, including the presentation of logic, search algorithms, knowledge representation, production systems,machine learning, and the programming techniques developed in LISP and PROLOG.These remain central to the practice of artificial intelligence, and required a relatively small effort to bring them up to date. However, several sections, including those on natural language understanding, reinforcement learning, and reasoning under uncertainty,required, and received, extensive reworking. Other topics, such as emergent computation,case-based reasoning, and model-based problem solving, that were treated cursorily in the first editions, have grown sufficiently in importance to merit a more complete discussion.These changes are evidence of the continued vitality of the field of artificial intelligence.
　　As the scope of the project grew, we were sustained by the support of our publisher,editors, friends, colleagues, and, most of all, by our readers, who have given our work such a long and productive life. We were also sustained by our own excitement at the opportunity afforded: Scientists are rarely encouraged to look up from their own, narrow research interests and chart the larger trajectories of their chosen field. Our publisher and readers have asked us to do just that. We are grateful to them for this opportunity.
　　Although artificial intelligence, like most engineering disciplines, must justify itself to the world of commerce by providing solutions to practical problems, we entered the field of AI for the same reasons as many of our colleagues and students: we want to understand and explore the mechanisms of mind that enable intelligent thought and action. We reject the rather provincial notion that intelligence is an exclusive ability of humans, and believe that we can effectively investigate the space of possible intelligences by designing and evaluating intelligent artifacts. Although the course of our careers has given us no cause to change these commitments, we have arrived at a greater appreciation for the scope, complexity, and audacity of this undertaking. In the preface to our earlier editions,we outlined three assertions that we believed distinguished our approach to teaching artificial intelligence. It is reasonable, in writing a preface to this fourth edition, to return to these themes and see how they have endured as our field has grown.
　　The first of these goals was to "unify the diverse branches of Al through a detailed discussion of its theoretical foundations." At the time we adopted that goal, it seemed that the main problem was reconciling researchers who emphasized the careful statement and analysis of formal theories of intelligence (the neats) with those who believed that intelligence itself was some sort of grand hack that could be best approached in an applicationdriven, ad hoc manner (the scruffies). That simple dichotomy has proven far too simple. In contemporary Al, debates between neats and scruffies have given way to dozens of other debates between proponents of physical symbol systems and students of neural networks,between logicians and designers of artificial life forms that evolve in a most illogical manner, between architects of expert systems and case-based reasoners, and finally, between those who believe artificial intelligence has already been achieved and those who believe it will never happen. Our original image of AI as frontier science where outlaws, prospectors, wild-eyed prairie prophets and other dreamers were being slowly tamed by the disciplines of formalism and empiricism has given way to a different metaphor: that of a large,chaotic but mostly peaceful city, where orderly bourgeois neighborhoods draw their vitality from diverse, chaotic, bohemian districts. Over the years we have devoted to the different editions of this book, a compelling picture of the architecture of intelligence has started to emerge from this city's structure, art, and industry.
　　Intelligence is too complex to be described by any single theory; instead, researchers are constructing a hierarchy of theories that characterize it at multiple levels of abstraction. At the lowest levels of this hierarchy, neural networks, genetic algorithms and other forms of emergent computation have enabled us to understand the processes of adaptation,perception, embodiment, and interaction with the physical world that must underlie any form of intelligent activity. Through some still partially understood resolution, this chaotic population of blind and primitive actors gives rise to the cooler patterns of logical inference. Working at this higher level, logicians have built on Aristotle's glib, tracing the outlines of deduction, abduction, induction, truth-maintenance, and countless other modes and manners of reason. Even higher levels of abstraction, designers of expert systems,intelligent agents, and natural language understanding programs have come to recognize the role of social processes in creating, transmitting, and sustaining knowledge. In this fourth edition, we have touched on all levels of this developing hierarchy.
