O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Artificial Intelligence

Book Description

Intelligent agents are employed as the central characters in this new introductory text. Beginning with elementary reactive agents, Nilsson gradually increases their cognitive horsepower to illustrate the most important and lasting ideas in AI. Neural networks, genetic programming, computer vision, heuristic search, knowledge representation and reasoning, Bayes networks, planning, and language understanding are each revealed through the growing capabilities of these agents. The book provides a refreshing and motivating new synthesis of the field by one of AI's master expositors and leading researchers. Artificial Intelligence: A New Synthesis takes the reader on a complete tour of this intriguing new world of AI.

  • An evolutionary approach provides a unifying theme
  • Thorough coverage of important AI ideas, old and new
  • Frequent use of examples and illustrative diagrams
  • Extensive coverage of machine learning methods throughout the text
  • Citations to over 500 references
  • Comprehensive index

Table of Contents

  1. Cover image
  2. Title page
  3. Table of Contents
  4. Copyright
  5. Dedication
  6. Preface
  7. 1. Introduction
    1. 1.1 What Is AI?
    2. 1.2 Approaches to Artificial Intelligence
    3. 1.3 Brief History of AI
    4. 1.4 Plan of the Book
    5. 1.5 Additional Readings and Discussion
    6. Exercises
  8. I: Reactive Machines
    1. Introduction to Reactive Machines
    2. 2. Stimulus–Response Agents
      1. 2.1 Perception and Action
      2. 2.2 Representing and Implementing Action Functions
      3. 2.3 Additional Readings and Discussion
      4. Exercises
    3. 3. Neural Networks
      1. 3.1 Introduction
      2. 3.2 Training Single TLUs
      3. 3.3 Neural Networks
      4. 3.4 Generalization, Accuracy, and Overfitting
      5. 3.5 Additional Readings and Discussion
      6. Exercises
    4. 4. Machine Evolution
      1. 4.1 Evolutionary Computation
      2. 4.2 Genetic Programming
      3. 4.3 Additional Readings and Discussion
      4. Exercises
    5. 5. State Machines
      1. 5.1 Representing the Environment by Feature Vectors
      2. 5.2 Elman Networks
      3. 5.3 Iconic Representations
      4. 5.4 Blackboard Systems
      5. 5.5 Additional Readings and Discussion
      6. Exercises
    6. 6. Robot Vision
      1. 6.1 Introduction
      2. 6.2 Steering an Automobile
      3. 6.3 Two Stages of Robot Vision
      4. 6.4 Image Processing
      5. 6.5 Scene Analysis
      6. 6.6 Stereo Vision and Depth Information
      7. 6.7 Additional Readings and Discussion
      8. Exercises
  9. II: Search in State Spaces
    1. Introduction to Search in State Spaces
    2. 7. Agents That Plan
      1. 7.1 Memory Versus Computation
      2. 7.2 State-Space Graphs
      3. 7.3 Searching Explicit State Spaces
      4. 7.4 Feature-Based State Spaces
      5. 7.5 Graph Notation
      6. 7.6 Additional Readings and Discussion
      7. Exercises
    3. 8. Uninformed Search
      1. 8.1 Formulating the State Space
      2. 8.2 Components of Implicit State-Space Graphs
      3. 8.3 Breadth-First Search
      4. 8.4 Depth-First or Backtracking Search
      5. 8.5 Iterative Deepening
      6. 8.6 Additional Readings and Discussion
      7. Exercises
    4. 9. Heuristic Search
      1. 9.1 Using Evaluation Functions
      2. 9.2 A General Graph-Searching Algorithm
      3. 9.3 Heuristic Functions and Search Efficiency
      4. 9.4 Additional Readings and Discussion
      5. Exercises
    5. 10. Planning, Acting, and Learning
      1. 10.1 The Sense/Plan/Act Cycle
      2. 10.2 Approximate Search
      3. 10.3 Learning Heuristic Functions
      4. 10.4 Rewards Instead of Goals
      5. 10.5 Additional Readings and Discussion
      6. Exercises
    6. 11. Alternative Search Formulations and Applications
      1. 11.1 Assignment Problems
      2. 11.2 Constructive Methods
      3. 11.3 Heuristic Repair
      4. 11.4 Function Optimization
      5. Exercises
    7. 12. Adversarial Search
      1. 12.1 Two-Agent Games
      2. 12.2 The Minimax Procedure
      3. 12.3 The Alpha-Beta Procedure
