<p>Engage your students with the ever-expanding field of AI with this industry-leading text.</p><p><strong>Artificial Intelligence: A Modern Approach, Global Edition, 4<sup>th</sup> Edition</strong> (AI) explores the full breadth and depth of the field, allowing your students to delve into the advanced methods of reasoning, deep learning, and mathematics.</p><p>From robotic planetary explorers to online services with billions of users, the textbook studies a wide range of applications, further considering the ethical aspects and values of practicing the discipline.</p><p>With a new site containing all the exercises, this leading text will support your students' understanding of the topics, offering a multi-faceted approach to the subject.</p>

<div class="c-non-traditional-number-list_container"><h3><strong>Chapter I&nbsp; Artificial Intelligence</strong></h3><ol><li><strong>Introduction</strong><ul><li>What Is AI?</li><li>The Foundations of Artificial Intelligence</li><li>The History of Artificial Intelligence</li><li>The State of the Art</li><li>Risks and Benefits of AI</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Intelligent Agents</strong><ul><li>Agents and Environments</li><li>Good Behavior: The Concept of Rationality</li><li>The Nature of Environments</li><li>The Structure of Agents</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><h3><strong>Chapter II&nbsp; Problem Solving</strong></h3><li><strong>Solving Problems by Searching</strong><ul><li>Problem-Solving Agents</li><li>Example Problems</li><li>Search Algorithms</li><li>Uninformed Search Strategies</li><li>Informed (Heuristic) Search Strategies</li><li>Heuristic Functions</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Search in Complex Environments</strong><ul><li>Local Search and Optimization Problems</li><li>Local Search in Continuous Spaces</li><li>Search with Nondeterministic Actions</li><li>Search in Partially Observable Environments</li><li>Online Search Agents and Unknown Environments</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Constraint Satisfaction Problems</strong><ul><li>Defining Constraint Satisfaction Problems</li><li>Constraint Propagation: Inference in CSPs</li><li>Backtracking Search for CSPs</li><li>Local Search for CSPs</li><li>The Structure of Problems</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Adversarial Search and Games</strong><ul><li>Game Theory</li><li>Optimal Decisions in Games</li><li>Heuristic Alpha--Beta Tree Search</li><li>Monte Carlo Tree Search</li><li>Stochastic Games</li><li>Partially Observable Games</li><li>Limitations of Game Search Algorithms</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><h3><strong>Chapter III&nbsp; Knowledge, Reasoning and Planning</strong></h3><li><strong>Logical Agents</strong><ul><li>Knowledge-Based Agents</li><li>The Wumpus World</li><li>Logic</li><li>Propositional Logic: A Very Simple Logic</li><li>Propositional Theorem Proving</li><li>Effective Propositional Model Checking</li><li>Agents Based on Propositional Logic</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>First-Order Logic</strong><ul><li>Representation Revisited</li><li>Syntax and Semantics of First-Order Logic</li><li>Using First-Order Logic</li><li>Knowledge Engineering in First-Order Logic</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Inference in First-Order Logic</strong><ul><li>Propositional vs. First-Order Inference</li><li>Unification and First-Order Inference</li><li>Forward Chaining</li><li>Backward Chaining</li><li>Resolution</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Knowledge Representation</strong><ul><li>Ontological Engineering</li><li>Categories and Objects</li><li>Events</li><li>Mental Objects and Modal Logic</li><li>for Categories</li><li>Reasoning with Default Information</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Automated Planning</strong><ul><li>Definition of Classical Planning</li><li>Algorithms for Classical Planning</li><li>Heuristics for Planning</li><li>Hierarchical Planning</li><li>Planning and Acting in Nondeterministic Domains</li><li>Time, Schedules, and Resources</li><li>Analysis of Planning Approaches</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><h3><strong>Chapter IV&nbsp; Uncertain Knowledge and Reasoning</strong></h3><li><strong>Quantifying Uncertainty</strong><ul><li>Acting under Uncertainty</li><li>Basic Probability Notation</li><li>Inference Using Full Joint Distributions</li><li>Independence 12.5 Bayes' Rule and Its Use</li><li>Naive Bayes Models</li><li>The Wumpus World Revisited</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Probabilistic Reasoning</strong><ul><li>Representing Knowledge in an Uncertain Domain</li><li>The Semantics of Bayesian Networks</li><li>Exact Inference in Bayesian Networks</li><li>Approximate Inference for Bayesian Networks</li><li>Causal Networks</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Probabilistic Reasoning over Time</strong><ul><li>Time and Uncertainty</li><li>Inference in Temporal Models</li><li>Hidden Markov Models</li><li>Kalman Filters</li><li>Dynamic Bayesian