正版 人工智能:一种现代的方法(第3版)大学计算机教育国外zhu名教材系列 人工智能理论和实践 计算机科技理论 正.

商品参数

书    名:人工智能：一种现代的方法（第3版）（大学计算机教育国外著名教材系列(影印版)）

作    者:（美）拉塞尔，（美）诺维格 著

I S B N (咨询特价)

出 版 社:清华大学出版社

出版时间:2011年7月第1版

印刷时间:2011年7月1日第1次印刷

字    数:字

页    数:1132页    

开    本:16开

包    装:平装

重    量: 克

原    价:(咨询特价)

编辑推荐

    《人工智能(一种现代的方法第3版影印版》(作者拉塞尔、诺维格)是“大学计算机教育国外著名教材系列”之一，是高等院校本科生和研究生人工智能课的**教材。全书仍分为八大部分：**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”。《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。

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 

(咨询特价) ensemble learning 

(咨询特价) practical machine learning 

(咨询特价) 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

内容推荐

    《人工智能(一种现代的方法第3版影印版》(作者拉塞尔、诺维格)是*权威、*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。

    《人工智能(一种现代的方法第3版影印版》的*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”。《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*前沿的进展，同时收集整理了详实的历史文献与事件。另外，《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。

    《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。