人工智能：一种现代的方法（英文版·第3版）

人工智能：一种现代的方法（英文版·第3版） 
出版时间：2011年版 
内容简介 
　　《大学计算机教育国外著名教材系列·人工智能：一种现代的方法（第3版）（影印版）》最权威、最经典的人工智能教材，已被全世界100多个国家的1200多所大学用作教材。《大学计算机教育国外著名教材系列·人工智能：一种现代的方法（第3版）（影印版）》的最新版全面而系统地介绍了人工智能的理论和实践，阐述了人工智能领域的核心内容，并深入介绍了各个主要的研究方向。全书仍分为八大部分：第一部分“人工智能”，第二部分“问题求解”，第三部分“知识与推理”，第四部分“规划”，第五部分“不确定知识与推理”，第六部分“学习”，第七部分“通信、感知与行动”，第八部分“结论”。《大学计算机教育国外著名教材系列·人工智能：一种现代的方法（第3版）（影印版）》既详细介绍了人工智能的基本概念、思想和算法，还描述了其各个研究方向最前沿的进展，同时收集整理了详实的历史文献与事件。另外，《大学计算机教育国外著名教材系列·人工智能：一种现代的方法（第3版）（影印版）》的配套网址为教师和学生提供了大量教学和学习资料。《大学计算机教育国外著名教材系列·人工智能：一种现代的方法（第3版）（影印版）》适合于不同层次和领域的研究人员及学生，是高等院校本科生和研究生人工智能课的首选教材，也是相关领域的科研与工程技术人员的重要参考书。 
目录 
Ⅰ artificial intelligence  
1 introduction  
1.1what is al?  
1.2the foundations of artificial intelligence  
1.3the history of artificial intelligence  
1.4the state of the art  
1.5summary, bibliographical and historical notes, exercises  
2 intelligent agents  
2.1agents and environments  
2.2good behavior: the concept of rationality  
2.3the nature of environments  
2.4the structure of agents  
2.5summary, bibliographical and historical notes, exercises  
Ⅱ problem-solving  
3 solving problems by searching  
3.1problem-solving agents  
3.2example problems  
3.3searching for solutions  
3.4uninformed search strategies  
3.5informed (heuristic) search strategies  
3.6heuristic functions  
3.7summary, bibliographical and historical notes, exercises  
4 beyond classical search  
4.1local search algorithms and optimization problems  
4.2local search in continuous spaces  
4.3searching with nondeterministic actions  
4.4searching with partial observations  
4.5online search agents and unknown environments  
4.6summary, bibliographical and historical notes, exercises  
5 adversarial search  
5.1games  
5.2optimal decisions in games  
5.3alpha-beta pruning  
5.4imperfect real-time decisions  
5.5stochastic games  
5.6partially observable games  
5.7state-of-the-art game programs  
5.8alternative approaches  
5.9summary, bibliographical and historical notes, exercises  
6 constraint satisfaction problems  
6.1defining constraint satisfaction problems  
6.2constraint propagation: inference in csps  
6.3backtracking search for csps  
6.4local search for csps  
6.5the structure of problems  
6.6summary, bibliographical and historical notes, exercises  
Ⅲ knowledge, reasoning, and planning  
7 logical agents  
7.1knowledge-based agents  
7.2the wumpus world  
7.3logic  
7.4propositional logic: a very simple logic  
7.5propositional theorem proving  
7.6effective propositional model checking  
7.7agents based on propositional logic  
7.8summary, bibliographical and historical notes, exercises  
8 first-order logic  
8.1representation revisited  
8.2syntax and semantics of first-order logic  
8.3using first-order logic  
8.4knowledge engineering in first-order logic  
8.5summary, bibliographical and historical notes, exercises  
9 inference in first-order logic  
9.1propositional vs. first-order inference  
9.2unification and lifting  
9.3forward chaining  
9.4backward chaining  
9.5resolution  
9.6summary, bibliographical and historical notes, exercises  
10 classical planning  
10.1 definition of classical planning  
10.2 algorithms for planning as state-space search  
10.3 planning graphs  
10.4 other classical planning approaches  
10.5 analysis of planning approaches  
10.6 summary, bibliographical and historical notes, exercises  
11 planning and acting in the real world  
11.1 time, schedules, and resources  
11.2 hierarchical planning  
11.3 planning and acting in nondeterministic domains  
11.4 multiagent planning  
11.5 summary, bibliographical and historical notes, exercises  
12 knowledge representation  
12.1 ontological engineering  
12.2 categories and objects  
12.3 events  
12.4 mental events and mental objects  
12.5 reasoning systems for categories  
12.6 reasoning with default information  
12.7 the intemet shopping world  
12.8 summary, bibliographical and historical notes, exercises  
Ⅳ uncertain knowledge and reasoning  
13 quantifying uncertainty  
13.1 acting under uncertainty  
13.2 basic probability notation  
13.3 inference using full joint distributions  
13.4 independence  
13.5 bayes\’ rule and its use  
13.6 the wumpus world revisited  
13.7 summary, bibliographical and historical notes, exercises  
14 probabilistic reasoning  
14.1 representing knowledge in an uncertain domain  