Networks</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Making Simple Decisions</strong><ul><li>Combining Beliefs and Desires under Uncertainty</li><li>The Basis of Utility Theory</li><li>Utility Functions</li><li>Multiattribute Utility Functions</li><li>Decision Networks</li><li>The Value of Information</li><li>Unknown Preferences</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Making Complex Decisions</strong><ul><li>Sequential Decision Problems</li><li>Algorithms for MDPs</li><li>Bandit Problems</li><li>Partially Observable MDPs</li><li>Algorithms for Solving POMDPs</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Multiagent Decision Making</strong><ul><li>Properties of Multiagent Environments</li><li>Non-Cooperative Game Theory</li><li>Cooperative Game Theory</li><li>Making Collective Decisions</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Probabilistic Programming</strong><ul><li>Relational Probability Models</li><li>Open-Universe Probability Models</li><li>Keeping Track of a Complex World</li><li>Programs as Probability Models</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><h3><strong>Chapter V&nbsp; Machine Learning</strong></h3><li><strong>Learning from Examples</strong><ul><li>Forms of Leaming</li><li>Supervised Learning .</li><li>Learning Decision Trees .</li><li>Model Selection and Optimization</li><li>The Theory of Learning</li><li>Linear Regression and Classification</li><li>Nonparametric Models</li><li>Ensemble Learning</li><li>Developing Machine Learning Systen</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Knowledge in Learning</strong><ul><li>A Logical Formulation of Learning</li><li>Knowledge in Learning</li><li>Exmplanation-Based Leaening</li><li>Learning Using Relevance Information</li><li>Inductive Logic Programming</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Learning Probabilistic Models</strong><ul><li>Statistical Learning</li><li>Learning with Complete Data</li><li>Learning with Hidden Variables: The EM Algorithm</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Deep Learning</strong><ul><li>Simple Feedforward Networks</li><li>Computation Graphs for Deep Learning</li><li>Convolutional Networks</li><li>Learning Algorithms</li><li>Generalization</li><li>Recurrent Neural Networks</li><li>Unsupervised Learning and Transfer Learning</li><li>Applications</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Reinforcement Learning</strong><ul><li>Learning from Rewards</li><li>Passive Reinforcement Learning</li><li>Active Reinforcement Learning</li><li>Generalization in Reinforcement Learning</li><li>Policy Search</li><li>Apprenticeship and Inverse Reinforcement Leaming</li><li>Applications of Reinforcement Learning</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><h3><strong>Chapter VI&nbsp; Communicating, perceiving, and acting</strong></h3><li><strong>Natural Language Processing</strong><ul><li>Language Models</li><li>Grammar</li><li>Parsing</li><li>Augmented Grammars</li><li>Complications of Real Natural Languagr</li><li>Natural Language Tasks</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Deep Learning for Natural Language Processing</strong><ul><li>Word Embeddings</li><li>Recurrent Neural Networks for NLP</li><li>Sequence-to-Sequence Models</li><li>The Transformer Architecture</li><li>Pretraining and Transfer Learning</li><li>State of the art</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Robotics</strong><ul><li>Robots</li><li>Robot Hardware</li><li>What kind of problem is robotics solving?</li><li>Robotic Perception</li><li>Planning and Control</li><li>Planning Uncertain Movements</li><li>Reinforcement Laming in Robotics</li><li>Humans and Robots</li><li>Alternative Robotic Frameworks</li><li>Application Domains</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>Computer Vision</strong><ul><li>Introduction</li><li>Image Formation</li><li>Simple Image Features</li><li>Classifying Images</li><li>Detecting Objects</li><li>The 3D World</li><li>Using Computer Vision</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><h3><strong>Chapter VII&nbsp; Conclusions</strong></h3><li><strong>Philosophy, Ethics, and Safety of Al</strong><ul><li>The Limits of Al</li><li>Can Machines Really Think?</li><li>The Ethics of Al</li></ul><h4 class="h5">Summary</h4><h4 class="h5">Bibliographical and Historical Notes</h4></li><li><strong>The Future of AI</strong><ul><li>Al Components</li><li>Al Architectures</li></ul></li></ol></div><div class="c-un-numbered-list_container"><h6><strong>A Mathematical Background</strong></h6><ul><li>A.1 Complexity Analysis and O0 Notation</li><li>A.2 Vectors, Matrices, and Linear Algebra</li><li>A.3 Probability Distributions</li><li>Bibliographical and Historical Notes</li></ul><p>&nbsp;</p><h6><strong>B Notes on Languages and Algorithms</strong></h6><ul><li>B.1 Defining Languages with Backus-Naur Form (BNF)</li><li>B.2 Describing Algorithms with Pseudocode</li><li>B.3 Online Supplemental Material</li></ul><p>&nbsp;</p><h5 class="h6"><strong>Bibliography</strong></h5><h5 class="h6"><strong>Index</strong></h5></div>

