Wikiwand AI

Talk:Artificial intelligence/Textbook survey

From Wikipedia, the free encyclopedia

This is a survey of major AI textbooks and a few academic course listings, designed to determine for Wikipedia what topics are essential to an introduction to artificial intelligence. This is intended to help the central articles about artificial intelligence to pass the featured article criteria. It should be noted that there is a great deal of consensus among experts on what subjects constitute the whole field of AI research.

Textbooks

These are listed on the list of textbooks at AI Topics, which also lists their relative popularity. These are the four most popular textbooks published since 1998 (i.e. in the ten years before this survey was done.)

Russell & Norvig (standard AI textbook)

Russell, Stuart J.; Norvig, Peter (2003), Artificial Intelligence: A Modern Approach (2nd ed.), Upper Saddle River, New Jersey: Prentice Hall, ISBN 0-13-790395-2 Chapters:

  • 1 Introduction History of AI, some philosophy of AI
  • 2 Intelligent agent paradigm
  • 3-6 Search
  • 7-9 Logic
  • 10 Knowledge representation
  • 11-12 Planning
  • 13-17 Uncertain reasoning
  • 18-21 Learning
  • 22-23 Natural language processing (they call "communication")
  • 24 Perception
  • 25 Robotics
  • 26 Philosophy of AI
  • 27 future of AI

Nilsson

Nilsson, Nils (1998), Artificial Intelligence: A New Synthesis, Morgan Kaufmann Publishers, ISBN 978-1-55860-467-4

1 Introduction

I Reactive Machines

2 Stimulus-Response Agents
3 Neural Networks
4 Machine Evolution
5 State Machines
6 Robot Vision

II Search in State Spaces

7-9 search, uninformed, heuristic
10 Planning, Acting, and Learning chapter is actually mostly about search, I think...
11 Alternative Search Formulations and Applications
12 Adversarial Search

III Knowledge Representation and Reasoning

13-16 The Propositional, Predicate Calculus and resolution
17 Knowledge-Based Systems
18 Representing Commonsense Knowledge
19 Reasoning with Uncertain Information
20 Learning and Acting with Bayes Nets

IV Planning Method Based on Logic

21 The Situation Calculus
22 Planning

V Communication and Integration

23 Multiple Agents
24 Communication Among Agents Natural Language Processing
25 Agent Architectures

Luger & Stubblefield

  • Luger, George; Stubblefield, William (2004), Artificial Intelligence: Structures and Strategies for Complex Problem Solving (5th ed.), The Benjamin/Cummings Publishing Company, Inc., p. 720, ISBN 0-8053-4780-1
  • 1 ARTIFICIAL INTELLIGENCE: ITS ROOTS AND SCOPE 1
  • 2 THE PREDICATE CALCULUS 45
  • 3-4 STRUCTURES AND STRATEGIES FOR STATE SPACE SEARCH 79 (including Hill Climbing and Dynamic Programming)
  • 5 STOCHASTIC METHODS 165
  • 6 CONTROL AND IMPLEMENTATION OF STATE SPACE SEARCH 193
  • 7 KNOWLEDGE REPRESENTATION 227
  • 8 STRONG METHOD PROBLEM SOLVING (Expert systems) 277
  • 9 REASONING IN UNCERTAIN SITUATIONS 333
  • 10-12 MACHINE LEARNING: SYMBOL-BASED 387 / CONNECTIONIST 453 / SOCIAL AND EMERGENT 507 (including: Genetic, classifier, artificial life)
  • 13 AUTOMATED REASONING 547
  • 14 UNDERSTANDING NATURAL LANGUAGE 591
  • 15 PROLOG 636
  • 16 AN INTRODUCTION TO LISP 723
  • 17 ARTIFICIAL INTELLIGENCE AS EMPIRICAL ENQUIRY 823

Poole & Macworth

Poole, David; Mackworth, Alan; Goebel, Randy (1998), Computational Intelligence: A Logical Approach, Oxford University Press {{citation}}: Unknown parameter |publisher-place= ignored (help)

  • Chapter 1 Computational Intelligence and Knowledge introduction
  • Chapter 2 A Representation and Reasoning System forward and backward chaining
  • Chapter 3 Using Definite Knowledge includes databases and natural language
  • Chapter 4 Searching includes standard state space searches, dynamic programming, constraint satisfation, hill climbing, "randomization algortihms" and genetic algorithms
  • Chapter 5 Representing Knowledge
  • Chapter 6 Knowledge Engineering,
  • Chapter 7 Beyond Definite Knowledge includes first order logic, proof systems
  • Chapter 8 Actions and Planning
  • Chapter 9 Assumption-Based Reasoning, default reasoning, abduction
  • Chapter 10 Using Uncertain Knowledge
  • Chapter 11 Learning
  • Chapter 12 Building Situated Robots