　　The second commitment we made in the earlier editions was to the central position of"advanced representational formalisms and search techniques" in Al methodology. This is, perhaps, the most controversial aspect of our previous editions and of much early work in Al, with many researchers in emergent computation questioning whether symbolic reasoning and referential semantics have any role at all in thought. Although the idea of representation as giving names to things has been challenged by the implicit representation provided by the emerging patterns of a neural network or an artificial life, we believe that an understanding of representation and search remains essential to any serious practitioner of artificial intelligence. More importantly, we feel that the skills acquired through the study of representation and search are invaluable tools for analyzing such aspects of non-symbolic Al as the expressive power of a neural network or the progression of candi-date problem solutions through the fitness landscape of a genetic algorithm. Comparisons,contrasts, and a critique of the various approaches of modern Al are offered in Chapter 16.
　　The third commitment we made at the beginning of this book's life cycle, to "place artificial intelligence within the context of empirical science," has remained unchanged.To quote from the preface to the third edition, we continue to believe that AI is not some strange aberration from the scientific tradition, but.., part of a general quest for knowledge about, and the understanding of intelligence-itself. Furthermore, our Al programming tools, along with the exploratory programming methodology.., are ideal for exploring an environment. Our tools give us a medium for both understanding and questions. We come to appreciate and know phenomena constructively, that is, by progressive approximation.
　　Thus we see each design and program as an experiment with nature: we propose a representation, we generate a search algorithm, and then we question the adequacy of our characterization to account for part of the phenomenon of intelligence. And the natural world gives a response to our query. Our experiment can be reconstructed, revised,extended, and run again. Our model can be refined, our understanding extended.
　　
New with This Edition
　　I, George Luger, am the sole author of the fourth edition. Although Bill Stubblefield has moved on to new areas and challenges in computing, his mark will remain on the present and any further editions of this book. In fact this book has always been the product of my efforts as Professor of Computer Science at the University of New Mexico together with those of my professional colleagues, graduate students, and friends: the members of the UNM artificial intelligence community, as well as of the many readers that have e-mailed me comments, corrections, and suggestions. The book will continue this way, and to reflect this community effort, I will continue using the prepositions we and us when presenting material. Individual debts in the preparation for this fourth edition are listed in the acknowledgement section of this preface.
　　We revised many sections of this book to recognize the growing importance of agent- based problem solving as an approach to Al technology. In discussions of the foundations of AI we recognize intelligence as physically embodied and situated in a natural and social world context. Apropros of this, we present in Chapter 6 the evolution of Al representational schemes from associative and early logic-based, through weak and strong method approaches, including connectionist and evolutionary/emergent models, to situated and social approaches to Al. Chapter 16 contains a critique of each of these paradigms.
　　In creating this fourth edition, we considered all topics presented earlier and brought them into a modern perspective. In particular, we added a reinforcement learning section to Chapter 9. Algorithms for reinforcement learning, taking cues from an environment to establish a policy for state change, including temporal difference and Q-learning, are presented.
　　Besides our previous analysis of data-driven and goal-driven rule-based systems,Chapter 7 now contains case-based and model-based reasoning, including examples from the NASA space program. The chapter includes a section on the strengths and weaknesses of each of these approaches to knowledge-intensive problem solving.
　　Chapter 8 describes reasoning with uncertain or incomplete information. A number of important approaches to this problem are presented, including Bayesian reasoning, belief networks, the Dempster-Shafer model, and the Stanford certainty factor algebra. Techniques for truth maintenance in nonmonotonic situations are also presented, as well as reasoning with minimal models and logic-based abduction. We conclude the chapter with an in-depth presentation of Bayesian Belief Networks and the clique-tree algorithm for propagating confidences through a belief network in the context of new evidence.
　　Chapter 13 presents issues in natural language understanding, including a section on stochastic models for language comprehension. The presentation includes Markov models, CART trees, mutual information clustering, and statistic-based parsing. The chapter closes with several examples, including the applications of text mining and text summarization techniques to the WWW.
　　Finally, in a revised Chapter 16, we return to the deeper questions of the nature of intelligence and the possibility of intelligent machines. We comment on the A1 endeavour from the perspectives of philosophy, psychology, and neuro-physiology.