<h4>Explore the ever-expanding, fascinating field of AI and its latest technologies with this industry-leading text.</h4><p><strong>Artificial Intelligence: A Modern Approach, Global Edition, 4<sup>th</sup> Edition</strong> (AI), explores the full breadth and depth of the field, delving into the advanced methods of reasoning, deep learning, perception, and mathematics.</p><p>From robotic planetary explorers to online services with billions of users, the textbook studies a wide range of current methods and technologies, further considering the ethical values of practicing the discipline. </p><p>With a new site containing all the exercises, this leading text is a must-read edition, offering a multi-faceted approach to this expanding subject.</p>

<p class="MsoNormal" style="margin-bottom:0in;line-height:18.0pt"><b><span style="font-size:10.0pt;font-family:&quot;Verdana&quot;,sans-serif;mso-fareast-font-family:&quot;Times New Roman&quot;;mso-bidi-font-family:&quot;Times New Roman&quot;">The mostcomprehensive, up-to-date introduction to the theory and practice of artificialintelligence</span></b><span style="font-size:10.0pt;font-family:&quot;Verdana&quot;,sans-serif;mso-fareast-font-family:&quot;Times New Roman&quot;;mso-bidi-font-family:&quot;Times New Roman&quot;"><o:p></o:p></span></p><p class="MsoNormal"><span style="font-size:10.0pt;line-height:107%;font-family:&quot;Verdana&quot;,sans-serif;mso-fareast-font-family:&quot;Times New Roman&quot;;mso-bidi-font-family:&quot;Times New Roman&quot;;mso-ansi-language:EN-US;mso-fareast-language:EN-US;mso-bidi-language:AR-SA">Thelong-anticipated revision of&nbsp;<b><i>Artificial Intelligence: A ModernApproach</i></b>&nbsp;explores the full breadth and depth of the field of artificialintelligence (AI). The&nbsp;<b>4th Edition</b>&nbsp;brings readers up to dateon the latest technologies, presents concepts in a more unified manner, andoffers new or expanded coverage of machine learning, deep learning, transferlearning, multiagent systems, robotics, natural language processing, causality,probabilistic programming, privacy, fairness, and safe AI.</span></p>

