人工智能 一种现代的方法 原书第3版 英文PDF|Epub|txt|kindle电子书版本网盘下载

人工智能 一种现代的方法 原书第3版 英文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

Ⅰ Artificial Intelligence1

1 Introduction1

1.1 What Is AI？1

1.2 The Foundations of Artificial Intelligence5

1.3 The History of Artificial Intelligence16

1.4 The State of the Art28

1.5 Summary，Bibliographical and Historical Notes，Exercises29

2 Intelligent Agents34

2.1 Agents and Environments34

2.2 Good Behavior：The Concept of Rationality36

2.3 The Nature of Environments40

2.4 The Structure of Agents46

2.5 Summary，Bibliographical and Historical Notes，Exercises59

Ⅱ Problem-solving64

3 Solving Problems by Searching64

3.1 Problem-Solving Agents64

3.2 Example Problems69

3.3 Searching for Solutions75

3.4 Uninformed Search Strategies81

3.5 Informed（Heuristic）Search Strategies92

3.6 Heuristic Functions102

3.7 Summary，Bibliographical and Historical Notes，Exercises108

4 Beyond Classical Search120

4.1 Local Search Algorithms and Optimization Problems120

4.2 Local Search in Continuous Spaces129

4.3 Searching with Nondeterministic Actions133

4.4 Searching with Partial Observations138

4.5 Online SearchAgents and Unknown Environments147

4.6 Summary，Bibliographical and Historical Notes，Exercises153

5 Adversarial Search161

5.1 Games161

5.2 Optimal Decisions in Games163

5.3 Alpha-Beta Pruning167

5.4 Imperfect Real-Time Decisions171

5.5 Stochastic Games177

5.6 Partially Observable Games180

5.7 State-of-the-Art Game Programs185

5.8 Alternative Approaches187

5.9 Summary，Bibliographical and Historical Notes，Exercises189

6 Constraint Satisfaction Problems202

6.1 Defining Constraint Satisfaction Problems202

6.2 Constraint Propagation：Inference in CSPs208

6.3 Backtracking Search for CSPs214

6.4 Local Search for CSPs220

6.5 The Structure of Problems222

6.6 Summary，Bibliographical and Historical Notes，Exercises227

Ⅲ Knowledge，reasoning，and planning234

7 Logical Agents234

7.1 Knowledge-Based Agents235

7.2 The Wumpus World236

7.3 Logic240

7.4 Propositional Logic：A Very Simple Logic243

7.5 Propositional Theorem Proving249

7.6 Effective Propositional Model Checking259

7.7 Agents Based on Propositional Logic265

7.8 Summary，Bibliographical and Historical Notes，Exercises274

8 First-Order Logic285

8.1 Representation Revisited285

8.2 Syntax and Semantics of First-Order Logic290

8.3 Using First-Order Logic300

8.4 Knowledge Engineering in First-Order Logic307

8.5 Summary，Bibliographical and Historical Notes，Exercises313

9 Inference in First-Order Logic322

9.1 Propositional vs.First-Order Inference322

9.2 Unification and Lifting325

9.3 Forward Chaining330

9.4 Backward Chaining337

9.5 Resolution345

9.6 Summary，Bibliographical and Historical Notes，Exercises357

10 Classical Planning366

10.1 Definition of Classical Planning366

10.2 Algorithms for Planning as State-Space Search373

10.3 Planning Graphs379

10.4 Other Classical Planning Approaches387

10.5 Analysis of Planning Approaches392

10.6 Summary，Bibliographical and Historical Notes，Exercises393

11 Planning and Acting in the Real World401

11.1 Time，Schedules，and Resources401

11.2 Hierarchical Planning406

11.3 Planning and Acting in Nondeterministic Domains415

11.4 Multiagent Planning425

11.5 Summary，Bibliographical and Historical Notes，Exercises430

12 Knowledge Representation437

12.1 Ontological Engineering437

12.2 Categories and Objects440

12.3 Events446

12.4 Mental Events and Mental Objects450

12.5 Reasoning Systems for Categories453

12.6 Reasoning with Default Information458

12.7 The Internet Shopping World462

12.8 Summary，Bibliographical and Historical Notes，Exercises467

Ⅳ Uncertain knowledge and reasoning480

13 Quantifying Uncertainty480

13.1 Acting under Uncertainty480

13.2 Basic Probability Notation483

13.3 Inference Using Full Joint Distributions490

13.4 Independence494

13.5 Bayes’Rule and Its Use495

13.6 The Wumpus World Revisited499

13.7 Summary，Bibliographical and Historical Notes，Exercises503

14 Probabilistic Reasoning510

14.1 Representing Knowledge in an Uncertain Domain510

14.2 The Semantics of Bayesian Networks513

14.3 Efficient Representation of Conditional Distributions518

14.4 Exact Inference in Bayesian Networks522

14.5 Approximate Inference in Bayesian Networks530

14.6 Relational and First-Order Probability Models539