Other textbooks

Rich & Knight

Rich, Elaine (1991), Artificial Intelligence (2nd ed.), New York: McGraw-Hill, ISBN 0-07-052263-4 {{citation}}: |first2= missing |last2= (help); Unknown parameter |laast2= ignored (help)

  • What is Artificial Intelligence?
  • Problems, Problem Spaces, and Search. Heuristic Search Techniques.
  • Knowledge Representation. Knowledge Representation Issues.
  • Using Predicate Logic. Representing Knowledge Using Rules.
  • Symbolic Reasoning Under Uncertainty. Statistical Reasoning.
  • Weak Slot-and-Filler Structures. Strong Slot-and-Filler Structures. Knowledge Representation Summary.
  • Game Playing.
  • Planning.
  • Understanding.
  • Natural Language Processing.
  • Parallel and Distributed AI.
  • Learning.
  • Connectionist Models.
  • Common Sense.
  • Expert Systems.
  • Perception and Action.
  • Conclusion.

Cawsey

Cawsey, Alison (1998), Essence of Artificial Intelligence, Prentice Hall, ISBN 0135717795

  • Introduction.
  • Knowledge Representation and Inference.
  • Expert Systems.
  • Using Search in Problem Solving.
  • Natural Language Processing.
  • Vision.
  • Machine Learning and Neural Networks.
  • Agents and Robots.

Murray

Murray, Arthur (2002), AI4U, iUniverse, ISBN 0595259227

  • Introduction.
  • 1-34 Modules of the AI Mind; Exercises.
  • JavaScript source code of the tutorial AI Mind.

Poole and Mackworth (2010)

Artificial Intelligence: Foundations of Computational Agents

I Agents in the World: What Are Agents and How Can They Be Built?
1 Artificial Intelligence and Agents
2 Agent Architectures and Hierarchical Control
II Representing and Reasoning
3 States and Searching
4 Features and Constraints
5 Propositions and Inference
6 Reasoning Under Uncertainty
III Learning and Planning
7 Learning: Overview and Supervised Learning
8 Planning with Certainty
9 Planning Under Uncertainty
10 Multiagent Systems
11 Beyond Supervised Learning
IV Reasoning About Individuals and Relations
12 Individuals and Relations
13 Ontologies and Knowledge-Based Systems
14 Relational Planning, Learning, and Probabilistic Reasoning
V The Big Picture
15 Retrospect and Prospect

Cambridge Handbook of Artificial Intelligence (2014)

Part I: Foundations
1. History, motivations, and core themes
2. Philosophical foundations
3. Philosophical challenges
Part II: Architectures
4. GOFAI
5. Connectionism and neural networks
6. Dynamical systems and embedded cognition
Part III: Dimensions
7. Learning
8. Perception and computer vision
9. Reasoning and decision making
10. Language and communication
11. Actions and agents
12. Artificial emotions and machine consciousness
Part IV: Extensions
13. Robotics
14. Artificial life
15. The ethics of artificial intelligence

ACM classification

ACM, (Association of Computing Machinery) (1998), ACM Computing Classification System: Artificial intelligence

  • I.2.0 General
  • I.2.1 Applications and Expert Systems (H.4, J) considered in this in the section "Applications"
  • I.2.2 Automatic Programming (D.1.2, F.3.1, F.4.1) not considered AI by wikipedia
  • I.2.3 Deduction and Theorem Proving (F.4.1)
  • I.2.4 Knowledge Representation Formalisms and Methods (F.4.1)
  • I.2.5 Programming Languages and Software (D.3.2)
  • I.2.6 Learning (K.3.2)
  • I.2.7 Natural Language Processing
  • I.2.8 Problem Solving, Control Methods, and Search (F.2.2) control theory, dynamic programming, search, planning & scheduling
  • I.2.9 Robotics
  • I.2.10 Vision and Scene Understanding (I.4.8, I.5)
  • I.2.11 Distributed Artificial Intelligence

Websites

Sloman

Sloman, Aaron (2007), Artificial intelligence: an illustrative overview, University of Birmingham

  • Perception
  • Natural language processing
  • Learning
  • Planning, problem solving, automatic design
  • Varieties of reasoning
  • Study of representations (knowledge representation)
  • Memory mechanisms and techniques
  • Multi agent systems
  • Affective mechanisms
  • Robotics
  • Architectures for complete systems.
  • Search
  • Ontologies

Leake

Leake, David B. (2002), "Artificial intelligence", Van Nostrand Scientific Encyclopedia (ninth ed.), New York: Wiley

  • Knowledge capture, representation and reasoning
  • Reasoning under uncertainty
  • Planning, Vision, and Robotics
  • Natural language processing
  • Machine Learning


Bringing it all together

This table lists (just about) every topic that appears in the title of a section or in a chapter summary of Russell & Norvig (2003), the most popular AI textbook. Information for the other textbooks is based on their tables of contents, available online. Several topics appear more than once, in different contexts.