<p class="MsoNormal"><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>Part I: Artificial Intelligence<br>1. Introduction</span></b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><br>&nbsp;&nbsp; &nbsp;1.1&nbsp; What Is AI?<br>&nbsp;&nbsp; &nbsp;1.2&nbsp; The Foundations of Artificial Intelligence<br>&nbsp;&nbsp; &nbsp;1.3&nbsp; The History of Artificial Intelligence<br>&nbsp;&nbsp; &nbsp;1.4&nbsp; The State of the Art<br>&nbsp;&nbsp; &nbsp;1.5&nbsp; Risks and Benefits of AI<br><b>2. Intelligent Agents</b><br>&nbsp;&nbsp; &nbsp;2.1&nbsp; Agents and Environments<br>&nbsp;&nbsp; &nbsp;2.2&nbsp; Good Behavior: The Concept of Rationality<br>&nbsp;&nbsp; &nbsp;2.3&nbsp; The Nature of Environments<br>&nbsp;&nbsp; &nbsp;2.4&nbsp; The Structure of Agents<br>&nbsp;<br><b>Part II: Problem Solving<br>3. Solving Problems by Searching</b><br>&nbsp;&nbsp;&nbsp; 3.1&nbsp; Problem-Solving Agents<br>&nbsp;&nbsp;&nbsp; 3.2&nbsp; Example Problems<br>&nbsp;&nbsp;&nbsp; 3.3&nbsp; Search Algorithms<br>&nbsp;&nbsp;&nbsp; 3.4&nbsp; Uninformed Search Strategies<br>&nbsp;&nbsp;&nbsp; 3.5&nbsp; Informed (Heuristic) Search Strategies<br>&nbsp;&nbsp;&nbsp; 3.6&nbsp; Heuristic Functions<br><b>4. Search in Complex Environments</b><br>&nbsp;&nbsp;&nbsp; 4.1&nbsp; Local Search and Optimization Problems<br>&nbsp;&nbsp;&nbsp; 4.2&nbsp; Local Search in Continuous Spaces<br>&nbsp;&nbsp;&nbsp; 4.3&nbsp; Search with Nondeterministic Actions<br>&nbsp;&nbsp;&nbsp; 4.4&nbsp; Search in Partially Observable Environments<br>&nbsp;&nbsp;&nbsp; 4.5&nbsp; Online Search Agents and Unknown Environments<br><b>5. Constraint Satisfaction Problems</b><br>&nbsp;&nbsp;&nbsp; 5.1&nbsp; Defining Constraint Satisfaction Problems<br>&nbsp;&nbsp;&nbsp; 5.2&nbsp; Constraint Propagation: Inference in CSPs<br>&nbsp;&nbsp;&nbsp; 5.3&nbsp; Backtracking Search for CSPs<br>&nbsp;&nbsp;&nbsp; 5.4&nbsp; Local Search for CSPs<br>&nbsp;&nbsp;&nbsp; 5.5&nbsp; The Structure of Problems<br><b>6. Adversarial Search and Games</b><br>&nbsp;&nbsp;&nbsp; 6.1&nbsp; Game Theory<br>&nbsp;&nbsp;&nbsp; 6.2&nbsp; Optimal Decisions in Games<br>&nbsp;&nbsp;&nbsp; 6.3&nbsp; Heuristic Alpha--Beta Tree Search<br>&nbsp;&nbsp;&nbsp; 6.4&nbsp; Monte Carlo Tree Search<br>&nbsp;&nbsp;&nbsp; 6.5&nbsp; Stochastic Games<br>&nbsp;&nbsp;&nbsp; 6.6&nbsp; Partially Observable Games<br>&nbsp;&nbsp;&nbsp; 6.7&nbsp; Limitations of Game Search Algorithms<br>&nbsp;<br><b>Part III: Knowledge and Reasoning<br>7. Logical Agents</b><br>&nbsp;&nbsp;&nbsp; 7.1&nbsp; Knowledge-Based Agents<br>&nbsp;&nbsp;&nbsp; 7.2&nbsp; The Wumpus World<br>&nbsp;&nbsp;&nbsp; 7.3&nbsp; Logic<br>&nbsp;&nbsp;&nbsp; 7.4&nbsp; Propositional Logic: A Very Simple Logic<br>&nbsp;&nbsp;&nbsp; 7.5&nbsp; Propositional Theorem Proving<br>&nbsp;&nbsp;&nbsp; 7.6&nbsp; Effective Propositional Model Checking<br>&nbsp;&nbsp;&nbsp; 7.7&nbsp; Agents Based on Propositional Logic<br><b>8. First-Order Logic</b><br>&nbsp;&nbsp;&nbsp; 8.1&nbsp; Representation Revisited<br>&nbsp;&nbsp;&nbsp; 8.2&nbsp; Syntax and Semantics of First-Order Logic<br>&nbsp;&nbsp;&nbsp; 8.3&nbsp; Using First-Order Logic<br>&nbsp;&nbsp;&nbsp; 8.4&nbsp; Knowledge Engineering in First-Order Logic<br><b>9. Inference in First-Order Logic</b><br>&nbsp;&nbsp;&nbsp; 9.1&nbsp; Propositional vs.