| Description |
xxviii, 792 pages : illustrations ; 27 cm |
| Contents |
Note continued: 13.6.2. Augmenting the Grammar -- 13.6.3. Building Structures for Non-terminals -- 13.6.4. Canned Text Output -- 13.6.5. Enforcing Constraints -- 13.6.6. Building a Natural Language Interface to a Database -- 13.6.7. Limitations -- 13.7. Equality -- 13.7.1. Allowing Equality Assertions -- 13.7.2. Unique Names Assumption -- 13.8. Complete Knowledge Assumption -- 13.8.1. Complete Knowledge Assumption Proof Procedures -- 13.9. Review -- 13.10. References and Further Reading -- 13.11. Exercises -- 14. Ontologies and Knowledge-Based Systems -- 14.1. Knowledge Sharing -- 14.2. Flexible Representations -- 14.2.1. Choosing Individuals and Relations -- 14.2.2. Graphical Representations -- 14.2.3. Classes -- 14.3. Ontologies and Knowledge Sharing -- 14.3.1. Uniform Resource Identifiers -- 14.3.2. Description Logic -- 14.3.3. Top-Level Ontologies -- 14.4. Implementing Knowledge-Based Systems -- 14.4.1. Base Languages and Metalanguages -- 14.4.2. A Vanilla Meta-Interpreter -- 14.4.3. Expanding the Base Language -- 14.4.4. Depth-Bounded Search -- 14.4.5. Meta-Interpreter to Build Proof Trees -- 14.4.6. Delaying Goals -- 14.5. Review -- 14.6. References and Further Reading -- 14.7. Exercises -- 15. Relational Planning, Learning, and Probabilistic Reasoning -- 15.1. Planning with Individuals and Relations -- 15.1.1. Situation Calculus -- 15.1.2. Event Calculus -- 15.2. Relational Learning -- 15.2.1. Structure Learning: Inductive Logic Programming -- 15.2.2. Learning Hidden Properties: Collaborative Filtering -- 15.3. Statistical Relational Artificial Intelligence -- 15.3.1. Relational Probabilistic Models -- 15.4. Review -- 15.5. References and Further Reading -- 15.6. Exercises -- 16. Retrospect and Prospect -- 16.1. Dimensions of Complexity Revisited -- 16.2. Social and Ethical Consequences -- 16.3. References and Further Reading -- 16.4. Exercises -- A.1. Discrete Mathematics -- A.2. Functions, Factors and Arrays -- A.3. Relations and the Relational Algebra |
|
Machine generated contents note: 1. Artificial Intelligence and Agents -- 1.1. What is Artificial Intelligence? -- 1.1.1. Artificial and Natural Intelligence -- 1.2. A Brief History of Artificial Intelligence -- 1.2.1. Relationship to Other Disciplines -- 1.3. Agents Situated in Environments -- 1.4. Designing Agents -- 1.4.1. Design Time, Offline and Online Computation -- 1.4.2. Tasks -- 1.4.3. Defining a Solution -- 1.4.4. Representations -- 1.5. Agent Design Space -- 1.5.1. Modularity -- 1.5.2. Planning Horizon -- 1.5.3. Representation -- 1.5.4. Computational Limits -- 1.5.5. Learning -- 1.5.6. Uncertainty -- 1.5.7. Preference -- 1.5.8. Number of Agents -- 1.5.9. Interaction -- 1.5.10. Interaction of the Dimensions -- 1.6. Prototypical Applications -- 1.6.1. An Autonomous Delivery Robot -- 1.6.2. A Diagnostic Assistant -- 1.6.3. An Intelligent Tutoring System -- 1.6.4. A Trading Agent -- 1.6.5. Smart House -- 1.7. Overview of the Book -- 1.8. Review -- 1.9. References and Further Reading -- 1.10. Exercises -- 2. Agent Architectures and Hierarchical Control -- 2.1. Agents -- 2.2. Agent Systems -- 2.2.1. The Agent Function -- 2.3. Hierarchical Control -- 2.4. Acting with Reasoning -- 2.4.1. Agents Modeling the World -- 2.4.2. Knowledge and Acting -- 2.4.3. Design Time and Offline Computation -- 2.4.4. Online Computation -- 2.5. Review -- 2.6. References and Further Reading -- 2.7. Exercises -- 3. Searching for Solutions -- 3.1. Problem Solving as Search -- 3.2. State Spaces -- 3.3. Graph Searching -- 3.3.1. Formalizing Graph Searching -- 3.4. A Generic Searching Algorithm -- 3.5. Uninformed Search Strategies -- 3.5.1. Breadth-First Search -- 3.5.2. Depth-First Search -- 3.5.3. Iterative Deepening -- 3.5.4. Lowest-Cost-First Search -- 3.6. Heuristic Search -- 3.6.1. A Search -- 3.6.2. Designing a Heuristic Function -- 3.7. Pruning the Search Space -- 3.7.1. Cycle Pruning -- 3.7.2. Multiple-Path Pruning -- 3.7.3. Summary of Search Strategies -- 3.8. More Sophisticated Search -- 3.8.1. Branch and Bound -- 3.8.2. Direction of Search -- 3.8.3. Dynamic Programming -- 3.9. Review -- 3.10. References and Further Reading -- 3.11. Exercises -- 4. Reasoning with Constraints -- 4.1. Possible Worlds, Variables, and Constraints -- 4.1.1. Variables and Worlds -- 4.1.2. Constraints -- 4.1.3. Constraint Satisfaction Problems -- 4.2. Generate-and-Test Algorithms -- 4.3. Solving CSPs Using Search -- 4.4. Consistency Algorithms -- 4.5. Domain Splitting -- 4.6. Variable Elimination -- 4.7. Local Search -- 4.7.1. Iterative Best Improvement -- 4.7.2. Randomized Algorithms -- 4.7.3. Local Search Variants -- 4.7.4. Evaluating Randomized Algorithms -- 4.7.5. Random Restart -- 4.8. Population-Based Methods -- 4.9. Optimization -- 4.9.1. Systematic Methods for Optimization -- 4.9.2. Local Search for Optimization -- 4.10. Review -- 4.11. References and Further Reading -- 4.12. Exercises -- 5. Propositions and Inference -- 5.1. Propositions -- 5.1.1. Syntax of Propositional Calculus -- 5.1.2. Semantics of the Propositional Calculus -- 5.2. Propositional Constraints -- 5.2.1. Clausal Form for Consistency Algorithms -- 5.2.2. Exploiting Propositional Structure in Local Search -- 5.3. Propositional Definite Clauses -- 5.3.1. Questions and Answers -- 5.3.2. Proofs -- 5.4. Knowledge Representation Issues -- 5.4.1. Background Knowledge and Observations -- 5.4.2. Querying the User -- 5.4.3. Knowledge-Level Explanation -- 5.4.4. Knowledge-Level Debugging -- 5.5. Proving by Contradiction -- 5.5.1. Horn Clauses -- 5.5.2. Assumables and Conflicts -- 5.5.3. Consistency-Based Diagnosis -- 5.5.4. Reasoning with Assumptions and Horn Clauses -- 5.6. Complete Knowledge Assumption -- 5.6.1. Non-monotonic Reasoning -- 5.6.2. Proof Procedures for Negation as Failure -- 5.7. Abduction -- 5.8. Causal Models -- 5.9. Review -- 5.10. References and Further Reading -- 5.11. Exercises -- 6. Planning with Certainty -- 6.1. Representing States, Actions, and Goals -- 6.1.1. Explicit State-Space Representation -- 6.1.2. The STRIPS Representation -- 6.1.3. Feature-Based Representation of Actions -- 6.1.4. Initial States and Goals -- 6.2. Forward Planning -- 6.3. Regression Planning -- 6.4. Planning as a CSP -- 6.4.1. Action Features -- 6.5. Partial-Order Planning -- 6.6. Review -- 6.7. References and Further Reading -- 6.8. Exercises -- 7. Supervised Machine Learning -- 7.1. Learning Issues -- 7.2. Supervised Learning -- 7.2.1. Evaluating Predictions -- 7.2.2. Types of Errors -- 7.2.3. Point Estimates with No Input Features -- 7.3. Basic Models for Supervised Learning -- 7.3.1. Learning Decision Trees -- 7.3.2. Linear Regression and Classification -- 7.4. Overfitting -- 7.4.1. Pseudocounts -- 7.4.2. Regularization -- 7.4.3. Cross Validation -- 7.5. Neural Networks and Deep Learning -- 7.6. Composite Models -- 7.6.1. Random Forests -- 7.6.2. Ensemble Learning -- 7.7. Case-Based Reasoning -- 7.8. Learning as Refining the Hypothesis Space -- 7.8.1. Version-Space Learning -- 7.8.2. Probably Approximately Correct Learning -- 7.9. Review -- 7.10. References and Further Reading -- 7.11. Exercises -- 8. Reasoning with Uncertainty -- 8.1. Probability -- 8.1.1. Semantics of Probability -- 8.1.2. Axioms for Probability -- 8.1.3. Conditional Probability -- 8.1.4. Expected Values -- 8.1.5. Information -- 8.2. Independence -- 8.3. Belief Networks -- 8.3.1. Observations and Queries -- 8.3.2. Constructing Belief Networks -- 8.4. Probabilistic Inference -- 8.4.1. Variable Elimination for Belief Networks -- 8.4.2. Representing Conditional Probabilities and Factors -- 