人工智能:一种现代方法(英文版)
分類: 图书,计算机/网络,人工智能,
作者： [英]拉塞尔，[美]诺文 著
出 版 社： 人民邮电出版社
出版时间： 2002-4-1字数： 1342000版次： 1页数： 932印刷时间： 2002-4-1开本：印次：纸张： 胶版纸I S B N ： 9787115102027包装： 平装编辑推荐
内容简介
本书在智能Agent的概念框架下，把人工智能中相互分离的领域统一起来。全书主体内容共分为六大部分，即问题解、知识与推理、合乎逻辑的行动、不确定知识与推理、学习，以及通信、感知与行动。本书通过Agent从感知外部环境、到实施行动、并最后对外部环境施加影响的全过程，将这六部分组织起来，形成一个相互联系的整体，使读者对人工智能有一个完整的概念，达到较好的效果。
本书可以作为信息领域及相关领域的高等院校本科生和研究生的教科书或教学参考书，也可以作为相关领域的科研与工程技术人员的参考书。
作者简介
目录
Ⅰ Artificial Intelligence1
1Introduction3
1.1What Is AI?4
Acting humanly: The Turing Test approach5
Thinking humanly: The cognitive modelling approach6
Thinking rationally: The laws of thought approach6
Acting rationally: The rational agent approach7
1.2The Foundations of Artificial Intelligence8
Philosophy(428 B.C.-present)8
Mathematics(c.800-present)11
Psychology (1879-present)12
Computer engineering(1940-present)14
Linguistics(1957-present)15
1.3The History of Artificial Intelligence16
The gestation of artificial Intelligence(1943-1956)16
Early enthusiasm, great expectations(1952-1969)17
A dose of reality(1966-1974)20
Knowledge-based systems: The key to power?(1969-1979)22
AI becomes an Industry(1980-1988)24
The return of neural networks(1986-present)24
Recent events(1987-present)25
1.4The State of the Art26
1.5Summary27
Bibliographical and Historical Notes28
Exercises28
2Intelligent Agents31
2.1Introduction31
2.2How Agents Should Act31
The Ideal mapping from percept sequences to actions34
Autonomy35
2.3Structure of Intelligent Agents35
Agent programs37
Why not just look up the answers?38
An example39
Simple reflex agents40
Agents that keep track of the world41
Goal-based agents42
Utility-based agents44
2.4Environments45
Properties of environments46
Environment programs47
2.5Summary49
Bibliographical and Historical Notes50
Exercises50
ⅡProblem-solving53
3Solving Problems by Searching55
3.1Problem-Solving Agents55
3.2Formulating Problems57
Knowledge and problem types58
Well-defined problems and solutions60
Measuring problem-solving performance61
Choosing states and actions61
3.3Example Problems63
Toy Problems63
Real-world problems68
3.4Searching for Solutions70
Generating action sequences70
Data structures for search trees72
3.5Search Strategies73
Breadth-first search74
Uniform cost search75
Depth-first search77
Depth-limited search78
Iterative deepening search78
Bidirectional search80
Comparing search strategies81
3.6Avoiding Repeated States82
3.7Constraint Satisfaction Search83
3.8Summary85
Bibliographical and Historical Notes86
Exercises87
4Informed Search Methods92
4.1Best-First Search92
Minimize estimated cost to reach a goal:Greedy Search93
Minimizing the total path cost: A* search96
4.2Heuristic Functions101
The effect of heuristic accuracy on performance102
Inventing heuristic functions103
Heuristics for constraint satisfaction problems104
4.3Memory bounded Search106
Iterative deepening A* search (IDA*)106
SMA* search107
4.4Iterative Improvement Algorithms111
Hill-climbing search111
Simulated annealing113
Applications in constraint Satisfaction problems114
4.5Summary115
Bibliographical and Historical Notes115
Exercises118
5Game Playing122
5.1Introduction: games as Search Problems122
5.2Perfect Decisions in Two-Person Games123
5.3Imperfect Decisions126
Evaluation functions127
Cutting off search129
5.4Alpha-Beta Pruning129
Effectiveness of alpha-beta pruning131
5.5Games That Include an Element of Chance133
Position evaluation in games with chance nodes135
Complexity of expectiminimax135
5.6State-of-the-Art Game Programs136
Chess137
Checkers or Draughts138
Othello138
Backgammon139
Go 139
5.7Discussion139
5.8Summary141
Bibliographical and Historical Notes141
Exercises145
ⅢKnowledge and reasoning149
6Agents that Reason Logically151
6.1A Knowledge-Based Agent151
6.2The Wumpus World Environment153
Specifying the environment154
Acting and reasoning in the wumpus world155
6.3Representation, Reasoning, and Logic157