　　
The Contents
　　Chapter I introduces artificial intelligence, beginning with a brief history of attempts to understand mind and intelligence in philosophy, psychology, and other areas of research. In an important sense, Al is an old science, tracing its roots back at least to Aristotle. An appreciation of this background is essential for an understanding of the issues addressed in modern research. We also present an overview of some of the important application areas in Al. Our goal in Chapter I is to provide both background and a motivation for the theory and applications that follow.
　　Chapters 2, 3, 4, and 5 (Part II) introduce the research tools for AI problem solving.These include the predicate calculus language to describe the essential features of a problem domain (Chapter 2), search to reason about these descriptions (Chapter 3) and the algorithms and data structures used to implement search. In Chapters 4 and 5, we discuss the essential role of heuristics in focusing and constraining search-based problem solving.We also present a number of architectures, including the blackboard and production system, for building these search algorithms.
　　Chapters 6, 7, and 8 make up Part III of the book: representations for Al and knowl-edge-intensive problem solving. In Chapter 6 we present the evolving story of AI representational schemes. We begin with a discussion of semantic networks and extend this model to include conceptual dependency theory, frames, and scripts. We then present an in-depth examination of a particular formalism, conceptual graphs, emphasizing the epistemological issues involved in representing knowledge and showing how these issues are addressed in a modern representation language. In Chapter 13, we show how conceptual graphs can be used to implement a natural language database front end. We conclude Chapter 6 with more modern approaches to representation, including Copycat and agentoriented architectures.
　　Chapter 7 presents the rule-based expert system along with case-based and modelbased reasoning systems, including examples from the NASA space program. These approaches to problem solving are presented as a natural evolution of the material in the first five chapters: using a production system of predicate calculus expressions to orchestrate a graph search. We end with an analysis of the strengths and weaknesses of each of these approaches to knowledge-intensive problem solving.
　　Chapter 8 presents models for reasoning with uncertainty as well as the use of unreliable information. We discuss Bayesian models, belief networks, Dempster-Shafer, causal models, and the Stanford certainty algebra for reasoning in uncertain situations. Chapter 8 also contains algorithms for truth maintenance, reasoning with minimum models, logicbased abduction, and the clique-tree algorithm for Bayesian belief networks.
　　Part IV, Chapters 9 through 11, offers an extensive presentation of issues in machine learning. In Chapter 9 we offer a detailed look at algorithms for symbol-based learning, a fruitful area of research spawning a number of different problems and solution approaches. These learning algorithms vary in their goals, the training data considered, their learning strategies, and the knowledge representations they employ. Symbol-based learning includes induction, concept learning, version-space search, and ID3. The role of inductive bias is considered, generalizations from patterns of data, as well as the effective use of knowledge to learn from a single example in explanation-based learning. Category learning, or conceptual clustering, is presented with unsupervised learning. Reinforcement learning, or the ability to integrate feedback from the environment into a policy for making new decisions concludes the chapter.
　　In Chapter 10 we present neural networks, often referred to as sub-symbolic or connectionist models of learning. In a neural net, information is implicit in the organization and weights on a set of connected processors, and learning involves a re-arrangement and modification of the overall weighting of nodes and structure of the system. We present a number of connectionist architectures, including perceptron learning, backpropagation,and counterpropagation. We demonstrate Kohonen, Grossberg, and Hebbian network models. We present associative learning and attractor models, including Hopfield networks.
　　Genetic algorithms and evolutionary approaches to learning are introduced in Chapter 11. On this viewpoint, learning is cast as an emerging and adaptive process. After several examples of problem solutions based on genetic algorithms, we introduce the application of genetic techniques to more general problem solvers. These include classifier systems and genetic programming. We then describe society-based learning with examples from artificial life, called a-life, research. We conclude the chapter with an example of emergent computation from research at the Santa Fe Institute. We compare and contrast the three approaches we present to machine learning (symbol-based, connectionist, social and emergent) in Chapter 16.Part V, Chapters 12 and 13, continues our presentation of important Al application areas. Theorem proving, often referred to as automated reasoning, is one of the oldest areas of AI research. In Chapter 12, we discuss the first programs in this area, including the Logic Theorist and the General Problem Solver. The primary focus of the chapter is binary resolution proof procedures, especially resolution refutations. More advanced inferencing with hyper-resolution and paramodulation is also presented. Finally, we describe the PROLOG interpreter as a Horn clause and resolution-based inferencing system, and see PROLOG computing to as an instance of the logic programming paradigm.
