Contents:I. Artificial Intelligence1. Introduction1.1 What is AI?1.2 The Foundations of Artificial Intelligence1.3 The History of Artificial Intelligence1.4 The State of the Art1.5 Summary, Bibliographical and Historical Notes, Exercises2. Intelligent Agents2.1 Agents and Environments2.2 Good Behavior: The Concept of Rationality2.3 The Nature of Environments2.4 The Structure of Agents2.5 Summary, Bibliographical and Historical Notes, ExercisesII. Problem-solving3. Solving Problems by Searching 3.1 Problem-Solving Agents3.2 Example Problems3.3 Searching for Solutions3.4 Uninformed Search Strategies3.5 Informed (Heuristic) Search Strategies3.6 Heuristic Functions3.7 Summary, Bibliographical and Historical Notes, Exercises4. Beyond Classical Search 4.1 Local Search Algorithms and Optimization Problems4.2 Local Search in Continuous Spaces4.3 Searching with Nondeterministic Actions4.4 Searching with Partial Observations4.5 Online Search Agents and Unknown Environments4.6 Summary, Bibliographical and Historical Notes, Exercises5. Adversarial Search5.1 Games5.2 Optimal Decisions in Games5.3 Alpha-Beta Pruning5.4 Imperfect Real-Time Decisions5.5 Stochastic Games5.6 Partially Observable Games5.7 State-of-the-Art Game Programs5.8 Alternative Approaches5.9 Summary, Bibliographical and Historical Notes, Exercises6. Constraint Satisfaction Problems6.1 Defining Constraint Satisfaction Problems6.2 Constraint Propagation: Inference in CSPs6.3 Backtracking Search for CSPs6.4 Local Search for CSPs6.5 The Structure of Problems6.6 Summary, Bibliographical and Historical Notes, ExercisesIII. Knowledge, Reasoning, and Planning7. Logical Agents 7.1 Knowledge-Based Agents7.2 The Wumpus World7.3 Logic7.4 Propositional Logic: A Very Simple Logic7.5 Propositional Theorem Proving7.6 Effective Propositional Model Checking7.7 Agents Based on Propositional Logic7.8 Summary, Bibliographical and Historical Notes, Exercises8. First-Order Logic 8.1 Representation Revisited8.2 Syntax and Semantics of First-Order Logic8.3 Using First-Order Logic8.4 Knowledge Engineering in First-Order Logic8.5 Summary, Bibliographical and Historical Notes, Exercises9. Inference in First-Order Logic9.1 Propositional vs. First-Order Inference9.2 Unification and Lifting9.3 Forward Chaining9.4 Backward Chaining9.5 Resolution9.6 Summary, Bibliographical and Historical Notes, Exercises10. Classical Planning10.1 Definition of Classical Planning10.2 Algorithms for Planning as State-Space Search10.3 Planning Graphs10.4 Other Classical Planning Approaches10.5 Analysis of Planning Approaches10.6 Summary, Bibliographical and Historical Notes, Exercises11. Planning and Acting in the Real World11.1 Time, Schedules, and Resources11.2 Hierarchical Planning11.3 Planning and Acting in Nondeterministic Domains11.4 Multiagent Planning11.5 Summary, Bibliographical and Historical Notes, Exercises12 Knowledge Representation 12.1 Ontological Engineering12.2 Categories and Objects12.3 Events12.4 Mental Events and Mental Objects12.5 Reasoning Systems for Categories12.6 Reasoning with Default Information12.7 The Internet Shopping World12.8 Summary, Bibliographical and Historical Notes, ExercisesIV. Uncertain Knowledge and Reasoning13. Quantifying Uncertainty 13.1 Acting under Uncertainty13.2 Basic Probability Notation13.3 Inference Using Full Joint Distributions13.4 Independence13.5 Bayes' Rule and Its Use13.6 The Wumpus World Revisited13.7 Summary, Bibliographical and Historical Notes, Exercises14. Probabilistic Reasoning14.1 Representing Knowledge in an Uncertain Domain14.2 The Semantics of Bayesian Networks14.3 Efficient Representation of Conditional Distributions14.4 Exact Inference in Bayesian Networks14.5 Approximate Inference in Bayesian Networks14.6 Relational and First-Order Probability