      4. 12.4 The Search Efficiency of the Alpha-Beta Procedure
      5. 12.5 Other Important Matters
      6. 12.6 Games of Chance
      7. 12.7 Learning Evaluation Functions
      8. 12.8 Additional Readings and Discussion
      9. Exercises
  10. III: Knowledge Representation and Reasoning
    1. Introduction to Knowledge Representation and Reasoning
    2. 13. The Propositional Calculus
      1. 13.1 Using Constraints on Feature Values
      2. 13.2 The Language
      3. 13.3 Rules of Inference
      4. 13.4 Definition of Proof
      5. 13.5 Semantics
      6. 13.6 Soundness and Completeness
      7. 13.7 The PSAT Problem
      8. 13.8 Other Important Topics
      9. Exercises
    3. 14. Resolution in the Propositional Calculus
      1. 14.1 A New Rule of Inference: Resolution
      2. 14.2 Converting Arbitrary wffs to Conjunctions of Clauses
      3. 14.3 Resolution Refutations
      4. 14.4 Resolution Refutation Search Strategies
      5. 14.5 Horn Clauses
      6. Exercises
    4. 15. The Predicate Calculus
      1. 15.1 Motivation
      2. 15.2 The Language and Its Syntax
      3. 15.3 Semantics
      4. 15.4 Quantification
      5. 15.5 Semantics of Quantifiers
      6. 15.6 Predicate Calculus as a Language for Representing Knowledge
      7. 15.7 Additional Readings and Discussion
      8. Exercises
    5. 16. Resolution in the Predicate Calculus
      1. 16.1 Unification
      2. 16.2 Predicate-Calculus Resolution
      3. 16.3 Completeness and Soundness
      4. 16.4 Converting Arbitrary wffs to Clause Form
      5. 16.5 Using Resolution to Prove Theorems
      6. 16.6 Answer Extraction
      7. 16.7 The Equality Predicate
      8. 16.8 Additional Readings and Discussion
      9. Exercises
    6. 17. Knowledge–Based Systems
      1. 17.1 Confronting the Real World
      2. 17.2 Reasoning Using Horn Clauses
      3. 17.3 Maintenance in Dynamic Knowledge Bases
      4. 17.4 Rule-Based Expert Systems
      5. 17.5 Rule Learning
      6. 17.6 Additional Readings and Discussion
      7. Exercises
    7. 18. Representing Commonsense Knowledge
      1. 18.1 The Commonsense World
      2. 18.2 Time
      3. 18.3 Knowledge Representation by Networks
      4. 18.4 Additional Readings and Discussion
      5. Exercises
    8. 19. Reasoning with Uncertain Information
      1. 19.1 Review of Probability Theory
      2. 19.2 Probabilistic Inference
      3. 19.3 Bayes Networks
      4. 19.4 Patterns of Inference in Bayes Networks
      5. 19.5 Uncertain Evidence
      6. 19.6 D-Separation
      7. 19.7 Probabilistic Inference in Polytrees
      8. 19.8 Additional Readings and Discussion
      9. Exercises
    9. 20. Learning and Acting with Bayes Nets
      1. 20.1 Learning Bayes Nets
      2. 20.2 Probabilistic Inference and Action
      3. 20.3 Additional Readings and Discussion
      4. Exercises
  11. IV: Planning Methods Based on Logic
    1. Introduction to Planning Methods Based on Logic
    2. 21. The Situation Calculus
      1. 21.1 Reasoning about States and Actions
      2. 21.2 Some Difficulties
      3. 21.3 Generating Plans
      4. 21.4 Additional Readings and Discussion
      5. Exercises
    3. 22. Planning
      1. 22.1 STRIPS Planning Systems
      2. 22.2 Plan Spaces and Partial-Order Planning
      3. 22.3 Hierarchical Planning
      4. 22.4 Learning Plans
      5. 22.5 Additional Readings and Discussion
      6. Exercises
  12. V: Communication and Integration
    1. Introduction to Communication and Integration
    2. 23. Multiple Agents
      1. 23.1 Interacting Agents
      2. 23.2 Models of Other Agents
      3. 23.3 A Modal Logic of Knowledge
      4. 23.4 Additional Readings and Discussion
      5. Exercises
    3. 24. Communication among Agents
      1. 24.1 Speech Acts
      2. 24.2 Understanding Language Strings
      3. 24.3 Efficient Communication
      4. 24.4 Natural Language Processing
      5. 24.5 Additional Readings and Discussion
      6. Exercises
    4. 25. Agent Architectures
      1. 25.1 Three-Level Architectures
      2. 25.2 Goal Arbitration
      3. 25.3 The Triple-Tower Architecture
      4. 25.4 Bootstrapping
      5. 25.5 Additional Readings and Discussion
      6. Exercises
  13. Bibliography
  14. Index