人工智能：复杂问题求解的结构和策略 英文版2025|PDF|Epub|mobi|kindle电子书版本百度云盘下载

人工智能：复杂问题求解的结构和策略 英文版PDF格式电子书版下载

注意：本站所有压缩包均有解压码： 点击下载压缩包解压工具

PART Ⅰ ARTIFICIAL INTELLIGENCE:ITS ROOTS AND SCOPE1

1 AI:HISTORY AND APPLICATIONS3

1.1 From Eden to ENIAC:Attitudes toward Intelligence,Knowledge,and Human Artifice3

1.2 Overview of AI Application Areas17

1.3 Artificial Intelligence—A Summary28

1.4 Epilogue and References29

1.5 Exercises31

PART Ⅱ ARTIFICIAL INTELLIGENCE AS REPRESENTATION AND SEARCH33

2.1 The Propositional Calculus47

2 THE PREDICATE CALCULUS47

2.0 Introduction47

2.2 The Predicate Calculus52

2.3 Using Inference Rules to Produce Predicate Calculus Expressions64

2.4 Application:A Logic-Based Financial Advisor75

2.5 Epilogue and References79

2.6 Exercises79

3 STRUCTURES AND STRATEGIES FOR STATE SPACE SEARCH81

3.0 Introduction81

3.1 Graph Theory84

3.2 Strategies for State Space Search93

3.3 Using the State Space to Represent Reasoning with the Predicate Calculus107

3.4 Epilogue and References121

3.5 Exercises121

4 HEURISTIC SEARCH123

4.0 Introduction123

4.1 An Algorithm for Heuristic Search127

4.2 Admissibility,Monotonicity,and Informedness139

4.3 Using Heuristics in Games144

4.4 Complexity Issues152

4.5 Epilogue and References156

4.6 Exercises156

5 CONTROL AND IMPLEMENTATION OF STATE SPACE SEARCH159

5.0 Introduction159

5.1 Recursion-Based Search160

5.2 Pattern-Directed Search164

5.3 Production Systems171

5.4 The Blackboard Architecture for Problem Solving187

5.5 Epilogue and References189

5.6 Exercises190

PART Ⅲ REPRESENTATION AND INTELLIGENCE:THE AI CHALLENGE193

6 KNOWLEDGE REPRESENTATION197

6.0 Issues in Knowledge Representation197

6.1 A Brief History of AI Representational Systems198

6.2 Conceptual Graphs:A Network Language218

6.3 Alternatives to Explicit Representation228

6.4 Agent Based and Distributed Problem Solving235

6.5 Epilogue and References240

6.6 Exercises243

7 STRONG METHOD PROBLEM SOLVING247

7.0 Introduction247

7.1 Overview of Expert System Technology249

7.2 Rule-Based Expert Systems256

7.3 Model-Based,Case Based,and Hybrid Systems268

7.4 Planning284

7.5 Epilogue and References299

7.6 Exercises301

8.0 Introduction303

8 REASONING IN UNCERTAIN SITUATIONS303

8.1 Logic-Based Abductive Inference305

8.2 Abduction:Alternatives to Logic320

8.3 The Stochastic Approach to Uncertainty333

8.4 Epilogue and References344

8.5 Exercises346

PART Ⅳ MACHINE LEARNING349

9 MACHINE LEARNING:SYMBOL-BASED351

9.1 A Framework for Symbol-based Learning354

9.2 Version Space Search360

9.3 The ID3 Decision Tree Induction Algorithm372

9.4 Inductive Bias and Learnability381

9.5 Knowledge and Learning386

9.6 Unsupervised Learning397

9.7 Reinforcement Learning406

9.8 Epilogue and References413

9.9 Exercises414

10.0 Introduction417

10 MACHINE LEARNING:CONNECTIONIST417

10.1 Foundations for Connectionist Networks419

10.2 Perceptron Learning422

10.3 Backpropagation Learning431

10.4 Competitive Learning438

10.5 Hebbian Coincidence Learning446

10.6 Attractor Networks or"Memories"457

10.7 Epilogue and References467

10.8 Exercises468

11 MACHINE LEARNING:SOCIAL AND EMERGENT469

11.0 Social and Emergent Models of Learning469

11.1 The Genetic Algorithm471

11.2 Classifier Systems and Genetic Programming481

11.3 Artificial Life and Society-Based Learning492

11.4 Epilogue and References503

11.5 Exercises504

PART Ⅴ ADVANCED TOPICS FOR AI PROBLEM SOLVING507

12 AUTOMATED REASONING509

12.0 Introduction to Weak Methods in Theorem Proving509

12.1 The General Problem Solver and Difference Tables510

12.2 Resolution Theorem Proving516

12.3 PROLOG and Automated Reasoning537

12.4 Further Issues in Automated Reasoning543

12.5 Epilogue and References550

12.6 Exercises551

13 UNDERSTANDING NATURAL LANGUAGE553

13.0 Role of Knowledge in Language Understanding553

13.1 Deconstructing Language:A Symbolic Analysis556

13.7 Exercises557

13.2 Syntax559

13.3 Syntax and Knowledge with ATN Parsers568

13.4 Stochastic Tools for Language Analysis578

13.5 Natural Language Applications585

13.6 Epilogue and References592

PART Ⅵ LANGUAGES AND PROGRAMMING TECHNIQUES FOR ARTIFICIAL INTELLIGENCE597

14.0 Introduction603

9.0 Introduction603

14 AN INTRODUCTION TO PROLOG603

14.1 Syntax for Predicate Calculus Programming604

14.2 Abstract Data Types(ADTs)in PROLOG616

14.3 A Production System Example in PROLOG620

14.4 Designing Alternative Search Strategies625

14.5 A PROLOG Planner630

14.6 PROLOG:Meta-Predicates,Types,and Unification633

14.7 Meta-Interpreters in PROLOG641

14.8 Learning Algorithms in PROLOG656

14.9 Natural Language Processing in PROLOG666

14.10 Epilogue and References673

14.11 Exercises676

15 AN INTRODUCTION TO LISP679

15.0 Introduction679

15.1 LISP:A Brief Overview680

15.2 Search in LISP:A Functional Approach to the Farmer,Wolf,Goat,and Cabbage Problem702

15.3 Higher-Order Functions and Procedural Abstraction707

15.4 Search Strategies in LISP711

15.5 Pattern Matching in LISP715

15.6 A Recursive Unification Function717

15.7 Interpreters and Embedded Languages721

15.8 Logic Programming in LISP723

15.9 Streams and Delayed Evaluation732

15.15 An Expert System Shell in LISP736

15.11 Semantic Networks and Inheritance in LISP743

15.12 Object-Oriented Programming Using CLOS747

15.13 Learning in LISP:The ID3 Algorithm759

15.14 Epilogue and References771

15.15 Exercises772

PART Ⅶ EPILOGUE777

16 ARTIFICIAL INTELLIGENCE AS EMPIRICAL ENQUIRY779

16.0 Introduction779

16.1 Artificial Intelligence:A Revised Definition781

16.2 The Science of Intelligent Systems792

16.3 AI:Current Issues and Future Directions803

16.4 Epilogue and References807

Bibliography809

Author Index837

Subject Index843