%{search_type} search results

• 1. Introduction
• 2. Intelligent Agents
• 3. Solving Problems by Searching
• 4. Search in Complex Environments
• 5. Adversarial Search and Games
• 6. Constraint Satisfaction Problems
• 7. Logical Agents
• 8. First-Order Logic
• 9. Inference in First-Order Logic
• 10. Knowledge Representation
• 11. Automated Planning
• 12. Quantifying Uncertainty
• 13. Probabilistic Reasoning
• 14. Probabilistic Reasoning over Time
• 15. Probabilistic Programming
• 16. Making Simple Decisions
• 17. Making Complex Decisions
• 18. Multiagent Decision Making
• 19. Learning from Examples
• 20. Learning Probabilistic Models
• 21. Deep Learning
• 22. Reinforcement Learning
• 23. Natural Language Processing
• 24. Deep Learning for Natural Language Processing
• 25. Robotics
• 26. Philosophy and Ethics of AI
• 27. The Future of AI.
• (source: Nielsen Book Data)

The most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence The long-anticipated revision of Artificial Intelligence: A Modern Approach explores the full breadth and depth of the field of artificial intelligence (AI). The 4th Edition brings readers up to date on the latest technologies, presents concepts in a more unified manner, and offers new or expanded coverage of machine learning, deep learning, transfer learning, multiagent systems, robotics, natural language processing, causality, probabilistic programming, privacy, fairness, and safe AI.
(source: Nielsen Book Data)

• If we succeed
• Intelligence in humans and machines
• How might AI progress in the future?
• Misuses of AI
• Overly intelligent AI
• The not-so-great AI debate
• AI : a different approach
• Provably beneficial AI
• Complications : us
• Problem solved?
• Searching for solutions
• Knowledge and logic
• Uncertainty and probability
• Learning from experience.

"In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is seen as inevitable and its outcome all too predictable. In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage. If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial. In a 2014 editorial co-authored with Stephen Hawking, Russell wrote, "Success in creating AI would be the biggest event in human history. Unfortunately, it might also be the last." Solving the problem of control over AI is not just possible; it is the key that unlocks a future of unlimited promise"-- Provided by publisher.

• If we succeed
• Intelligence in humans and machines
• How might AI progress in the future?
• Misuses of AI
• Overly intelligent AI
• The not-so-great AI debate
• AI : a different approach
• Provably beneficial AI
• Complications : us
• Problem solved?
• Appendix A. Searching for solutions
• Appendix B. Knowledge and logic
• Appendix C. Uncertainty and probability
• Appendix D. Learning from experience

"In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is seen as inevitable and its outcome all too predictable. In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage. If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial. In a 2014 editorial co-authored with Stephen Hawking, Russell wrote, "Success in creating AI would be the biggest event in human history. Unfortunately, it might also be the last." Solving the problem of control over AI is not just possible; it is the key that unlocks a future of unlimited promise"-- Provided by publisher

"In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is seen as inevitable and its outcome all too predictable. In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage. If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial. In a 2014 editorial co-authored with Stephen Hawking, Russell wrote, "Success in creating AI would be the biggest event in human history. Unfortunately, it might also be the last." Solving the problem of control over AI is not just possible; it is the key that unlocks a future of unlimited promise"-- Provided by publisher

• Introduction
• Intelligent agents
• Solving problems by searching
• Beyond classical search
• Adversarial search
• Constraint satisfaction problems
• Logical agents
• First-order logic
• Inference in first-order logic
• Classical planning
• Planning and acting in the real world
• Knowledge representation
• Quantifying uncertainty
• Probabilistic reasoning
• Probabilistic reasoning over time
• Making simple decisions
• Making complex decisions
• Learning from examples
• Knowledge in learning
• Learning probabilistic models
• Reinforcement learning
• Natural language processing
• Natural language for communication
• Perception
• Robotics
• Philosophical foundations
• AI : the present and future.