　　Chapter 13 presents natural language understanding. Our traditional approach to language understanding, exemplified by many of the semantic structures presented in Chapter 6, is complemented with the stochastic approach. These include Markov models,CART trees, mutual information clustering, and statistics-based parsing. The chapter coneludes with examples applying these natural language techniques to database query systems and also to a text summarization system for use on the WWW.
　　Part VI presents LISP and PROLOG. Chapter 14 covers PROLOG, and Chapter 15, LISR We demonstrate these languages as tools for AI problem solving by building the search and representation techniques of the earlier chapters, including breadth-, depth-,and best-first search algorithms. We implement these search techniques in a problem-inde-pendent fashion so that they may be extended to create shells for search in rule-based expert systems, to build semantic networks, natural language understanding systems, and learning applications.
　　Finally, Chapter 16 serves as an epilogue for the book. It addresses the issue of the possibility of a science of intelligent systems, and considers contemporary challenges to AI; it discusses AI's current limitations, and projects its exciting future.Using This Book Artificial intelligence is a big field, and consequently, this is a big book. Although it would require more than a single semester to cover all of the material in the text, we have designed it so that a number of paths may be taken through the material. By selecting subsets of the material, we have used this text for single semester and full year (two semester) courses.
　　We assume that most students will have had introductory courses in discrete mathematics, including predicate calculus and introductory graph theory. If this is not true, the instructor should spend more time on these concepts in the sections at the beginning of the text (2.1, 3.1). We also assume that students have had courses in data structures including trees, graphs, and recursion-based search, using stacks, queues, and priority queues. If they have not, then spend more time on the beginning sections of Chapters 3, 4, and 5.
　　In a one semester course, we go quickly through the first two parts of the book. With this preparation, students are able to appreciate the material in Part III. We then consider the PROLOG and LISP in Part VI and require students to build many of the representation and search techniques of the first sections. Alternatively, one of the languages, PROLOG,for example, can be introduced early in the course and be used to test out the data structures and search techniques as they are encountered. We feel the recta-interpreters presented in the language chapters are very helpful for building rule-based and other knowledge-intensive problem solvers. PROLOG is an excellent tool for building natural language understanding systems.
　　In a two-semester course, we are able to cover the application areas of Parts IV and V, especially the machine learning chapters, in appropriate detail. We also expect a much more detailed programming project from students. We think that it is very important in the second semester for students to revisit many of the primary sources in the AI literature. It is crucial for students to see both where we are, as well as how we got here, and to have an appreciation of the future promises of artificial intelligence. We use a collected set of readings for this purpose, Computation and Intelligence (Luger 1995).
　　The algorithms of our book are described using a Pascal-like pseudo-code. This notation uses the control structures of Pascal along with English descriptions of the tests and operations. We have added two useful constructs to the Pascal control structures. The first is a modified case statement that, rather than comparing the value of a variable with constant case labels, as in standard Pascal, lets each item be labeled with an arbitrary boolean test. The case evaluates these tests in order until one of them is true and then performs the associated action; all other actions are ignored. Those familiar with LISP will note that this has the same semantics as the LISP cond statement.
　　The other addition to the language is a return statement which takes one argument and can appear anywhere within a procedure or function. When the return is encountered,it causes the program to immediately exit the function, returning its argument as a result.Other than these modifications we used Pascal structure, with a reliance on the English descriptions, to make the algorithms clear.

