人工智能：复杂问题求解的结构和策略（英文版）（第6版）简介，目录书摘
目录:PrefacePublishers AcknowledgementsPART Ⅰ ARTIFIClAL INTELLIGENCE：ITS ROOTS AND SCOPE1 A1：HISTORY AND APPLICATIONS1.1 From Eden to ENIAC：Attitudes toward Intelligence，Knowledge，andHuman Artifice1.2 0verview ofAl Application Areas1.3 Artificial Intelligence A Summary1.4 Epilogue and References1.5 ExercisesPART Ⅱ ARTIFlClAL INTELLIGENCE AS REPRESENTATION AN D SEARCH2 THE PREDICATE CALCULUS2.0 Intr0血ction2.1 The Propositional Calculus2.2 The Predicate Calculus2.3 Using Inference Rules to Produce Predicate Calculus Expressions2.4 Application：A Logic-Based Financial Advisor2.5 Epilogue and References2.6 Exercises
3 STRUCTURES AND STRATEGIES FOR STATE SPACE SEARCH3.0 Introducfion3.1 GraphTheory3.2 Strategies for State Space Search3.3 using the state Space to Represent Reasoning with the Predicate Calculus3.4 Epilogue and References3.5 Exercises
4 HEURISTIC SEARCH4.0 Introduction4.l Hill Climbing and Dynamic Programmin94.2 The Best-First Search Algorithm4.3 Admissibility,Monotonicity,and Informedness4.4 Using Heuristics in Games4.5 Complexity Issues4.6 Epilogue and References4.7 Exercises
5 STOCHASTIC METHODS5.0 Introduction5.1 The Elements ofCountin95.2 Elements ofProbabilityTheory5.3 Applications ofthe Stochastic Methodology5.4 BayesTheorem5.5 Epilogue and References5.6 Exercises
6 coNTROL AND IMPLEMENTATION OF STATE SPACE SEARCH6.0 Introduction l936.1 Recursion.Based Search6.2 Production Systems6.3 The Blackboard Architecture for Problem Solvin96.4 Epilogue and References6.5 Exercises
PARTⅢ CAPTURING INTELLIGENCE：THE AI CHALLENGE7 KNOWLEDGE REPRESENTATION7.0 Issues in Knowledge Representation7.1 A BriefHistory ofAI Representational Systems7.2 Conceptual Graphs：A Network Language7.3 Alternative Representations and Ontologies7.4 Agent Based and Distributed Problem Solving7.5 Epilogue and References7.6 Exercises
8 STRONG METHOD PROBLEM SOLVING8.0 Introduction8.1 Overview ofExpert Sygem Technology8.2 Rule.Based Expert Sygems8.3 Model-Based,Case Based and Hybrid Systems8.4 Planning8.5 Epilogue and References8.6 Exercises9 REASONING IN UNCERTAIN STUATIONS9.0 Introduction9.1 Logic-Based Abductive Inference9.2 Abduction：Alternatives to Logic9.3 The Stochastic Approach to Uncertainty9.4 Epilogue and References9.5 Exercises
PART ⅣMACHINE LEARNING10 MACHINE LEARNING：SYMBOL-BASED10.0 Introduction10.1 A Framework for Symbol based Learning10.2 version Space Search10.3 The ID3 Decision Tree Induction Algorithm10.4 Inductive Bias and Learnability10.5 Knowledge and Learning10.6 Unsupervised Learning10.7 Reinforcement Learning10.8 Epilogue and Referenees10.9 Exercises
11 MACHINE LEARNING：CONNECTIONtST11.0 Introduction11.1 Foundations for Connectionist Networks11.2 Perceptron Learning11.3 Backpropagation Learning11.4 Competitive Learning11.5 Hebbian Coincidence Learning11.6 Attractor Networks or“Memories”11.7 Epilogue and References11.8 Exercises 506
12 MACHINE LEARNING：GENETIC AND EMERGENT12.0 Genetic and Emergent MedeIs ofLearning12.1 11Ic Genetic Algorithm12.2 Classifier Systems and Genetic Programming12.3 Artmcial Life and Society-Based Learning12.4 EpilogueandReferences12.5 Exercises
13 MACHINE LEARNING：PROBABILISTIC13.0 Stochastic andDynamicModelsofLearning13.1 Hidden Markov Models(HMMs)13.2 DynamicBayesianNetworksandLearning13.3 Stochastic Extensions to Reinforcement Learning13.4 EpilogueandReferences13.5 Exercises
PART ⅤAD，ANCED TOPlCS FOR Al PROBLEM SOLVING14 AUTOMATED REASONING14.0 Introduction to Weak Methods inTheorem Proving14.1 TIIeGeneralProblem SolverandDifiel"enceTables14.2 Resolution TheOrem Proving14.3 PROLOG and Automated Reasoning14.4 Further Issues in Automated Reasoning14.5 EpilogueandReferences14.6 Exercises
15 UNDERs-rANDING NATURAL LANGUAGE15.0 TheNaturalLang~~geUnderstandingProblem15.1 Deconstructing Language：An Analysis15.2 Syntax15.3 TransitionNetworkParsers and Semantics15.4 StochasticTools forLanguage Understanding15.5 Natural LanguageApplications15.6 Epilogue and References15.7 Exercises……PART Ⅵ EPILOGUE16 ARTIFICIAL INTELLIGENCE AS EMPIRICAL ENQUIRY
人工智能：复杂问题求解的结构和策略中文第6版免费下载
这是一本经典的人工智能教材，全面阐述了人工智能的基础理论，有效结合了求解智能问题的数据结构以及实现的算法，把人工智能的应用程序应用于实际环境中，并从社会和哲学、心理学以及神经生理学角度对人工智能进行了独特的讨论。新版中增加了对“基于随机方法的机器学习”的介绍，并提出了一些新的主题，如涌现计算、本体论、随机分割算法等。《人工智能复杂问题求解的结构和策略（原书第6版）》适合作为高等院校计算机专业人工智能教材，也可供人工智能领域的研究者及相关工程技术人员参考。
《人工智能：复杂问题求解的结构和策略（原书第6版）》第1章简单介绍人工智能。我们从哲学、心理学和其他研究领域中试图了解头脑和智能的历史。从重要意义上讲，AI是一门古老的科学，至少可以追溯到亚里士多德。对这些背景的了解是理解现代研究中主要问题的基本条件。我们还介绍了AI中一些重要应用领域的概要情况。本节为大家介绍从伊甸园到第一台电子计算机：对智能、知识和人类技能的态度。
人工智能：一个尝试性的定义
可以把人工智能（ArtificialIntelligence，AI）定义为计算机科学的一个分支，它关心智能行为的自动化。本书恰好使用这样的定义，因为这个定义强调了AI是计算机科学的一部分，因而必须建立在坚实的理论基础之上并应用计算机科学领域的原理。这些原理包括用于知识表示的数据结构、应用该知识所需的算法以及用来实现算法的语言和编程技术。
然而，这个定义由于“智能”本身并没有被很好地定义和理解而受到影响。虽然大多数人确信在看到智能行为时能识别出它是智能的，但是似乎没有人能够使“智能”的定义既足够具体以评估计算机程序的智能性，同时又反映了人类意识的生动性和复杂性的特性。