"In this third edition, the authors have updated the treatment of all major areas. A new organizing principle--the representational dimension of atomic, factored, and structured models--has been added. Significant new material has been provided in areas such as partially observable search, contingency planning, hierarchical planning, relational and first-order probability models, regularization and loss functions in machine learning, kernel methods, web search engines, information extraction, and learning in vision and robotics. The book also includes hundreds of new exercises."-- Provided by publisher.

• I Artificial Intelligence 1 Introduction 1.1 What is AI? ... 1 1.2 The Foundations of Artificial Intelligence ... 5 1.3 The History of Artificial Intelligence ... 16 1.4 The State of the Art ... 28 1.5 Summary, Bibliographical and Historical Notes, Exercises ... 29
• 2 Intelligent Agents 2.1 Agents and Environments ... 34 2.2 Good Behavior: The Concept of Rationality ... 36 2.3 The Nature of Environments ... 40 2.4 The Structure of Agents ... 46 2.5 Summary, Bibliographical and Historical Notes, Exercises ... 59 II Problem-solving 3 Solving Problems by Searching 3.1 Problem-Solving Agents ... 64 3.2 Example Problems ... 69 3.3 Searching for Solutions ... 75 3.4 Uninformed Search Strategies ... 81 3.5 Informed (Heuristic) Search Strategies ... 92 3.6 Heuristic Functions ... 102 3.7 Summary, Bibliographical and Historical Notes, Exercises ... 108
• 4 Beyond Classical Search 4.1 Local Search Algorithms and Optimization Problems ... 120 4.2 Local Search in Continuous Spaces ... 129 4.3 Searching with Nondeterministic Actions ... 133 4.4 Searching with Partial Observations ... 138 4.5 Online Search Agents and Unknown Environments ... 147 4.6 Summary, Bibliographical and Historical Notes, Exercises ... 153
• 5 Adversarial Search 5.1 Games ... 161 5.2 Optimal Decisions in Games ... 163 5.3 Alpha-Beta Pruning ... 167 5.4 Imperfect Real-Time Decisions ... 171 5.5 Stochastic Games ... 177 5.6 Partially Observable Games ... 180 5.7 State-of-the-Art Game Programs ... 185 5.8 Alternative Approaches ... 187 5.9 Summary, Bibliographical and Historical Notes, Exercises ... 189
• 6 Constraint Satisfaction Problems 6.1 Defining Constraint Satisfaction Problems ... 202 6.2 Constraint Propagation: Inference in CSPs ... 208 6.3 Backtracking Search for CSPs ... 214 6.4 Local Search for CSPs ... 220 6.5 The Structure of Problems ... 222 6.6 Summary, Bibliographical and Historical Notes, Exercises ... 227 III Knowledge, Reasoning, and Planning 7 Logical Agents 7.1 Knowledge-Based Agents ... 235 7.2 The Wumpus World ... 236 7.3 Logic ... 240 7.4 Propositional Logic: A Very Simple Logic ... 243 7.5 Propositional Theorem Proving ... 249 7.6 Effective Propositional Model Checking ... 259 7.7 Agents Based on Propositional Logic ... 265 7.8 Summary, Bibliographical and Historical Notes, Exercises ... 274
• 8 First-Order Logic 8.1 Representation Revisited ... 285 8.2 Syntax and Semantics of First-Order Logic ... 290 8.3 Using First-Order Logic ... 300 8.4 Knowledge Engineering in First-Order Logic ... 307 8.5 Summary, Bibliographical and Historical Notes, Exercises ... 313