Models14.7 Other Approaches to Uncertain Reasoning14.8 Summary, Bibliographical and Historical Notes, Exercises15. Probabilistic Reasoning over Time 15.1 Time and Uncertainty15.2 Inference in Temporal Models15.3 Hidden Markov Models15.4 Kalman Filters15.5 Dynamic Bayesian Networks15.6 Keeping Track of Many Objects15.7 Summary, Bibliographical and Historical Notes, Exercises16. Making Simple Decisions 16.1 Combining Beliefs and Desires under Uncertainty16.2 The Basis of Utility Theory16.3 Utility Functions16.4 Multiattribute Utility Functions16.5 Decision Networks16.6 The Value of Information16.7 Decision-Theoretic Expert Systems16.8 Summary, Bibliographical and Historical Notes, Exercises17. Making Complex Decisions 17.1 Sequential Decision Problems17.2 Value Iteration17.3 Policy Iteration17.4 Partially Observable MDPs17.5 Decisions with Multiple Agents: Game Theory17.6 Mechanism Design17.7 Summary, Bibliographical and Historical Notes, ExercisesV. Learning18. Learning from Examples 18.1 Forms of Learning18.2 Supervised Learning18.3 Learning Decision Trees18.4 Evaluating and Choosing the Best Hypothesis18.5 The Theory of Learning18.6 Regression and Classification with Linear Models18.7 Artificial Neural Networks18.8 Nonparametric Models18.9 Support Vector Machines18.10 Ensemble Learning18.11 Practical Machine Learning18.12 Summary, Bibliographical and Historical Notes, Exercises19. Knowledge in Learning 19.1 A Logical Formulation of Learning19.2 Knowledge in Learning19.3 Explanation-Based Learning19.4 Learning Using Relevance Information19.5 Inductive Logic Programming19.6 Summary, Bibliographical and Historical Notes, Exercises20. Learning Probabilistic Models20.1 Statistical Learning20.2 Learning with Complete Data20.3 Learning with Hidden Variables: The EM Algorithm20.4 Summary, Bibliographical and Historical Notes, Exercises21. Reinforcement Learning 21.1 Introduction21.2 Passive Reinforcement Learning21.3 Active Reinforcement Learning21.4 Generalization in Reinforcement Learning21.5 Policy Search21.6 Applications of Reinforcement Learning21.7 Summary, Bibliographical and Historical Notes, ExercisesVI. Communicating, Perceiving, and Acting22. Natural Language Processing 22.1 Language Models22.2 Text Classification22.3 Information Retrieval22.4 Information Extraction22.5 Summary, Bibliographical and Historical Notes, Exercises23. Natural Language for Communication 23.1 Phrase Structure Grammars23.2 Syntactic Analysis (Parsing)23.3 Augmented Grammars and Semantic Interpretation23.4 Machine Translation23.5 Speech Recognition23.6 Summary, Bibliographical and Historical Notes, Exercises24. Perception 24.1 Image Formation24.2 Early Image-Processing Operations24.3 Object Recognition by Appearance24.4 Reconstructing the 3D World24.5 Object Recognition from Structural Information24.6 Using Vision24.7 Summary, Bibliographical and Historical Notes, Exercises25. Robotics25.1 Introduction25.2 Robot Hardware25.3 Robotic Perception25.4 Planning to Move25.5 Planning Uncertain Movements25.6 Moving25.7 Robotic Software Architectures25.8 Application Domains25.9 Summary, Bibliographical and Historical Notes, ExercisesVII. Conclusions26 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 Intelligence26.4 Summary, Bibliographical and Historical Notes, Exercises27. AI: The Present and Future27.1 Agent Components27.2 Agent Architectures27.3 Are We Going in the Right Direction?27.4 What If AI Does Succeed?AppendicesA. Mathematical Background A.1 Complexity Analysis and O() NotationA.2 Vectors, Matrices, and Linear AlgebraA.3 Probability DistributionsB. Notes on Languages and Algorithms B.1 Defining Languages with Backus-Naur Form (BNF)B.2 Describing Algorithms with PseudocodeB.3 Online HelpBibliographyIndex
There are no comments on this title.