Representation160
Inference163
Logics165
6.4Propositional Logic: A Very Simple Logic166
Syntax166
Semantics168
Validity and inference169
Models170
Rules of inference for propositional logic171
Complexity of propositional inference173
6.5An Agent for the Wumpus World174
The knowledge base174
Finding the wumpus175
Translating knowledge into action176
Problems with the propositional agent176
6.6Summary178
Bibliographical and Historical Notes178
Exercises180
7First-Order Logic185
7.1Syntax and Semantics186
Terms188
Atomic sentences189
Complex sentences189
Quantifiers189
Equality193
7.2Extensions and Notational Variations194
Higher-order logic195
Functional and predicate expressions using the λ operator195
The uniqueness quantifier Э!196
The uniqueness operator ι196
Notational variations196
7.3Using First-Order Logic197
The kinship domain197
Axioms, definitions, and theorems198
The domain of sets199
Special notations for sets, lists and arithmetic200
Asking questions and getting answers200
7.4Logical Agents for the Wumpus World201
7.5A Simple Reflex Agent202
Limitations of simple reflex agents203
7.6Representing Change in the World203
Situation calculus204
Keeping track of location206
7.7Deducing Hidden Properties of the World208
7.8Preferences Among Actions210
7.9Toward a Goal-Based Agent211
7.10Summary211
Bibliographical and Historical Notes212
Exercises213
8Building a knowledge Base217
8.1Properties of Good and Bad Knowledge Bases218
8.2Knowledge Engineering221
8.3The Electronic Circuits Domain223
Decide what to talk about223
Decide on a vocabulary224
Encode general rules225
Encode the specific instance225
Pose queries to the inference procedure226
8.4General Ontology226
Representing Categories229
Measures231
Composite objects233
Representing change with events234
Times, intervals, and actions238
Objects revisited240
Substances and objects241
Mental events and mental objects243
Knowledge and action247
8.5The Grocery Shopping World247
Complete description of the shopping simulation248
Organizing knowledge249
Menu-planning249
Navigating252
Gathering253
Communicating254
Paying256
8.6Summary256
Bibliographical and Historical Notes256
Exercises261
9Inference in First-Order Logic265
9.1Inference Rules Involving Quantifiers265
9.2An Example Proof266
9.3Generalized Modus Ponens269
Canonical form270
Unification270
Sample proof revisited271
9.4Forward and Backward Chaining272
Forward-chaining algorithm273
Backward-chaining algorithm275
9.5Completeness276
9.6Resolution: A Complete Inference Procedure277
The resolution inference rule278
Canonical forms for resolution278
Resolution Proofs279
Conversion to Normal Form281
Example proof282
Dealing with equality284
Resolution strategies284
9.7Completeness of resolution286
9.8Summary290
Bibliographical and Historical Notes291
Exercises294
10Logical Reasoning Systens297
10.1Introduction297
10.2Indexing, Retrieval, and Unification299
Implementing sentences and terms299
Store and fetch299
Table-based indexing300
Tree-based indexing301
The unification algorithm302
10.3Logic Programming Systems304
The Prolog language304
Implementation305
Compilation of logic programs306
Other logic programming languages308
Advanced control facilities308
10.4Theorem Provers310
Design of a theorem prover310
Extending Prolog311
Theorem provers as assistants312
Practical uses of theorem provers313
10.5Forward-Chaining Production Systems313
Match phase314
Conflict resolution phase315
Practical uses of production systems316
10.6Frame Systems and Semantic Networks316
Syntax and semantics of semantic networks317
Inheritance with exceptions319
Multiple inheritance320
Inheritance and change320
Implementation of semantic networks321
Expressiveness of semantic networks323
10.7Description Logics323
Practical uses of description logics325
10.8Managing Retractions, Assumptions, and Explanations325
10.9Summary327