• 9 Inference in First-Order Logic 9.1 Propositional vs. First-Order Inference ... 322 9.2 Unification and Lifting ... 325 9.3 Forward Chaining ... 330 9.4 Backward Chaining ... 337 9.5 Resolution ... 345 9.6 Summary, Bibliographical and Historical Notes, Exercises ... 357
• 10 Classical Planning 10.1 Definition of Classical Planning ... 366 10.2 Algorithms for Planning as State-Space Search ... 373 10.3 Planning Graphs ... 379 10.4 Other Classical Planning Approaches ... 387 10.5 Analysis of Planning Approaches ... 392 10.6 Summary, Bibliographical and Historical Notes, Exercises ... 393
• 11 Planning and Acting in the Real World 11.1 Time, Schedules, and Resources ... 401 11.2 Hierarchical Planning ... 406 11.3 Planning and Acting in Nondeterministic Domains ... 415 11.4 Multiagent Planning ... 425 11.5 Summary, Bibliographical and Historical Notes, Exercises ... 430
• 12 Knowledge Representation 12.1 Ontological Engineering ... 437 12.2 Categories and Objects ... 440 12.3 Events ... 446 12.4 Mental Events and Mental Objects ... 450 12.5 Reasoning Systems for Categories ... 453 12.6 Reasoning with Default Information ... 458 12.7 The Internet Shopping World ... 462 12.8 Summary, Bibliographical and Historical Notes, Exercises ... 467 IV Uncertain Knowledge and Reasoning 13 Quantifying Uncertainty 13.1 Acting under Uncertainty ... 480 13.2 Basic Probability Notation ... 483 13.3 Inference Using Full Joint Distributions ... 490 13.4 Independence ... 494 13.5 Bayes' Rule and Its Use ... 495 13.6 The Wumpus World Revisited ... 499 13.7 Summary, Bibliographical and Historical Notes, Exercises ... 503
• 14 Probabilistic Reasoning 14.1 Representing Knowledge in an Uncertain Domain ... 510 14.2 The Semantics of Bayesian Networks ... 513 14.3 Efficient Representation of Conditional Distributions ... 518 14.4 Exact Inference in Bayesian Networks ... 522 14.5 Approximate Inference in Bayesian Networks ... 530 14.6 Relational and First-Order Probability Models ... 539 14.7 Other Approaches to Uncertain Reasoning ... 546 14.8 Summary, Bibliographical and Historical Notes, Exercises ... 551
• 15 Probabilistic Reasoning over Time 15.1 Time and Uncertainty ... 566 15.2 Inference in Temporal Models ... 570 15.3 Hidden Markov Models ... 578 15.4 Kalman Filters ... 584 15.5 Dynamic Bayesian Networks ... 590 15.6 Keeping Track of Many Objects ... 599 15.7 Summary, Bibliographical and Historical Notes, Exercises ... 603
• 16 Making Simple Decisions 16.1 Combining Beliefs and Desires under Uncertainty ... 610 16.2 The Basis of Utility Theory ... 611 16.3 Utility Functions ... 615 16.4 Multiattribute Utility Functions ... 622 16.5 Decision Networks ... 626 16.6 The Value of Information ... 628 16.7 Decision-Theoretic Expert Systems ... 633 16.8 Summary, Bibliographical and Historical Notes, Exercises ... 636
• 17 Making Complex Decisions 17.1 Sequential Decision Problems ... 645 17.2 Value Iteration ... 652 17.3 Policy Iteration ... 656 17.4 Partially Observable MDPs ... 658 17.5 Decisions with Multiple Agents: Game Theory ... 666 17.6 Mechanism Design ... 679 17.7 Summary, Bibliographical and Historical Notes, Exercises ... 684 V Learning 18 Learning from Examples 18.1 Forms of Learning ... 693 18.2 Supervised Learning ... 695 18.3 Learning Decision Trees ... 697 18.4 Evaluating and Choosing the Best Hypothesis ... 708 18.5 The Theory of Learning ... 713 18.6 Regression and Classification with Linear Models ... 717 18.7 Artificial Neural Networks ... 727 18.8 Nonparametric Models ... 737 18.9 Support Vector Machines ... 744 18.10 Ensemble Learning ... 748 18.11 Practical Machine Learning ... 753 18.12 Summary, Bibliographical and Historical Notes, Exercises ... 757