~First-Order Inference<br>&nbsp;&nbsp;&nbsp; 9.2&nbsp; Unification and First-Order Inference<br>&nbsp;&nbsp;&nbsp; 9.3&nbsp; Forward Chaining<br>&nbsp;&nbsp;&nbsp; 9.4&nbsp; Backward Chaining<br>&nbsp;&nbsp;&nbsp; 9.5&nbsp; Resolution<br><b>10. Knowledge Representation</b><br>&nbsp;&nbsp;&nbsp; 10.1&nbsp; Ontological Engineering<br>&nbsp;&nbsp;&nbsp; 10.2&nbsp; Categories and Objects<br>&nbsp;&nbsp;&nbsp; 10.3&nbsp; Events<br>&nbsp;&nbsp;&nbsp; 10.4&nbsp; Mental Objects and Modal Logic<br>&nbsp;&nbsp;&nbsp; 10.5&nbsp; Reasoning Systems for Categories<br>&nbsp;&nbsp;&nbsp; 10.6&nbsp; Reasoning with Default Information<br><b>11. Automated Planning</b><br>&nbsp;&nbsp;&nbsp; 11.1&nbsp; Definition of Classical Planning<br>&nbsp;&nbsp;&nbsp; 11.2&nbsp; Algorithms for Classical Planning<br>&nbsp;&nbsp;&nbsp; 11.3&nbsp; Heuristics for Planning<br>&nbsp;&nbsp;&nbsp; 11.4&nbsp; Hierarchical Planning<br>&nbsp;&nbsp;&nbsp; 11.5&nbsp; Planning and Acting in Nondeterministic Domains<br>&nbsp;&nbsp;&nbsp; 11.6&nbsp; Time, Schedules, and Resources<br>&nbsp;&nbsp;&nbsp; 11.7&nbsp; Analysis of Planning Approaches<br><b>12. Quantifying Uncertainty</b><br>&nbsp;&nbsp;&nbsp; 12.1&nbsp; Acting under Uncertainty<br>&nbsp;&nbsp;&nbsp; 12.2&nbsp; Basic Probability Notation<br>&nbsp;&nbsp;&nbsp; 12.3&nbsp; Inference Using Full Joint Distributions<br>&nbsp;&nbsp;&nbsp; 12.4&nbsp; Independence<br>&nbsp;&nbsp;&nbsp; 12.5&nbsp; Bayes' Rule and Its Use<br>&nbsp;&nbsp;&nbsp; 12.6&nbsp; Naive Bayes Models<br>&nbsp;&nbsp;&nbsp; 12.7&nbsp; The Wumpus World Revisited<br>&nbsp;<br><b>Part IV: Uncertain Knowledge and Reasoning<br>13. Probabilistic Reasoning</b><br>&nbsp;&nbsp;&nbsp; 13.1&nbsp; Representing Knowledge in an Uncertain Domain<br>&nbsp;&nbsp;&nbsp; 13.2&nbsp; The Semantics of Bayesian Networks<br>&nbsp;&nbsp;&nbsp; 13.3&nbsp; Exact Inference in Bayesian Networks<br>&nbsp;&nbsp;&nbsp; 13.4&nbsp; Approximate Inference for Bayesian Networks<br>&nbsp;&nbsp;&nbsp; 13.5&nbsp; Causal Networks<br><b>14. Probabilistic Reasoning over Time</b><br>&nbsp;&nbsp;&nbsp; 14.1&nbsp; Time and Uncertainty<br>&nbsp;&nbsp;&nbsp; 14.2&nbsp; Inference in Temporal Models<br>&nbsp;&nbsp;&nbsp; 14.3&nbsp; Hidden Markov Models<br>&nbsp;&nbsp;&nbsp; 14.4&nbsp; Kalman Filters<br>&nbsp;&nbsp;&nbsp; 14.5&nbsp; Dynamic Bayesian Networks<br><b>15. Making Simple Decisions</b><br>&nbsp;&nbsp;&nbsp; 16.1&nbsp; Combining Beliefs and Desires under Uncertainty<br>&nbsp;&nbsp;&nbsp; 16.2&nbsp; The Basis of Utility Theory<br>&nbsp;&nbsp;&nbsp; 16.3&nbsp; Utility Functions<br>&nbsp;&nbsp;&nbsp; 