Bibliographical and Historical Notes328
Exercises332
Ⅳ Acting logically335
11Planning337
11.1A Simple Planning Agent337
11.2From Problem Solving to Planning3380
11.3Planning in Situation Calculus341
11.4Basic Representations for Planning343
Representations for states and goals343
Representations for actions344
Situation space and plan space345
Representations for plans346
Solutions349
11.5A Partial-Order Planning Example349
11.6A Partial-Order Planning Algorithm355
11.7Planning with Partially Instantiated Operators357
11.8Knowledge Engineering for Planning359
The blocks world359
Shakey's world360
11.9Summary362
Bibliographical and Historical Notes363
Exercises364
12Practical Planning367
12.1Practical Planners367
Spacecraft assembly, integration, and verification367
Job shop scheduling369
Scheduling for space missions369
Buildings, aircraft carriers, and beer factories371
12.2Hierarchical Decomposition371
Extending the language372
Modifying the planner374
12.3Analysis of Hierarchical Decomposition375
Decomposition and sharing379
Decomposition versus approximation380
12.4More Expressive Operator Descriptions381
Conditional effects381
Negated and disjunctive goals382
Universal quantification383
A planner for expressive operator descriptions384
12.5Resource Constraints386
Using measures in planning386
Temporal constraints388
12.6Summary388
Bibliographical and Historical Notes389
Exercises390
13Planning and Acting392
13.1Conditional Planning393
The nature of conditional plans393
An algorithm for generating conditional plans395
Extending the plan language398
13.2A Simple Replanning Agent401
Simple replanning with execution monitoring402
13.3Fully Integrated Planning and Execution403
13.4Discussion and Extensions407
Comparing conditional planning and replanning407
Coercion and abstraction409
13.5Summary410
Bibliographical and Historical Notes 411
Exercises412
ⅤUncertain knowledge and reasoning413
14Uncertainty415
14.1Acting under Uncertainty415
Handing uncertain knowledge416
Uncertainty and rational decisions418
Design for a decision-theoretic agent419
14.2Basic Probability Notation420
Prior probability420
Conditional probability421
14.3The Axioms of Probability422
Why the axioms of probability are reasonable423
The joint probability distribution425
14.4Bayes' Rule and Its Use426
Applying Bayes' rule: The simple case426
Normalization427
Using Bayes' rule: Combining evidence428
14.5Where Do Probabilities Come From?430
14.6Summary431
Bibliographical and Historical Notes431
Exercises433
15Probabilistic Reasoning Systems436
15.1Representing Knowledge in an Uncertain Domain436
15.2The Semantics of Belief Networks438
Representing the joint probability distribution439
Conditional independence relations in belief networks444
15.3Inference in Belief Networks445
The nature of probabilistic inferences446
An algorithm for answering queries447
15.4Inference in Multiply Connected Belief Networks453
Clustering methods453
Cutset conditioning methods454
Stochastic simulation methods455
15.5Knowledge Engineering for Uncertain Reasoning 456
Case study: The Pathfinder system457
15.6Other Approaches to Uncertain Reasoning 458
Defaulet reasoning459
Rule-based methods for uncertain reasoning460
Representing ignorance: Dempster-Shafer theory462
Representing vagueness: Fuzzy sets and fuzzy logic463
15.7Summary464
Bibliographical and Historical Notes464
Exercises467
16Making Simple Decisions471
16.1Combining Beliefs and Desires Under Uncertainty471
16.2The Basis of Utility Theory473
Constraints on rational preferences473
…and then there was Utility474
16.3Utility Functions475
The utility of money476
UtilityScales and utility assessment478
16.4Multiattribute utility functions480
Dominance481
Preference structure and multiattribute utility483
16.5Decision Networks484
Representing a decision problem using decision net works484
Evaluating decision networks486