14.2 the semantics of bayesian networks  
14.3 efficient representation of conditional distributions  
14.4 exact inference in bayesian networks  
14.5 approximate inference in bayesian networks  
14.6 relational and first-order probability models  
14.7 other approaches to uncertain reasoning  
14.8 summary, bibliographical and historical notes, exercises  
15 probabilistic reasoning over time  
15.1 time and uncertainty  
15.2 inference in temporal models  
15.3 hidden markov models  
15.4 kalman filters  
15.5 dynamic bayesian networks  
15.6 keeping track of many objects  
15.7 summary, bibliographical and historical notes, exercises  
16 making simple decisions  
16.1 combining beliefs and desires under uncertainty  
16.2 the basis of utility theory  
16.3 utility functions  
16.4 multiattribute utility functions  
16.5 decision networks  
16.6 the value of information  
16.7 decision-theoretic expert systems  
16.8 summary, bibliographical and historical notes, exercises  
17 making complex decisions  
17.1 sequential decision problems  
17.2 value iteration  
17.3 policy iteration  
17.4 partially observable mdps  
17.5 decisions with multiple agents: game theory  
17.6 mechanism design  
17.7 summary, bibliographical and historical notes, exercises  
V learning  
18 learning from examples  
18.1 forms of learning  
18.2 supervised learning  
18.3 leaming decision trees  
18.4 evaluating and choosing the best hypothesis  
18.5 the theory of learning  
18.6 regression and classification with linear models  
18.7 artificial neural networks  
18.8 nonparametric models  
18.9 support vector machines  
18.10 ensemble learning  
18.11 practical machine learning  
18.12 summary, bibliographical and historical notes, exercises  
19 knowledge in learning  
19.1 a logical formulation of learning  
19.2 knowledge in learning  
19.3 explanation-based learning  
19.4 learning using relevance information  
19.5 inductive logic programming  
19.6 summary, bibliographical and historical notes, exercis  
20 learning probabilistic models  
20.1 statistical learning  
20.2 learning with complete data  
20.3 learning with hidden variables: the em algorithm.  
20.4 summary, bibliographical and historical notes, exercis  
21 reinforcement learning  
21. l introduction  
21.2 passive reinforcement learning  
21.3 active reinforcement learning  
21.4 generalization in reinforcement learning  
21.5 policy search  
21.6 applications of reinforcement learning  
21.7 summary, bibliographical and historical notes, exercis  
VI communicating, perceiving, and acting  
22 natural language processing  
22.1 language models  
22.2 text classification  
22.3 information retrieval  
22.4 information extraction  
22.5 summary, bibliographical and historical notes, exercis  
23 natural language for communication  
23.1 phrase structure grammars  
23.2 syntactic analysis (parsing)  
23.3 augmented grammars and semantic interpretation  
23.4 machine translation  
23.5 speech recognition  
23.6 summary, bibliographical and historical notes, exercis  
24 perception  
24.1 image formation  
24.2 early image-processing operations  
24.3 object recognition by appearance  
24.4 reconstructing the 3d world  
24.5 object recognition from structural information  
24.6 using vision  
24.7 summary, bibliographical and historical notes, exercises  
25 robotics  
25.1 introduction  
25.2 robot hardware  
25.3 robotic perception  
25.4 planning to move  
25.5 planning uncertain movements  
25.6 moving  
25.7 robotic software architectures  
25.8 application domains  
25.9 summary, bibliographical and historical notes, exercises  
VII conclusions  
26 philosophical foundations  
26.1 weak ai: can machines act intelligently?  
26.2 strong ai: can machines really think?  
26.3 the ethics and risks of developing artificial intelligence  
26.4 summary, bibliographical and historical notes, exercises  
27 al: the present and future  
27.1 agent components  
27.2 agent architectures  
27.3 are we going in the right direction?  
27.4 what if ai does succeed?  
a mathematical background  
a. 1complexity analysis and o0 notation  
a.2 vectors, matrices, and linear algebra  
a.3 probability distributions  
b notes on languages and algorithms  
b.1defining languages with backus-naur form (bnf)  
b.2describing algorithms with pseudocode  
b.3online help  
bibliography  
index