• 19 Knowledge in Learning 19.1 A Logical Formulation of Learning ... 768 19.2 Knowledge in Learning ... 777 19.3 Explanation-Based Learning ... 780 19.4 Learning Using Relevance Information ... 784 19.5 Inductive Logic Programming ... 788 19.6 Summary, Bibliographical and Historical Notes, Exercises ... 797
• 20 Learning Probabilistic Models 20.1 Statistical Learning ... 802 20.2 Learning with Complete Data ... 806 20.3 Learning with Hidden Variables: The EM Algorithm ... 816 20.4 Summary, Bibliographical and Historical Notes, Exercises ... 825
• 21 Reinforcement Learning 21.1 Introduction ... 830 21.2 Passive Reinforcement Learning ... 832 21.3 Active Reinforcement Learning ... 839 21.4 Generalization in Reinforcement Learning ... 845 21.5 Policy Search ... 848 21.6 Applications of Reinforcement Learning ... 850 21.7 Summary, Bibliographical and Historical Notes, Exercises ... 853 VI Communicating, Perceiving, and Acting 22 Natural Language Processing 22.1 Language Models ... 860 22.2 Text Classification ... 865 22.3 Information Retrieval ... 867 22.4 Information Extraction ... 873 22.5 Summary, Bibliographical and Historical Notes, Exercises ... 882
• 23 Natural Language for Communication 23.1 Phrase Structure Grammars ... 888 23.2 Syntactic Analysis (Parsing) ... 892 23.3 Augmented Grammars and Semantic Interpretation ... 897 23.4 Machine Translation ... 907 23.5 Speech Recognition ... 912 23.6 Summary, Bibliographical and Historical Notes, Exercises ... 918
• 24 Perception 24.1 Image Formation ... 929 24.2 Early Image-Processing Operations ... 935 24.3 Object Recognition by Appearance ... 942 24.4 Reconstructing the 3D World ... 947 24.5 Object Recognition from Structural Information ... 957 24.6 Using Vision ... 961 24.7 Summary, Bibliographical and Historical Notes, Exercises ... 965
• 25 Robotics 25.1 Introduction ... 971 25.2 Robot Hardware ... 973 25.3 Robotic Perception ... 978 25.4 Planning to Move ... 986 25.5 Planning Uncertain Movements ... 993 25.6 Moving ... 997 25.7 Robotic Software Architectures ... 1003 25.8 Application Domains ... 1006 25.9 Summary, Bibliographical and Historical Notes, Exercises ... 1010 VII Conclusions 26 Philosophical Foundations 26.1 Weak AI: Can Machines Act Intelligently? ... 1020 26.2 Strong AI: Can Machines Really Think? ... 1026 26.3 The Ethics and Risks of Developing Artificial Intelligence ... 1034 26.4 Summary, Bibliographical and Historical Notes, Exercises ... 1040 27 AI: The Present and Future 1044 27.1 Agent Components ... 1044 27.2 Agent Architectures ... 1047 27.3 Are We Going in the Right Direction? ... 1049 27.4 What If AI Does Succeed? ... 1051 A Mathematical Background A.1 Complexity Analysis and O() Notation ... 1053 A.2 Vectors, Matrices, and Linear Algebra ... 1055 A.3 Probability Distributions ... 1057 B Notes on Languages and Algorithms B.1 Defining Languages with Backus-Naur Form (BNF) ... 1060 B.2 Describing Algorithms with Pseudocode ... 1061 B.3 Online Help ... 1062 Bibliography 1063 Index 1095.
• (source: Nielsen Book Data)