More information Subject, ACM 1998 ...
SubjectACM 1998Russell & Norvig 2003Poole, Mackworth & Goebel 1998Luger & Stubblefield 2004Nilsson 1998
Defining AI and philosophy of AI[1] I.2.0pp. 1-5, 947-967pp. 1-6pp. 1-2, 30, ~823-848[2]~chpt. 1.1[2]
History of AI[3] pp. 5-28pp. 3-30chpt. 1.3
Approaches to AI[4] chpt. 1.2
Future of AI[5] pp. 968-974pp. 848-853
Intelligent agent paradigm[6] pp. 32-58, 968-972pp. 7-21pp. 235-240
Agent architecture)[7] I.2.11pp. 27, 932, 970-972chpt. 25
Search[8] ~I.2.8[2]pp. 59-189pp. 113-163pp. 79-164, 193-219chpt. 7-12
Standard searches (breadth first, depth first, backtracking, state space, graph, etc.)[9] pp. 59-93pp. 113-132pp. 79-121chpt. 8
Informed Heuristic searches (greedy best first, A*, dynamic programming, etc.)[10] pp. 94-109pp. 132-147pp. 133-150chpt. 9
Local search and optimization searches (hill climbing, simulated annealing, beam search, continuous search (i.e. Hessian matrix searches)), exploratory search ("online search" and random walk searches)[11] pp. 110-116,120-129pp. 56-163[12]pp. ~127-133[2]
Genetic algorithms[13] pp. 116-119pp. 162pp. 509-530chpt. 4.2
Constraint satisfaction[14] pp. 137-156pp. 147-163
Adversarial search (minimax, alpha-beta pruning, using utility)[15] pp. 161-185pp. 150-157chpt. 12
Logic[16] ~I.2.3[2]pp. 194-310variouspp. 35-77chpt. 13-16
Propositional logic[17] pp. 204-233variouspp. 45-50chpt. 13
First order logic (incl. equality)[18] ~I.2.4[2]pp. 240-310pp. 268-275pp. 50-62chpt. 15
Inference (and inference engine, production system, logic programming)[19] pp. 213-224, 272-310pp. 46-58pp. 62-73, 194-219, 547-589chpt. 14 & 16
Resolution and unification[20] pp. 213-217, 275-280, 295-306pp. 56-58pp. 554-575chpt. 14 & 16
Forward and backward chaining (also Horn clause): a form of search[21] pp. 217-225, 280-294pp. ~46-52[2]~chpt. 17.2[2]
Theorem provers[22] pp. 306-310
Truth maintenance systems[23] pp. 360-362
Knowledge representation[24] I.2.4pp. 320-363pp. 23-46, 69-81, 169-196, 235-277, 281-298, 319-345pp. 227-243chpt. 18
Ontology[25] pp. 320-328
Representing events and time: Situation calculus, event calculus, fluent calculus (including solving the frame problem)[26] pp. 328-341pp. 281-298chpt. 18.2
Representing knowledge about knowlege: Belief calculus, modal logics[27] pp. 341-344pp. 275-277
Representing categories and relations: Semantic networks, description logics, inheritance, (including the deprecated[28] concept of frames and scripts)[29] pp. 349-354pp. 174-177pp. 248-258chpt. 18.3
Default reasoning and default logic, non-monotonic logics, circumscription, closed world assumption, abduction[30][31] pp. 354-360pp. 248-256, 323-335pp. 335-363~chpt. 18.3.3[2]
Causal calculus[32] pp. 335-337
Knowledge engineering[33] pp. 260-266pp. 199-233~chpt. 17.1-17.4[2]
Knowledge acquisition: getting information from experts.[34] pp. 260pp. 212-217
Explanation[35] pp. 217-220
Planning[36] ~I.2.8[2]pp. 375-459pp. 281-316pp. 314-329chpt. 10 & 21
State space search and planning[37] pp. 382-387pp. 298-305chpt. 10
Partial order planning[38] pp. 387-395pp. 309-315
Graph planning[39] pp. 395-402
Planning with propositional logic (satplan)[40] pp. 402-407pp. 300-301chpt. 21
Hierarchical task network[41] pp. 422-430
Planning and acting in non-deterministic domains, conditional planning; search in the space of belief states, execution monitoring, replanning and continuous planning.[42] pp. 430-449
Multi-agent planning[43] pp. 449-455