8.5. Sequential Probability Models -- 8.5.1. Markov Chains -- 8.5.2. Hidden Markov Models -- 8.5.3. Algorithms for Monitoring and Smoothing -- 8.5.4. Dynamic Belief Networks -- 8.5.5. Time Granularity -- 8.5.6. Probabilistic Models of Language -- 8.6. Stochastic Simulation -- 8.6.1. Sampling from a Single Variable -- 8.6.2. Forward Sampling in Belief Networks -- 8.6.3. Rejection Sampling -- 8.6.4. Likelihood Weighting -- 8.6.5. Importance Sampling -- 8.6.6. Particle Filtering -- 8.6.7. Markov Chain Monte Carlo -- 8.7. Review -- 8.8. References and Further Reading -- 8.9. Exercises -- 9. Planning with Uncertainty -- 9.1. Preferences and Utility -- 9.1.1. Axioms for Rationality -- 9.1.2. Factored Utility -- 9.1.3. Prospect Theory -- 9.2. One-Off Decisions -- 9.2.1. Single-Stage Decision Networks -- 9.3. Sequential Decisions -- 9.3.1. Decision Networks -- 9.3.2. Policies -- 9.3.3. Variable Elimination for Decision Networks -- 9.4. The Value of Information and Control -- 9.5. Decision Processes -- 9.5.1. Policies -- 9.5.2. Value Iteration -- 9.5.3. Policy Iteration -- 9.5.4. Dynamic Decision Networks -- 9.5.5. Partially Observable Decision Processes -- 9.6. Review -- 9.7. References and Further Reading -- 9.8. Exercises -- 10. Learning with Uncertainty -- 10.1. Probabilistic Learning -- 10.1.1. Learning Probabilities -- 10.1.2. Probabilistic Classifiers -- 10.1.3. MAP Learning of Decision Trees -- 10.1.4. Description Length -- 10.2. Unsupervised Learning -- 10.2.1. k-Means -- 10.2.2. Expectation Maximization for Soft Clustering -- 10.3. Learning Belief Networks -- 10.3.1. Learning the Probabilities -- 10.3.2. Hidden Variables -- 10.3.3. Missing Data -- 10.3.4. Structure Learning -- 10.3.5. General Case of Belief Network Learning -- 10.4. Bayesian Learning -- 10.5. Review -- 10.6. References and Further Reading -- 10.7. Exercises -- 11. Multiagent Systems -- 11.1. Multiagent Framework -- 11.2. Representations of Games -- 11.2.1. Normal Form Games -- 11.2.2. Extensive Form of a Game -- 11.2.3. Multiagent Decision Networks -- 11.3. Computing Strategies with Perfect Information -- 11.4. Reasoning with Imperfect Information -- 11.4.1. Computing Nash Equilibria -- 11.5. Group Decision Making -- 11.6. Mechanism Design -- 11.7. Review -- 11.8. References and Further Reading -- 11.9. Exercises -- 12. Learning to Act -- 12.1. Reinforcement Learning Problem -- 12.2. Evolutionary Algorithms -- 12.3. Temporal Differences -- 12.4. Q-learning -- 12.5. Exploration and Exploitation -- 12.6. Evaluating Reinforcement Learning Algorithms -- 12.7. On-Policy Learning -- 12.8. Model-Based Reinforcement Learning -- 12.9. Reinforcement Learning with Features -- 12.9.1. SARSA with Linear Function Approximation -- 12.10. Multiagent Reinforcement Learning -- 12.10.1. Perfect-Information Games -- 12.10.2. Learning to Coordinate -- 12.11. Review -- 12.12. References and Further Reading -- 12.13. Exercises -- 13. Individuals and Relations -- 13.1. Exploiting Relational Structure -- 13.2. Symbols and Semantics -- 13.3. Datalog: A Relational Rule Language -- 13.3.1. Semantics of Ground Datalog -- 13.3.2. Interpreting Variables -- 13.3.3. Queries with Variables -- 13.4. Proofs and Substitutions -- 13.4.1. Instances and Substitutions -- 13.4.2. Bottom-up Procedure with Variables -- 13.4.3. Unification -- 13.4.4. Definite Resolution with Variables -- 13.5. Function Symbols -- 13.5.1. Proof Procedures with Function Symbols -- 13.6. Applications in Natural Language -- 13.6.1. Using Definite Clauses for Context-Free Grammars |
| Bibliography |
Includes bibliographical references (pages 751-771) and index |
| Subject |
Computational intelligence -- Textbooks
|
|
Artificial intelligence -- Textbooks
|
| Genre/Form |
Textbooks.
|
| Author |
Mackworth, Alan K., author.
|
| ISBN |
110719539X |
|
9781107195394 |
|