16.6The Value of Information487
A simple example487
A general formula488
Propertiesof the value of information489
Implementing an information-gathering agent490
16.7Decision-Theoretic Expert Systems491
16.8Summary493
Bibliographical and Historical Notes493
Exercises495
17Making Complex Decision Problems498
17.1Sequential Decision Problems498
17.2Value Iteration502
17.3Policy Iteration505
17.4Decision-Theoretic Agent Design508
The decision cycle of a rational agent508
Sensing in uncertain worlds510
17.5Dynamic Belief Networks514
17.6Dynamic Decision Networks516
Discussion518
17.7Summary519
Bibliographical and Historical Notes520
Exercises521
ⅥLearning523
18Learning from Observations525
18.1A General Model of Learning Agents525
Components of the performance element527
Representation of the components528
Available feedback528
Prior knowledge528
Bringing it all together529
18.2Inductive Learning529
18.3Learning Decision Trees531
Decision trees as performance elements531
Expressiveness of decision trees532
Inducing decision trees from examples534
Assessing the performance of the learning algorithm538
Practical uses of decision tree learning538
18.4Using Information Theory540
Noise and overfitting542
Broadening the applicability of decision trees543
18.5Learning General Logical Descriptions544
Hypotheses544
Examples545
Current-best-hypothesis search546
Least-commitment search549
Discussion 552
18.6Why Learning Works: Computational Learning Theory552
How many examples are needed?553
Learning decision lists555
Discussion 557
18.7Summary558
Bibliographical and Historical Notes559
Exercises560
19Learning in Neural and Belief Networks563
19.1How the Brain Works564
Comparing brains with digital computers565
19.2Neural Networks567
Notation567
Simple computing elements567
Network structures570
Optimal network structure572
19.3Perceptrons573
What perceptrons can represent573
Learning linearly separable functions575
19.4Multilayer Feed-Forward Networks578
Back-propagation learning578
Back-propagation as gradient descent search580
Discussion583
19.5Applications of Neural Networks584
Pronunciation585
Handwritten character recognition586
Driving586
19.6Bayesian Methods for Learning Belief Networks588
Bayesian learning588
Belief network learning problems589
Learning networks with fixed structure589
A comparison of belief networks and neural networks592
19.7Summary593
Bibliographical and Historical Notes594
Exercises596
20Reinforcement Learning598
20.1Introduction598
20.2Passive Learning in a Known Environment600
Naive updating 601
Adaptive dynamic programming603
Temporal difference learning604
20.3Passive Learning in an Unknown Environment605
20.4Active Learning in anUnknown Environment607
20.5Exploration609
20.6Learning an Action-Value Function612
20.7Generalization in Reinforcement Learning615
Applications to game-playing617
Application to robot control617
20.8Genetic Algorithms and Evolutionary Programming619
20.9Summary621
Bibliographical and Historical Notes622
Exercises623
21Knowledge in Learning625
21.1Knowledge in Learning625
Some simple examples626
Some general schemes627
21.2Explanation-Based Learning629
Extracting general rules from examples630
Improving efficiency631
21.3Learning Using Relevance Information633
Determining the hypothesis space633
Learning and using relevance information634
21.4Inductive Logic Programming636
An example637
Inverse resolution639
Top-down learning methods641
21.5Summary644
Bibliographical and Historical Notes645
Exercises647
ⅦCommunicating, perceiving, and acting649
22Agents that Communicate651
22.1Communication as Action652
Fundamentals of language654
The component steps of communication655
Two modelsof communication659
22.2Types of Communicating Agents659
Communicating using Tell and Ask660
Communicating using formal language661
An agent that communicates662