Artificial Intelligence: A Modern Approach, 3e offers the most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence. Number one in its field, this textbook is ideal for one or two-semester, undergraduate or graduate-level courses in Artificial Intelligence. Dr. Peter Norvig, contributing Artificial Intelligence author and Professor Sebastian Thrun, a Pearson author are offering a free online course at Stanford University on artificial intelligence. According to an article in The New York Times, the course on artificial intelligence is "one of three being offered experimentally by the Stanford computer science department to extend technology knowledge and skills beyond this elite campus to the entire world." One of the other two courses, an introduction to database software, is being taught by Pearson authorDr. Jennifer Widom. Artificial Intelligence: A Modern Approach, 3e is available to purchase as an eText for your Kindle(t), NOOK(t), and the iPhone(R)/iPad(R). To learn more about the course on artificial intelligence, visit http://www.ai-class.com. To read the full New York Timesarticle, click here.
(source: Nielsen Book Data)
The long-anticipated revision of this #1 selling book offers the most comprehensive, state of the art introduction to the theory and practice of artificial intelligence for modern applications.
(source: Nielsen Book Data)

• I. ARTIFICIAL INTELLIGENCE.
• 1. Introduction.
• 2. Intelligent Agents. II. PROBLEM-SOLVING.
• 3. Solving Problems by Searching.
• 4. Informed Search and Exploration.
• 5. Constraint Satisfaction Problems.
• 6. Adversarial Search. III. KNOWLEDGE AND REASONING.
• 7. Logical Agents.
• 8. First-Order Logic.
• 9. Inference in First-Order Logic.
• 10. Knowledge Representation. IV. PLANNING.
• 11. Planning.
• 12. Planning and Acting in the Read World. V. UNCERTAIN KNOWLEDGE AND REASONING.
• 13. Uncertainty.
• 14. Probabilistic Reasoning Systems.
• 15. Probabilistic Reasoning Over Time.
• 16. Making Simple Decisions.
• 17. Making Complex Decisions. VI. LEARNING.
• 18. Learning from Observations.
• 19. Knowledge in Learning.
• 20. Statistical Learning Methods.
• 21. Reinforcement Learning. VII. COMMUNICATING, PERCEIVING, AND ACTING.
• 22. Agents that Communicate.
• 23. Text Processing in the Large.
• 24. Perception.
• 25. Robotics. VIII. CONCLUSIONS.
• 26. Philosophical Foundations.
• 27. AI: Present and Future.
• (source: Nielsen Book Data)

View chapters 3 and 4 from the upcoming Third Edition. For one or two-semester, undergraduate or graduate-level courses in Artificial Intelligence. The long-anticipated revision of this best-selling text offers the most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence. Click on "Features" tab below for more information Resources: Visit the author's website http://aima.cs.berkeley.edu/ to access both student and instructor resources including Power Point slides, syllabus. homework and exams, and solutions text problems.
(source: Nielsen Book Data)

Like Mooki, the hero of Spike Lee's film "Do the Right Thing, " artificially intelligent systems have a hard time knowing what to do in all circumstances. Classical theories of perfect rationality prescribe the "right thing" for any occasion, but no finite agent can compute their prescriptions fast enough. In Do the Right Thing, the authors argue that a new theoretical foundation for artificial intelligence can be constructed in which rationality is a property of "programs" within a finite architecture, and their behavior over time in the task environment, rather than a property of individual decisions.Do the Right Thing suggests that the rich structure that seems to be exhibited by humans, and ought to be exhibited by AI systems, is a necessary result of the pressure for optimal behavior operating within a system of strictly limited resources. It provides an outline for the design of new intelligent systems and describes theoretical and practical tools for bringing about intelligent behavior in finite machines. The tools are applied to game planning and realtime problem solving, with surprising results.Stuart Russell is Associate Professor of Computer Science at the University of California, Berkeley. This book builds on important philosophical and technical work by his coauthor, the late Eric Wefald.
(source: Nielsen Book Data)

• I. ARTIFICIAL INTELLIGENCE.
• 1. Introduction.
• 2. Intelligent Agents. II. PROBLEM-SOLVING.
• 3. Solving Problems by Searching.
• 4. Informed Search Methods.
• 5. Game Playing. III. KNOWLEDGE AND REASONING.
• 6. Agents that Reason Logically.
• 7. First-order Logic.
• 8. Building a Knowledge Base.
• 9. Inference in First-Order Logic.
• 10. Logical Reasoning Systems. IV. ACTING LOGICALLY.
• 11. Planning.
• 12. Practical Planning.
• 13. Planning and Acting. V. UNCERTAIN KNOWLEDGE AND REASONING.
• 14. Uncertainty.
• 15. Probabilistic Reasoning Systems.
• 16. Making Simple Decisions.
• 17. Making Complex Decisions. VI. LEARNING.
• 18. Learning from Observations.
• 19. Learning with Neural Networks.
• 20. Reinforcement Learning.
• 21. Knowledge in Learning. VII. COMMUNICATING, PERCEIVING, AND ACTING.
• 22. Agents that Communicate.
• 23. Practical Communication in English.
• 24. Perception.
• 25. Robotics. VIII. CONCLUSIONS.
• 26. Philosophical Foundations.
• 27. AI: Present and Future.
• (source: Nielsen Book Data)