16.4&nbsp; Multiattribute Utility Functions<br>&nbsp;&nbsp;&nbsp; 16.5&nbsp; Decision Networks<br>&nbsp;&nbsp;&nbsp; 16.6&nbsp; The Value of Information<br>&nbsp;&nbsp;&nbsp; 16.7&nbsp; Unknown Preferences<br><b>16. Making Complex Decisions</b><br>&nbsp;&nbsp;&nbsp; 17.1&nbsp; Sequential Decision Problems<br>&nbsp;&nbsp;&nbsp; 17.2&nbsp; Algorithms for MDPs<br>&nbsp;&nbsp;&nbsp; 17.3&nbsp; Bandit Problems<br>&nbsp;&nbsp;&nbsp; 17.4&nbsp; Partially Observable MDPs<br>&nbsp;&nbsp;&nbsp; 17.5&nbsp; Algorithms for solving POMDPs<br>&nbsp;<br><b>Part V: Learning</b><br><b>17. Multiagent Decision Making</b><br>&nbsp;&nbsp;&nbsp; 17.1&nbsp; Properties of Multiagent Environments<br>&nbsp;&nbsp;&nbsp; 17.2&nbsp; Non-Cooperative Game Theory<br>&nbsp;&nbsp;&nbsp; 17.3&nbsp; Cooperative Game Theory<br>&nbsp;&nbsp;&nbsp; 17.4&nbsp; Making Collective Decisions<br style="mso-special-character: line-break;"><br style="mso-special-character: line-break;"><b><o:p></o:p></b></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>18. ProbabilisticProgramming</span></b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><br>&nbsp;&nbsp;&nbsp; 18.1&nbsp; Relational Probability Models<br>&nbsp;&nbsp;&nbsp; 18.2&nbsp; Open-Universe Probability Models<br>&nbsp;&nbsp;&nbsp; 18.3&nbsp; Keeping Track of a Complex World<br>&nbsp;&nbsp;&nbsp; 18.4&nbsp; Programs as Probability Models<br style="mso-special-character: line-break;"><br style="mso-special-character: line-break;"><b><o:p></o:p></b></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>19. Learning fromExamples</span></b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><br>&nbsp;&nbsp;&nbsp; 19.1&nbsp; Forms of Learning<br>&nbsp;&nbsp;&nbsp; 19.2&nbsp; Supervised Learning<br>&nbsp;&nbsp;&nbsp; 19.3&nbsp; Learning Decision Trees<br>&nbsp;&nbsp;&nbsp; 19.4&nbsp; Model Selection and Optimization<br>&nbsp;&nbsp;&nbsp; 19.5&nbsp; The Theory of Learning<br>&nbsp;&nbsp;&nbsp; 19.6&nbsp; Linear Regression and Classification<br>&nbsp;&nbsp;&nbsp; 19.7&nbsp; Nonparametric Models<br>&nbsp;&nbsp;&nbsp; 19.8&nbsp; Ensemble Learning<br>&nbsp;&nbsp;&nbsp; 19.9&nbsp; Developing Machine Learning Systems<o:p></o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><o:p>&nbsp;</o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>20. Knowledge inLearning<o:p></o:p></span></b></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><span style="mso-spacerun: yes;">&nbsp;&nbsp; </span></span></b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>20.1 A Logical Formulation of Learning<o:p></o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><span style="mso-spacerun: yes;">&nbsp;&nbsp; </span>20.2 Knowledge in Learning<o:p></o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><span style="mso-spacerun: yes;">&nbsp;&nbsp; </span>20.3 Explanation-Based Learning<o:p></o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><span style="mso-spacerun: yes;">&nbsp;&nbsp; </span>20.4 Learning Using Relevance Information<o:p></o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><span style="mso-spacerun: yes;">&nbsp;&nbsp; </span>20.5 Inductive Logic Programming<o:p></o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><o:p>&nbsp;</o:p></span></b></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>21. LearningProbabilistic Models</span></b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><br>&nbsp;&nbsp;&nbsp; 21.1&nbsp; Statistical Learning<br>&nbsp;&nbsp;&nbsp; 21.2&nbsp; Learning with Complete Data<br>&nbsp;&nbsp;&nbsp; 21.3&nbsp; Learning with Hidden Variables: The EM Algorithm<br><b>22. Deep Learning</b><br>&nbsp;&nbsp;&nbsp; 22.1&nbsp; Simple Feedforward Networks<br>&nbsp;&nbsp;&nbsp; 22.2&nbsp; Mixing and matching models, loss functions andoptimizers<br>&nbsp;&nbsp;&nbsp; 22.3&nbsp; Loss functions<br>&nbsp;&nbsp;&nbsp; 22.4&nbsp; Models<br>&nbsp;&nbsp;&nbsp; 22.5&nbsp; Optimization Algorithms<br>&nbsp;&nbsp;&nbsp; 22.6&nbsp; Generalization<br>&nbsp;&nbsp;&nbsp; 22.7&nbsp; Recurrent neural networks<br>&nbsp;&nbsp;&nbsp; 22.8&nbsp; Unsupervised, semi-supervised and transferlearning<br>&nbsp;&nbsp;&nbsp; 22.9&nbsp; Applications<br>&nbsp;<br><b>Part VI: Communicating, Perceiving, and Acting</b><br><b>23. Reinforcement Learning</b><br>&nbsp;&nbsp;&nbsp; 23.1&nbsp; Learning from Rewards<br>&nbsp;&nbsp;&nbsp; 23.2&nbsp; Passive Reinforcement Learning<br>&nbsp;&nbsp;&nbsp; 23.3&nbsp; Active Reinforcement Learning<br>&nbsp;&nbsp;&nbsp; 23.4&nbsp; Safe Exploration<br>&nbsp;&nbsp;&nbsp; 23.5&nbsp; Generalization in Reinforcement Learning<br>&nbsp;&nbsp;&nbsp; 23.6&nbsp; Policy Search<br>&nbsp;&nbsp;&nbsp; 23.7&nbsp; Applications of Reinforcement Learning<br><b>24. Natural Language Processing</b><br>&nbsp;&nbsp;&nbsp; 24.1&nbsp; Language Models<br>&nbsp;&nbsp;&nbsp; 24.2&nbsp; Grammar<br>&nbsp;&nbsp;&nbsp; 24.3&nbsp; Parsing<br>&nbsp;&nbsp;&nbsp; 24.4&nbsp; Augmented Grammars<br>&nbsp;&nbsp;&nbsp; 24.5&nbsp; Complications of Real Natural Language<br>&nbsp;&nbsp;&nbsp; 24.6&nbsp; Natural Language Tasks<br><b>25. Deep Learning for Natural Language Processing</b><br>&nbsp;&nbsp;&nbsp; 25.1&nbsp; Limitations of Feature-Based NLP Models<br>&nbsp;&nbsp;&nbsp; 25.2&nbsp; Word Embeddings<br>&nbsp;&nbsp;&nbsp; 25.3&nbsp; Recurrent Neural Networks<br>&nbsp;&nbsp;&nbsp; 25.4&nbsp; Sequence-to-sequence Models<br>&nbsp;&nbsp;&nbsp; 25.5&nbsp; The Transformer Architecture<br>&nbsp;&nbsp;&nbsp; 25.6&nbsp; Pretraining and Transfer Learning<br style="mso-special-character: line-break;"><br style="mso-special-character: line-break;"><o:p></o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>26. Robotics</span></b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><br>&nbsp;&nbsp;&nbsp; 26.1&nbsp; Robots<br>&nbsp;&nbsp;&nbsp; 26.2&nbsp; Robot Hardware<br>&nbsp;&nbsp;&nbsp; 26.3&nbsp; What kind of problem is robotics solving?