Stochastic tools and uncertain reasoning.[44] ~I.2.3[2]pp. 462-644pp. 345-395pp. 165-191, 333-381chpt. 19
Probability[45] pp. 462-489pp. 346-366pp. ~165-182[2]chpt. 19.1
Bayesian networks[46] pp. 492-523pp. 361-381pp. ~182-190, ~363-379[2]chpt. 19.3-4, 19.7
Bayesian inference[47] pp. 504-519pp. 361-381pp. ~363-379[2]chpt. 19.4
Polytrees[48] chpt. 19.7
Deprecated methods for uncertain reasoning[28][49] pp. 523-528
Certainty factors[50] pp. 524-525
Dempster-Shafer theory: measuring ignorance[51] pp. 525-526
Fuzzy logic: degrees of truth[52] pp. 526-527
Temporal models (Markov property) used for filtering, prediction, smoothing and computing the most likely explanation[53] pp. 537-581
Hidden Markov models[54] pp. 549-551
Kalman filters[55] pp. 551-557
Dynamic Bayesian networks[56] pp. 551-557
Decision theory or decision analysis (= utility theory + probability theory)[57] pp. 584-604pp. 381-394
Bayesian Decision networks[58] pp. 597-600
Information value theory[59] pp. 600-604
Markov decision processes, and dynamic decision networks[60] pp. 613-631
Game theory and its "inverse", mechanism design[61] pp. 631-643
Learning (supervised (inductive) / unsupervised / reinforcement)[62] I.2.6pp. 649-788pp. 397-438pp. 385-542chpt. 3.3 , 10.3, 17.5, 20
Symbolic[63] pp. 653-736, 763-788pp. 387-450
Decision tree[64] pp. 653-664pp. 403-408pp. 408-417
Explanation based learning, relevance based learning, inductive logic programming, case based reasoning[65] pp. 678-710pp. 414-416pp. ~422-442[2]chpt. 10.3, 17.5
Statistical[66] pp. 712-754pp. 453-541
Reinforcement learning (uses elements of decision theory, like utility)[67] pp. 763-788pp. 442-449[68]
Bayesian learning, including expectation-maximization algorithm[69] pp. 712-724pp. 424-433chpt. 20
K-nearest neighbor algorithm[70] pp. 733-736
kernel methods[71] pp. 749-752
Connectionism and neural nets[72] pp. 736-748pp. 408-414pp. 453-505chpt. 3
Perceptron[73] pp. 740-743pp. 458-467
Backpropagation[74] pp. 744-748pp. 467-474chpt. 3.3
Competitive learning, Hebbian coincidence learning, Attractor networks[75] pp. 474-505
Social and emergent[76] pp. 507-542chpt. 4
Classifiers and genetic algorithms[77] pp. 509-530chpt. 4.2
Artificial life and society based learning[78] pp. 530-541
Natural language processing[79] I.2.7pp. 790-831pp. 91-104pp. 591-632
Syntax and parsing[80] pp. 795-810pp. 597-616
Semantics and disambiguation[81] pp. 810-821
Discourse understanding: coherence relations, speech acts, pragmatics[82] pp. 820-824
Probabilistic methods (learning)[83] pp. 834-840pp. 616-623
Applications[84] pp. 840-857pp. 623-630
Information retrieval and text mining[85] pp. 840-850
Machine translation[86] pp. 850-857
Perception[87] pp. 537-581, 863-898~chpt. 6[2]
Perception with stochastic temporal models[88] pp. 547-581
Hidden markov models[89] pp. 549-551
Kalman filters[90] pp. 551-559
Dynamic Bayesian networks[91] pp. 559-568
Speech recognition[92] ~I.2.7[2]pp. 568-578
Machine vision[93] I.2.10pp. 863-898chpt. 6
Robotics[94] I.2.9pp. 901-942pp. 443-460
Control theory[95] ~I.2.8[2]pp. 926-932
Specialized languages[96] I.2.5pp. 477-491pp. 641-821
Prolog[97] pp. 477-491pp. 641-676, 575-581
Lisp[98] p. 723-821
Applications of AI[99] I.2.1
Expert systems[100] I.2.1(several mentions)pp. 227-331chpt. 17.4
Automatic programming (other sources don't consider this AI)[101] I.2.2
Close

Notes

Related Articles

Timelines

Top Qs

Fact Checks