22.3A Formal Grammar for a Subset of English662
The Lexicon of ε0664
The Grammar ofε0664
22.4Syntactic Analysis(Parsing)664
22.5Definite Clause Grammar(DCG)667
22.6Augmenting a Grammar668
Verb Subcategorization669
Generative Capacity of Augmented Grammars671
22.7Semantic Interpretation672
Semantics as DCG Augmentations673
The semantics of “john loves Mary”673
The semantics ofε1
Converting quasi-logical form to logical form677
Pragmatic Interpretation678
22.8ambiguity and Disambiguation680
Disambiguation682
22.9A Communicating Agent683
22.10Summary684
Bibliographical and Historical Notes685
Exercises688
23Practical Natural Language Processing691
23.1Practical Applications691
Machine translation691
Database access693
Information retrieval694
Text categorization695
Extracting data from text696
23.2Efficient Parsing701
Extracting parses from the chart: Packing701
23.3Scaling Up the Lexicon703
23.4Scaling Up the Grammar705
Nominal compounds and apposition706
Adjective phrases707
Determiners708
Noun phrases revisited709
Clausal complements710
Relative clauses710
Questions711
Handling agrammatical strings712
23.5Ambiguity712
Syntactic evidence713
Lexical evidence713
Semantic evidence713
Metonymy714
Metaphor715
23.6Discourse Understanding715
The structure of coherent discourse717
23.7Summary719
Bibliographical and Historical Notes720
Exercises721
24Perception724
24.1Introduction724
24.2Image Formation725
Pinhole camera725
Lens systems727
Photometry of image formation729
Spectrophotometry of image formation730
24.3Image-Processing Operations for Early Vision730
Convolution with linear filters732
Edge detection733
24.4Extracting3-D Information Using Vision734
Motion735
Binocular stereopsis737
Texture gradients742
Shading743
Contour745
24.5Using Vision for Manipulation and Navigation749
24.6Object representation and Recognition751
The alignment method752
Using projective invariants754
24.7Speech Recognition757
Signal processing758
Defining the overall speech recognition model760
The language model: P(words)760
The acoustic model: P(signallwords)762
Putting the models together764
The search algorithm765
Training the model766
24.8Summary767
Bibliographical and Historical Notes767
Exercises771
25Robotics773
25.1Introduction773
25.2Tasks: What Are Robots Good For?774
Manufacturing and materials handling774
Gofer robots775
Hazardous environments775
Telepresence and virtual reality776
Augmentation of human abilities776
25.3Parts: What are Robots Made Of?777
Effectors: Tools for action777
Sensors: Tools for Perception782
25.4Architectures786
Classical architecture787
Situated automata788
25.5Configuration Spaces: A Framework for Analysis790
Generalized configuration space792
Recognizable Sets795
25.6Navigation and Motion Planning796
Cell decomposition796
Skeletonization methods798
Fine-motion planning802
Landmark-based navigation805
Online algorithms806
25.7Summary809
Bibliographical and Historical Notes809
Exercises811
ⅧConclusions815
26Philosophical Foundations817
26.1The Big Questions817
26.2Foundations of Reasoning and Perception819
26.3On the Possibility of Achieving Intelligent Behavior822
The mathematical objection824
The argument from informality826
26.4Intentionality and Consciousness830
The Chinese Room831
The Brain Prosthesis Experiment835
Discussion836
26.5Summary837
Bibliographical and Historical Notes838
Exercises840
27AI: Present and Future842
27.1Have We Succeeded Yet?842
27.2What Exactly Are We Trying to Do?845
27.3What If we Do Succeed?848
AComplexity analysis and O() notation851
A.1Asymptotic Analysis851
A.2Inherently Hard Problems852
Bibliographical and Historical Notes853
BNotes on Languages and Algorithms854
B.1Defining Languages with Backus-Naur Form(BNF)854
B.2Describing Algorithms with Pseudo-Code855
Nondeterminism855
Static variables856
Functions as values856
B.3The Code Repository857
B.4Comments857
Bibliography859
Index905
媒体评论