<br>&nbsp;&nbsp;&nbsp; 26.4&nbsp; Robotic Perception<br>&nbsp;&nbsp;&nbsp; 26.5&nbsp; Planning and Control<br>&nbsp;&nbsp;&nbsp; 26.6&nbsp; Planning Uncertain Movements<br>&nbsp;&nbsp;&nbsp; 26.7&nbsp; Reinforcement Learning in Robotics<br>&nbsp;&nbsp;&nbsp; 26.8&nbsp; Humans and Robots<br>&nbsp;&nbsp;&nbsp; 26.9&nbsp; Alternative Robotic Frameworks<br>&nbsp;&nbsp;&nbsp; 26.10 Application Domains<br><b>27. Computer Vision<o:p></o:p></b></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 0in;"><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>&nbsp;&nbsp;&nbsp; 27.1&nbsp;Introduction<br>&nbsp;&nbsp;&nbsp; 27.2 Image Formation<br>&nbsp;&nbsp;&nbsp; 27.3&nbsp; Simple Image Features<br>&nbsp;&nbsp;&nbsp; 27.4 Classifying Images<br>&nbsp;&nbsp;&nbsp; 27.5 Detecting Objects<br>&nbsp;&nbsp;&nbsp; 27.6 The 3D World<br>&nbsp;&nbsp;&nbsp; 27.7 Using Computer Vision<br>&nbsp;<br><b>Part VII: Conclusions</b><br><b>28. Philosophy and Ethics of AI</b><br>&nbsp;&nbsp;&nbsp; 28.1&nbsp; Weak AI: What are the Limits of AI?<br>&nbsp;&nbsp;&nbsp; 28.2&nbsp; Strong AI: Can Machines Really Think?<br>&nbsp;&nbsp;&nbsp; 28.3&nbsp; The Ethics of AI<br><b>29. The Future of AI</b><br>&nbsp;&nbsp;&nbsp; 29.1&nbsp; AI Components<br>&nbsp;&nbsp;&nbsp; 29.2&nbsp; AI Architectures<br>&nbsp;<o:p></o:p></span></p><p class="MsoNormal" style="line-height: 18pt; margin-bottom: 5pt;"><b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'>Appendix A:Mathematical Background</span></b><span style='font-family: "Verdana",sans-serif; font-size: 10pt; mso-fareast-font-family: "Times New Roman"; mso-bidi-font-family: "Times New Roman";'><br>&nbsp;&nbsp;&nbsp; A.1&nbsp; Complexity Analysis and O() Notation<br>&nbsp;&nbsp;&nbsp; A.2&nbsp; Vectors, Matrices, and Linear Algebra<br>&nbsp;&nbsp;&nbsp; A.3&nbsp; Probability Distributions<br><b>Appendix B: Notes on Languages and Algorithms</b><br>&nbsp;&nbsp;&nbsp; B.1&nbsp; Defining Languages with Backus--Naur Form (BNF)<br>&nbsp;&nbsp;&nbsp; B.2&nbsp; Describing Algorithms with Pseudocode<br>&nbsp;&nbsp;&nbsp; B.3&nbsp; Online Supplemental Material<o:p></o:p></span></p><br><p></p>

Stuart Russell

Peter Norvig

A digital version of the text you can personalize and read online or offline.

eTextbook

Artificial Intelligence: A Modern Approach, Global Edition 180 days Subscription

A digital version of the text you can personalize and read online or offline. If your instructor has invited you to join a specific Pearson eTextbook course for your class, you will need to purchase your eText through the course invite link they provide.

Now available on

Artificial Intelligence: A Modern Approach, Global Edition

Artificial Intelligence: A Modern Approach, Global Edition 5Yr Subscription

This product is a bound, printed text book.

Print

Paperback

Artificial Intelligence: A Modern Approach, Global Edition, 4th edition

Access details

Features

Paperback

Details

Pearson eText