(美)George F.Luger：George F.Luger: 1973年在宾夕法尼亚大学获得博士学位。在其后的五年，他在爱丁堡大学人工智能系从事博士后研究工作。目前，他是新墨西哥大学的计算机科学、语言学以及心理学教授。他的研究兴趣、课程信息异己发表的论文可从以下网址找到：http://www.cs.unm.edu/~luger/

Preface
PART I
ARTIFICIAL INTELLIGENCE: ITS ROOTS
AND SCOPE 1
1　Al: HISTORY AND APPLICATIONS 3
1.1　From Eden to ENIAC: Attitudes toward Intelligence, Knowledge, and Human Artifice　3
1.2　Overview of AI Application Areas　17
1.3　Artificial Intelligence--A Summary 28
1.4　Epilogue and References　29
1.5　Exercises 31
PART II
ARTIFICIAL INTELLIGENCE AS
REPRESENTATION AND SEARCH　33
2　THE PREDICATE CALCULUS 47
2.0　Introduction 47
2.1　The Propositional Calculus 47
2.2　The Predicate Calculus 52
2.3　Using Inference Rules to Produce Predicate Calculus Expressions 64
2.4　Application: A Logic-Based Financial Advisor 75
2.5　Epilogue and References　79
2.6　Exercises　79
PART II (continued)
3　　 STRUCTURES AND STRATEGIES FOR STATE SPACE SEARCH
3.0　　Introduction　81
3.1　　Graph Theory 84
3.2　　Strategies for State Space Search 93
3.3　　Using the State Space to Represent Reasoning with the Predicate Calculus
3.4　　Epilogue and References　121
3.5　　Exercises 121
4　　HEURISTIC SEARCH 123
4.0　　Introduction　123
4.1　　An Algorithm for Heuristic Search　127
4.2　　Admissibility, Monotonicity, and Informedness　139
4.3　　Using Heuristics in Games　144
4.4　　Complexity Issues　152
4.5　　Epilogue and References　156
4.6　　Exercises　156
5　　　　　CONTROL AND IMPLEMENTATION OF STATE SPACE SEARCH
5.0　　Introduction　159
5.1　　Recursion-Based Search　160
5.2　　Pattern-Directed Search　164
5.3　　Production Systems　171
5.4　　The Blackboard Architecture for Problem Solving　187
5.5　　Epilogue and References　189
5.6　　Exercises　190
PART III
REPRESENTATION AND INTELLIGENCE:
THE Al CHALLENGE 193
6　　 KNOWLEDGE REPRESENTATION　197
6.0　　Issues in Knowledge Representation　197
6.1　　A Brief History of AI Representational Systems 198
6.2　　Conceptual Graphs: A Network Language 218
6.3　　Alternatives to Explicit Representation 228
6.4　　Agent Based and Distributed Problem Solving 235
6.5　　Epilogue and References 240
6.6　　Exercises 243
PART III (continued)
7　　　　 STRONG METHOD PROBLEM SOLVING　 247
7.0　　Introduction　247
7.1　　Overview of Expert System Technology　249
7.2　　Rule-Based Expert Systems 256
7.3　　Model-Based, Case Based, and Hybrid Systems 268
7.4　　Planning 284
7.5　　Epilogue and References　299
7.6　　Exercises 301
8　　 REASONING IN UNCERTAIN SITUATIONS　303
8.0　　Introduction 303
8.1　　Logic-Based Abductive Inference　305
8.2　　Abduction: Alternatives to Logic 320
8.3　　The Stochastic Approach to Uncertainty 333
8.4　　Epilogue and References 344
8.5　　Exercises　346
PART IV
MACHINE LEARNING　349
9　　MACHINE LEARNING: SYMBOL-BASED 351
9.0　　Introduction　603
9.1　　A Framework for Symbol-based Learning 354
9.2　　Version Space Search　360
9.3　　The ID3 Decision Tree Induction Algorithm　372
9.4　　Inductive Bias and Learnability　381
9.5　　Knowledge and Learning　386
9.6　　Unsupervised Learning 397
9.7　　Reinforcement Learning 406
9.8　　Epilogue and References 413
9.9　　Exercises 414
10　　　 MACHINE LEARNING: CONNECTIONIST　 417