This is an introduction to the theory and practice of artificial intelligence. It uses an intelligent agent as the unifying theme throughout, and covers areas that are sometimes underemphasized elsewhere. These include reasoning under uncertainty, learning, natural language, vision and robotics. The book also explains in detail some of the more recent ideas in the field, including simulated annealing, memory-bounded search, global ontologies, dynamic belief networks, neural nets, inductive logic programming, computational learning theory, and reinforcement learning.
(source: Nielsen Book Data)

• Limited rationality
• execution architectures for decision procedures
• metareasoning architecture
• rational metareasoning
• application to game playing
• application to problem solving search
• learning the value of computation
• toward limited rational agents.
• (source: Nielsen Book Data)

Like Mooki, the hero of Spike Lee's film "Do the Right Thing, " artificially intelligent systems have a hard time knowing what to do in all circumstances. Classical theories of perfect rationality prescribe the "right thing" for any occasion, but no finite agent can compute their prescriptions fast enough. In "Do the Right Thing, " the authors argue that a new theoretical foundation for artificial intelligence can be constructed in which rationality is a property of "programs" within a finite architecture, and their behavior over time in the task environment, rather than a property of individual decisions."Do the Right Thing" suggests that the rich structure that seems to be exhibited by humans, and ought to be exhibited by AI systems, is a necessary result of the pressure for optimal behavior operating within a system of strictly limited resources. It provides an outline for the design of new intelligent systems and describes theoretical and practical tools for bringing about intelligent behavior in finite machines. The tools are applied to game planning and real-time problem solving, with surprising results.Contents Limited Rationality. Execution Architectures for Decision Procedures. Metareasoning Architecture. Rational Metareasoning. Application to Game Playing. Application to Problem Solving Search. Learning the Value of Computation. Toward Limited Rational Agents.
(source: Nielsen Book Data)
Like Mooki, the hero of Spike Lee's film "Do the Right Thing" artificially, intelligent systems have a hard time knowing what to do in all circumstances. Classical theories of perfect rationality prescribe the "right thing" for any occasion, but no finite agent can compute their prescriptions fast enough. In "Do the Right Thing", the authors argue that a new theoretical foundation for artificial intelligence can be constructed in which rationality is a property of "programs" within a finite architecture, and their behaviour over time in the task environment, rather than a property of individual decisions. "Do The Right Thing" suggests that the rich structure that seems to be exhibited by humans, and ought to be exhibited by AI systems, is a necessary result of the pressure for optimal behaviour operating within a system of strictly limited resources. It provides an outline for the design of new intelligent systems and describes theoretical and practical tools for bringing about intelligent behaviour in finite machines. The tools are applied to game planning and real-time problem solving, with surprising results.
(source: Nielsen Book Data)

• Limited rationality
• execution architectures for decision procedures
• metareasoning architecture
• rational metareasoning
• application to game playing
• application to problem solving search
• learning the value of computation
• toward limited rational agents.
• (source: Nielsen Book Data)

Like Mooki, the hero of Spike Lee's film "Do the Right Thing" artificially, intelligent systems have a hard time knowing what to do in all circumstances. Classical theories of perfect rationality prescribe the "right thing" for any occasion, but no finite agent can compute their prescriptions fast enough. In "Do the Right Thing", the authors argue that a new theoretical foundation for artificial intelligence can be constructed in which rationality is a property of "programs" within a finite architecture, and their behaviour over time in the task environment, rather than a property of individual decisions. "Do The Right Thing" suggests that the rich structure that seems to be exhibited by humans, and ought to be exhibited by AI systems, is a necessary result of the pressure for optimal behaviour operating within a system of strictly limited resources. It provides an outline for the design of new intelligent systems and describes theoretical and practical tools for bringing about intelligent behaviour in finite machines. The tools are applied to game planning and real-time problem solving, with surprising results.
(source: Nielsen Book Data)