14.7 Other Approaches to Uncertain Reasoning546

14.8 Summary，Bibliographical and Historical Notes，Exercises551

15 Probabilistic Reasoning over Time566

15.1 Time and Uncertainty566

15.2 Inference in Temporal Models570

15.3 Hidden Markov Models578

15.4 Kalman Filters584

15.5 Dynamic Bayesian Networks590

15.6 Keeping Track of Many Objects599

15.7 Summary，Bibliographical and Historical Notes，Exercises603

16 Making Simple Decisions610

16.1 Combining Beliefs and Desires under Uncertainty610

16.2 The Basis of Utility Theory611

16.3 Utility Functions615

16.4 Multiattribute Utility Functions622

16.5 Decision Networks626

16.6 The Value of Information628

16.7 Decision-Theoretic Expert Systems633

16.8 Summary，Bibliographical and Historical Notes，Exercises636

17 Making Complex Decisions645

17.1 Sequential Decision Problems645

17.2 Value Iteration652

17.3 Policy Iteration656

17.4 Partially Observable MDPs658

17.5 Decisions with Multiple Agents：Game Theory666

17.6 Mechanism Design679

17.7 Summary，Bibliographical and Historical Notes，Exercises684

Ⅴ Learning693

18 Learning from Examples693

18.1 Forms of Learning693

18.2 Supervised Learning695

18.3 Learning Decision Trees697

18.4 Evaluating and Choosing the Best Hypothesis708

18.5 The Theory of Leaming713

18.6 Regression and Classification with Linear Models717

18.7 Artificial Neural Networks727

18.8 Nonparametric Models737

18.9 Support Vector Machines744

18.10 Ensemble Learning748

18.11 Practical Machine Learning753

18.12 Summary，Bibliographical and Historical Notes，Exercises757

19 Knowledge in Learning768

19.1 A Logical Formulation of Learning768

19.2 Knowledge in Learning777

19.3 Explanation-Based Learning780

19.4 Learning Using Relevance Information784

19.5 Inductive Logic Programming788

19.6 Summary，Bibliographical and Historical Notes，Exercises797

20 Learning Probabilistic Models802

20.1 Statistical Learning802

20.2 Learning with Complete Data806

20.3 Learning with Hidden Variables：The EM Algorithm816

20.4 Summary，Bibliographical and Historical Notes，Exercises825

21 Reinforcement Learning830

21.1 Introduction830

21.2 Passive Reinforcement Learning832

21.3 Active Reinforcement Learning839

21.4 Generalization in Reinforcement Learning845

21.5 Policy Search848

21.6 Applications of Reinforcement Learning850

21.7 Summary，Bibliographical and Historical Notes，Exercises853

Ⅵ Communicating，perceiving，and acting860

22 Natural Language Processing860

22.1 Language Models860

22.2 Text Classification865

22.3 Information Retrieval867

22.4 Information Extraction873

22.5 Summary，Bibliographical and Historical Notes，Exercises882

23 Natural Language for Communication888

23.1 Phrase Structure Grammars888

23.2 Syntactic Analysis（Parsing）892

23.3 Augmented Grammars and Semantic Interpretation897

23.4 Machine Translation907

23.5 Speech Recognition912

23.6 Summary，Bibliographical and Historical Notes，Exercises918

24 Perception928

24.1 Image Formation929

24.2 Early Image-Processing Operations935

24.3 Object Recognition by Appearance942

24.4 Reconstructing the 3D World947

24.5 Object Recognition from Structural Information957

24.6 Using Vision961

24.7 Summary，Bibliographical and Historical Notes，Exercises965

25 Robotics971

25.1 Introduction971

25.2 Robot Hardware973

25.3 Robotic Perception978

25.4 Planning to Move986

25.5 Planning Uncertain Movements993

25.6 Moving997

25.7 Robotic Software Architectures1003

25.8 Application Domains1006

25.9 Summary，Bibliographical and Historical Notes，Exercises1010

Ⅶ Conclusions1020

26 Philosophical Foundations1020

26.1 Weak AI：Can Machines Act Intelligently？1020

26.2 Strong AI：Can Machines Really Think？1026

26.3 The Ethics and Risks of Developing Artificial Intelligence1034

26.4 Summary，Bibliographical and Historical Notes，Exercises1040

27 AI：ThePresentandFuture1044

27.1 Agent Components1044

27.2 Agent Architectures1047

27.3 Are We Going in the Right Direction？1049

27.4 What If AI Does Succeed？1051

A Mathematical background1053

A.1 Complexity Analysis and O（）Notation1053

A.2 Vectors，Matrices，and Linear Algebra1055

A.3 Probability Distributions1057

B Notes on Languages and Algorithms1060

B.1 Defining Languages with Backus-Naur Form（BNF）1060

B.2 Describing Algorithms with Pseudocode1061

B.3 Online Help1062

Bibliography1063

Index1095