10.0　 Introduction 417
10.1　 Foundations for Connectionist Networks 419
10.2　 Perceptron Learning 422
10.3　 Backpropagation Learning 431
10.4　 Competitive Learning 438
10.5　 Hebbian Coincidence Learning 446
10.6　 Attractor Networks or "Memories" 457
10.7　 Epilogue and References 467
10.8　 Exercises 468
PART IV (continued)
11　 MACHINE LEARNING: SOCIAL AND EMERGENT　 469
11.0　 Social and Emergent Models of Learning 469
11.1　 The Genetic Algorithm 471
11.2　 Classifier Systems and Genetic Programming 481
11.3　 Artificial Life and Society-Based Learning 492
11.4　 Epilogue and References 503
11.5　 Exercises　504
PARTV
ADVANCED TOPICS FOR Al PROBLEM SOLVING　 507
12　AUTOMATED REASONING　 509
12.0　 Introduction to Weak Methods in Theorem Proving 509
12.1　 The General Problem Solver and Difference Tables 510
12.2　 ResohtionTheorem Proving 516
12.3　 PROLOG and Automated Reasoning 537
12.4　 Further Issues in Automated Reasoning　543
12.5　 Epilogue and References 550
12.6　 Exercises　551
13　 UNDERSTANDING NATURAL LANGUAGE　 553
13.0　 Role of Knowledge in Language Understanding 553
13.1　 Deconstructing Language: A Symbolic Analysis 556
13.2　 Syntax 559
13.3　 Syntax and Knowledge with ATN Parsers 568
13.4　 Stochastic Tools for Language Analysis 578
13.5　 Natural Language Applications 585
13.6　 Epilogue and References 592
13.7　 Exercises 557
PART VI
LANGUAGES AND PROGRAMMING TECHNIQUES
FOR ARTIFICIAL INTELLIGENCE　 597
14　AN INTRODUCTION TO PROLOG　 603
14.0　Introduction 603
14.1　 Syntax for Predicate Calculus Programming 604
14.2　 Abstract Data Types (ADTs) in PROLOG 616
14.3　 A Production System Example in PROLOG 620
PART VI: 14 AN INTRODUCTION TO PROLOG (continued)
14.4　 Designing Alternative Search Strategies 625
14.5　 A PROLOG Planner 630
14.6　 PROLOG: Meta-Predicates, Types, and Unification 633
14.7　 Meta-Interpreters in PROLOG 641
t4.8　 Learning Algorithms in PROLOG 656
14.9　 Natural Language Processing in PROLOG 666
14.10　Epilogue and References 673
14.11　Exercises 676
15　　　AN INTRODUCTION TO LISP　 679
15.0　 Introduction 679
15.1　 LISP: A Brief Overview 680
15.2　 Search in LISP: A Functional Approach to the Farmer, Wolf, Goat,and Cabbage Problem 702
15.3　 Higher-Order Functions and Procedural Abstraction 707
15.4　 Search Strategies in LISP 711
15.5　 Pattern Matching in LISP 715
15.6　 A Recursive Unification Function　717
15.7　 Interpreters and Embedded Languages 721
15.8　 Logic Programming in LISP 723
15.9　 Streams and Delayed Evaluation 732
15.15　An Expert System Shell in LISP 736
15.11　Semantic Networks and Inheritance in LISP 743
15.12　Object-Oriented Programming Using CLOS 747
15.13　Learning in LISP: The ID3 Algorithm 759
15.14　Epilogue and References 771
15.15　Exercises 772
PART VII
EPILOGUE 777
16　 ARTIFICIAL INTELLIGENCE AS EMPIRICAL ENQUIRY　 779
16.0　 Introduction 779
16.1　 Artificial Intelligence: A Revised Definition 781
16.2　 The Science of Intelligent Systems 792
16.3　 Al: Current Issues and Future Directions 803
16.4　 Epilogue and References 807
Bibliography 809
Author Index 837
Subject Index 843