• Front Cover; Machine Learning; Copyright Page; Table of Contents; Preface; Advisory Committee; Program Committee; Auxiliary Reviewers; Workshops; Tutorials;
• PART 1: CONTRIBUTED PAPERS;
• Chapter 1. On-line Learning of Binary Lexical Relations Using Two-dimensional Weighted Majority Algorithms; ABSTRACT; 1 Introduction; 2 On-line Learning Model for Binary Relations; 3 Two-dimensional Weighted Majority Prediction Algorithms; 4 Experimental Results; 5 Theoretical Performance Analysis; 6 Concluding Remarks; Acknowledgement; References

• Chapter 2. On Handling Tree-Structured Attributes in Decision Tree LearningAbstract; 1 Introduction; 2 Decision Trees With Tree-Structured Attributes; 3 Pre-processing Approaches; 4 A Direct Approach; 5 Analytical Comparison; 6 Experimental Comparison; 7 Summary and Conclusion; Acknowledgement; References;
• Chapter 3. Theory and Applications of Agnostic PAC-Learning with Small Decision Trees; Abstract; 1 INTRODUCTION; 2 THE AGNOSTIC PAC-LEARNING ALGORITHM T2; 3 EVALUATION OF T2 ON ""REAL-WORLD"" CLASSIFICATION PROBLEMS; 4 LEARNING CURVES FOR DECISION TREES OF SMALL DEPTH; 5 CONCLUSION

• AcknowledgementReferences;
• Chapter 4. Residual Algorithms: Reinforcement Learning with Function Approximation; ABSTRACT; 1 INTRODUCTION; 2 ALGORITHMS FOR LOOKUP TABLES; 3 DIRECT ALGORITHMS; 4 RESIDUAL GRADIENT ALGORITHMS; 5 RESIDUAL ALGORITHMS; 6 STOCHASTIC MDPS AND MODELS; 7 MDPS WITH MULTIPLE ACTIONS; 8 RESIDUAL ALGORITHM SUMMARY; 9 SIMULATION RESULTS; 10 CONCLUSIONS; Acknowledgments; References;
• Chapter 5. Removing the Genetics from the Standard Genetic Algorithm; Abstract; 1. THE GENETIC ALGORITHM (GA); 2. FOUR PEAKS: A PROBLEM DESIGNED TO BE GA-FRIENDLY; 3. SELECTING THE GA'S PARAMETERS

• 4. POPULATION-BASED INCREMENTAL LEARNING5. EMPIRICAL ANALYSIS ON THE FOUR PEAKS PROBLEM; 6. DISCUSSION; 7. CONCLUSIONS; ACKNOWLEDGEMENTS; REFERENCES;
• Chapter 6. Inductive Learning of Reactive Action Models; Abstract; 1 INTRODUCTION; 2 CONTEXT OF THE LEARNER; 3 ACTIONS AND TELEO-OPERATORS; 4 COLLECTING INSTANCES FOR LEARNING; 5 THE INDUCTIVE LOGIC PROGRAMMING ALGORITHM; 6 EVALUATION; 7 RELATED WORK; 8 FUTURE WORK; Acknowledgements; References;
• Chapter 7. Visualizing High-Dimensional Structure with the Incremental Grid Growing Neural Network; Abstract; 1 INTRODUCTION; 2 INCREMENTAL GRID GROWING

• 3 COMPARISON USING MINIMUM SPANNING TREEDATA4 DEMONSTRATION USING REALWORLD SEMANTIC DATA; 5 DISCUSSION AND FUTURE WORK; 6 CONCLUSION; References;
• Chapter 8. Empirical support for Winnow and Weighted-Majority based algorithms: results on a calendar scheduling domain; Abstract; 1 Introduction; 2 The learning problem; 3 Description of the algorithms; 4 Experimental results; 5 Theoretical results; Acknowledgements; References; Appendix;
• Chapter 9. Automatic Selection of Split Criterion during Tree Growing Based on Node Location; Abstract; 1 DECISION TREE CONSTRUCTION

Machine Learning Proceedings 1995.