Rent 9780321545893 | Artificial Intelligence : Structures and Strategies for Complex Problem Solving

Summary Table of Contents Author Biography

George Luger is currently a Professor of Computer Science, Linguistics, and Psychology at the University of New Mexico.

KEY MESSAGE: In this accessible, comprehensive text, George Luger captures the essence of artificial intelligence-solving the complex problems that arise wherever computer technology is applied. Key representation techniques including logic, semantic and connectionist networks, graphical models, and many more are introduced. Presentation of agent technology and the use of ontologies are added. A n... MOREew machine-learning chapter is based on stochastic methods, including first-order Bayesian networks, variants of hidden Markov models, inference with Markov random fields and loopy belief propagation. A new presentation of parameter fitting with expectation maximization learning and structure learning using Markov chain Monte Carlo sampling. Use of Markov decision processes in reinforcement learning. Natural language processing with dynamic programming (the Earley parser) and other probabilistic parsing techniques including Viterbi, are added. A new supplemental programming book is available online and in print: "AI Algorithms in Prolog, Lisp and Java (TM). "References and citations are updated throughout the Sixth Edition. For all readers interested in artificial intelligence.

In this accessible, comprehensive text, George Luger captures the essence of artificial intelligence; solving the complex problems that arise wherever computer technology is applied.Key representation techniques including logic, semantic and connectionist networks, graphical models, and many more are introduced. Presentation of agent technology and the use of ontologies are added. A new machine-learning chapter is based on stochastic methods, including first-order Bayesian networks, variants of hidden Markov models, inference with Markov random fields and loopy belief propagation. A new presentation of parameter fitting with expectation maximization learning and structure learning using Markov chain Monte Carlo sampling. Use of Markov decision processes in reinforcement learning. Natural language processing with dynamic programming (the Earley parser) and other probabilistic parsing techniques including Viterbi, are added. A new supplemental programming book is available online and in print: AI Algorithms in Prolog, Lisp and Java trade;.References and citations are updated throughout the Sixth Edition.For all readers interested in artificial intelligence.

Artificial Intelligence: Structures and Strategies for Complex Problem Solving is ideal for a one- or two-semester undergraduate course on AI.

In this accessible, comprehensive text, George Luger captures the essence of artificial intelligence�solving the complex problems that arise wherever computer technology is applied. Ideal for an undergraduate course in AI, the Sixth Edition presents the fundamental concepts of the discipline first then goes into detail with the practical information necessary to implement the algorithms and strategies discussed. Readers learn how to use a number of different software tools and techniques to address the many challenges faced by today�s computer scientists.

Artificial Intelligence: Its Roots and Scope	p. 1
AI: History and Applications	p. 3
From Eden to ENIAC: Attitudes toward Intelligence, Knowledge, and Human Artifice	p. 3
Overview of AI Application Areas	p. 20
Artificial Intelligence A Summary	p. 30
Epilogue and References	p. 31
Exercises	p. 33
Artificial Intelligence as Representation and Search	p. 3... MORE5
The Predicate Calculus	p. 45
Introduction	p. 45
The Propositional Calculus	p. 45
The Predicate Calculus	p. 50
Using Inference Rules to Produce Predicate Calculus Expressions	p. 62
Application: A Logic-Based Financial Advisor	p. 73
Epilogue and References	p. 77
Exercises	p. 77
Structures and Strategies for State Space Search	p. 79
Introduction	p. 79
Graph Theory	p. 82
Strategies for State Space Search	p. 93
Using the State Space to Represent Reasoning with the Predicate Calculus	p. 107
Epilogue and References	p. 121
Exercises	p. 121
Heuristic Search	p. 123
Introduction	p. 123
Hill Climbing and Dynamic Programming	p. 127
The Best-First Search Algorithm	p. 133
Admissibility, Monotonicity, and Informedness	p. 145
Using Heuristics in Games	p. 150
Complexity Issues	p. 157
Epilogue and References	p. 161
Exercises	p. 162
stochastic methods	p. 165
Introduction	p. 165
The Elements of Counting	p. 167
Elements of Probability Theory	p. 170
Applications of the Stochastic Methodology	p. 182
Bayes Theorem	p. 184
Epilogue and References	p. 190
Exercises	p. 191
Control and Implementation of State Space Search	p. 193
Introduction	p. 193
Recursion-Based Search	p. 194
Production Systems	p. 200
The Blackboard Architecture for Problem Solving	p. 187
Epilogue and References	p. 219
Exercises	p. 220
Capturing Intelligence: The AI Challenge	p. 223
Knowledge Representation	p. 227
Issues in Knowledge Representation	p. 227
A Brief History of AI Representational Systems	p. 228
Conceptual Graphs: A Network Language	p. 248
Alternative Representations and Ontologies	p. 258
Agent Based and Distributed Problem Solving	p. 265
Epilogue and References	p. 270
Exercises	p. 273
Strong Method Problem Solving	p. 277
Introduction	p. 277
Overview of Expert System Technology	p. 279
Rule-Based Expert Systems	p. 286
Model-Based, Case Based, and Hybrid Systems	p. 298
Planning	p. 314
Epilogue and References	p. 329
Exercises	p. 331
Reasoning in Uncertain Situations	p. 333
Introduction	p. 333
Logic-Based Abductive Inference	p. 335
Abduction: Alternatives to Logic	p. 350
The Stochastic Approach to Uncertainty	p. 363
Epilogue and References	p. 378
Exercises	p. 380
Machine Learning	p. 385
Machine Learning: Symbol-Based	p. 387
Introduction	p. 387
A Framework for Symbol-based Learning	p. 390
Version Space Search	p. 396
The ID3 Decision Tree Induction Algorithm	p. 408
Inductive Bias and Learnability	p. 417
Knowledge and Learning	p. 422
Unsupervised Learning	p. 433
Reinforcement Learning	p. 442
Epilogue and References	p. 449
Exercises	p. 450
Machine Learning: Connectionist	p. 453
Introduction	p. 453
Foundations for Connectionist Networks	p. 455
Perceptron Learning	p. 458
Backpropagation Learning	p. 467
Competitive Learning	p. 474
Hebbian Coincidence Learning	p. 484
Attractor Networks or Memories	p. 495
Epilogue and References	p. 505
Exercises 506
Table of Contents provided by Publisher. All Rights Reserved.

George Luger is currently a Professor of Computer Science, Linguistics, and Psychology at the University of New Mexico. He received his PhD from the University of Pennsylvania and spent five years researching and teaching at the Department of Artificial Intelligence at the University of Edinburgh.

RENT TEXTBOOKS

Artificial Intelligence : Structures and Strategies for Complex Problem Solving

Why Rent from Knetbooks?

Top 5 reasons to order all your textbooks from Knetbooks:

Related Products